Dish abnormality detection method, intelligent dish delivery system and intelligent kitchen appliance
By acquiring data on the weight changes, temperature, and liquid levels of the food, multi-dimensional anomaly detection is performed, solving the problem of abnormal food output during intelligent cooking and improving the quality and intelligence of the food output.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- NINGBO FOTILE KITCHEN WARE CO LTD
- Filing Date
- 2026-02-09
- Publication Date
- 2026-05-29
AI Technical Summary
During intelligent cooking, abnormalities may occur in the weight of the ingredients, the amount of liquid in the broth, and the arrangement of the ingredients, leading to abnormal dishes that are difficult to detect and resolve effectively with existing technologies.
By acquiring data on food weight changes, temperature, and liquid levels, and combining this data with temperature differences, liquid concentration, and liquid level height, multi-dimensional anomaly detection is performed, including the detection of weight anomalies, liquid anomalies, and temperature anomalies.
It enables multi-dimensional anomaly detection during the cooking and serving process, allowing for timely identification of problems and improving the quality and intelligence of food serving.
Smart Images
Figure CN122108252A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent kitchen appliance technology, and in particular to a method for detecting abnormal food dispensing, an intelligent food dispensing system, and intelligent kitchen appliances. Background Technology
[0002] With the improvement of people's living standards and the promotion and popularization of technologies such as artificial intelligence, more and more traditional lifestyles are gradually changing. The use of home appliances is gradually moving towards intelligence, bringing more convenience to users while diversifying the functions of various home appliances, among which the application of intelligent cooking is increasing. During the process of intelligent cooking and serving dishes, various abnormal situations may occur, such as discrepancies in the weight of the ingredients, liquid broth, or placement, which may prevent the dishes from being served properly. Therefore, it is necessary to conduct multi-dimensional anomaly detection during the cooking and serving process to promptly and accurately identify and resolve problems, thereby improving the quality and intelligence of the dishes served. Summary of the Invention
[0003] To address the aforementioned problems in existing technologies, this invention discloses a method for detecting abnormal food output, an intelligent food output system, and intelligent kitchen appliances. These systems enable multi-dimensional anomaly detection during the cooking and food output process, improving both the quality and intelligence of the food output. The technical solution disclosed in this invention is as follows: According to one aspect of the disclosed embodiments of the present invention, a method for detecting abnormal food output is provided, the method comprising: During the food preparation process, the weight change data, temperature measurement data, desired temperature data, and liquid data corresponding to the food to be tested are acquired, including liquid concentration data and liquid level data. Based on the measured temperature data, the temperature change data corresponding to the dish to be tested is determined; Based on the temperature difference data between the measured temperature data and the expected temperature data, and the temperature change data, the corrected temperature data corresponding to the dish to be tested is determined; Based on the liquid concentration data and the liquid level data, the liquid state change data corresponding to the dish to be tested is determined; the liquid state change data is used to characterize the uniformity of the liquid corresponding to the dish to be tested. Based on the weight change data, the corrected temperature data, and the liquid state change data, anomaly detection is performed on the dish to be tested, and anomaly detection results are obtained.
[0004] Optionally, the anomaly detection of the dish to be tested based on the weight change data, the corrected temperature data, and the liquid state change data, to obtain the anomaly detection results, includes: Based on the weight change data, the corrected temperature data, and the liquid state change data, the comprehensive test data corresponding to the dish to be tested is determined. If the comprehensive detection data exceeds the preset detection threshold range, the dish to be detected is subjected to anomaly detection to obtain anomaly detection results.
[0005] Optionally, the abnormal detection results include weight abnormality results. When the comprehensive detection data exceeds a preset detection threshold, the abnormal detection results obtained by performing abnormal detection on the dish to be detected include: During the food preparation process, the measured weight data of the food to be tested is acquired; the measured weight data includes the first measured weight data after the food preparation is completed. If the comprehensive detection data exceeds the preset detection threshold range, obtain the expected weight data of the dish to be tested under the condition that the dish is finished serving. Based on the weight difference data between the first measured weight data and the expected weight data, and the expected weight data, the weight deviation data corresponding to the dish to be tested is determined; If the weight deviation data is greater than a preset weight deviation threshold, the weight abnormality result is determined.
[0006] Optionally, the anomaly detection results include liquid anomaly results, and the liquid data further includes liquid measurement weight data and second liquid weight data at the start of serving. When the comprehensive detection data exceeds a preset detection threshold, the dish to be tested is subjected to anomaly detection, and the resulting anomaly detection results include: If the comprehensive detection data exceeds the preset detection threshold range, the first liquid weight change data corresponding to the dish to be tested is calculated based on the liquid weight difference information between the liquid measurement weight data and the second liquid weight data, as well as the container area data corresponding to the dish to be tested. Based on the liquid measurement weight data, the second liquid weight change data is determined; Determine the scaling factor between the second liquid weight change data and the weight change data; If the first liquid weight change data is greater than a preset weight change threshold and the proportional coefficient is less than a preset coefficient threshold, the abnormal liquid result is determined.
[0007] Optionally, the abnormal detection results include temperature abnormality results. When the comprehensive detection data exceeds a preset detection threshold, the abnormal detection results obtained by performing abnormal detection on the dish to be tested include: If the comprehensive detection data exceeds the preset detection threshold range, the temperature deviation data corresponding to the dish to be tested is determined based on the first temperature difference data between the measured temperature data and the preset upper limit temperature data, and the second temperature difference data between the measured temperature data and the preset lower limit temperature data. If the temperature deviation data is greater than a preset temperature deviation threshold, the temperature anomaly result is determined.
[0008] Optionally, when the comprehensive detection data exceeds a preset detection threshold, performing anomaly detection on the dish to be detected and obtaining the anomaly detection result includes: Acquire the weight deviation data, first liquid weight change data, and temperature deviation data corresponding to the dish to be tested; Based on the weight deviation data, determine the weight anomaly detection data corresponding to the dish to be tested; Based on the first liquid weight change data, determine the liquid anomaly detection data corresponding to the dish to be tested; Based on the temperature deviation data, the temperature anomaly detection data corresponding to the dish to be tested is determined; Based on the weight anomaly detection data, the liquid anomaly detection data, the temperature anomaly detection data, and their respective weight information, the anomaly confidence level of the dish to be detected is determined. If the comprehensive detection data exceeds the preset detection threshold range and the anomaly confidence level is greater than the preset confidence threshold, anomaly detection is performed on the dish to be detected to obtain the anomaly detection result.
[0009] Optionally, the anomaly detection results include distribution anomaly results, and the placement area of the dish to be detected is equipped with multiple weight sensors evenly distributed. The method further includes: Based on the measurement data corresponding to each weight sensor, the measurement change data corresponding to each weight sensor is calculated. Based on the measurement change data corresponding to each weight sensor, the measurement weight variance corresponding to the multiple weight sensors is calculated; If the variance of the measured weight is greater than a preset variance threshold, the distribution anomaly result is determined.
[0010] Optionally, the anomaly detection results include abnormal tableware placement results, and the placement area of the dish to be detected is equipped with multiple weight sensors evenly distributed. The method further includes: Obtain the measurement posture data of the tableware on which the dish to be tested is placed; Based on the measurement data corresponding to each weight sensor, the measurement change data corresponding to each weight sensor is calculated. Based on the measurement change data corresponding to each weight sensor, the measurement weight variance corresponding to the multiple weight sensors is calculated; If the variance of the measured weight is greater than a preset variance threshold, or if the attitude difference information between the measured attitude data and the preset attitude data does not meet the preset conditions, the abnormal result of the tableware placement is determined.
[0011] According to another aspect of the embodiments disclosed in this invention, an intelligent food dispensing system is provided. The intelligent food dispensing system includes a temperature detection module, a weight detection module, a liquid detection module, and a control module. The temperature detection module, the weight detection module, and the liquid detection module are disposed on the tableware on which the food to be detected is placed and / or in the placement area of the tableware. An radio frequency module is disposed on both the tableware and the placement area of the tableware. The temperature detection module, the weight detection module, the liquid detection module, and the radio frequency module are respectively communicatively connected to the control module. The temperature detection module is used to collect the measured temperature data of the dish to be tested; the weight detection module is used to collect the measured weight data of the dish to be tested, and the measured weight data is used to determine the weight change data; the liquid detection module is used to collect the liquid data corresponding to the dish to be tested; the radio frequency module is used to store the attribute information of the tableware; and the control module is used to execute the dish dispensing anomaly detection method as described above to perform dish dispensing anomaly detection.
[0012] According to another aspect of the disclosed embodiments of the present invention, a smart kitchen appliance is provided, including the smart food dispensing system described above.
[0013] The method for detecting abnormal food output provided by this invention has the following technical effects: The method includes acquiring, during the food preparation process, weight change data, measured temperature data, desired temperature data, and liquid data corresponding to the dish to be tested, including liquid concentration data and liquid level data; determining temperature change data corresponding to the dish to be tested based on the measured temperature data; determining corrected temperature data corresponding to the dish to be tested based on the temperature difference data between the measured temperature data and the desired temperature data, as well as the temperature change data; determining liquid state change data corresponding to the dish to be tested based on the liquid concentration data and liquid level data; the liquid state change data is used to characterize the uniformity of the liquid corresponding to the dish to be tested; and performing anomaly detection on the dish to be tested based on the weight change data, corrected temperature data, and liquid state change data to obtain anomaly detection results.
[0014] Therefore, by using the temperature data of the dish to be tested to determine the corresponding corrected temperature data, and by using the liquid concentration data and liquid level data to determine the corresponding liquid state change data to characterize the liquid uniformity of the dish, and then combining the weight change data, corrected temperature data, and liquid state change data of the dish to be tested, anomaly detection is performed on the dish to be tested, and anomaly detection results are obtained. This enables multi-dimensional anomaly detection during the cooking process, allowing for timely and accurate problem identification and resolution, thereby improving the quality and intelligence of the dish.
[0015] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description
[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0017] Figure 1 This is a schematic diagram illustrating an application scenario of a method for detecting abnormal food output according to an exemplary embodiment; Figure 2 This is a flowchart illustrating a method for detecting abnormal food output according to an exemplary embodiment; Figure 3 This is a schematic diagram illustrating a process for determining anomaly detection results according to an exemplary embodiment; Figure 4 This is a schematic diagram illustrating another process for determining anomaly detection results according to an exemplary embodiment; Figure 5 This is a schematic diagram illustrating another process for determining anomaly detection results according to an exemplary embodiment; Figure 6 This is a schematic diagram illustrating another process for determining anomaly detection results according to an exemplary embodiment. Detailed Implementation
[0018] To enable those skilled in the art to better understand the technical solutions disclosed in this invention, the technical solutions in the disclosed embodiments will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.
[0019] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention disclosed herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.
[0020] This application provides a method for detecting abnormal food output. Please refer to [link / reference]. Figure 1 , Figure 1 This is a schematic diagram illustrating an application scenario of a method for detecting abnormal food output according to an exemplary embodiment. This method can be applied to smart kitchen appliances, which can be used for the food output process after cooking, or for both the cooking process and the output process after cooking. Specifically, the smart kitchen appliance may include a smart food output system and a cooktop. The smart food output system may include a temperature detection module, a weight detection module, a liquid detection module, and a control module. The control module can be used to execute the abnormal food output detection method to detect abnormalities. Specifically, the temperature detection module can be a thermistor sensor, and the weight detection module can be a pressure sensor.
[0021] The temperature detection module, weight detection module, and liquid detection module can be installed on the tableware where the food to be detected is placed and / or in the tableware placement area. Radio frequency (RF) modules can be installed on the tableware and in the tableware placement area. These RF modules can be either Radio Frequency Identification (RFID) modules or Near Field Communication (NFC) modules. The temperature detection module, weight detection module, liquid detection module, and RF module can each communicate with the control module.
[0022] Specifically, the temperature detection module can be used to collect the measured temperature data of the dish to be tested; the weight detection module can be used to collect the measured weight data of the dish to be tested, which can be used to determine weight change data; the liquid detection module can be used to collect the liquid data corresponding to the dish to be tested, which can include liquid concentration data and liquid level data, etc. The radio frequency (RF) module can be used to store the attribute information of the tableware. RF modules installed in the tableware can store the attribute information of that tableware, and RF modules installed in the tableware placement area can read the attribute information of the placed tableware to send to the control module for subsequent processing. Specifically, the attribute information of the tableware can include tableware identification information, tableware type, and tableware weight information, etc. Each piece of tableware corresponds to a tableware identification information, and the tableware type can be related to the shape, material, etc. Different dishes to be tested can correspond to different types of tableware.
[0023] Specifically, the intelligent food serving system may also include an auxiliary food serving device, which can be used to place the tableware corresponding to the cooked dish to be tested in the corresponding position and serve the dish to be tested into the corresponding tableware. The auxiliary food serving device may be a robotic arm or a robot.
[0024] In addition, it should be noted that, Figure 1 The examples shown are merely one application scenario for detecting abnormal food output, and the embodiments in this specification are not limited to the above.
[0025] The following describes a method for detecting abnormal food output according to this application. Figure 2 This is a flowchart illustrating a method for detecting abnormal food output according to an exemplary embodiment. This specification provides the operational steps of the method as described in the embodiments or flowchart, but based on conventional or non-inventive labor, more or fewer operational steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual system or server products, the method can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment) as shown in the embodiments or drawings. Specifically, as... Figure 2 As shown, the above method may include: S201: During the food preparation process, acquire the weight change data, measured temperature data, expected temperature data, and liquid data of the food to be tested.
[0026] In one specific embodiment, the dish to be tested can be a dish requiring anomaly detection. During the process of the auxiliary serving device placing the cooked dish to be tested into the corresponding plate, the aforementioned weight change data, measured temperature data, desired temperature data, and liquid data are acquired. Specifically, the liquid data may include liquid concentration data and liquid level data, and the liquid may be the broth in the dish to be tested. The weight change data can be the rate of weight change per unit time, which can be obtained by dividing the difference between the measured weight data at two time points by the difference between the time points.
[0027] Specifically, the measured temperature data can include the temperature data collected by the temperature detection module at each moment, and the expected temperature data can include the expected temperature data corresponding to the measured temperature data at each moment. This expected temperature data can be related to the dish to be tested and can be used as standard data for temperature comparison. The specific settings can be made according to actual application requirements.
[0028] S203: Based on the measured temperature data, determine the temperature change data corresponding to the dish to be tested.
[0029] Specifically, temperature change data can be the change between the measured temperature data at two different times, or the difference between the measured temperature data at two different times.
[0030] S205: Based on the temperature difference data between the measured temperature data and the expected temperature data, as well as the temperature change data, determine the corrected temperature data corresponding to the dish to be tested.
[0031] In one specific embodiment, the temperature change data can be the maximum difference between two measured temperature data points from multiple time points. The corrected temperature data can be determined based on the difference between the current measured temperature data and the corresponding expected temperature data, as well as the aforementioned temperature change data, when the current measured temperature data does not meet the preset temperature range. Specifically, the difference between the current measured temperature data and the corresponding expected temperature data can be divided by the aforementioned temperature change data, and the quotient is determined as the corrected temperature data. If the current measured temperature data meets the preset temperature range, the preset temperature data can be determined as the corrected temperature data. Specifically, both the preset temperature range and the preset temperature data can be set according to actual application requirements; the preset temperature data can be set to the current measured temperature data or to zero.
[0032] S207: Based on the liquid concentration data and liquid level data, determine the liquid state change data corresponding to the dish to be tested.
[0033] In one specific embodiment, liquid state change data can be used to characterize the uniformity of the liquid corresponding to the dish being tested. Specifically, the liquid state change data can be the rate of change of the ratio between liquid concentration data and liquid level height data over time, i.e., the liquid state gradient, which can be calculated using the optical characteristics of the liquid sensor. This ratio can be the quotient obtained by dividing the liquid concentration data by the liquid level height data.
[0034] S209: Based on weight change data, corrected temperature data, and liquid state change data, perform anomaly detection on the dish to be tested and obtain anomaly detection results.
[0035] In one specific embodiment, the abnormal detection results may include abnormal weight results, abnormal liquid results, and abnormal temperature results. Specifically, the abnormal weight result may be an abnormal detection result of the overall weight of the dish to be detected, the abnormal liquid result may be an abnormal detection result of the soup of the dish to be detected, and the abnormal temperature result may be an abnormal detection result of the temperature of the dish to be detected.
[0036] In an optional embodiment, the anomaly detection of the dish to be tested based on the weight change data, corrected temperature data, and liquid state change data, and the resulting anomaly detection results may include: Based on weight change data, corrected temperature data, and liquid state change data, the comprehensive test data corresponding to the dish to be tested is determined. If the comprehensive test data exceeds the preset test threshold range, an anomaly test is performed on the dish to be tested, and an anomaly test result is obtained.
[0037] In one specific embodiment, the comprehensive detection data can be a comprehensive judgment value for anomaly detection of the dish to be tested. This comprehensive detection data can be obtained by weighted summation of weight change data, corrected temperature data, and liquid state change data. Specifically, the weight change data, corrected temperature data, liquid state change data, and their respective weight information can be multiplied, and the resulting products can be added together to obtain the comprehensive detection data. The preset detection threshold range and weight information can be set according to actual application requirements. For example, the weight information corresponding to the weight change data, corrected temperature data, and liquid state change data can be set to 0.6, 0.3, and 0.1, respectively.
[0038] In the embodiments of this specification, when the comprehensive detection data exceeds the preset detection threshold range, the dish to be tested can be subjected to abnormal detection in terms of dish temperature, dish weight, and liquid content, and the corresponding abnormal detection results can be obtained.
[0039] Optional, such as Figure 3As shown, when the comprehensive detection data exceeds the preset detection threshold range, the dish to be tested undergoes anomaly detection, and the resulting anomaly detection results may include: S301: During the food preparation process, acquire the measured weight data of the food to be tested.
[0040] In one specific embodiment, the measured weight data may include weight data collected at multiple moments during the food preparation process. The weight data collected at multiple moments may include the weight data at the moment when the food preparation is completed, i.e., the first measured weight data under the condition that the food preparation is completed.
[0041] S303: When the comprehensive detection data exceeds the preset detection threshold range, obtain the expected weight data of the dish to be tested under the condition that the dish is finished.
[0042] Specifically, the expected weight data can be the standard weight data corresponding to the first measured weight data mentioned above, such as the preset standard weight value in the recipe. The first measured weight data can be compared with the expected weight data to determine the deviation between the two.
[0043] S305: Based on the weight difference data between the first measured weight data and the expected weight data, and the expected weight data, determine the weight deviation data corresponding to the dish to be tested.
[0044] Specifically, the weight deviation data can be the deviation rate between the first measured weight data and the expected weight data, which can represent the deviation between the actual yield and the yield in the standard recipe. The weight difference data can be the difference between the first measured weight data and the expected weight data. The weight difference data is then divided by the expected weight data, and the quotient is the aforementioned weight deviation data.
[0045] S307: If the weight deviation data is greater than the preset weight deviation threshold, determine the weight abnormality result.
[0046] Specifically, the preset weight deviation threshold can be set according to actual application needs, for example, it can be set to 5%.
[0047] Optional, such as Figure 4 As shown, when the comprehensive detection data exceeds the preset detection threshold range, the dish to be tested undergoes anomaly detection, and the resulting anomaly detection results may include: S401: When the comprehensive detection data exceeds the preset detection threshold range, the first liquid weight change data corresponding to the dish to be tested is calculated based on the liquid weight difference information between the liquid measurement weight data and the second liquid weight data, as well as the container area data corresponding to the dish to be tested.
[0048] In one specific embodiment, the aforementioned liquid data may further include liquid measurement weight data and second liquid weight data at the start of serving. The second liquid weight data may be the initial liquid weight data at the start of serving, the liquid measurement weight data may be the liquid measurement weight data at the current moment, and the container area data may be the bottom area data of the tableware corresponding to the dish to be tested. Specifically, the liquid weight difference information may be the difference between the liquid measurement weight data at the current moment and the second liquid weight data at the start of serving. Furthermore, the indefinite integral of the liquid weight difference information over time can be calculated, and the result can be divided by the container area data. The quotient obtained is the aforementioned first liquid weight change data.
[0049] S403: Determine the second liquid weight change data based on the liquid measurement weight data.
[0050] Specifically, the second liquid weight change data can be the rate of liquid change, or the quotient of the difference between the liquid weight measurement data at two different times and the difference between the two times.
[0051] S405: Determine the scaling factor between the second liquid weight change data and the weight change data.
[0052] Specifically, the weight change data can be the overall weight change rate of the dish. This proportionality coefficient can be used to characterize the proportional relationship between the liquid weight change and the overall weight change of the dish; specifically, it can be the quotient between the second liquid weight change data and the overall weight change data. This proportionality coefficient can also be used to characterize the degree of broth adsorption, specifically representing the amount of broth adsorbed / carried per unit weight of dish.
[0053] S407: If the first liquid weight change data is greater than the preset weight change threshold and the proportional coefficient is less than the preset coefficient threshold, an abnormal liquid result is determined.
[0054] Specifically, the preset weight change threshold and preset coefficient threshold can be set according to actual application needs. For example, the preset weight change threshold can be set to 500 ml, and the preset coefficient threshold can be set to 0.2.
[0055] In the above embodiments, based on the liquid weight difference information between the liquid measurement weight data and the second liquid weight data, and the container area data corresponding to the dish to be tested, the first liquid weight change data corresponding to the dish to be tested is calculated, and the liquid change rate is determined based on the liquid measurement weight data. The proportional coefficient between the liquid change rate and the overall weight change rate of the dish is determined, thereby determining whether the dish soup is abnormal. If the first liquid weight change data is greater than the preset weight change threshold and the proportional coefficient is less than the preset coefficient threshold, the liquid is determined to be abnormal, thus improving the accuracy of liquid abnormality judgment.
[0056] Optional, such as Figure 5 As shown, when the comprehensive detection data exceeds the preset detection threshold range, the dish to be tested undergoes anomaly detection, and the resulting anomaly detection results may include: S501: When the comprehensive detection data exceeds the preset detection threshold range, the temperature deviation data corresponding to the dish to be detected is determined based on the first temperature difference data between the measured temperature data and the preset upper limit temperature data, and the second temperature difference data between the measured temperature data and the preset lower limit temperature data.
[0057] In one specific embodiment, the preset upper limit temperature data can be the upper limit of the safe temperature of the dish, and the preset lower limit temperature data can be the lower limit of the safe temperature of the dish. The preset upper limit temperature data and the preset lower limit temperature data can be set according to actual application needs. For example, for soups, the preset upper limit temperature data can be set to 85 degrees Celsius, and for hot dishes, the preset lower limit temperature data can be set to 65 degrees Celsius.
[0058] Specifically, the difference between the preset lower limit temperature data and the current measured temperature data, and the maximum value between these two values, can be calculated. Similarly, the difference between the current measured temperature data and the preset upper limit temperature data, and the maximum value between these two values, can also be calculated. Adding these two values together yields the aforementioned temperature deviation data. The preset temperature can be set according to actual application requirements; for example, it can be set to zero.
[0059] S503: If the temperature deviation data is greater than the preset temperature deviation threshold, determine the temperature anomaly result.
[0060] Specifically, the preset temperature deviation threshold can be set according to actual application needs, for example, it can be set to 10 degrees Celsius.
[0061] In the above embodiments, temperature deviation data is determined based on the measured temperature data and the upper and lower safe temperatures of the dish, respectively, to determine whether the dish temperature is abnormal. If the temperature deviation data is greater than the preset temperature deviation threshold, the temperature is determined to be abnormal, thereby improving the accuracy and intelligence of temperature abnormality judgment.
[0062] Optional, such as Figure 6 As shown, when the comprehensive detection data exceeds the preset detection threshold range, the dish to be tested undergoes anomaly detection, and the resulting anomaly detection results may include: S601: Obtain the weight deviation data, first liquid weight change data, and temperature deviation data corresponding to the dish to be tested.
[0063] S603: Based on weight deviation data, determine the corresponding weight anomaly detection data for the dish to be tested.
[0064] Optionally, the aforementioned weight anomaly detection data can be determined based on weight deviation data and a preset weight control coefficient. The preset weight control coefficient can be used to control the growth rate of the weight anomaly detection data, and can be set according to actual application requirements. Specifically, the weight anomaly detection data can be calculated using the formula Sw=1-exp(-λw*ηw), where Sw represents the aforementioned weight anomaly detection data, λw represents the aforementioned weight control coefficient, and ηw represents the aforementioned weight deviation data.
[0065] S605: Based on the first liquid weight change data, determine the liquid anomaly detection data corresponding to the dish to be tested.
[0066] Optionally, the aforementioned liquid anomaly detection data can be determined based on the first liquid weight change data and a preset liquid control coefficient. The preset liquid control coefficient can be used to control the growth rate of the liquid anomaly detection data, and can be set according to actual application requirements. Specifically, the liquid anomaly detection data can be calculated using the formula Sl=tanh(μ*Land), where Sl represents the aforementioned liquid anomaly detection data, μ represents the aforementioned liquid control coefficient, and Land represents the aforementioned first liquid weight change data.
[0067] S607: Based on temperature deviation data, determine the temperature anomaly detection data corresponding to the dish to be tested.
[0068] Optionally, the temperature anomaly detection data can be determined based on temperature deviation data and a preset upper limit deviation temperature. The preset upper limit deviation temperature can be the maximum allowable deviation of the temperature data, and can be set according to actual application requirements. Specifically, the temperature anomaly detection data can be calculated using the formula St=Tdev / ΔTmax, where St represents the temperature anomaly detection data, Tdev represents the temperature deviation data, and ΔTmax represents the preset upper limit deviation temperature.
[0069] S609: Based on the weight anomaly detection data, liquid anomaly detection data, temperature anomaly detection data, and their respective weight information, determine the anomaly confidence level of the dish to be detected.
[0070] Specifically, the anomaly confidence score can be used to represent the accuracy of the aforementioned comprehensive detection data. Specifically, the weight anomaly detection data, liquid anomaly detection data, and temperature anomaly detection data can be multiplied by their respective weight information, and the resulting products can be summed to obtain the anomaly confidence score.
[0071] S611: When the comprehensive detection data exceeds the preset detection threshold range and the anomaly confidence level is greater than the preset confidence threshold, perform anomaly detection on the dish to be tested and obtain the anomaly detection result.
[0072] Specifically, the preset reliability threshold can be set according to the actual application requirements.
[0073] In the above embodiments, comprehensive detection data and its corresponding anomaly confidence can be combined. When both meet the corresponding conditions, anomaly detection can be performed on the dish to be tested to obtain anomaly detection results, which can improve the accuracy of the judgment of anomaly detection nodes of the dish to be tested.
[0074] Optionally, the above method may also include: Based on the measurement data corresponding to each weight sensor, the measurement change data corresponding to each weight sensor is calculated. Based on the measurement change data corresponding to each weight sensor, the variance of the measured weight corresponding to multiple weight sensors is calculated. If the variance of the measured weight exceeds a preset variance threshold, an abnormal distribution result is identified.
[0075] In one specific embodiment, the area where the dish to be detected is placed can be equipped with multiple weight sensors that are evenly distributed. The above-mentioned abnormal detection results can also include distribution abnormality results, which can be used to characterize the distribution abnormality of the measurement change data corresponding to each of the multiple weight sensors.
[0076] In one specific embodiment, the measurement change data corresponding to each weight sensor can be the rate of change of the weight data collected by each weight sensor over time, and the measurement weight variance can be used to characterize the distribution of the measurement change data corresponding to multiple weight sensors. Specifically, the preset variance threshold can be set according to actual application requirements.
[0077] Optionally, the above method may also include: Acquire measurement posture data of the tableware on which the dish to be tested is placed; Based on the measurement data corresponding to each weight sensor, the measurement change data corresponding to each weight sensor is calculated. Based on the measurement change data corresponding to each weight sensor, the variance of the measured weight corresponding to multiple weight sensors is calculated. If the variance of the measured weight is greater than the preset variance threshold, or if the attitude difference information between the measured attitude data and the preset attitude data does not meet the preset conditions, an abnormal tableware placement result is determined.
[0078] In one specific embodiment, the intelligent food serving system may further include a posture detection module, which can be an accelerometer. The posture detection module can acquire measurement posture data of the tableware. Specifically, the measurement posture data may include the rotation angle information of the tableware in a three-dimensional coordinate system, with each coordinate axis as a reference. The aforementioned anomaly detection results may also include tableware placement anomaly results, which characterize whether the tableware placement posture is abnormal, such as whether the tableware is tilted.
[0079] In one specific embodiment, the preset posture data can be the standard posture data of the tableware when it is placed stably without tilting. The preset condition can be that the posture difference information is less than the preset posture difference threshold, or the posture difference information is zero.
[0080] As can be seen from the technical solutions provided in the embodiments of this specification above, during the food preparation process, the following steps are taken: First, the weight change data, measured temperature data, desired temperature data, and liquid data corresponding to the dish to be tested are acquired. The liquid data includes liquid concentration data and liquid level data. Based on the measured temperature data, the temperature change data corresponding to the dish to be tested is determined. Second, based on the temperature difference data between the measured temperature data and the desired temperature data, and the temperature change data, the corrected temperature data corresponding to the dish to be tested is determined. Third, based on the liquid concentration data and liquid level data, the liquid state change data corresponding to the dish to be tested is determined. The liquid state change data is used to characterize the uniformity of the liquid in the dish to be tested. Finally, based on the weight change data, corrected temperature data, and liquid state change data, anomaly detection is performed on the dish to be tested, yielding anomaly detection results. Thus, by determining the corresponding corrected temperature data through the temperature data of the dish to be tested, and by determining the corresponding liquid state change data characterizing the uniformity of the liquid in the dish to be tested through the liquid concentration data and liquid level data, and then combining the weight change data, corrected temperature data, and liquid state change data of the dish to be tested, anomaly detection is performed on the dish to be tested, yielding anomaly detection results. Therefore, it is possible to perform multi-dimensional anomaly detection during the cooking and serving process, so as to identify and resolve problems in a timely and accurate manner, thereby improving the quality and intelligence of the dishes served.
[0081] This invention also provides an intelligent food dispensing system, which includes a temperature detection module, a weight detection module, a liquid detection module, and a control module. The temperature detection module, weight detection module, and liquid detection module are disposed on the tableware on which the food to be detected is placed and / or in the tableware placement area. Radio frequency modules are disposed on both the tableware and the tableware placement area. The temperature detection module, weight detection module, liquid detection module, and radio frequency module are respectively communicatively connected to the control module.
[0082] The temperature detection module collects the measured temperature data of the dish to be tested; the weight detection module collects the measured weight data of the dish to be tested, and the measured weight data is used to determine the weight change data; the liquid detection module collects the liquid data corresponding to the dish to be tested; the radio frequency module stores the attribute information of the tableware; and the control module executes the above-mentioned dish dispensing anomaly detection method to detect dish dispensing anomalies. Specifically, the intelligent dish dispensing system may also include a communication module, which can provide communication functions between the above modules, and the communication module can be a wireless communication module. The intelligent dish dispensing system may also include an attitude detection module, which can be an accelerometer sensor, and the attitude detection module can be used to acquire the measured attitude data of the tableware.
[0083] Specifically, the intelligent food serving system may also include an auxiliary food serving device, which can be used to place the tableware corresponding to the cooked dish to be tested in the appropriate position and serve the dish into the corresponding tableware. Specifically, the auxiliary food serving device can be a robotic arm or a robot.
[0084] Specifically, the intelligent food serving system may also include a posture detection module, which can be an accelerometer. This module acquires measurement posture data of the tableware, specifically including the rotation angle information of the tableware in a three-dimensional coordinate system, with each coordinate axis as a reference. The aforementioned anomaly detection results may also include tableware placement anomaly results, which characterize whether the tableware's placement posture is abnormal, such as whether the tableware is tilted.
[0085] Regarding the system in the above embodiments, the specific methods by which each module performs operations have been described in detail in the foregoing embodiments, and will not be elaborated upon here.
[0086] The present invention also provides a smart kitchen appliance, including the aforementioned smart food dispensing system. Specifically, the smart kitchen appliance can be used for the food dispensing process after cooking, or for both the cooking process and the dispensing process after cooking.
[0087] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.
[0088] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles disclosed herein and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.
[0089] It should be understood that the present invention is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is limited only by the appended claims.
Claims
1. A method for detecting abnormal food output, characterized in that, The method includes: During the food preparation process, the weight change data, temperature measurement data, desired temperature data, and liquid data corresponding to the food to be tested are acquired, including liquid concentration data and liquid level data. Based on the measured temperature data, the temperature change data corresponding to the dish to be tested is determined; Based on the temperature difference data between the measured temperature data and the expected temperature data, and the temperature change data, the corrected temperature data corresponding to the dish to be tested is determined; Based on the liquid concentration data and the liquid level data, the liquid state change data corresponding to the dish to be tested is determined; the liquid state change data is used to characterize the uniformity of the liquid corresponding to the dish to be tested. Based on the weight change data, the corrected temperature data, and the liquid state change data, anomaly detection is performed on the dish to be tested, and anomaly detection results are obtained.
2. The method according to claim 1, characterized in that, Based on the weight change data, the corrected temperature data, and the liquid state change data, anomaly detection is performed on the dish to be tested, and the anomaly detection results include: Based on the weight change data, the corrected temperature data, and the liquid state change data, the comprehensive test data corresponding to the dish to be tested is determined. If the comprehensive detection data exceeds the preset detection threshold range, the dish to be detected is subjected to anomaly detection to obtain anomaly detection results.
3. The method according to claim 2, characterized in that, The abnormal detection results include weight abnormality results. When the comprehensive detection data exceeds a preset detection threshold, the dish to be tested is subjected to abnormal detection, and the resulting abnormal detection results include: During the food preparation process, the measured weight data of the food to be tested is acquired; the measured weight data includes the first measured weight data after the food preparation is completed. If the comprehensive detection data exceeds the preset detection threshold range, obtain the expected weight data of the dish to be tested under the condition that the dish is finished serving. Based on the weight difference data between the first measured weight data and the expected weight data, and the expected weight data, the weight deviation data corresponding to the dish to be tested is determined; If the weight deviation data is greater than a preset weight deviation threshold, the weight abnormality result is determined.
4. The method according to claim 2, characterized in that, The anomaly detection results include liquid anomaly results. The liquid data further includes liquid measurement weight data and second liquid weight data at the start of serving. When the comprehensive detection data exceeds a preset detection threshold, anomaly detection is performed on the dish to be tested, and the resulting anomaly detection results include: If the comprehensive detection data exceeds the preset detection threshold range, the first liquid weight change data corresponding to the dish to be tested is calculated based on the liquid weight difference information between the liquid measurement weight data and the second liquid weight data, as well as the container area data corresponding to the dish to be tested. Based on the liquid measurement weight data, the second liquid weight change data is determined; Determine the scaling factor between the second liquid weight change data and the weight change data; If the first liquid weight change data is greater than a preset weight change threshold and the proportional coefficient is less than a preset coefficient threshold, the abnormal liquid result is determined.
5. The method according to claim 2, characterized in that, The abnormal detection results include temperature abnormality results. When the comprehensive detection data exceeds a preset detection threshold, the dish to be tested is subjected to abnormal detection, and the resulting abnormal detection results include: If the comprehensive detection data exceeds the preset detection threshold range, the temperature deviation data corresponding to the dish to be tested is determined based on the first temperature difference data between the measured temperature data and the preset upper limit temperature data, and the second temperature difference data between the measured temperature data and the preset lower limit temperature data. If the temperature deviation data is greater than a preset temperature deviation threshold, the temperature anomaly result is determined.
6. The method according to any one of claims 2 to 5, characterized in that, When the comprehensive detection data exceeds the preset detection threshold range, the dish to be detected is subjected to anomaly detection, and the anomaly detection results include: Acquire the weight deviation data, first liquid weight change data, and temperature deviation data corresponding to the dish to be tested; Based on the weight deviation data, determine the weight anomaly detection data corresponding to the dish to be tested; Based on the first liquid weight change data, determine the liquid anomaly detection data corresponding to the dish to be tested; Based on the temperature deviation data, the temperature anomaly detection data corresponding to the dish to be tested is determined; Based on the weight anomaly detection data, the liquid anomaly detection data, the temperature anomaly detection data, and their respective weight information, the anomaly confidence level of the dish to be detected is determined. If the comprehensive detection data exceeds the preset detection threshold range and the anomaly confidence level is greater than the preset confidence threshold, anomaly detection is performed on the dish to be detected to obtain the anomaly detection result.
7. The method according to claim 1, characterized in that, The anomaly detection results include distribution anomaly results. The area where the dish to be detected is placed is equipped with multiple weight sensors evenly distributed. The method further includes: Based on the measurement data corresponding to each weight sensor, the measurement change data corresponding to each weight sensor is calculated. Based on the measurement change data corresponding to each weight sensor, the measurement weight variance corresponding to the multiple weight sensors is calculated; If the variance of the measured weight is greater than a preset variance threshold, the distribution anomaly result is determined.
8. The method according to claim 1, characterized in that, The anomaly detection results include results of abnormal tableware placement. The area where the dish to be detected is placed is equipped with multiple evenly distributed weight sensors. The method further includes: Obtain the measurement posture data of the tableware on which the dish to be tested is placed; Based on the measurement data corresponding to each weight sensor, the measurement change data corresponding to each weight sensor is calculated. Based on the measurement change data corresponding to each weight sensor, the measurement weight variance corresponding to the multiple weight sensors is calculated; If the variance of the measured weight is greater than a preset variance threshold, or if the attitude difference information between the measured attitude data and the preset attitude data does not meet the preset conditions, the abnormal result of the tableware placement is determined.
9. An intelligent food dispensing system, characterized in that, The intelligent food dispensing system includes a temperature detection module, a weight detection module, a liquid detection module, and a control module. The temperature detection module, the weight detection module, and the liquid detection module are disposed on the tableware on which the food to be detected is placed and / or in the placement area of the tableware. Radio frequency modules are disposed on the tableware and in the placement area of the tableware. The temperature detection module, the weight detection module, the liquid detection module, and the radio frequency module are respectively communicatively connected to the control module. The temperature detection module is used to collect the measured temperature data of the dish to be tested; the weight detection module is used to collect the measured weight data of the dish to be tested, and the measured weight data is used to determine the weight change data; the liquid detection module is used to collect the liquid data corresponding to the dish to be tested; the radio frequency module is used to store the attribute information of the tableware; and the control module is used to execute the dish dispensing anomaly detection method as described in any one of claims 1 to 8 to perform dish dispensing anomaly detection.
10. A smart kitchen appliance, characterized in that, Including the intelligent food dispensing system as described in claim 9.