Method and device for making horse hoof cake, electronic equipment and computer readable medium

Abstract

Embodiments of the present disclosure disclose a horse hoof cake making method, device, electronic device and computer readable medium. A specific embodiment of the method comprises: putting raw materials stored in a preparation cabin into a stirrer; controlling a stirring rod to stir the raw materials in the stirring cabin; collecting real-time internal temperature and real-time internal humidity of the dough during the stirring; collecting dough state images during the stirring; generating real-time stirring strategy information; adjusting the state of the stirrer; in response to completion of the stirring, performing dough extension on the raw dough through a dough extender; controlling a feeder to put fillings into the center of the extended dough sheet; folding the dough sheet after the fillings are put in through a dough sheet folding machine; segmenting the dough sheet wrapped with the fillings through a segmenting machine; folding the dough segments into horse hoof shapes through a dough segment folding machine; and generating the horse hoof cake according to an oven and a horse hoof cake raw embryo. The embodiment guarantees the quality of the prepared horse hoof cake and improves the making efficiency.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the field of food preparation, in particular the field of preparation of baked food, and more particularly to a method, device, electronic device and computer readable medium for making horse hoof cake. BACKGROUND

[0002] Horse hoof cake is a kind of Chinese pastry shaped like a horse hoof. At present, in the process of making horse hoof cake, the commonly used way is to make horse hoof cake by manual method combined with manual experience.

[0003] However, when the above method is used, the following technical problem I often exists:

[0004] The manual method relies on manual experience, and it is difficult to ensure the consistency of the quality of the horse hoof cake, and the production efficiency is low.

[0005] In addition, in the process of making horse hoof cake, such as the process of making dough, the dough may be made in combination with a stirrer (used for stirring raw materials to make dough), and the following technical problem II may exist:

[0006] Because butterfly cake making involves multiple raw materials, especially oily raw materials, and common stirrers often use constant speed or different speeds in different stages to stir, which may cause the knife to be stuck or the stirring to be uneven.

[0007] The above information disclosed in the background section is only used to enhance the understanding of the background of the present inventive concept, and therefore, it can contain information that does not form the prior art known to those skilled in the art. SUMMARY

[0008] The summary section of the present disclosure is used to introduce the concepts in a brief form, which will be described in detail in the specific embodiments section. The summary section of the present disclosure is not intended to identify key or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0009] Some embodiments of the present disclosure propose a method, device, electronic device and computer readable medium for making horse hoof cake to solve one or more of the technical problems mentioned in the background section.

[0010] In a first aspect, some embodiments of the present disclosure provide a method for making horse hoof crisp, the method comprising: sequentially opening, in order of feeding, ingredient preparation compartments in an ingredient preparation compartment set comprised in an ingredient preparation box to feed raw materials stored in the ingredient preparation compartments into a mixer, wherein the mixer is used for preparing dough, and the mixer comprises a mixing chamber, a mixing rod, and a first camera, wherein a temperature sensor and a humidity sensor are embedded in the mixing rod, the temperature sensor is used to collect the temperature in the dough, the humidity sensor is used to collect the humidity in the dough, and the first camera faces the mixing chamber; in response to completion of feeding, performing the following processing steps: controlling the mixing rod to mix the raw materials in the mixing chamber; collecting real-time dough temperature and real-time dough humidity during mixing through the temperature sensor and the humidity sensor, respectively; collecting dough state images during mixing through the first camera as first images; generating real-time mixing strategy information according to the real-time dough temperature, the real-time dough humidity, the first images, and a pre-trained mixing strategy optimization model; adjusting the state of the mixer according to the real-time mixing strategy information; in response to completion of mixing, performing dough extension on the dough through a dough extender to generate an extended dough sheet; controlling a feeder to feed fillings into the center of the extended dough sheet to generate a fed dough sheet; folding the fed dough sheet through a dough sheet folding machine to generate a dough sheet wrapped with fillings; segmenting the dough sheet wrapped with fillings through a segmenting machine to obtain noodle segments; folding the noodle segments into horse hoof shape through a noodle folding machine to obtain a horse hoof crisp dough blank; and generating a horse hoof crisp according to an oven and the horse hoof crisp dough blank.

[0011] In a second aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; and a storage device having one or more programs stored thereon, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method described in any implementation manner of the first aspect.

[0012] In a third aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any implementation manner of the first aspect.

[0013] The above various embodiments of the present disclosure have the following beneficial effects: through the horse hoof crisp making method of some embodiments of the present disclosure, the quality of the prepared horse hoof crisp is ensured, and the production efficiency is improved. Specifically, the reason for the poor quality and low production efficiency is that the manual method relies more on manual experience. Based on this, the horse hoof crisp making method of some embodiments of the present disclosure first opens the ingredient preparation compartments in the ingredient preparation compartment set included in the ingredient preparation box in turn according to the feeding order to feed the raw materials stored in the ingredient preparation compartments into a mixer, wherein the mixer is used to prepare the dough, and the mixer includes a mixing chamber, a mixing rod, and a first camera, wherein a temperature sensor and a humidity sensor are embedded in the rod body of the mixing rod, the temperature sensor is used to collect the temperature in the dough, the humidity sensor is used to collect the humidity in the dough, and the first camera faces the mixing chamber. The ingredient preparation box can accurately control the feeding amount and feeding order of the raw materials. Secondly, in response to the completion of feeding, the following processing steps are performed: first, the mixing rod is controlled to mix the raw materials in the mixing chamber. The mixing rod accelerates the mixing speed. Second, the real-time dough temperature and real-time dough humidity during mixing are collected by the temperature sensor and the humidity sensor, respectively. In practice, due to the influence of the production environment (e.g., weather, mixing time, etc.), the temperature and humidity in the dough may change during mixing, thereby affecting the quality of the dough. Therefore, the dough state can be monitored by collecting the temperature and humidity. Third, the dough state image during mixing is collected by the first camera as a first image. Since multiple raw materials need to be mixed during mixing, the image can be collected to monitor the state of the dough surface (e.g., whether the raw materials are mixed evenly, etc.). Fourth, real-time mixing strategy information is generated according to the real-time dough temperature, the real-time dough humidity, the first image, and a pre-trained mixing strategy optimization model. The mixing strategy is dynamically adjusted by combining temperature, humidity, and image. Fifth, the mixer is adjusted according to the real-time mixing strategy information. Then, in response to the completion of mixing, the dough extender is used to extend the dough to generate an extended dough sheet. The extension facilitates subsequent filling. Further, the filler feeds the filling into the center of the extended dough sheet to generate a filled dough sheet. In addition, the dough sheet folding machine folds the filled dough sheet to generate a wrapped filling dough sheet. In addition, the dough strip machine segments the wrapped filling dough sheet to obtain a dough strip segment. This realizes automatic segmentation. Further, the dough strip folding machine folds the dough strip segment into a horse hoof shape to obtain a horse hoof crisp dough. This ensures that the shape of the horse hoof crisp dough is consistent. Finally, the horse hoof crisp is generated according to the oven and the horse hoof crisp dough. In this way, the horse hoof crisp making process is automated, the quality of the prepared horse hoof crisp is ensured, and the production efficiency is improved. Attached Figure Description

[0014] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0015] Figure 1 This is a flowchart of some embodiments of the method for making horseshoe pastries according to the present disclosure;

[0016] Figure 2 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0017] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0018] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0019] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0020] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0021] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0022] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0023] refer to Figure 1 The diagram illustrates a process 100 of some embodiments of a method for making horseshoe-shaped pastries according to the present disclosure. The method for making horseshoe-shaped pastries includes the following steps:

[0024] Step 101, open the ingredient compartments in the ingredient compartment set included in the ingredient box in turn according to the feeding sequence, so as to feed the raw materials stored in the ingredient compartments into the mixer.

[0025] In some embodiments, the execution subject (e.g., a computing device) of the method for making horse hoof cakes can open the ingredient compartments in the ingredient compartment set included in the ingredient box in turn according to the feeding sequence, so as to feed the raw materials stored in the ingredient compartments into the mixer. The mixer is used to prepare the dough. In practice, the mixer is used to mix the raw materials for preparing the dough uniformly. The mixer includes a mixing chamber, a mixing rod, and a first camera. The rod body of the mixing rod is internally embedded with a temperature sensor and a humidity sensor. The temperature sensor is used to collect the temperature inside the dough. The humidity sensor is used to collect the humidity inside the dough. The first camera faces the inside of the mixing chamber. The mixing rod is driven by a motor. The temperature sensor and the humidity sensor are embedded at 3 cm below the lower end of the mixing rod. The lower setting position can ensure that the temperature and humidity inside the corresponding dough can be measured when the amount of raw materials fed into the mixing chamber is small. The mixing chamber adopts a semi-spherical cylindrical chamber. The ingredient box faces the hatch of the mixing chamber, so that the raw materials can be fed into the mixer. The ingredient compartment includes a compartment body and a door, and the door is driven by an electromagnet to control the opening and closing. The first camera can be a camera that faces the inside of the mixing chamber and is used to collect images of the state of the dough.

[0026] Optionally, the raw materials of the horse hoof cakes include, by parts, icing: 50 parts, milk powder: 40 parts, egg liquid: 50 parts, monoglyceride: 2 parts, water: 400 parts, butter: 50 parts, sweet oil: 500 parts, low-gluten flour: 1350 parts, fondant: 500 parts, salt: 15 parts, onion powder: 25 parts, lard: 225 parts, sesame: 100 parts, egg yolk: 200 parts. In practice, the icing, milk powder, egg liquid, monoglyceride, water, butter, sweet oil, low-gluten flour, fondant, salt, onion powder, lard, and sesame can be pre-stored in the ingredient box.

[0027] It should be noted that the computing device can be hardware or software. When the computing device is hardware, it can be implemented as a single server or a single terminal device. When the computing device is software, it can be installed in the hardware devices listed above. It can be implemented as a single software or a software module. Herein, no specific limitation is made. In practice, the computing device can adopt a single-chip microcomputer. The execution subject can be in communication connection with the ingredient compartment, the first camera, the temperature sensor, and the humidity sensor.

[0028] Step 102, in response to the completion of feeding, the following processing steps are performed:

[0029] Step 1021, the stirring rod stirs the raw materials in the stirring cabin.

[0030] In some embodiments, the execution subject can control the stirring rod to stir the raw materials in the stirring cabin. In practice, the execution subject can control the stirring rod to rotate at the initial rotating speed to stir the raw materials in the stirring cabin.

[0031] Step 1022, the temperature sensor and the humidity sensor are used to collect the real-time dough temperature and the real-time dough humidity during the stirring process.

[0032] In some embodiments, the execution subject can use the temperature sensor and the humidity sensor to collect the real-time dough temperature and the real-time dough humidity during the stirring process. In practice, due to the different viscosity of the dough, there may be a situation that the dough sticks to the stirring rod, so in order to avoid affecting the accuracy of the dough temperature and the dough humidity collected by the temperature sensor and the humidity sensor in this case, the temperature sensor and the humidity sensor collect in a non-continuous manner, that is, at fixed time intervals, the dough temperature and the dough humidity are collected periodically.

[0033] Step 1023, the first camera is used to collect the dough state image during the stirring process as the first image.

[0034] In some embodiments, the execution subject can use the first camera to collect the dough state image during the stirring process as the first image. In practice, when the stirring rod starts stirring, the execution subject can start the first camera to collect the dough state image in the stirring cabin as the first image.

[0035] Step 1024, according to the real-time dough temperature, the real-time dough humidity, the first image, and the pre-trained stirring strategy optimization model, real-time stirring strategy information is generated.

[0036] In some embodiments, the execution subject can generate real-time stirring strategy information according to the real-time dough temperature, the real-time dough humidity, the first image, and the pre-trained stirring strategy optimization model. The stirring strategy optimization model is a model used to update the stirring state of the stirrer. The real-time stirring strategy information is information used to adjust the stirring state of the stirrer. For example, the execution subject can use a multi-modal, pre-trained, generative model as the stirring strategy optimization model.

[0037] Optionally, the stirring strategy optimization model comprises a temperature feature extraction network, a humidity feature extraction network, an image feature extraction network, a feature fusion network, a first classifier, a second classifier, a third classifier, and a stirring strategy information generation network. The first classifier is used to classify the state of the dough. The second classifier is used to classify the color uniformity of the dough. The third classifier is used to classify the uniformity of the raw materials on the surface of the dough. In practice, since the real-time dough temperature and the real-time dough humidity are both in the form of signals, the temperature feature extraction network and the humidity feature extraction network can adopt the same network structure. Specifically, the temperature feature extraction network and the humidity feature extraction network can both adopt a ShuffleNet network. The image feature extraction network can adopt a MobileNet network. Considering the limited computing power of the execution subject, in order to reduce the computational pressure on the execution subject as much as possible when the model is deployed locally, the networks and classifiers in the stirring strategy optimization model all adopt lightweight network structures. The feature fusion network adopts a 2-layer encoder based on the Transformer structure as the network structure to realize the feature fusion of different modalities (signal modalities and image modalities). The first classifier, the second classifier, and the third classifier all contain at least one fully connected layer. Specifically, the first classifier can be a multi-classifier. The second classifier and the third classifier are both binary classifiers. For example, the categories corresponding to the first classifier can include dough liquid, dough flocculation, and dough lump. The categories corresponding to the second classifier can include dough color uniformity and dough color non-uniformity. The categories corresponding to the third classifier can include dough surface raw material uniformity and dough surface raw material non-uniformity. The stirring strategy information generation network adopts a 2-layer decoder based on the Transformer structure as the network structure. In addition, considering that non-lightweight models have higher model accuracy, a local-server deployment method can be adopted, that is, the temperature feature extraction network, the humidity feature extraction network, the image feature extraction network, the first classifier, the second classifier, and the third classifier are deployed on the execution subject, the feature fusion network and the stirring strategy information generation network of the non-lightweight model are deployed on the server side, and more accurate real-time stirring strategy information is obtained through the communication between the execution subject and the server side.

[0038] In some optional implementations of some embodiments, the execution subject generates real-time stirring strategy information according to the real-time internal dough temperature, the real-time internal dough humidity, the first image, and the pre-trained stirring strategy optimization model, which can include the following steps:

[0039] Firstly, the temperature feature extraction network is used to perform temperature feature extraction on the real-time internal dough temperature to generate temperature features.

[0040] Secondly, the humidity feature of the real-time dough internal humidity is extracted by the humidity feature extraction network to generate a humidity feature.

[0041] Thirdly, the image feature of the first image is extracted by the image feature extraction network to generate an image feature.

[0042] Fourthly, the humidity feature, the temperature feature and the image feature are fused by the feature fusion network to generate a fusion feature.

[0043] Fifthly, the first classification result is generated by the first classifier and the fusion feature.

[0044] In practice, the execution subject can input the fusion feature into the first classifier to obtain the first classification result.

[0045] Sixthly, the second classification result is generated by the second classifier and the fusion feature.

[0046] In practice, the execution subject can input the fusion feature into the second classifier to obtain the second classification result.

[0047] Seventhly, the third classification result is generated by the third classifier and the fusion feature.

[0048] In practice, the execution subject can input the fusion feature into the third classifier to obtain the third classification result.

[0049] Eighthly, the real-time stirring strategy information is generated by the stirring strategy information generation network according to the first classification result, the second classification result, the third classification result and the fusion feature.

[0050] In practice, the execution subject can input the first classification result, the second classification result, the third classification result and the fusion feature into the stirring strategy information generation network to generate the real-time stirring strategy information.

[0051] The "optionally" and "in some optional implementations of some embodiments" are an invention point of the present disclosure, which solves the second technical problem mentioned in the background, i.e., "since multiple raw materials, especially oily raw materials, are involved in the making of butterfly cakes, the common stirrer often adopts a stirring mode of fixed speed or different speeds in different stages, which may cause the knife to be stuck or the dough to be stirred unevenly". Based on this, the present disclosure, by combining images, temperatures and humidity, especially by combining images, analyzes the color of the dough, the mixing uniformity of the raw materials and the state of the dough, and adjusts the stirring strategy in real time, thereby improving the stirring efficiency and the uniformity of stirring.

[0052] Step 1025, according to the real-time stirring strategy information, the state of the stirrer is adjusted.

[0053] In some embodiments, the execution state can be adjusted according to the real-time stirring strategy information.

[0054] Optionally, the real-time stirring strategy information includes speed adjustment information, humidity adjustment information and temperature adjustment information. Specifically, the stirring strategy information generation network includes three prediction heads for generating speed adjustment information, humidity adjustment information and temperature adjustment information, respectively. The speed adjustment information represents the updated stirring rod speed of the stirring rod. The humidity adjustment information represents the amount of water added to the dough in the stirring chamber. The temperature adjustment information represents the temperature adjustment amount of the dough in the stirring chamber.

[0055] Optionally, the inner wall of the stirring chamber is embedded with a stirring chamber thermostat. The above-mentioned stirrer further comprises a water feeder, and the water outlet of the water feeder is connected with an atomizer. In practice, the atomization of water can make the water better sprayed on the surface of the dough. The water feeder is connected with a water pipe.

[0056] In some optional implementations of some embodiments, the execution subject adjusts the state of the stirrer according to the real-time stirring strategy information, which can include the following steps:

[0057] First, according to the speed adjustment information, the stirring speed of the stirring rod is adjusted.

[0058] As an example, the speed represented by the speed adjustment information can be K. The current stirring speed of the stirring rod is M. Wherein, M≠K. In practice, when the difference between M and K is small, the stirring speed of the stirring rod can be directly adjusted to K. When the difference between M and K is large, in order to avoid the damage to the motor caused by directly adjusting M to K, the execution subject can first generate a speed curve from M to K. Specifically, when M is less than K, a hyperbolic tangent function curve with M as the starting endpoint and K as the ending endpoint can be generated. When M is greater than K, a negative hyperbolic tangent function curve with M as the starting endpoint and K as the ending endpoint can be generated. Then, the stirring speed of the stirring rod is adjusted through the speed curve.

[0059] Second, according to the humidity adjustment information, the humidity in the stirring chamber is adjusted through the water feeder.

[0060] In practice, the execution subject can atomize and add water to the stirring chamber through the water feeder based on the water supplement amount corresponding to the humidity adjustment information.

[0061] Third, according to the temperature adjustment information, the temperature in the stirring chamber is controlled through the stirring chamber thermostat.

[0062] In practice, the execution subject can adjust the constant temperature of the constant temperature device of the mixing tank based on the temperature adjustment amount corresponding to the temperature adjustment information, so as to control the change of the in-tank temperature in the mixing tank.

[0063] At step 103, in response to the completion of the mixing, the dough extender is used to perform dough extension on the raw dough to generate an extended dough sheet.

[0064] In some embodiments, the execution subject can perform dough extension on the raw dough by using the dough extender to generate an extended dough sheet in response to the completion of the mixing.

[0065] Optionally, the dough extender comprises an extension table, a first dough extender, a second dough extender, a second camera, and a patch constant temperature device. The first dough extender and the second dough extender are symmetrically arranged. The first dough extender and the second dough extender are driven by a chain arranged at the bottom of the extension table. The patch constant temperature device is arranged at the bottom of the extension table. In practice, the first dough extender and the second dough extender move horizontally along the extension table. Specifically, the first dough extender is composed of a roller and a roller shaft. The second camera faces the extension table.

[0066] In some optional implementations of some embodiments, the execution subject performs dough extension on the raw dough by using the dough extender to generate an extended dough sheet can comprise the following steps:

[0067] First, according to the raw dough, the following dough extension steps are performed:

[0068] First sub-step, the raw dough on the extension table is subjected to dough extension by the first dough extender and the second dough extender to obtain an initial extended dough.

[0069] Among them, the execution subject can simultaneously start the first dough extender and the second dough extender, so that the first dough extender and the second dough extender symmetrically extend the raw dough on the extension table to obtain an initial extended dough.

[0070] Second sub-step, the second camera is used to capture an initial extended dough image as a second image.

[0071] Among them, the execution subject can control the second camera to be turned on and capture an initial extended dough image as a second image.

[0072] Third sub-step, a dough state information and an extension category are generated by using a pre-trained dough state prediction model and the second image.

[0073] The above extension category represents whether the dough after initial extension is re-extended. In practice, in order to improve the reusability of the model, the dough state prediction model can use the image feature extraction network included in the mixing strategy optimization model as the backbone network structure and connect a multi-classifier and a binary classifier. The multi-classifier is used to generate dough state information. The binary classifier is used to generate the extension category.

[0074] The fourth sub-step is to control the surface temperature of the extension table according to the above dough state information.

[0075] In practice, the dough state information can represent that the dough is soft, so the surface temperature of the extension table can be appropriately reduced. In practice, the surface temperature can be controlled between 0-5°C.

[0076] The fifth sub-step is to determine the initial extension dough as the extension dough in response to the extension identifier representing that the initial extension dough is not re-extended.

[0077] The second step is to re-execute the dough extension step by taking the initial extension dough as the dough in response to the extension identifier representing that the initial extension dough is re-extended.

[0078] Step 104, control the feeder to feed the filling into the center of the extension dough to generate a filling dough.

[0079] In some embodiments, the execution subject can control the feeder to feed the filling into the center of the extension dough to generate a filling dough.

[0080] In some optional implementations of some embodiments, the execution subject controls the feeder to feed the filling into the center of the extension dough to generate a filling dough, which can include the following steps:

[0081] Step 1, capture a third image through the second camera.

[0082] The third image is a wide-angle image containing the extension dough. In practice, after the dough is extended, it may exceed the image range, so using a wide-angle image to capture the third image can ensure that the extension dough is contained in the third image, and thus the subsequently determined dough center coordinates are actual center coordinates.

[0083] Step 2, locate the dough center according to the third image to determine the dough center coordinates.

[0084] In practice, the execution subject can determine the dough center through target detection, and obtain the dough center coordinates through coordinate conversion between the image coordinate system and the geodetic coordinate system.

[0085] Thirdly, the above-mentioned feeding device feeds the stuffing to the position corresponding to the center coordinate of the above-mentioned dough sheet to obtain the dough sheet after feeding.

[0086] In practice, the stuffing can be butter pieces. It can also be other flavored stuffing, such as red bean stuffing, bean paste stuffing, etc. In addition, since the extension table is kept at a constant temperature of 0-5℃ by the patch-type thermostat, the stuffing such as butter pieces can be filled without melting.

[0087] Step 105, folding the dough sheet after feeding by the dough sheet folding machine to generate the dough sheet after wrapping the stuffing.

[0088] In some embodiments, the above-mentioned execution subject can fold the dough sheet after feeding by the dough sheet folding machine to generate the dough sheet after wrapping the stuffing. In practice, the dough sheet folding machine can be a folding and oiling device for shortening-type dough.

[0089] Step 106, segmenting the dough sheet after wrapping the stuffing by the segmenting machine to obtain noodle segments.

[0090] In some embodiments, the above-mentioned execution subject can segment the dough sheet after wrapping the stuffing by the segmenting machine to obtain noodle segments. In practice, the segmenting machine can include a roller and a transmission belt. The roller is driven by a motor to rotate at a constant speed. A plurality of parallel blades are arranged on the roller to cut the dough sheet after wrapping the stuffing into a plurality of noodle segments.

[0091] Step 107, folding the noodle segments into horseshoe shape by the noodle folding machine to obtain the horseshoe shortening dough.

[0092] In some embodiments, the above-mentioned execution subject can fold the noodle segments into horseshoe shape by the noodle folding machine to obtain the horseshoe shortening dough. The dough folding machine includes a rounding machine and a water droplet-shaped extrusion device. First, the rounding machine rounds the noodle segments to form circular noodle segments, and then the water droplet-shaped extrusion device extrudes towards the opening of the circular noodle segments to generate the horseshoe shortening dough.

[0093] Optionally, after the noodle segments are folded into horseshoe shape by the noodle folding machine to obtain the horseshoe shortening dough, the method further includes:

[0094] The horseshoe shortening dough is stored at low temperature. In practice, the horseshoe shortening dough can be packaged and stored in a low-temperature storage cabinet. Specifically, the production speed of the horseshoe shortening dough can be greater than the baking speed of the horseshoe shortening dough. In order to avoid the accumulation of the prepared horseshoe shortening dough, the horseshoe shortening dough can be stored in the form of low-temperature storage. In addition, for different sales strategies, such as two sales strategies of selling the horseshoe shortening dough and the horseshoe shortening, the low-temperature horseshoe shortening dough is conducive to the sale of the horseshoe shortening dough.

[0095] Step 108, generating horse hoof crisp according to the baking oven and the horse hoof crisp dough.

[0096] In some embodiments, the above execution subject can generate horse hoof crisp according to the baking oven and the horse hoof crisp dough. In practice, the horse hoof crisp dough can be put into the baking oven according to the preset baking time and baking temperature to generate the horse hoof crisp.

[0097] In some optional implementations of some embodiments, the above execution subject for generating horse hoof crisp according to the baking oven and the horse hoof crisp dough can include the following steps:

[0098] First, capturing a third image through a third camera.

[0099] The third image includes the horse hoof crisp dough. The third camera is directed at the outlet of the noodle folding machine.

[0100] Second, generating a dough category through a pre-trained defective product classification model and the third image.

[0101] The dough category includes a non-defective product category and a defective product category. In practice, to further reduce the computational pressure of the execution subject, the temperature feature extraction network + binary classifier structure included in the stirring strategy optimization model can also be used to classify the dough category.

[0102] Third, in response to the dough category being the non-defective product category, controlling the spreader to spray egg yolks and sesame seeds onto the horse hoof crisp dough and moving it into the baking oven.

[0103] Fourth, in response to the dough category being the defective product category, rejecting the horse hoof crisp dough.

[0104] In practice, the execution subject can move the horse hoof crisp dough of the defective product category to the recycling area by controlling the push arm.

[0105] Fifth, in response to the horse hoof crisp dough being moved into the baking oven and the oven door being closed, controlling the baking oven to bake the horse hoof crisp dough according to preset baking strategy information.

[0106] In practice, the baking strategy information can include baking temperature and baking time. Specifically, the baking process of the horse hoof crisp can correspond to multiple baking stages, each of which corresponds to a baking temperature and a baking time.

[0107] Sixth, capturing an image of the horse hoof crisp dough during the baking process through a high-temperature-resistant camera inside the baking oven as a fourth image.

[0108] In the seventh step, the baking adjustment information is generated according to the fourth image. In practice, the execution subject can input the fourth image as a model input, and generate the baking adjustment information through a pre-trained baking adjustment information generation model. Specifically, the model structure of the baking adjustment information generation model is the same as that of the stirring strategy optimization model. In the training process, the migration learning method can be used to quickly train the baking adjustment information generation model. In addition, the baking adjustment information generation model is connected with two predictors for predicting the baking time and the baking temperature, respectively.

[0109] In the seventh step, the baking adjustment information is generated according to the fourth image. In practice, the execution subject can input the fourth image as a model input, and generate the baking adjustment information through a pre-trained baking adjustment information generation model. Specifically, the model structure of the baking adjustment information generation model is the same as that of the stirring strategy optimization model. In the training process, the migration learning method can be used to quickly train the baking adjustment information generation model. In addition, the baking adjustment information generation model is connected with two predictors for predicting the baking time and the baking temperature, respectively.

[0110] The above various embodiments of the present disclosure have the following beneficial effects: through the horse hoof crisp making method of some embodiments of the present disclosure, the quality of the prepared horse hoof crisp is ensured, and the production efficiency is improved. Specifically, the reason for the poor quality and low production efficiency is that the manual method relies more on manual experience. Based on this, the horse hoof crisp making method of some embodiments of the present disclosure first opens the ingredient preparation compartments in the ingredient preparation compartment set included in the ingredient preparation box in turn according to the feeding order to feed the raw materials stored in the ingredient preparation compartments into a mixer, wherein the mixer is used to prepare the dough, and the mixer includes a mixing chamber, a mixing rod, and a first camera, wherein a temperature sensor and a humidity sensor are embedded in the rod body of the mixing rod, the temperature sensor is used to collect the temperature in the dough, the humidity sensor is used to collect the humidity in the dough, and the first camera faces the mixing chamber. The ingredient preparation box can accurately control the feeding amount and feeding order of the raw materials. Secondly, in response to the completion of feeding, the following processing steps are performed: first, the mixing rod is controlled to mix the raw materials in the mixing chamber. The mixing rod accelerates the mixing speed. Second, the real-time dough temperature and real-time dough humidity during mixing are collected by the temperature sensor and the humidity sensor, respectively. In practice, due to the influence of the production environment (e.g., weather, mixing time, etc.), the temperature and humidity in the dough may change during mixing, thereby affecting the quality of the dough. Therefore, the dough state can be monitored by collecting the temperature and humidity. Third, the dough state image during mixing is collected by the first camera as a first image. Since multiple raw materials need to be mixed during mixing, the image can be collected to monitor the state of the dough surface (e.g., whether the raw materials are mixed evenly, etc.). Fourth, real-time mixing strategy information is generated according to the real-time dough temperature, the real-time dough humidity, the first image, and a pre-trained mixing strategy optimization model. The mixing strategy is dynamically adjusted by combining temperature, humidity, and image. Fifth, the mixer is adjusted according to the real-time mixing strategy information. Then, in response to the completion of mixing, the dough extender is used to extend the dough to generate an extended dough sheet. The extension facilitates subsequent filling. Further, the filler feeds the filling into the center of the extended dough sheet to generate a filled dough sheet. In addition, the dough sheet folding machine folds the filled dough sheet to generate a wrapped filling dough sheet. In addition, the dough strip machine segments the wrapped filling dough sheet to obtain a dough strip segment. This realizes automatic segmentation. Further, the dough strip folding machine folds the dough strip segment into a horse hoof shape to obtain a horse hoof crisp dough. This ensures that the shape of the horse hoof crisp dough is consistent. Finally, the horse hoof crisp is generated according to the oven and the horse hoof crisp dough. In this way, the horse hoof crisp making process is automated, the quality of the prepared horse hoof crisp is ensured, and the production efficiency is improved.

[0111] The following description refers to Figure 2 which shows a structural schematic diagram of an electronic device (e.g., a computing device) 200 suitable for implementing some embodiments of the present disclosure. Figure 2 The electronic device shown is merely an example and should not bring any limitation to the function and scope of use of embodiments of the present disclosure.

[0112] As Figure 2 shown, the electronic device 200 can include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 201, which can perform various appropriate actions and processes according to programs stored in a read-only memory 202 or loaded into a random access memory 203 from a storage device 208. In the random access memory 203, various programs and data required for the operation of the electronic device 200 are also stored. The processing device 201, the read-only memory 202, and the random access memory 203 are connected to each other through a bus 204. An input / output interface 205 is also connected to the bus 204.

[0113] Generally, the following devices can be connected to the I / O interface 205: input devices 206 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 207 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 208 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 209. The communication devices 209 can allow the electronic device 200 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 2 The electronic device 200 is shown with various devices, but it should be understood that all the devices shown are not required, and more or less devices can alternatively be implemented. Figure 2 Each block shown in the figure can represent a device or multiple devices as needed.

[0114] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to some embodiments of the present disclosure. For example, some embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In some such embodiments, the computer program can be downloaded and installed from a network through the communication devices 209, or installed from the storage devices 208, or installed from the read-only memory 202. When the computer program is executed by the processing device 201, the above-mentioned functions defined in the methods of some embodiments of the present disclosure are performed.

[0115] Note that the computer readable medium in some embodiments of the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination thereof. The computer readable storage medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program used by an instruction execution system, apparatus or device, or that can be used by or in connection with an instruction execution system, apparatus or device. In some embodiments of the present disclosure, the computer readable signal medium can include a computer readable program code propagated in or on a carrier medium, in which the computer readable program code is embodied. Such propagated computer readable program code can take many forms, including but not limited to, an electromagnetic signal, an optical signal or any suitable combination of the foregoing. The computer readable signal medium can also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate or transport a program for use by or in connection with an instruction execution system, apparatus or device. Program code embodied on a computer readable medium can be transmitted using any suitable medium, including but not limited to, wire, cable, wireless, RF, infrared or any suitable combination of the foregoing.

[0116] In some embodiments, the client, server, or both can communicate using any current known or future developed network protocol, such as HTTP (Hyper Text Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet, and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any current known or future developed networks.

[0117] The computer readable medium can be included in the electronic device or exist separately from the electronic device. The computer readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: open the ingredient supply bins in the ingredient supply bin set included in the ingredient supply box in the order of the ingredient supply sequence to supply the raw materials stored in the ingredient supply bins into a mixer, wherein the mixer is used to prepare dough, the mixer includes a mixing chamber, a mixing rod, and a first camera, the mixing rod has a rod body, and a temperature sensor and a humidity sensor are embedded in the rod body, the temperature sensor is used to collect the temperature of the dough, the humidity sensor is used to collect the humidity of the dough, and the first camera faces the mixing chamber; in response to completion of the supply of the raw materials, perform the following processing steps: control the mixing rod to mix the raw materials in the mixing chamber; collect the real-time temperature and the real-time humidity of the dough in the mixing process by the temperature sensor and the humidity sensor, respectively; collect a dough state image in the mixing process as a first image by the first camera; generate real-time mixing strategy information according to the real-time temperature, the real-time humidity, the first image, and a pre-trained mixing strategy optimization model; perform state adjustment on the mixer according to the real-time mixing strategy information; in response to completion of the mixing, perform dough extension on the dough by a dough extender to generate an extended dough sheet; control a filler to supply a filling to the center of the extended dough sheet to generate a filled dough sheet; fold the filled dough sheet by a dough sheet folding machine to generate a dough sheet wrapped with the filling; segment the dough sheet wrapped with the filling by a dough segmenting machine to obtain a dough segment; fold the dough segment into a horseshoe shape by a dough segment folding machine to obtain a horseshoe cracker dough; and generate a horseshoe cracker according to the oven and the horseshoe cracker dough.

[0118] Computer program code for carrying out operations of some embodiments of the present disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++, or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0119] The computer program product of the first aspect can further include one or more of the following features. The computer program product can include a computer readable medium. The computer readable medium can include a computer readable storage medium or a computer readable signal medium. The computer readable storage medium can include tangible storage medium. The computer readable signal medium can include a propagated data signal with computer readable program code embodied therein. The computer readable program code can be downloaded into a working memory of a computer from the computer readable signal medium or from the computer readable storage medium. The computer readable program code can cause the computer to perform the steps of the first aspect. The computer readable program code can be executed by one or more processors associated with the computer.

[0120] The functions described above can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, non-limiting examples of hardware logic components that can be used include field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SOCs), complex programmable logic devices (CPLDs), etc.

[0121] The above description is merely exemplary of the disclosure and the application of the principles thereof. It is not intended to limit the scope of the disclosure to the precise forms disclosed. The disclosure is to cover all modifications, equivalents, and alternatives falling within the scope of the application as defined by the claims. The disclosure can also cover combinations of the features set out above.

Claims

1. A method for making horseshoe pastries, comprising: The material preparation chambers in the material preparation box are opened sequentially according to the feeding order to put the raw materials stored in the material preparation chambers into the mixer. The mixer is used to prepare raw dough and includes a mixing chamber, a mixing rod, and a first camera. The mixing rod is equipped with a temperature sensor and a humidity sensor. The temperature sensor is used to collect the temperature inside the dough, and the humidity sensor is used to collect the humidity inside the dough. The first camera faces the inside of the mixing chamber. Upon completion of feeding, the following processing steps are performed: The stirring rod is controlled to stir the raw materials in the stirring chamber; The real-time temperature and humidity inside the dough during the mixing process are collected using the temperature sensor and the humidity sensor, respectively. The first camera captures images of the dough's state during the mixing process, which are then used as the first image. Based on the real-time dough temperature, the real-time dough humidity, the first image, and the pre-trained mixing strategy optimization model, real-time mixing strategy information is generated. The state of the stirrer is adjusted according to the real-time stirring strategy information; In response to the completion of mixing, the raw dough is stretched using a dough stretcher to produce stretched sheets; The feeder is controlled to feed the filling into the center of the extended back sheet to generate the filling back sheet; The dough sheet is folded using a dough folding machine to create a dough sheet that encloses the filling. The filling-wrapped sheet is slit into segments using a slitting machine to obtain noodle segments; Using a noodle folding machine, the noodle segments are folded into a horseshoe shape to obtain horseshoe pastry dough; Horseshoe pastries are produced by baking in an oven with the raw pastry dough. The stirring strategy optimization model includes: a temperature feature extraction network, a humidity feature extraction network, an image feature extraction network, a feature fusion network, a first classifier, a second classifier, a third classifier, and a stirring strategy information generation network. The first classifier is used to classify the dough state, the second classifier is used to classify the dough color uniformity, and the third classifier is used to classify the uniformity of raw materials on the dough surface. The step of generating real-time mixing strategy information based on the real-time dough temperature, the real-time dough humidity, the first image, and the pre-trained mixing strategy optimization model includes: The temperature feature extraction network is used to extract temperature features from the real-time dough to generate temperature features. The humidity feature extraction network is used to extract humidity features from the real-time dough to generate humidity features. Image features are extracted from the first image using the image feature extraction network to generate image features; The feature fusion network is used to fuse the humidity feature, the temperature feature, and the image feature to generate a fused feature. A first classification result is generated using the first classifier and the fused features; A second classification result is generated using the second classifier and the fused features; A third classification result is generated using the third classifier and the fused features; Based on the first classification result, the second classification result, the third classification result, and the fusion feature, the real-time stirring strategy information is generated through the stirring strategy information generation network.

2. The method according to claim 1, wherein, The dough stretching machine includes: a stretching table, a first stretching machine, a second stretching machine, a second camera, and a patch-type thermostat. The first stretching machine and the second stretching machine are symmetrically arranged and driven by a chain disposed at the bottom of the stretching table. The patch-type thermostat is disposed at the bottom of the stretching table. The process of using a dough stretching machine to stretch raw dough to produce stretched sheets includes: Based on the raw dough, perform the following dough stretching steps: The dough on the stretching table is stretched once using the first stretching machine and the second stretching machine to obtain the initially stretched dough; The second camera captures an image of the dough after its initial stretching, which is then used as the second image. Using a pre-trained dough state prediction model and the second image, dough state information and extension category are generated, wherein the extension category represents whether the dough is re-extended after the initial extension; Based on the dough state information, the surface temperature of the stretching table is adjusted by the patch thermostat. In response to the extension category characterization no longer performing dough re-extension on the initially extended dough, the initially extended dough is identified as the extended sheet; In response to the extension category characterization of re-extensioning the dough after the initial extension, the dough after the initial extension is treated as raw dough, and the dough extension step is repeated.

3. The method according to claim 2, wherein, The real-time stirring strategy information includes: speed adjustment information, humidity adjustment information and temperature adjustment information. A stirring chamber thermostat is embedded inside the chamber wall. The stirrer also includes: a water dispenser, and the outlet of the water dispenser is connected to an atomizer. The step of adjusting the state of the stirrer based on the real-time stirring strategy information includes: Adjust the stirring speed of the stirring rod according to the speed adjustment information; Based on humidity adjustment information, the humidity inside the mixing chamber is adjusted via the water dispenser. Based on the temperature adjustment information, the internal temperature of the mixing chamber is controlled by the mixing chamber thermostat.

4. The method according to claim 3, wherein, The control feeder feeds the filling into the center of the extended back sheet to generate the filling back sheet, including: A third image is captured using the second camera, wherein the third image is a wide-angle image including the extended rear panel; The center of the patch is located based on the third image to determine the coordinates of the patch center. The feeder is controlled to feed the filling to the position corresponding to the center coordinate of the dough sheet, thus obtaining the dough sheet after feeding.

5. The method according to claim 4, wherein, The process of producing horseshoe pastries by baking in an oven and using the horseshoe pastry dough includes: A third image is captured using a third camera, wherein the third image includes the raw horseshoe pastry dough; Using a pre-trained defective product classification model and the third image, a raw embryo category is generated, wherein the raw embryo category includes: a non-defective product category and a defective product category; In response to the fact that the raw dough is a non-defective product category, the dispenser is controlled to spray egg yolk and sesame seeds onto the horseshoe pastry raw dough and transfer it into the baking oven; In response to the fact that the raw embryo category is a defective product category, the horseshoe pastry raw embryo is discarded; In response to the horseshoe pastry dough being moved into the baking oven and the oven door being closed, the baking oven is controlled to bake the horseshoe pastry dough according to preset baking strategy information; Images of the horseshoe pastry dough during the baking process are captured by a high-temperature resistant camera inside the baking oven and used as the fourth image. Based on the fourth image, baking adjustment information is generated; The oven temperature is adjusted according to the baking adjustment information.

6. An electronic device, comprising: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 5.

7. A computer-readable medium having a computer program stored thereon, wherein, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 5.

Images