An Automatic Flavoring Control Method and System for an Intelligent Cooking Machine

Abstract

The present invention provides an automatic seasoning control method and system for an intelligent cooking machine. Among them, the method includes: Step 1: Obtain the first execution step being executed when the intelligent cooking machine is cooking a dish; Step 2: Obtain the step type of the first execution step, and determine whether the step type is adding seasonings. If so, determine a seasoning plan; Step 3: Based on the seasoning plan, control the intelligent cooking machine to perform automatic seasoning. The automatic seasoning control method of the intelligent cooking machine of the present invention, based on the first execution step being executed by the intelligent cooking machine, when the step type of the first execution step is adding seasonings, determines a suitable seasoning plan, without the need for manual seasoning, reducing labor costs. At the same time, it also avoids the situation where the amount of seasonings added by manual seasoning is not accurately controlled, improving the suitability of the taste of the dish.

Description

Technical Field

[0001] The present invention relates to the technical field of cooking machine control, and particularly relates to an automatic seasoning control method and system for an intelligent cooking machine. Background Art

[0002] Currently, when an intelligent cooking machine is frying products, it is often necessary for manual workers to put a certain amount of seasonings according to experience, resulting in a large labor cost. At the same time, due to the lack of experience of the staff, it is easy to have situations where the amount of seasonings added is inappropriate and the quality of the dishes produced is unstable, affecting the taste of the dishes.

[0003] Therefore, a solution is urgently needed. Summary of the Invention

[0004] The present invention provides an automatic seasoning control method and system for an intelligent cooking machine. Based on the first execution step being executed by the intelligent cooking machine, when the step type of the first execution step is adding seasonings, a suitable seasoning scheme is determined, eliminating the need for manual seasoning, reducing the labor cost, and at the same time, avoiding the situation where the amount of seasonings added by manual workers is inaccurate, improving the suitability of the taste of the dishes.

[0005] The present invention provides an automatic seasoning control method for an intelligent cooking machine, including:

[0006] Step 1: Obtain the first execution step being executed when the intelligent cooking machine is frying a dish;

[0007] Step 2: Obtain the step type of the first execution step, and determine whether the step type is adding seasonings. If so, determine a seasoning scheme;

[0008] Step 3: Based on the seasoning scheme, control the intelligent cooking machine to perform automatic seasoning.

[0009] Preferably, Step 1: Obtain the first execution step being executed when the intelligent cooking machine is frying a dish, including:

[0010] Obtain the first control signal currently received by the intelligent cooking machine;

[0011] Obtain a preset control signal - execution step library, where the control signal - execution step library includes: a plurality of second control signals and second execution steps that correspond one by one;

[0012] Match the first control signal with the second control signals in the control signal - execution step library;

[0013] If there is a match, use the second execution step corresponding to the matched second control signal as the first execution step.

[0014] Preferably, determining a flavoring solution includes:

[0015] Obtain the dish quality of the dish and the executed steps of the intelligent cooking machine;

[0016] Train a flavoring solution formulation model;

[0017] Based on the flavoring solution formulation model, determine a flavoring solution according to the dish quality of the dish and the executed steps of the intelligent cooking machine.

[0018] Preferably, training a flavoring solution formulation model includes:

[0019] Based on big data technology, obtain multiple first flavoring solution formulation records;

[0020] Obtain the reliability value of the first flavoring solution formulation record;

[0021] If the reliability value is greater than or equal to a preset reliability value threshold, use the corresponding first flavoring solution formulation record as the training target;

[0022] Input the training target into a preset neural network model for model training;

[0023] When the neural network model is trained to convergence, use the corresponding neural network model as the flavoring solution formulation model.

[0024] Preferably, obtaining the reliability value of the first flavoring solution formulation record includes:

[0025] Obtain the identity type of the provider of the first flavoring solution formulation record;

[0026] When the identity type is a practitioner, obtain a preset practitioner-historical experience value library, determine the historical experience value of the practitioner, and use it as the reliability value of the corresponding first flavoring solution formulation record;

[0027] When the identity type is a non-practitioner, obtain the historical providing behavior of the collection node where the non-practitioner collects the first flavoring solution formulation record;

[0028] Query a preset providing behavior-specification value library, determine the specification value of the historical providing behavior, and associate it with the corresponding first flavoring solution formulation record;

[0029] Accumulatively calculate the specification values associated with the first flavoring solution formulation record to obtain the reliability value.

[0030] Preferably, step 3: Based on the flavoring solution to be added, control the intelligent cooking machine to perform automatic flavoring, including:

[0031] Analyze the flavoring solution to obtain the addition amount of at least one first flavoring agent;

[0032] Obtain the remaining amount of the first seasoning in the storage unit corresponding to the first seasoning;

[0033] Determine whether the addition amount is less than or equal to the remaining amount;

[0034] If not, based on a preset reminder rule, remind the staff to replenish the corresponding first seasoning;

[0035] If so, based on the seasoning plan, control the intelligent cooking machine to add the first seasoning to the dish.

[0036] Preferably, the automatic seasoning control method of the intelligent cooking machine further includes:

[0037] Analyze the seasoning plan to obtain the seasoning types of multiple first seasonings;

[0038] Based on the seasoning types, based on a preset judgment rule, judge whether it is necessary to preprocess the first seasoning;

[0039] If so, based on a preset preprocessing rule, preprocess the first seasoning to obtain a second seasoning after the processing is completed;

[0040] After the first seasoning or the second seasoning is added to the dish, control the intelligent cooking machine to evenly season the dish.

[0041] Preferably, controlling the intelligent cooking machine to evenly season the dish includes:

[0042] Obtain the feeding path and feeding range of the feeding port of the intelligent cooking machine in the first area corresponding to the pot mouth;

[0043] Based on the feeding path and feeding range, determine the second area where feeding has been completed in the first area and the third area where feeding has not been completed in the first area;

[0044] Based on the second area and the third area, determine a uniform spreading control plan, control the intelligent cooking machine to evenly spread the seasoning, and after the uniform spreading is completed, obtain the cooking record of the first dish;

[0045] Sequentially extract the frying behaviors of the target object after adding the seasoning from the cooking record to obtain a frying behavior sequence, sequentially traverse the frying behaviors in the frying behavior sequence, and control the intelligent cooking machine to simulate the currently traversed frying behavior to fry the dish until the traversal is completed, thereby completing the uniform seasoning of the dish.

[0046] Preferably, obtaining the uniform spreading control plan includes:

[0047] Based on a preset feature extraction template, extract features from the coverage relationship of the second region relative to the third region to obtain multiple coverage relationship feature values;

[0048] Based on the coverage relationship feature values, construct a first spreading relationship description vector;

[0049] Obtain a preset uniform spreading control scheme library, determine a second spreading relationship description vector in the uniform spreading control scheme library with the smallest vector angle with the first spreading relationship description vector, and determine the uniform spreading control scheme corresponding to the second spreading relationship description vector in the uniform spreading control scheme library;

[0050] Based on the uniform spreading control scheme, control the intelligent cooking machine to spread seasonings evenly.

[0051] An embodiment of the present invention provides an automatic seasoning control system for an intelligent cooking machine, including:

[0052] An acquisition module, configured to acquire a first execution step currently being executed when the intelligent cooking machine cooks a dish;

[0053] A judgment module, configured to acquire the step type of the first execution step, judge whether the step type is adding seasonings, and if so, determine a seasoning scheme;

[0054] A control module, configured to control the intelligent cooking machine to perform automatic seasoning based on the seasoning scheme that needs to be added.

[0055] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in the written specification, claims, and drawings.

[0056] The following will further describe the technical solutions of the present invention in detail through the drawings and embodiments. Description of the Drawings

[0057] The 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 to the present invention. In the drawings:

[0058] Figure 1 is a flowchart of an automatic seasoning control method for an intelligent cooking machine in an embodiment of the present invention;

[0059] Figure 2 is a schematic diagram of an automatic seasoning control system for an intelligent cooking machine in an embodiment of the present invention. Detailed Embodiments

[0060] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only for illustrating and explaining the present invention, and are not used to limit the present invention.

[0061] The present invention provides an automatic seasoning control method for an intelligent cooking machine, as Figure 1 shown, including:

[0062] Step 1: Obtain the first execution step being executed when the intelligent cooking machine is cooking a dish;

[0063] Step 2: Obtain the step type of the first execution step, and determine whether the step type is adding seasonings. If so, determine the seasoning plan;

[0064] Step 3: Based on the seasoning plan, control the intelligent cooking machine to perform automatic seasoning.

[0065] The working principle and beneficial effects of the above technical solution are as follows:

[0066] Obtain the first execution step when the intelligent cooking machine is currently cooking a dish (for example: adding light soy sauce), obtain the step type of the first execution step (for example: adding seasonings). If the step type is adding seasonings, determine the seasoning plan (for example: light soy sauce), and control the intelligent cooking machine to perform automatic seasoning (for example: control the peristaltic pump to extract an appropriate amount of light soy sauce to season the dish).

[0067] Based on the first execution step being executed by the intelligent cooking machine, when the step type of the first execution step is adding seasonings, determine an appropriate seasoning plan, without the need for manual seasoning, reducing labor costs. At the same time, it also avoids the situation where the amount of seasonings added during manual seasoning is not accurately controlled, improving the suitability of the dish taste.

[0068] The present invention provides an automatic seasoning control method for an intelligent cooking machine. Step 1: Obtain the first execution step being executed when the intelligent cooking machine is cooking a dish, including:

[0069] Obtain the current first control signal of the intelligent cooking machine;

[0070] Obtain a preset control signal - execution step library, where the control signal - execution step library includes: a plurality of second control signals and second execution steps that correspond one by one;

[0071] Match the first control signal with the second control signals in the control signal - execution step library;

[0072] If there is a match, use the second execution step corresponding to the matched second control signal as the first execution step.

[0073] The working principle and beneficial effects of the above technical solution are as follows:

[0074] The obtained first control signal is specifically: the electrical signal corresponding to the operation instruction issued by the control system of the current intelligent cooking machine to the intelligent cooking machine. The preset control signal - execution step library is specifically: storing multiple second control signals (the electrical signals corresponding to all operation instructions that the control system of the intelligent cooking machine can issue to the intelligent cooking machine) and second execution steps (the operations executed by the intelligent cooking machine under the control of the second control signal) that are in one-to-one correspondence, and determining the second execution step corresponding to the second control signal that is the same as the first control signal in the control signal - execution step library as the first execution step.

[0075] This application matches the first control signal with the second control signal in the control signal - execution step library to determine the corresponding first execution step, improving the rationality of obtaining the first execution step.

[0076] The present invention provides an automatic flavoring control method for an intelligent cooking machine. The determination of the flavoring scheme includes:

[0077] Obtaining the quality of the dish and the execution steps of the intelligent cooking machine;

[0078] Training a flavoring scheme formulation model;

[0079] Based on the flavoring scheme formulation model, determining a flavoring scheme according to the quality of the dish and the executed steps of the intelligent cooking machine.

[0080] The working principle and beneficial effects of the above technical solution are as follows:

[0081] Obtaining the quality of the dish (which can be obtained through a gravity sensor built in the intelligent cooking machine, for example: 300g). The obtained executed steps are specifically: the steps that the intelligent cooking machine has already executed, such as how much water has been added, how much salt has been put, etc.

[0082] Training the flavoring scheme formulation model is specifically: using a large amount of records of flavoring scheme formulation for dishes based on different dishes, different dish qualities, and executed steps by a large number of people as training data to train a neural network model. The trained neural network model converges and determines the addition amount of the first flavoring according to the quality of the dish and the executed steps of the intelligent cooking machine.

[0083] This application trains a flavoring scheme formulation model and determines the addition amount of the first flavoring according to the quality of the dish and the executed steps of the intelligent cooking machine, improving the rationality and accuracy of obtaining the addition amount of the first flavoring.

[0084] The present invention provides an automatic flavoring control method for an intelligent cooking machine. Training the flavoring scheme formulation model includes:

[0085] Based on big data technology, obtain multiple first flavoring scheme formulation records;

[0086] Obtain the reliability value of the first flavoring scheme formulation record;

[0087] If the reliability value is greater than or equal to a preset reliability value threshold, use the first flavoring scheme formulation record corresponding thereto as a training target;

[0088] Input the training target into a preset neural network model for model training;

[0089] When the neural network model is trained to convergence, use the neural network model corresponding thereto as the flavoring scheme formulation model.

[0090] The working principle and beneficial effects of the above technical solution are as follows:

[0091] Based on big data technology (big data technology belongs to the prior art and its principle will not be elaborated), obtain multiple first flavoring scheme formulation records (multiple different dishes and the corresponding seasoning addition records obtained by big data), obtain the reliability value of the first flavoring scheme formulation record (for example: 150), use the first flavoring scheme formulation record with a reliability value greater than or equal to a preset reliability value threshold (for example: 200) as a training target, input the training target into a preset neural network model (an untrained neural network model) for model training, and when the neural network model is trained to a convergence state, obtain a seasoning addition control model.

[0092] This application screens out the first flavoring scheme formulation records with high reliability values as the training targets for training the flavoring scheme formulation model, improving the rationality of the flavoring scheme formulation model.

[0093] The present invention provides an automatic flavoring control method for an intelligent cooking machine, and obtaining the reliability value of the first flavoring scheme formulation record includes:

[0094] Obtain the identity type of the provider of the first flavoring scheme formulation record;

[0095] When the identity type is an employee, obtain a preset employee - historical experience value library, determine the historical experience value of the employee, and use it as the reliability value corresponding to the first flavoring scheme formulation record;

[0096] When the identity type is a non - employee, obtain the historical providing behavior of the collection node where the non - employee collects the first flavoring scheme formulation record;

[0097] Query a preset providing behavior - specification value library, determine the specification value of the historical providing behavior, and associate it with the corresponding first flavoring scheme formulation record;

[0098] Accumulatively calculate the standard values associated with the first flavoring plan formulation record to obtain a reliable value.

[0099] The working principle and beneficial effects of the above technical solution are as follows:

[0100] Obtain the identity type of the provider of the first flavoring plan formulation record, where the identity type includes: practitioners (e.g., chefs) and non-practitioners (e.g., the collector of the first flavoring plan formulation record).

[0101] When the identity type is a practitioner, obtain the preset practitioner-historical experience value library (a database containing multiple groups of corresponding practitioners and their historical experience values), and determine the historical experience value of the practitioner as the reliable value of the first flavoring plan formulation record.

[0102] When the identity type is a non-practitioner, determine the collection node where the non-practitioner collects the first flavoring plan formulation record (the source node where the record provider collects the first flavoring plan formulation record, e.g., an online recipe, a network platform), obtain the historical providing behavior of the collection node (which can be extracted from the historical providing records of the collection node), query the preset providing behavior-standard value library (a database containing multiple groups of corresponding providing behaviors and their standard values), determine the standard value of the historical providing behavior, and associate it with the corresponding first flavoring plan formulation record.

[0103] Accumulatively calculate the standard values associated with the first flavoring plan formulation record to obtain the sum of standard values (the larger the sum of standard values, the more available the corresponding first flavoring plan), and use the sum of standard values as the reliable value of the corresponding first flavoring plan formulation record.

[0104] Based on the different identity types of the providers of the first flavoring plan formulation records, this application determines the reliable values of the first flavoring plan formulation records provided by the providers, improving the comprehensiveness of obtaining the reliable values of the first flavoring plan formulation records.

[0105] The present invention provides an automatic flavoring control method for an intelligent cooking machine. Step 3: Based on the flavoring plan to be added, control the intelligent cooking machine to perform automatic flavoring, including:

[0106] Analyze the flavoring plan to obtain the addition amount of at least one first flavoring agent;

[0107] Obtain the remaining amount of the first flavoring agent in the storage unit corresponding to the first flavoring agent;

[0108] Judge whether the addition amount is less than or equal to the remaining amount;

[0109] If not, based on the preset reminder rule, remind the staff to replenish the corresponding first flavoring agent;

[0110] If so, based on the seasoning plan, control the intelligent cooking machine to add the first seasoning to the dish.

[0111] The working principle and beneficial effects of the above technical solution are as follows:

[0112] The preset reminder rule is specifically: a rule for generating reminder information for lack of corresponding seasonings according to the required amounts of different seasonings and the remaining amounts of seasonings.

[0113] Obtain the addition amount of the first seasoning (for example: 10 ml of light soy sauce), obtain the remaining amount of the first seasoning in the corresponding first seasoning storage unit (for example: light soy sauce seasoning jar) (for example: 30 ml). If the addition amount is less than or equal to the remaining amount, control the intelligent cooking machine to perform the operation of adding the seasoning. If the remaining amount is insufficient, send a reminder message to the staff (it can be sent through an intelligent terminal device) to remind the staff to replenish the first seasoning.

[0114] Based on obtaining the addition amount of the first seasoning and the remaining amount of the first seasoning, this application determines whether the first seasoning needs to be replenished, avoiding inappropriate seasoning caused by insufficient seasonings and improving the timeliness of adding the first seasoning.

[0115] The present invention provides an automatic seasoning control method for an intelligent cooking machine, which further includes:

[0116] Analyze the seasoning plan to obtain the seasoning types of multiple first seasonings;

[0117] Based on the seasoning types and based on a preset judgment rule, determine whether the first seasoning needs to be preprocessed;

[0118] If so, based on a preset preprocessing rule, preprocess the first seasoning to obtain a second seasoning after the processing is completed;

[0119] After the first seasoning or the second seasoning is added to the dish, control the intelligent cooking machine to evenly season the dish.

[0120] The working principle and beneficial effects of the above technical solution are as follows:

[0121] Obtain the seasoning types of the first seasonings (such as liquid seasonings and solid seasonings, etc.). The preset judgment rule is specifically: use a machine learning algorithm to learn a large number of logical processes of manual judgment on whether seasonings need to be preprocessed according to seasoning types to generate a judgment logic. Based on the above judgment logic, determine whether the first seasoning needs to be preprocessed. If so, preprocess the first seasoning according to the preset preprocessing rule to obtain a second seasoning (for example: dilute starch with water to obtain starch solution), and evenly season the dish with the first seasoning or the second seasoning.

[0122] The present application pre-processes the first seasoning that needs to be pre-processed based on the pre-processing rules before seasoning, thereby improving the suitability of seasoning for the intelligent cooking machine.

[0123] The present invention provides an automatic seasoning control method for an intelligent cooking machine, which controls the intelligent cooking machine to evenly season the dishes, comprising:

[0124] Acquire a first area of the pot mouth of the intelligent cooking machine, and at the same time, acquire a feeding path and a feeding range of the feeding port of the intelligent cooking machine;

[0125] Based on the feeding path and the feeding range, determining a second area in the first area where feeding has been done, and at the same time, determining a third area in the first area where feeding has not been done;

[0126] Based on the second area and the third area, the intelligent cooking machine is controlled to evenly season the dish.

[0127] The working principle and beneficial effects of the above technical solution are:

[0128] The first area of the pot mouth of the intelligent cooking machine obtained is specifically: the corresponding plane image of the pot mouth of the intelligent cooking machine can be obtained based on the pot mouth image of the intelligent cooking machine taken in advance by the staff. The feeding path and feeding range of the feeding port are specifically: the movement path and feeding range of the feeding port of the intelligent cooking machine. The movement path can be obtained by parsing the pre-set control program, and the feeding range can be obtained according to the size of the feeding port and the feeding height. Based on the feeding path and feeding range, the third area (unfed area) where feeding has been done is determined.

[0129] Based on the second area where materials have been added and the third area where materials have not been added, determine the uniform spreading control scheme to control the intelligent cooking machine to evenly season the dishes (control the direction in which the feeding port of the intelligent cooking machine moves and which direction not to move as much as possible), and control the intelligent cooking machine to evenly spread the first dish. After the spreading is completed, obtain the cooking record of the first dish (for example: the cooking video of the first dish uploaded on the Internet), and extract the stir-frying behavior of the target object (for example: the chef who is cooking) after adding seasoning from the cooking record in sequence. The stir-frying behavior is specifically: in which direction the target object stirs the dish, and the magnitude of the stir-frying. Sort the stir-frying behavior according to the extraction order to obtain the stir-frying behavior sequence, traverse the stir-frying behavior sequence in sequence, and control the intelligent cooking machine to simulate the currently traversed stir-frying behavior to stir-fry the dishes. The simulated stir-frying behavior to stir-fry the dishes is specifically: control the direction in which the intelligent cooking robot stirs the dishes, and the magnitude of the stir-frying until the traversal is completed and the uniform seasoning is completed.

[0130] The present application controls the intelligent cooking machine to spread seasoning evenly, thereby avoiding uneven seasoning caused by uneven seasoning spraying, improving rationality, and controlling the intelligent cooking machine to simulate manual stir-frying behavior to stir-fry dishes, which is more intelligent.

[0131] The present invention provides an automatic seasoning control method for an intelligent cooking machine, which obtains a uniform spreading control scheme, including:

[0132] Based on a preset feature extraction template, feature extraction is performed on the coverage relationship of the second area relative to the third area to obtain a plurality of coverage relationship feature values;

[0133] Based on the covering relationship eigenvalue, construct a first spreading relationship description vector;

[0134] Obtain a preset uniform spreading control scheme library, determine a second spreading relationship description vector in the uniform spreading control scheme library that has the smallest vector angle with the first spreading relationship description vector, and determine a uniform spreading control scheme corresponding to the second spreading relationship description vector in the uniform spreading control scheme library;

[0135] Based on the uniform spreading control scheme, the intelligent cooking machine is controlled to spread the seasoning evenly.

[0136] The working principle and beneficial effects of the above technical solution are:

[0137] When the smart cooking machine adds seasoning to dishes, the spreading position of the seasoning will change with the relative position of the feeding port and the dish. If a fixed feeding port is set, the feeding will be too concentrated, which will easily lead to seasoning accumulation, resulting in inconsistent taste of the food produced. Therefore, it needs to be spread evenly.

[0138] A preset feature extraction template is introduced to perform feature extraction on the coverage relationship of the second area relative to the first area, and multiple coverage relationship feature values are obtained. The coverage relationship feature values are specifically: in which direction the coverage area of the feeding port of the intelligent cooking machine projected on the cooking area needs to extend and in which direction it should not extend as much as possible, etc. The preset feature extraction template is specifically: a feature extraction template pre-formulated to adapt to the extraction of such coverage relationship feature values.

[0139] Based on the coverage relationship feature values, a first spreading relationship description vector of the second region and the third region is constructed (for example, the area of the second region, the shape of the second region, the area of the third region, the shape of the third region, etc.).

[0140] The preset uniform spreading control scheme library is specifically as follows: based on a large number of manually listed situations in which chefs spread seasonings, the same means as mentioned above are adopted to construct a second spreading relationship description vector of the spread area and the unspread area, and according to the situation of seasoning spreading, a suitable uniform spreading control scheme is formulated to enable the intelligent cooking machine to spread the seasoning uniformly. The uniform spreading control scheme is specifically as follows: control the direction in which the feeding port of the intelligent cooking machine moves and the direction in which it should not move as much as possible.

[0141] Calculate the similarity of the first paving relationship description vector and the vector angle of the second paving relationship description vector in the uniform paving control scheme library, determine the uniform paving control scheme corresponding to the second paving relationship description vector with the largest vector angle, and control the intelligent cooking machine to spread the dishes evenly based on the above uniform paving control scheme.

[0142] The present application evenly spreads the dishes cooked in the intelligent cooking machine to avoid uneven seasoning caused by uneven seasoning spreading. A uniform spreading control scheme library is introduced to determine a suitable uniform spreading control scheme to control the intelligent cooking machine, thereby improving the accuracy of seasoning spreading and the suitability of the taste of dishes cooked by the cooking machine.

[0143] The present invention provides an automatic seasoning control method for an intelligent cooking machine, wherein the method sequentially extracts the stir-frying behavior of a target object after adding seasoning from a cooking record, and comprises:

[0144] Extracting a plurality of first images containing the target object from the cooking record;

[0145] Based on a preset gray value correction rule, gray value correction is performed on the pre-corrected image to obtain a corrected second image;

[0146] Extract the stir-frying behavior of the target object in the second image. When all the stir-frying behaviors to be extracted are extracted, the extraction of the stir-frying behaviors is completed.

[0147] The working principle and beneficial effects of the above technical solution are:

[0148] Since the first image may not be clear, the extracted stir-frying behavior may not be accurate. In order to improve the accuracy of behavior extraction, the first image needs to be corrected.

[0149] The preset gray value correction rules are as follows:

[0150] The original grayscale function of the first image is obtained, and based on a preset transformation function, a modified grayscale function after transformation is determined, wherein the modified grayscale function is specifically:

[0151] g(x,y)=log[f(x,y)]

[0152] Among them, (x, y) are the coordinates of the pixel points on the first image to be transformed, f(x, y) is the original grayscale function, g(x, y) is the corrected grayscale function, and log[…] is the transformation function.

[0153] The first image is corrected through the corrected grayscale function to obtain a second image.

[0154] This application corrects the first image based on the introduction of a transformation function, improves the contrast of the image, and improves the accuracy of the extraction of the first stir-frying behavior.

[0155] The present invention provides an automatic seasoning control system for an intelligent cooking machine, as Figure 2 shown, including:

[0156] An acquisition module 1 for acquiring the first execution step currently being executed when the intelligent cooking machine fries a dish;

[0157] A judgment module 2 for acquiring the step type of the first execution step and judging whether the step type is adding seasonings. If so, a seasoning plan is determined;

[0158] A control module 3 for controlling the intelligent cooking machine to perform automatic seasoning based on the required seasoning plan.

[0159] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. An automatic flavoring control method for an intelligent cooking machine, characterized in that, Including: Step 1: Obtain the first execution step being executed when the intelligent cooking machine fries a dish; Step 2: Obtain the step type of the first execution step, and determine whether the step type is adding seasonings. If so, determine a seasoning plan; Step 3: Based on the seasoning plan, control the intelligent cooking machine to perform automatic seasoning; The determining of the seasoning plan includes: Obtain the quality of the dish and the executed steps of the intelligent cooking machine; Train a seasoning plan formulation model; Based on the seasoning plan formulation model, determine a seasoning plan according to the quality of the dish and the executed steps of the intelligent cooking machine; The training of the seasoning plan formulation model includes: Based on big data technology, obtain multiple first seasoning plan formulation records; Obtain the reliability value of the first seasoning plan formulation record; If the reliability value is greater than or equal to a preset reliability value threshold, use the corresponding first seasoning plan formulation record as a training target; Input the training target into a preset neural network model for model training; When the neural network model is trained to convergence, use the corresponding neural network model as the seasoning plan formulation model; The obtaining of the reliability value of the first seasoning plan formulation record includes: Obtain the identity type of the provider of the first seasoning plan formulation record; When the identity type is a practitioner, obtain a preset practitioner-historical experience value library, determine the historical experience value of the practitioner, and use it as the reliability value corresponding to the first seasoning plan formulation record; When the identity type is a non-practitioner, obtain the historical providing behavior of the collection node where the non-practitioner collects the first seasoning plan formulation record; Query a preset providing behavior-specification value library, determine the specification value of the historical providing behavior, and associate it with the corresponding first seasoning plan formulation record; Accumulatively calculate the specification values associated with the first seasoning plan formulation record to obtain the reliability value.

2. The automatic seasoning control method of an intelligent cooking machine according to claim 1, characterized in that Step 1: Obtain the first execution step being executed when the intelligent cooking machine fries a dish, including: Obtain the first control signal currently received by the intelligent cooking machine; Obtain a preset control signal-execution step library, where the control signal-execution step library includes: multiple corresponding second control signals and second execution steps; Match the first control signal with the second control signals in the control signal-execution step library; If there is a match, use the second execution step corresponding to the matched second control signal as the first execution step.

3. The automatic flavoring control method of an intelligent cooking machine according to claim 1, characterized in that, Step 3: Based on the seasoning plan, control the intelligent cooking machine to perform automatic seasoning, including: Parse the seasoning plan to obtain the addition amounts of at least one first seasoning; Obtain the remaining amount of the first seasoning in the corresponding storage unit of the first seasoning; Determine whether the addition amount is less than or equal to the remaining amount; If not, based on a preset reminder rule, remind the staff to replenish the corresponding first seasoning; If so, based on the seasoning plan, control the intelligent cooking machine to add the first seasoning to the dish.

4. The automatic flavoring control method of an intelligent cooking machine according to claim 1, characterized in that, It also includes: Parse the seasoning plan to obtain the seasoning types of multiple first seasonings; Based on the type of the seasoning, determine whether pretreatment of the first seasoning is required according to a preset judgment rule; If so, perform pretreatment on the first seasoning according to a preset pretreatment rule to obtain a second seasoning after the treatment is completed; After the first seasoning or the second seasoning is added to the dish, control the intelligent cooking machine to evenly season the dish.

5. The automatic flavoring control method of an intelligent cooking machine according to claim 4, characterized in that The control of the intelligent cooking machine to evenly season the dish includes: Obtain the feeding path and feeding range within a first area corresponding to the pot mouth at the feeding port of the intelligent cooking machine; Based on the feeding path and feeding range, determine a second area where feeding has been performed and a third area where feeding has not been performed within the first area; Based on the second area and the third area, determine a uniform spreading control scheme, control the intelligent cooking machine to evenly spread the seasoning, and after the uniform spreading is completed, obtain the cooking record of the first dish; Sequentially extract the frying behaviors after adding the seasoning to the target object from the cooking record to obtain a frying behavior sequence, sequentially traverse the frying behaviors in the frying behavior sequence, and control the intelligent cooking machine to simulate the currently traversed frying behavior to fry the dish until the traversal is completed, thus completing the uniform seasoning of the dish.

6. The automatic flavoring control method of an intelligent cooking machine according to claim 5, wherein, The determination of the uniform spreading control scheme includes: Based on a preset feature extraction template, extract features of the coverage relationship of the second area relative to the third area to obtain a plurality of coverage relationship feature values; Based on the coverage relationship feature values, construct a first spreading relationship description vector; Obtain a preset uniform spreading control scheme library, determine a second spreading relationship description vector in the uniform spreading control scheme library with the smallest vector angle with the first spreading relationship description vector, and determine the uniform spreading control scheme corresponding to the second spreading relationship description vector in the uniform spreading control scheme library; Based on the uniform spreading control scheme, control the intelligent cooking machine to evenly spread the seasoning.

Images