A control method for an intelligent cooking machine

Abstract

The present invention provides a control method for an intelligent cooking machine, comprising: receiving a user's dish request, and determining a corresponding control instruction according to the user's dish request; wherein the control instruction includes a dish-taking instruction, a step-by-step cooking instruction, a seasoning instruction, and a delivery instruction; and controlling the intelligent cooking machine to complete the cooking work and the delivery work according to the corresponding control instruction; the present invention is used to solve the problem that the existing cooking machines cannot meet the needs of users with different tastes for dishes.

Description

Technical Field

[0001] The present invention relates to the technical field of stir-fry machine control, and particularly relates to a control method for an intelligent stir-fry machine. Background Art

[0002] In recent years, with the continuous improvement of living standards, intelligent stir-fry machines have gradually emerged in the market and are increasingly accepted by people. However, the existing stir-fry machines can only complete stir-frying according to the corresponding programs and cannot meet the needs of users with different tastes for dishes. For example, in Chinese Patent CN113126513A, an invention patent with the patent name of a control method for an intelligent stir-fry machine, its method includes S1: the stir-fry center receives the customer menu and arranges for the stir-fry machine to stir-fry; S2: the vegetable-taking mechanism assigns a vegetable side dish box to the stir-fry machine; S3: the stir-fry machine stir-fries according to the corresponding program; S4: delivers the completed dish to the pick-up port or the customer's table; S5: cleans the stir-fry machine, the vegetable-taking mechanism replaces the vegetable side dish box of the stir-fry machine, and the stir-fry machine stir-fries until the stir-fry machine completes the stir-fry task. It solves the technical problem that the stir-fry machine is prone to errors in the order and time of adding ingredients because ingredients need to be added manually. However, it always uses a fixed program for stir-frying each dish and cannot meet the needs of users with different tastes for dishes. Therefore, there is an urgent need for a control method for an intelligent stir-fry machine to select the corresponding stir-fry program according to the taste requirements of different users and meet the taste needs of users. Summary of the Invention

[0003] Aiming at the deficiencies of the prior art, the present invention provides a control method for an intelligent stir-fry machine to solve the problem that the existing stir-fry machines cannot meet the needs of users with different tastes for dishes.

[0004] A control method for an intelligent stir-fry machine includes:

[0005] Receiving a user dish request and determining a corresponding control instruction according to the user dish request; wherein, the control instruction includes a vegetable-taking instruction, a step-by-step stir-fry instruction, a seasoning instruction, and a delivery instruction;

[0006] Controlling the intelligent stir-fry machine to complete the stir-fry work and the delivery work according to the corresponding control instruction.

[0007] As an embodiment of the present invention, receiving a user dish request and determining a corresponding control instruction according to the user dish request includes:

[0008] Receiving the user dish request input by the user and parsing the user dish request to obtain a parsing result;

[0009] Obtaining the specific dish and the delivery instruction included in the parsing result, judging whether the parsing result includes stir-fry guiding opinions, generating a judgment result, and determining the corresponding control instruction according to the judgment result.

[0010] As an embodiment of the present invention, determining corresponding control instructions according to the judgment result includes:

[0011] If the judgment result is that there is no cooking guidance, automatically call the default cooking step-by-step instructions, default ingredient-taking instructions, and default seasoning instructions corresponding to the specific dish in the database according to the specific dish;

[0012] If the judgment result is that there is cooking guidance, judge whether the cooking guidance conforms to the normal guidance based on the cooking logic judgment model;

[0013] If it does not conform, rectify the cooking guidance to obtain the normal guidance;

[0014] If it conforms, obtain the personalized cooking step-by-step instructions and taste preference instructions included in the cooking guidance;

[0015] Determine the personalized ingredient-taking instructions according to the personalized cooking step-by-step instructions;

[0016] Automatically call the personalized seasoning instructions corresponding to the specific dish and the taste preference instructions in the database according to the taste preference instructions and the specific dish.

[0017] As an embodiment of the present invention, the training steps of the cooking logic judgment model include:

[0018] Obtain the cooking step-by-step instruction data of several correct different specific dishes as the first data, and correctly mark the first data;

[0019] Randomly arrange the cooking step-by-step instructions of all specific dishes in the first data as the second data, and incorrectly mark the second data; wherein, any cooking step-by-step instruction in the second data is different from any cooking step-by-step instruction in the first data;

[0020] Train the initial judgment model according to the first data and the second data until the training meets the first preset condition and ends, to obtain the cooking logic judgment model.

[0021] As an embodiment of the present invention, rectifying the cooking guidance to obtain the normal guidance includes:

[0022] Obtain the specific cooking step-by-step instructions in each cooking step-by-step instruction in the first data that has the same specific dish as the cooking guidance, to obtain several first specific cooking step-by-step instructions;

[0023] Obtain the specific cooking step-by-step instructions in the cooking guidance to obtain the second specific cooking step-by-step instructions;

[0024] Select the first specific stir-fry step instruction with the highest text similarity to the second specific stir-fry step instruction among several first specific stir-fry step instructions as the specific stir-fry step instruction in the stir-fry guidance opinion. At the same time, combine the specific dishes in the stir-fry guidance opinion to obtain the normal guidance opinion.

[0025] As an embodiment of the present invention, according to the corresponding control instruction, control the intelligent stir-fry machine to complete the stir-fry work, including:

[0026] According to the vegetable-taking instruction, determine the position of the to-be-taken ingredients and the quantity of the to-be-taken ingredients;

[0027] Control the ingredient-grabbing module to grab the corresponding ingredients and put them into the pot according to the position of the to-be-taken ingredients and the quantity of the to-be-taken ingredients;

[0028] After the corresponding ingredients are put into the pot, determine the current stir-fry step according to the stir-fry step instruction, and control the stir-fry module to perform the corresponding stir-fry operation according to the current stir-fry step;

[0029] While the stir-fry module is performing the corresponding stir-fry operation, according to the seasoning instruction, determine whether there are types of seasonings to be put in and the quantity of seasonings to be put in for the current stir-fry step;

[0030] If there are types of seasonings to be put in and the quantity of seasonings to be put in currently, control the seasoning-grabbing unit to grab the corresponding seasonings and put them into the pot according to the types of seasonings to be put in and the quantity of seasonings to be put in;

[0031] If the current stir-fry step is a preset time away from the end time, determine the position of the next to-be-taken ingredient and the quantity of the next to-be-taken ingredient according to the vegetable-taking instruction, and control the ingredient-grabbing module to grab the corresponding ingredients and put them into the pot when the current stir-fry step ends;

[0032] At the same time, according to the seasoning instruction, determine whether there are types of seasonings to be put in and the quantity of seasonings to be put in for the next stir-fry step, and control the seasoning-grabbing unit to grab the corresponding seasonings and put them into the pot after the current stir-fry step ends;

[0033] Repeat the above steps until the intelligent stir-fry machine completes the stir-fry work.

[0034] As an embodiment of the present invention, according to the corresponding control instruction, control the intelligent stir-fry machine to complete the delivery work, including:

[0035] After the intelligent stir-fry machine completes the stir-fry work, according to the delivery instruction, control the delivery module to send the cooked dishes to the user-specified delivery location and send a delivery completion message to the user.

[0036] As an embodiment of the present invention, a control method for an intelligent stir-fry machine further includes:

[0037] After the intelligent cooking machine finishes cooking, it automatically cleans the intelligent cooking machine, and at the same time receives the next user's dish request. After the cleaning is completed, it controls the intelligent cooking machine to complete the next cooking work and the next delivery work.

[0038] As an embodiment of the present invention, a control method for an intelligent cooking machine further includes:

[0039] Obtain the blind box request input by the user, and determine the first user dish request according to the blind box request;

[0040] Classify all the first user dish requests using a group divider to obtain the groups of all flavor preference types in all the first user dish requests as the first group; wherein, each first user dish request includes the specific dish types of this flavor preference type, and each specific dish type includes at least one specific dish;

[0041] Obtain all the specific dishes within each group of each flavor preference type in the first group, and calculate the first number of times each specific dish is ordered;

[0042] Determine the first probability of the corresponding specific dish having a signature dish relationship with the group of the corresponding flavor preference type according to the ratio of the first number of times to the second number of times that all the specific dishes within the group of the corresponding flavor preference type are ordered;

[0043] Assign weight values to different flavor preference types in the user's recent dish requests according to the acquisition time, where the longer the acquisition time is from the current time, the higher the weight value;

[0044] Perform multiplication operations on all the first probabilities and the weight values of the corresponding flavor preference types respectively to obtain a number of second probabilities; select the specific dish corresponding to the largest second probability as the specific dish corresponding to this blind box request.

[0045] As an embodiment of the present invention, determining the first user dish request according to the blind box request includes:

[0046] Parse the user information carried in the blind box request, obtain the user's historical dish requests according to the user information, and determine the user's flavor preference and consumption habit according to the user's recent dish requests in the user's historical dish requests;

[0047] Obtain all the user dish requests received recently except the blind box request, and screen all the user dish requests according to the user's flavor preference and consumption habit to obtain the first user dish requests that meet the user's flavor preference and consumption habit.

[0048] The beneficial effects of the present invention are:

[0049] The present invention provides a control method for an intelligent cooking machine, which is used to solve the problem that existing cooking machines cannot meet the needs of users with different tastes for dishes.

[0050] 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 achieved and obtained by the structures specifically pointed out in the written specification and the drawings.

[0051] The technical solution of the present invention will be further described in detail below through the drawings and embodiments. Description of the Drawings

[0052] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0053] Figure 1 is a flowchart of a control method for an intelligent cooking machine in an embodiment of the present invention;

[0054] Figure 2 is a flowchart of determining a control instruction in a control method for an intelligent cooking machine in an embodiment of the present invention;

[0055] Figure 3 is a training flowchart of training a cooking logic judgment model in a control method for an intelligent cooking machine in an embodiment of the present invention;

[0056] Figure 4 is a rectification step flowchart of rectifying cooking guidance opinions in a control method for an intelligent cooking machine in an embodiment of the present invention. Detailed Embodiments

[0057] The following describes the preferred embodiments of the present invention with reference to the drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0058] Please refer to Figure 1 , an embodiment of the present invention provides a control method for an intelligent cooking machine, including:

[0059] S101. Receive a user's dish request, and determine a corresponding control instruction according to the user's dish request; wherein, the control instruction includes a dish-taking instruction, a step-by-step cooking instruction, a seasoning instruction, and a delivery instruction;

[0060] S102. Control the intelligent cooking machine to complete the cooking work and the delivery work according to the corresponding control instruction.

[0061] The working principle of the above technical solution is as follows: The intelligent cooking machine is often arranged in places such as users' kitchens and canteens. When a user needs to cook, the user's dish request is input through an external input screen or corresponding APP modules. After the control module of the intelligent cooking machine obtains the user's dish request, according to this user's dish request, it filters the corresponding control instructions in the preset database, or analyzes the user's dish request through the processing module to obtain the corresponding control instructions. Finally, according to this control instruction, it controls other modules of the intelligent cooking machine to complete the cooking work and distribution work;

[0062] The beneficial effect of the above technical solution is as follows: It is beneficial to solve the problem that the existing cooking machines cannot meet the needs of users with different tastes for dishes.

[0063] Please refer to Figure 2 , in one embodiment, receiving the user's dish request and determining the corresponding control instruction according to the user's dish request includes:

[0064] S201. Receive the user's dish request input by the user and parse the user's dish request to obtain the parsing result;

[0065] S202. Obtain the specific dishes and distribution instructions included in the parsing result, and determine whether the parsing result includes cooking guidance opinions, generate a judgment result, and determine the corresponding control instruction according to the judgment result;

[0066] The working principle of the above technical solution is as follows: After receiving the user's dish request, parse the user's dish request to understand the user's specific needs in real time. Among them, if the user has specific needs, the parsing result will include cooking guidance opinions, otherwise it will not include cooking guidance opinions. Finally, the corresponding control instruction is determined according to the specific judgment result;

[0067] The beneficial effect of the above technical solution is as follows: Different control instructions are generated according to the user's specific needs, which is beneficial to meeting the user's personalized dish needs and improving user satisfaction.

[0068] In one embodiment, determining the corresponding control instruction according to the judgment result includes:

[0069] If the judgment result is that there is no cooking guidance opinion, automatically call the default cooking step-by-step instructions, default dish-taking instructions, and default seasoning instructions corresponding to the specific dishes in the database according to the specific dishes;

[0070] If the judgment result is that there is cooking guidance opinion, judge whether the cooking guidance opinion conforms to the normal guidance opinion based on the cooking logic judgment model;

[0071] If it does not conform, rectify the cooking guidance opinion to obtain the normal guidance opinion;

[0072] If it meets the requirements, obtain the personalized step-by-step cooking instructions and taste preference instructions included in the cooking guidance opinion;

[0073] Determine the personalized ingredient selection instructions according to the personalized step-by-step cooking instructions;

[0074] Automatically call the personalized seasoning instructions corresponding to the specific dish and taste preference instructions in the database according to the taste preference instructions and the specific dish;

[0075] The working principle of the above technical solution is as follows: When the user does not input cooking guidance opinions, that is, when the user does not have many independent ideas about the taste of the dish, the intelligent cooking machine automatically calls the default step-by-step cooking instructions, default ingredient selection instructions and default seasoning instructions corresponding to the specific dish in the database according to the specific dish input by the user. The taste of the dish cooked by the default control instructions is usually selected as the taste that most users can adapt to. When the user inputs cooking guidance opinions, first, perform a logical judgment on the cooking guidance opinions to determine whether there are unreasonable places in the cooking guidance opinions. For example, when the user inputs incorrect information, and the method of logical judgment is to judge whether the cooking guidance opinions meet the normal guidance opinions through the cooking logic judgment model. When the cooking guidance opinions are unreasonable, rectify the cooking guidance opinions through the set rectification rules to obtain the normal guidance opinions and perform subsequent operations. When the cooking guidance opinions input by the user are normal guidance opinions themselves, obtain the personalized step-by-step cooking instructions and taste preference instructions included in the cooking guidance opinions. The taste preference instructions include various taste preference instructions such as heavy spicy, medium spicy, slightly spicy, slightly salty, sweet, etc. Finally, determine the personalized ingredient selection instructions according to the personalized step-by-step cooking instructions. Among them, the step-by-step cooking instructions and the ingredient selection instructions are corresponding. For example, after taking ingredients once, the step-by-step cooking instructions perform a cooking step. When it is almost finished, take the ingredients needed for the next step through the ingredient selection instructions, and so on until the cooking is completed. At the same time, automatically call the personalized seasoning instructions corresponding to the specific dish and taste preference instructions in the database according to the taste preference instructions and the specific dish, and during the cooking process, select the corresponding seasonings according to the personalized seasoning instructions and add them into the pot at the appropriate time;

[0076] The beneficial effects of the above technical solution are as follows: Through the above solution, the taste of the dish can be adjusted according to the user's taste. At the same time, when there are errors in the content input by the user, the intelligent cooking machine can automatically adjust the error content, thereby improving the intelligence of the intelligent cooking machine and improving the user experience.

[0077] Please refer to Figure 3 , in one embodiment, the training steps of the cooking logic judgment model include:

[0078] S301. Obtain the different step-by-step cooking instruction data of several correct different specific dishes as the first data, and correctly label the first data;

[0079] S302. Shuffle the step-by-step cooking instructions of all specific dishes in the first data as the second data, and incorrectly label the second data; wherein, any step-by-step cooking instruction in the second data is different from any step-by-step cooking instruction in the first data;

[0080] S303. Train the initial judgment model according to the first data and the second data until the training meets the first preset condition and ends, obtaining a cooking logic judgment model;

[0081] The working principle of the above technical solution is as follows: The training steps of the cooking logic judgment model include Step 1: Obtain the different step-by-step cooking instruction data of several correct different specific dishes as the first data, and correctly label the first data. Step 2: Shuffle the step-by-step cooking instructions of all specific dishes in the first data as the second data, and incorrectly label the second data; wherein, any step-by-step cooking instruction in the second data is different from any step-by-step cooking instruction in the first data. Step 3: Train the initial judgment model according to the first data and the second data until the training meets the first preset condition and ends, obtaining a cooking logic judgment model. During the training, the first data or the second data is randomly input, so that the model outputs a correct or incorrect result, and at the same time, the correctness of the output result is judged according to the label of the first data or the second data. Repeated training is carried out until the preset condition is met and ends. The preset condition can be that the correct rate reaches 98%;

[0082] The beneficial effect of the above technical solution is: Through the cooking logic judgment model, the rationality of the cooking guidance opinions input by the user is judged, preventing the occurrence of dish waste caused by incorrect user input.

[0083] Please refer to Figure 4 , in one embodiment, rectify the cooking guidance opinions to obtain normal guidance opinions, including:

[0084] S401. Obtain the specific cooking step-by-step instructions in each cooking step-by-step instruction in the first data that has the same specific dish as the cooking guidance opinion, obtaining several first specific cooking step-by-step instructions;

[0085] S402. Obtain the specific cooking step-by-step instructions in the cooking guidance opinion, obtaining second specific cooking step-by-step instructions;

[0086] S403. Select the first specific cooking step instruction with the highest text similarity to the second specific cooking step instruction among several first specific cooking step instructions as the specific cooking step instruction in the cooking guidance opinion. At the same time, combine the specific dishes in the cooking guidance opinion to obtain the normal guidance opinion;

[0087] The working principle of the above technical solution is as follows: Step 1. Obtain the specific cooking step instructions in each cooking step instruction in the first data that have the same specific dishes as the cooking guidance opinion to obtain several first specific cooking step instructions; Step 2. Obtain the specific cooking step instructions in the cooking guidance opinion to obtain the second specific cooking step instruction; Step 3: Select the first specific cooking step instruction with the highest text similarity to the second specific cooking step instruction among several first specific cooking step instructions as the specific cooking step instruction in the cooking guidance opinion. At the same time, combine the specific dishes in the cooking guidance opinion to obtain the normal guidance opinion; Further, the rectification result can also be sent to the user, and the cooking operation can be performed according to the rectification plan with the user's permission, which is beneficial to improving the user's sense.

[0088] The beneficial effect of the above technical solution: When it is found that the guidance opinion input by the user is unreasonable, if the reminder method is used to remind the user to re-enter, the cooking efficiency will be greatly reduced. At the same time, using the method of the user re-entering will also reduce the user's sense, resulting in a poor user experience. However, through the above solution, when the user enters wrongly, the unreasonable guidance opinion is automatically rectified, which is beneficial to improving the cooking efficiency.

[0089] In one embodiment, according to the corresponding control instruction, control the intelligent cooking machine to complete the cooking work, including:

[0090] According to the ingredient-taking instruction, determine the position and quantity of the ingredients to be taken;

[0091] According to the position and quantity of the ingredients to be taken, control the ingredient-grabbing module to grab the corresponding ingredients and put them into the pot;

[0092] After the corresponding ingredients are put into the pot, determine the current cooking step according to the cooking step instruction, and control the cooking module to perform the corresponding cooking operation according to the current cooking step;

[0093] While the cooking module is performing the corresponding cooking operation, according to the seasoning instruction, determine whether there are the types and quantities of seasonings to be put in the current cooking step;

[0094] If there are the types and quantities of seasonings to be put in currently, control the seasoning-grabbing unit to grab the corresponding seasonings and put them into the pot according to the types and quantities of seasonings to be put in;

[0095] When the remaining time of the current cooking step is equal to the preset time, determine the position and quantity of the next ingredient to be fetched according to the ingredient fetching instruction, and control the ingredient grasping module to grasp the corresponding ingredient and put it into the pot when the current cooking step ends;

[0096] Meanwhile, according to the seasoning instruction, determine whether there are types and quantities of seasonings to be put in the next cooking step, and control the seasoning grasping unit to grasp the corresponding seasonings and put them into the pot after the current cooking step ends;

[0097] Repeat the above steps until the intelligent cooking machine finishes the cooking work;

[0098] The working principle of the above technical solution is as follows: Determine the position and quantity of the ingredient to be fetched according to the ingredient fetching instruction. Usually, the intelligent cooking machine is equipped with a side dish box. By pre-identifying and positioning the ingredients in the side dish box, it can quickly obtain the correct ingredients during cooking. Then, control the ingredient grasping module to grasp the corresponding ingredient and put it into the pot according to the position and quantity of the ingredient to be fetched. Conventional steps such as heating the oil in the pot are also included in this step. After the corresponding ingredient is put into the pot, determine the current cooking step according to the step-by-step cooking instruction, and control the cooking module to perform the corresponding cooking operation according to the current cooking step. Cooking operations include heating operation, frying operation, rotating operation, etc. While the cooking module is performing the corresponding cooking operation, determine whether there are types and quantities of seasonings to be put in the current cooking step according to the seasoning instruction. The seasoning instruction also includes the specific time of putting. If there are types and quantities of seasonings to be put in the current step, control the seasoning grasping unit to grasp the corresponding seasonings and put them into the pot according to the types and quantities of seasonings to be put. And when the current cooking step is about to end, determine the position and quantity of the next ingredient to be fetched according to the ingredient fetching instruction, and control the ingredient grasping module to grasp the corresponding ingredient and put it into the pot when the current cooking step ends. Meanwhile, determine whether there are types and quantities of seasonings to be put in the next cooking step according to the seasoning instruction, and control the seasoning grasping unit to grasp the corresponding seasonings and put them into the pot after the current cooking step ends. This step is beneficial to improving the cooking efficiency. Repeat the above steps until the intelligent cooking machine finishes the cooking work;

[0099] The beneficial effect of the above technical solution is as follows: Each step is divided, and there is no need to add all the ingredients into the pot at one time like the existing cooking machines, which is beneficial to improving the taste of the dishes and thus improving the user satisfaction.

[0100] In one embodiment, control the intelligent cooking machine to complete the delivery work according to the corresponding control instruction, including:

[0101] After the intelligent cooking machine finishes cooking, according to the delivery instruction, it controls the delivery module to send the cooked dishes to the delivery location specified by the user and sends a delivery completion message to the user.

[0102] The beneficial effect of the above technical solution is that by the above solution, the dishes in the pot are cleaned out in time after cooking, which is beneficial to improving the cooking efficiency.

[0103] In one embodiment, a control method for an intelligent cooking machine further includes: after the intelligent cooking machine finishes cooking, automatically cleaning the intelligent cooking machine, and at the same time receiving the next user's dish request. After the cleaning is completed, it controls the intelligent cooking machine to complete the next cooking work and the next delivery work.

[0104] The beneficial effect of the above technical solution is that by the above solution, the next round of cooking is quickly carried out after cooking, which is beneficial to improving the cooking efficiency.

[0105] In one embodiment, a control method for an intelligent cooking machine further includes:

[0106] Obtain the blind box request input by the user, and determine the first user dish request according to the blind box request.

[0107] Classify all the first user dish requests using a grouper to obtain the groups of all taste preference types in all the first user dish requests as the first group; wherein, each first user dish request includes the specific dish types of the taste preference type, and each specific dish type includes at least one specific dish.

[0108] Obtain all the specific dishes in each group of taste preference types in the first group, and calculate the first number of times each specific dish is ordered.

[0109] Determine the first probability of the corresponding specific dish having a signature dish relationship with the group of the corresponding taste preference type according to the ratio of the first number of times to the second number of times that all the specific dishes in the group of the corresponding taste preference type are ordered.

[0110] Assign weight values to different taste preference types in the user's recent dish requests according to the acquisition time, where the longer the acquisition time is from the current time, the higher the weight value.

[0111] Perform multiplication operations on all the first probabilities and the weight values of the corresponding taste preference types respectively to obtain a number of second probabilities; select the specific dish corresponding to the largest second probability as the specific dish corresponding to this blind box request.

[0112] The working principle of the above technical solution is as follows: In actual situations, there are often some users who don't know how to choose what to eat. In the existing food blind box model, the food blind boxes are often distributed to customers according to the will of the merchant itself or randomly, which will lead to some customers receiving food blind boxes that are not the types they like to eat, thus having a bad impression of the relevant restaurants, and further reducing the recognition rate of the restaurants. Through this solution, customized blind box meals are developed for each customer according to the user's taste, consumption habits, and the most popular food at present, so that each blind box meal can meet the customer's needs, thereby improving the customer's satisfaction with the cooking machine. The specific solution is as follows: When a user requests a blind box, obtain the blind box request input by the user, and determine the first user dish request according to the blind box request; determining the first user dish request according to the blind box request includes: parsing the user information carried in the blind box request, obtaining the user's historical dish requests according to the user information, and determining the user's taste preference and consumption habit according to the user's recent dish requests in the user's historical dish requests; obtain all user dish requests received recently except the blind box request, and screen all user dish requests according to the user's taste preference and consumption habit to obtain the first user dish request that meets the user's taste preference and consumption habit; among them, the user's consumption habit preferably refers to the average value of the amount of each consumption in the restaurant by the user recently; then classify all the first user dish requests using a grouper to obtain the grouping N = {N1, N2... N r} of all taste preference types in all the first user dish requests, where r is the total number of taste preference types, as the first grouping N; among them, each first user dish request includes the specific dish type of this taste preference type, and each specific dish type includes at least one specific dish; obtain all the specific dishes N i = {n1, n2... n p} in the grouping of each taste preference type in the first grouping N, where i is a natural number and is greater than or equal to 1 and less than or equal to r, and p is the number of specific dishes in the grouping of the i-th taste preference type, and calculate the first number of times K that each specific dish is ordered; determine the first probability P of the corresponding specific dish having a signature dish relationship with the grouping of the corresponding taste preference type according to the ratio of the first number of times K to the second number of times L that all the specific dishes in the grouping of the corresponding taste preference type are ordered, that is, P = K / L; then assign weights to different taste preference types in the user's recent dish requests according to the acquisition time, where the longer the acquisition time is from the current time, the higher the weight value is, and the shorter the acquisition time is from the current time, the lower the weight value is, and the weight value is greater than 0 and less than 1; recently is preferably half a month; perform multiplication operations on all the first probabilities and the weight values of the corresponding taste preference types respectively to obtain several second probabilities; select the specific dish corresponding to the largest second probability as the specific dish corresponding to this blind box request;

[0113] The beneficial effects of the above technical solution are as follows: Through the above solution, while satisfying the user's desire to pursue a sense of the unknown, the taste needs of the user are met according to the user's taste preferences and the taste preferences of relevant users, thereby further improving the user's satisfaction with the product. In addition, when the product is used in commercial food industries such as restaurants, this solution can provide a targeted blind box experience for different users, improve customers' recognition of the restaurant, and thus increase the customer flow of the restaurant.

[0114] 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 modifications and variations.

Claims

1. A control method for an intelligent cooking machine, characterized in that, Including: Receiving a user's dish request and determining a corresponding control instruction according to the user's dish request; wherein, the control instruction includes a dish-taking instruction, step-by-step cooking instructions, a seasoning instruction, and a delivery instruction; Controlling an intelligent cooking machine to complete cooking work and delivery work according to the corresponding control instruction; Receiving a user's dish request and determining a corresponding control instruction according to the user's dish request, including: Receiving the user's dish request input by the user and parsing the user's dish request to obtain a parsing result; Obtaining the specific dish and delivery instruction included in the parsing result, determining whether the parsing result includes cooking guidance, generating a judgment result, and determining a corresponding control instruction according to the judgment result; Determining a corresponding control instruction according to the judgment result, including: If the judgment result is that there is no cooking guidance, automatically calling the default step-by-step cooking instruction, default dish-taking instruction, and default seasoning instruction corresponding to the specific dish in the database according to the specific dish; If the judgment result is that there is cooking guidance, judging whether the cooking guidance conforms to normal guidance based on a cooking logic judgment model; If not, rectifying the cooking guidance to obtain normal guidance; If so, obtaining the personalized step-by-step cooking instruction and taste preference instruction included in the cooking guidance; Determining a personalized dish-taking instruction according to the personalized step-by-step cooking instruction; Automatically calling the personalized seasoning instruction corresponding to the specific dish and the taste preference instruction in the database according to the taste preference instruction and the specific dish.

2. The control method of an intelligent cooking machine according to claim 1, characterized in that, The training steps of the cooking logic judgment model include: Obtaining different step-by-step cooking instruction data of several correct specific dishes as the first data and correctly marking the first data; Randomly arranging the step-by-step cooking instructions of all specific dishes in the first data as the second data and wrongly marking the second data; wherein, any step-by-step cooking instruction in the second data is different from any step-by-step cooking instruction in the first data; Training an initial judgment model according to the first data and the second data until the training meets a first preset condition and ends, obtaining a cooking logic judgment model.

3. The control method of an intelligent cooking machine according to claim 2, characterized in that, Rectifying the cooking guidance to obtain normal guidance, including: Obtaining the specific cooking steps in each step-by-step cooking instruction having the same specific dish as the cooking guidance in the first data to obtain several first specific cooking steps; Obtaining the specific cooking steps in the cooking guidance to obtain a second specific cooking step; Selecting the first specific cooking step with the highest text similarity to the second specific cooking step among several first specific cooking steps as the specific cooking step in the cooking guidance, and at the same time combining the specific dish in the cooking guidance to obtain normal guidance.

4. The control method of an intelligent cooking machine according to claim 1, characterized in that, Controlling an intelligent cooking machine to complete cooking work according to the corresponding control instruction, including: Determining the position of the ingredients to be taken and the quantity of the ingredients to be taken according to the dish-taking instruction; Controlling an ingredient grabbing module to grab the corresponding ingredients and put them into the pot according to the position of the ingredients to be taken and the quantity of the ingredients to be taken; After the corresponding ingredients are put into the pot, determining the current cooking step according to the step-by-step cooking instruction and controlling a cooking module to execute the corresponding cooking operation according to the current cooking step; While the cooking module is performing the corresponding cooking operation, according to the seasoning instruction, determine whether there is a type of seasoning to be put in and the quantity of the seasoning to be put in for the current cooking step; If there is a type of seasoning to be put in and the quantity of the seasoning to be put in currently, control the seasoning grabbing unit to grab the corresponding seasoning and put it into the pot according to the type of seasoning to be put in and the quantity of the seasoning to be put in; When the remaining time of the current cooking step is within a preset time from the end time, determine the position of the next ingredient to be taken and the quantity of the next ingredient to be taken according to the ingredient taking instruction, and control the ingredient grabbing module to grab the corresponding ingredient and put it into the pot when the current cooking step ends; Meanwhile, according to the seasoning instruction, determine whether there is a type of seasoning to be put in and the quantity of the seasoning to be put in for the next cooking step, and control the seasoning grabbing unit to grab the corresponding seasoning and put it into the pot after the current cooking step ends; Repeat the above steps until the intelligent cooking machine completes the cooking work.

5. The control method of an intelligent cooking machine according to claim 4, wherein, According to the corresponding control instruction, control the intelligent cooking machine to complete the delivery work, including: After the intelligent cooking machine completes the cooking work, according to the delivery instruction, control the delivery module to send the cooked dish to the user-specified delivery location and send a delivery completion message to the user.

6. The control method of an intelligent cooking machine according to claim 1, characterized in that, It further includes: After the intelligent cooking machine completes the cooking work, automatically clean the intelligent cooking machine, and at the same time receive the next user's dish request. After the cleaning is completed, control the intelligent cooking machine to complete the next cooking work and the next delivery work.

7. A control method for an intelligent cooking machine according to claim 1, characterized in that, It further includes: Obtain the blind box request input by the user, and determine the first user dish request according to the blind box request; Classify all the first user dish requests using a grouper to obtain groups of all the flavor preference types in all the first user dish requests as the first group; wherein, each first user dish request includes the specific dish type of this flavor preference type, and each specific dish type includes at least one specific dish; Obtain all the specific dishes within the group of each flavor preference type in the first group, and calculate the first number of times each specific dish is ordered; Determine the first probability of the relationship between the corresponding specific dish and the group of the corresponding flavor preference type as a signature dish according to the ratio of the first number of times to the second number of times that all the specific dishes within the group of the corresponding flavor preference type are ordered; Assign weights to different flavor preference types in the user's recent dish requests according to the acquisition time, where the longer the acquisition time is from the current time, the higher the weight value; Perform multiplication operations on all the first probabilities and the weight values of the corresponding flavor preference types respectively to obtain a number of second probabilities; select the specific dish corresponding to the largest second probability as the specific dish corresponding to this blind box request.

8. The control method of an intelligent cooking machine according to claim 7, characterized in that, Determine the first user dish request according to the blind box request, including: Parse the user information carried in the blind box request, obtain the user's historical dish requests according to the user information, and determine the user's flavor preference and consumption habit according to the user's recent dish requests in the user's historical dish requests; Obtain all the user dish requests received recently except the blind box request, and screen all the user dish requests according to the user's flavor preference and consumption habit to obtain the first user dish requests that meet the user's flavor preference and consumption habit.

Images