CN114451499A

CN114451499A - Preparation method of medlar drink

Info

Publication number: CN114451499A
Application number: CN202011217066.8A
Authority: CN
Inventors: 郭成哲; 孙保伟
Original assignee: Shanghai Haigeya Biotechnology Co ltd
Current assignee: Shanghai Haigeya Biotechnology Co ltd
Priority date: 2020-11-04
Filing date: 2020-11-04
Publication date: 2022-05-10

Abstract

The embodiment of the disclosure discloses a preparation method of a medlar drink. One embodiment of the method comprises: acquiring a medlar image of each medlar to obtain a medlar image set; inputting each medlar image into a classification model to obtain a classification result set corresponding to the medlar image; selecting a target Chinese wolfberry based on the classification result set; soaking a target Chinese wolfberry to generate a soaked target Chinese wolfberry serving as a first Chinese wolfberry; crushing and softening the first medlar to generate serous fluid; heating the slurry to 30-75 ℃ so as to soften the slurry and generate a mixed solution; filtering the mixed solution, and performing acid treatment on the filtrate to generate medlar juice; performing enzyme treatment on the medlar juice, and keeping the enzyme treatment temperature at 50-60 ℃; sterilizing and filtering the medlar juice after enzyme treatment to generate medlar original juice; adding adjuvants into fructus Lycii natural juice to obtain fructus Lycii beverage. The implementation mode can improve the nutritional and health-care value of the medlar drink, improve the flavor of the drink and improve the sensory experience of users.

Description

Preparation method of medlar drink

Technical Field

The embodiment of the disclosure relates to the field of processing of medlar drinks, and in particular relates to a preparation method of a medlar drink.

Background

The medlar is a medicine and food dual-purpose food with health care efficacy, and the prepared beverage has the effect of improving eyesight. Currently, wolfberry beverages are usually prepared by selecting, soaking, crushing, filtering, filling, and sealing.

However, when selecting the medlar to prepare the medlar drink in the above way, the following technical problems often exist:

firstly, in the process of preparing the common medlar drink, the selection efficiency of medlar is often low, and meanwhile, the problems of nutrient loss, bacterial pollution, dim and unsharp color and luster and the like exist in the preparation process flow.

Secondly, because the wolfberry pulp is homogenized at high temperature in the preparation process flow, the activity of cells and beneficial bacteria is damaged, and meanwhile, because the homogenization treatment of the pulp is not thorough, nutrient components are lost, and then, the nutrient value is reduced.

Disclosure of Invention

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Some embodiments of the present disclosure provide a method for preparing a wolfberry beverage to solve one or more of the technical problems mentioned in the background section above.

In a first aspect, some embodiments of the present disclosure provide a method for preparing a wolfberry beverage, the method comprising: acquiring a medlar image of each medlar in the medlar group to obtain a medlar image set; inputting each medlar image included in the medlar image set into a classification model to obtain a classification result set corresponding to the medlar image; selecting a target Chinese wolfberry from the Chinese wolfberry group based on the generated classification result set; soaking a target Chinese wolfberry with a preset weight to generate a soaked target Chinese wolfberry serving as a first Chinese wolfberry; crushing and softening the first medlar to generate serous fluid; heating the slurry to 30-75 ℃ so as to further soften the slurry and generate a mixed solution; filtering the mixed solution by a 80-mesh screen to obtain a filtrate, and performing acid treatment on the generated filtrate to generate the medlar juice; adding 0.05% -0.1% pectinase into the fructus Lycii juice for 4-6h enzyme treatment, and keeping the enzyme treatment temperature at 50-60 deg.C; sterilizing and filtering the medlar juice after enzyme treatment to generate medlar original juice; adding adjuvants into the above fructus Lycii natural juice to make fructus Lycii beverage.

The above embodiments of the present disclosure have the following advantages: firstly, acquiring a medlar image of each medlar in a medlar group to obtain a medlar image set. And inputting each medlar image included in the medlar image set into a classification model to obtain a classification result set corresponding to the medlar image. And obtaining a classification result set by using a pre-trained classification model. The time spent on selecting the medlar is reduced, and the medlar selection efficiency is improved. Next, a target wolfberry is selected from the group of wolfberries based on the generated set of classification results. The medlar used for preparing the medlar drink can be selected according to the identification result output by the classification model. And then, soaking the target Chinese wolfberry with a preset weight to generate the soaked target Chinese wolfberry serving as the first Chinese wolfberry. Soaking the target medlar in potassium permanganate solution to kill bacteria and viruses on the medlar epidermis. Then, the first Chinese wolfberry is crushed and softened to generate slurry, and the generated slurry is heated to 30-75 ℃ so that the slurry is further softened to generate a mixed solution. Crushing and softening the first medlar, so that the nutrient substances in medlar fruits can be conveniently extracted, and meanwhile, the fruit stalk and peel residues influencing the mouthfeel can be removed. Then, the mixed solution is filtered through a 80-mesh screen to obtain a filtrate, and the obtained filtrate is subjected to acid treatment to obtain the wolfberry fruit juice. The resulting filtrate was subjected to acid treatment to remove bacteria produced during the preparation. Then, 0.05% -0.1% of pectinase is added into the medlar juice for enzyme treatment for 4-6h, and the enzyme treatment temperature is kept at 50-60 ℃. The fructus Lycii juice contains a large amount of pectin substances, and is decomposed and precipitated with pectinase, so that the fructus Lycii juice is clearer, and the filtering speed of the fructus Lycii juice is increased. Then, sterilizing and filtering the medlar juice after enzyme treatment to generate medlar original juice. Due to the treatment of pectinase, the filtering speed is increased, and the raw wolfberry juice is produced. Finally, adding the ingredients into the raw juice of the medlar to prepare the medlar beverage. Because the efficiency of selecting the medlar is improved, and the medlar is treated by the technical processes of potassium manganate solution sterilization, crushing softening, filtration, acid treatment, pectinase treatment, ingredient addition and the like. Furthermore, the loss of the nutrient components of the medlar fruits is reduced, the bacterial pollution is avoided, and the clarity of the medlar drink is improved. Therefore, the nutritional health-care value of the medlar drink is improved, the taste and flavor of the medlar drink are enriched and improved, and the sensory experience of users is improved.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and elements are not necessarily drawn to scale.

Fig. 1 is a schematic diagram of an application scenario of a method of making a wolfberry beverage according to some embodiments of the present disclosure;

fig. 2 is a flow diagram of some embodiments of a method of making a wolfberry beverage according to the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.

It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1 is a schematic diagram of an application scenario of a method of making a wolfberry drink, according to some embodiments of the present disclosure.

In the application scenario of fig. 1, first, the computing device 101 may receive a wolfberry image of each wolfberry in the wolfberry group sent by the terminal device 102, resulting in a wolfberry image set 103. Then, the computing device 101 may input each of the images 1031 included in the set of images of chinese wolfberry to a classification model, so as to obtain a set of classification results 104 corresponding to the images of chinese wolfberry. The computing device 101 may then select a target wolfberry 105 from the group of wolfberries based on the generated set of classification results 104. Next, the computing device 101 may take a preset weight of the target wolfberry 105 for soaking, generating a soaked target wolfberry as the first wolfberry 106. The computing device 101 may then crush and soften the first wolfberry 106 to produce a slurry 107. The computing device 101 may then heat the slurry 107 to 30-75 ℃ so that the slurry further softens, producing a mixed liquor 108. The computing device 101 may then filter the mixture 108 through a 80 mesh screen to obtain a filtrate, and perform an acid treatment on the resulting filtrate to produce the wolfberry juice 109. Thereafter, the computing device 101 may add 0.05% -0.1% pectinase to the wolfberry fruit juice 109 for 4-6 hours and maintain the enzyme treatment at 50-60 ℃. The computing device 101 may then sterilize and filter the enzyme-treated wolfberry juice to produce raw wolfberry juice 110. Finally, the computing device 101 can add ingredients to the raw juice 110 to make a raw juice 111.

The computing device 101 may be hardware or software. When the computing device is hardware, it may be implemented as a distributed cluster composed of multiple servers or terminal devices, or may be implemented as a single server or a single terminal device. When the computing device is embodied as software, it may be installed in the hardware devices enumerated above. It may be implemented, for example, as multiple software or software modules to provide distributed services, or as a single software or software module. And is not particularly limited herein.

It should be understood that the number of computing devices in FIG. 1 is merely illustrative. There may be any number of computing devices, as implementation needs dictate.

With continued reference to fig. 2, a flow 200 of some embodiments of a method of making a wolfberry beverage in accordance with the present disclosure is shown. The preparation method of the medlar drink comprises the following steps:

step 201, acquiring a wolfberry image of each wolfberry in a wolfberry group to obtain a wolfberry image set.

In some embodiments, the executing body (101 described in fig. 1) of the method for preparing a wolfberry beverage may obtain, through a wired connection or a wireless connection, a wolfberry image of each wolfberry in a group of wolfberries sent by a user to a computing device, to obtain a set of wolfberry images.

As an example, the image of the chinese wolfberry may be: wolfberry image 001, wolfberry image 002, wolfberry image 003, wolfberry image 004, and wolfberry image 005. The above-mentioned wolfberry image set may be [ wolfberry image 001, wolfberry image 002, wolfberry image 003, wolfberry image 004, wolfberry image 005 ].

Step 202, inputting each medlar image included in the medlar image set to a classification model to obtain a classification result set corresponding to the medlar image.

For each image of the set of images of lycium barbarum, performing the following processing steps: and inputting the medlar images into the classification model to obtain an identification result set corresponding to the medlar images.

In some embodiments, the executing subject may input each of the images of the lycium barbarum set to a pre-trained classification model, so as to obtain a classification result set of each image of the lycium barbarum. The pre-trained classification model may include an input layer, a hidden layer, and an output layer. The classification results may be class A, class B, class C and class D. Wherein, the quality of the A-type medlar is optimal, and the quality of the D-type medlar is the lowest. The image of the Chinese wolfberry can be: wolfberry image 001, wolfberry image 002, wolfberry image 003, wolfberry image 004, and wolfberry image 005. Wherein, the classification result corresponding to the medlar image 001 is B type. The classification result corresponding to the image 002 of lycium barbarum is class C. The classification result corresponding to the image 003 of lycium barbarum is class a. The classification result corresponding to the image 004 of the Chinese wolfberry is D. The classification result corresponding to the image 005 of lycium barbarum is class C. The above classification set may be: { [ wolfberry image 001: b type ], [ wolfberry image 002: class C, [ image of matrimony vine 003: class a ], [ image of lycium barbarum 004: class D ], [ image of lycium barbarum 005: class C ] }.

For example, the executing entity may input the lycium barbarum image 001 to a classification model trained in advance, and obtain a classification result of the lycium barbarum image 001 [ lycium barbarum image 001: class B ]. The execution subject may input the image 002 into a classification recognition model trained in advance to obtain a classification result of the image 002 [ image 002: class C ]. The execution subject may input the image 003 of lycium barbarum into a classification model trained in advance, and obtain a classification result of the image 003 of lycium barbarum [ image 003 of lycium barbarum: class A ]. The execution subject may input the image 004 into a classification model trained in advance, and obtain a classification result of the image 004 [ image 004: class D ]. The execution subject may input the wolfberry image 005 to a classification model trained in advance, and obtain a classification result of the wolfberry image 005 [ wolfberry image 005: class C ]. Therefore, a classification result set corresponding to each Chinese wolfberry image is obtained { [ Chinese wolfberry image 001: b type ], [ wolfberry image 002: class C, [ image of matrimony vine 003: class a ], [ image of lycium barbarum 004: class D ], [ image of lycium barbarum 005: class C ] }.

In some optional implementations of some embodiments, the classification model may be trained by:

the method comprises the steps of firstly, determining a network structure of an initial neural network and initializing network parameters of the initial neural network.

As an example, the executing agent of the training mode may first determine the network structure of the initial neural network. For example, it is necessary to determine which layers the initial neural network includes, the connection order relationship between layers, and which neurons each layer includes, the weight (weight) and bias term (bias) corresponding to each neuron, the activation function of each layer, and so on. The executive agent of the training mode may then initialize the network parameters of the initial neural network. For example, the network parameters (e.g., weight parameters and bias parameters) of the initial neural network may be initialized with some different small random numbers.

And secondly, acquiring a training sample set, wherein the training sample comprises a sample image and a sample category corresponding to the sample image.

As an example, the execution subject of the training mode may obtain the training sample set from other terminal devices connected to the execution subject network locally or remotely. The training sample comprises a sample image and a sample category corresponding to the sample image.

Thirdly, selecting samples from the sample set, and executing the following training steps:

firstly, a sample image of a selected sample is input to an initial neural network, and the category of the selected sample is obtained.

Secondly, the category of the selected sample is compared with the corresponding sample category. As an example, the difference between the class of the selected sample and the corresponding sample class may be calculated using a preset loss function.

And then, determining whether the initial neural network reaches a preset optimization target according to the comparison result. Wherein, the preset optimization target may include, but is not limited to, at least one of the following: the training time exceeds the preset time; the training times exceed the preset times; the calculated difference is less than a preset difference threshold.

And finally, in response to determining that the initial neural network reaches the optimization goal, taking the initial neural network as the trained classification model.

In addition, in response to determining that the initial neural network is not trained, adjusting relevant parameters in the initial neural network, reselecting samples from the sample set, using the adjusted initial neural network as the initial neural network, and performing the training step again.

Step 203, selecting a target medlar from the medlar group based on the classification result set.

In some embodiments, the performing agent may select a target wolfberry from the group of wolfberries based on the generated set of classification results. Wherein the target fructus Lycii can be fructus Lycii for preparing fructus Lycii beverage.

As an example, the target lycium barbarum may be lycium barbarum 3 corresponding to the lycium barbarum image 003.

In some optional implementations of some embodiments, the executing subject may select a target lycium barbarum from the group of lycium barbarum based on the generated classification result set, and may include the following steps:

in a first step, a classification result is selected from the generated classification result set as a target classification result.

As an example, inputting each lycium barbarum image to a classification model generates a classification result set { [ lycium barbarum image 001: b type ], [ wolfberry image 002: class C, [ image of matrimony vine 003: class a ], [ image of lycium barbarum 004: class D ], [ image of lycium barbarum 005: class C ] }. From the classification result set { [ lycium barbarum image 001: b type ], [ wolfberry image 002: class C, [ image of matrimony vine 003: class a ], [ image of lycium barbarum 004: class D ], [ image of lycium barbarum 005: c types, selecting the medlar image with the highest quality [ 003: class a ] as the target classification result.

And secondly, determining the medlar corresponding to the target classification result as the target medlar.

As an example, the target classification result [ lycium barbarum image 003: category a ] lycium barbarum 3 was identified as the target lycium barbarum.

And 204, soaking the target Chinese wolfberry with preset weight to generate the soaked target Chinese wolfberry serving as the first Chinese wolfberry.

In some embodiments, the executing body may take a preset weight of the target lycium barbarum for soaking after selecting the target lycium barbarum, and generate the soaked target lycium barbarum as the first lycium barbarum.

As an example, the target lycium barbarum may be lycium barbarum 3 (class a) described above. The predetermined weight may be 900 g. Soaking 3 g of the above fructus Lycii in 900 g. The generated soaked target medlar is used as the first medlar required by the subsequent preparation process flow.

In some optional implementation manners of some embodiments, the executing body may soak target lycium barbarum with a preset weight, and generate the soaked target lycium barbarum as the first lycium barbarum, and the executing body may include the following steps:

firstly, soaking the target Chinese wolfberry with the preset weight in warm water at the temperature of 30-40 ℃ for 10-12min, and then taking out the Chinese wolfberry to obtain primary soaked Chinese wolfberry.

For example, a total of 900g of the above-mentioned wolfberries are placed in warm water at 15 ℃ and soaked for 10min, and then taken out to obtain primary soaked wolfberries.

And secondly, soaking the primary soaked Chinese wolfberry in 0.03% potassium permanganate solution for 10-12min, and taking out to obtain secondary soaked Chinese wolfberry.

For example, the primary soaked Chinese wolfberry is soaked in 0.03% potassium permanganate solution to kill bacteria and viruses on the skin of the Chinese wolfberry 3. Taking out after 10min to obtain the secondary soaked Chinese wolfberry.

And thirdly, rinsing and soaking the twice-soaked Chinese wolfberry fruits by using water to generate soaked target Chinese wolfberry fruits serving as the first Chinese wolfberry fruits.

As an example, the twice-soaked Chinese wolfberry is placed in clear water for rinsing and soaking to remove the residual potassium permanganate solution. And taking the generated target medlar after rinsing and soaking as a first medlar. Wherein, the soaking time in clear water can be 3 min. The soaking time is too long and is easily polluted by mixed bacteria.

Step 205, crushing and softening the first medlar to generate slurry.

In some embodiments, the execution body may place the first fructus Lycii in a rubber roller to crush and soften to generate slurry. Wherein, the first medlar is easier to generate serous fluid due to soaking.

In some optional implementations of some embodiments, the performing body may crush and soften the first wolfberry to generate a slurry, and may include the following steps:

firstly, placing the first Chinese wolfberry in a rubber roller for crushing and softening to generate Chinese wolfberry pulp.

For example, the execution body may place the first lycium barbarum in a rubber roller, set the rubber roller to be opened, and crush and soften the lycium barbarum after 3min to generate lycium barbarum pulp.

And step two, filtering the medlar pulp by a filter screen of 40 meshes to generate pulp.

For example, the execution body may filter the medlar pulp through a filter screen of 40 meshes to remove the stalk and peel residues, thereby generating the pulp.

Step 206, heating the slurry to 65-75 ℃ to further soften the slurry and produce a mixed solution.

In some embodiments, the execution body may heat and soften the slurry in a water bath to generate a mixed solution.

In some optional implementations of some embodiments, the performing body may heat the slurry to 30-75 ℃ so that the slurry is further softened to generate a mixed solution, and may include the following steps:

step one, adding 300-450ml of water into the slurry, heating to 75 ℃ so as to uniformly mix the slurry, and filtering by using a screen to generate primary slurry and primary filter residue.

For example, 400ml of water is added into the slurry, the slurry is heated to 75 ℃ in a water bath, so that the slurry is heated uniformly, the mixing of the slurry is facilitated, and primary slurry and primary filter residue are generated by filtering the slurry through a screen.

And step two, cooling the primary filter residue to 20-30 ℃. Adding 200-300ml of water, heating to 65 ℃, and filtering by a screen to generate secondary slurry.

As an example, the above primary filter residue was cooled to 28 ℃. Water 280ml is added to heat to 65 ℃ in a water bath, and secondary slurry is generated after filtration through a screen.

And thirdly, mixing the primary slurry and the secondary slurry, heating to 45 ℃, and filtering by a screen to generate a mixed solution.

For example, the primary slurry and the secondary slurry are mixed to obtain a more homogeneous slurry while retaining most of the nutrients of the slurry, and the mixed solution obtained by mixing is used as a material for the subsequent process.

The above steps are taken as an invention point of the embodiment of the disclosure, and the technical problem mentioned in the background art is solved, namely, the activity of cells and beneficial bacteria is damaged due to high-temperature homogenization of the medlar serous fluid in the preparation process flow, and simultaneously, nutrient components are lost due to incomplete homogenization treatment of the serous fluid, so that the nutrient value is reduced. The factors causing the loss of the nutrient components of the medlar are as follows: the high temperature destroys the structure of cells and beneficial bacteria in the slurry, which leads to the inactivation of the cells and beneficial bacteria and the loss of nutrient components. Meanwhile, the single homogenization treatment of the slurry can also cause the loss of nutrient components. If the factors are solved, the loss of the nutrient components of the pulp is avoided, and the nutrient and health-care value of the medlar drink is improved. To achieve this effect, embodiments of the present disclosure provide a method of heating the slurry in a water bath. The water bath heating not only achieves the effect of heating and homogenizing, but also keeps the activity of cells and beneficial bacteria. In addition, in order to make the slurry mixed more uniform, the embodiment of the disclosure provides a method of multiple homogenization treatment. First, the obtained slurry was added with water, heated in a water bath, and filtered through a screen, thereby obtaining a primary slurry and a primary residue. And then, cooling the primary filter residue to avoid destroying the activity of cells and beneficial bacteria due to overhigh temperature. And heating the cooled primary filter residue in water bath again, and filtering by using a screen to obtain secondary slurry. And finally, mixing the primary slurry and the secondary slurry, and heating in a water bath again. The step not only retains most of the nutrient components of the primary slurry, but also obtains more uniform slurry, and the mixed solution obtained by mixing is used as the material of the subsequent process flow.

And step 207, filtering the mixed solution by using a 80-mesh screen to obtain a filtrate, and performing acid treatment on the filtrate to generate the medlar juice.

In some embodiments, the execution body may filter the mixed solution through a 80-mesh screen to obtain a filtrate. Adding 0.01% potassium permanganate solution into the filtrate to perform acid treatment on the filtrate to obtain the medlar juice.

Step 208, adding 0.05-0.1% of pectinase into the wolfberry fruit juice for enzyme treatment for 4-6h, and keeping the enzyme treatment temperature at 50-60 ℃.

In some embodiments, the above-mentioned performing body may add 0.05% -0.1% pectinase to the wolfberry fruit juice for enzyme treatment for 4-6 h. Keeping the enzyme treatment temperature at 50-60 ℃.

For example, the executive body may add 0.08% of pectinase to the lycium barbarum juice, maintain the lycium barbarum juice at 55 ℃, and complete the enzyme treatment after 5 hours.

And 209, sterilizing and filtering the medlar juice after the enzyme treatment to generate medlar juice.

In some embodiments, the execution subject may sterilize the enzyme-treated lycium barbarum juice and filter the pulp residue of the lycium barbarum juice to produce the lycium barbarum raw juice.

In some optional implementations of some embodiments, the performing step of sterilizing and filtering the enzyme-treated raw juice of lycium barbarum to generate raw juice of lycium barbarum may include the following steps:

in the first step, 60-80mg/L of a mixture of sodium sulfite and sodium bisulfite is added into the enzyme-treated wolfberry fruit juice for sterilization to generate sterile wolfberry fruit juice.

As an example, the above-mentioned performing body may add 65mg/L of a mixture of sodium sulfite and sodium bisulfite to the enzyme-treated lycium barbarum juice, wherein the above-mentioned sodium sulfite and sodium bisulfite may be mixed in a ratio of 1: 1, were mixed. The mixture of sodium sulfite and sodium bisulfite has the function of normal temperature sterilization, and avoids the influence of high temperature sterilization on the color of the medlar juice. Sterilizing at normal temperature to obtain sterile fructus Lycii natural juice.

And secondly, filtering the sterile medlar raw juice through a 200-mesh screen to generate medlar juice.

For example, the execution body may filter the sterile raw lycium barbarum juice through a 200-mesh screen to remove small particulate matters, thereby producing a lycium barbarum juice.

And step 210, adding ingredients into the raw wolfberry juice to prepare the wolfberry beverage.

In some embodiments, the execution body can add ingredients to raw juice of lycium barbarum to make a lycium barbarum beverage. Wherein, one or more of the ingredients can be added, and the ingredients can be added in different proportions.

In some optional implementations of some embodiments, the ingredients may include, but are not limited to, at least one of: 1.5% of citric acid, 0.9% of ascorbic acid, 0.7% of vitamin C, 0.5% of radix ophiopogonis, 15-40g of honey, 20-40g of hawthorn, 8-25g of Chinese date, 10-15g of chrysanthemum and 15-30g of honeysuckle. Wherein, one or more of the ingredients can be added, and the ingredients can be added in different proportions.

Optionally, the above fructus Lycii beverage is sterilized instantaneously at ultra-high temperature, and filled and sealed with 200ml of the above beverage to obtain fructus Lycii beverage.

By way of example, the execution body can perform ultrahigh-temperature instant sterilization on the medlar drink added with one or more ingredients, fill the medlar drink with the specification of 200ml, and cover the medlar drink to prepare the medlar drink.

In some optional implementation manners of some embodiments, the ultra-high temperature instant sterilization of the lycium barbarum beverage may be performed by subjecting the lycium barbarum beverage to sterilization at a temperature of 135-.

The above embodiments of the present disclosure have the following advantages: firstly, acquiring a medlar image of each medlar in a medlar group to obtain a medlar image set. And inputting each medlar image included in the medlar image set into a classification model to obtain a classification result set corresponding to the medlar image. And obtaining a classification result set by using a pre-trained classification model. The time spent on selecting the medlar is reduced, and the medlar selection efficiency is improved. Next, a target wolfberry is selected from the group of wolfberries based on the generated set of classification results. And selecting the medlar for preparing the medlar drink according to the identification result output by the classification model. And then, soaking the target medlar with preset weight to generate soaked target medlar serving as first medlar. Soaking the target medlar in potassium permanganate solution to kill bacteria and viruses on the medlar epidermis. Then, the first Chinese wolfberry is crushed and softened to generate slurry, and the generated slurry is heated to 30-75 ℃ so that the slurry is further softened to generate a mixed solution. Crush and soften above-mentioned first matrimony vine, be convenient for obtain the nutrient substance in the matrimony vine fruit, simultaneously, get rid of the stalk skin sediment that influences the taste. Then, the mixed solution is filtered through a 80-mesh screen to obtain a filtrate, and the obtained filtrate is subjected to acid treatment to obtain the wolfberry fruit juice. The resulting filtrate was subjected to acid treatment to remove bacteria produced during the preparation. Then, 0.05% -0.1% of pectinase is added into the medlar juice for enzyme treatment for 4-6h, and the enzyme treatment temperature is kept at 50-60 ℃. The fructus Lycii juice contains a large amount of pectin substances, and is decomposed and precipitated with pectinase, so that the fructus Lycii juice is clearer, and the filtering speed of the fructus Lycii juice is increased. Then, sterilizing and filtering the medlar juice after enzyme treatment to generate medlar original juice. Due to the treatment of pectinase, the filtering speed is increased, and the raw wolfberry juice is produced. Finally, adding ingredients into the raw wolfberry juice to prepare the wolfberry beverage. Because the efficiency of selecting the medlar is improved, and the medlar is treated by the technical processes of potassium manganate solution sterilization, crushing softening, filtration, acid treatment, pectinase treatment, ingredient addition and the like. Furthermore, the loss of the nutrient components of the medlar fruits is reduced, the bacterial pollution is avoided, and the clarity of the medlar drink is improved. Therefore, the nutritional health-care value of the medlar drink is improved, the taste and flavor of the medlar drink are enriched and improved, and the sensory experience of users is improved.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.

Claims

1. A preparation method of a medlar drink comprises the following steps:

acquiring a medlar image of each medlar in the medlar group to obtain a medlar image set;

inputting each medlar image included in the medlar image set into a classification model to obtain a classification result set corresponding to the medlar image;

selecting a target wolfberry from the group of wolfberries based on the generated set of classification results;

soaking a target Chinese wolfberry with a preset weight to generate a soaked target Chinese wolfberry serving as a first Chinese wolfberry;

crushing and softening the first medlar to generate serous fluid;

heating the slurry to 30-75 ℃ so as to further soften the slurry and generate a mixed solution;

filtering the mixed solution by a sieve of 80 meshes to obtain a filtrate, and performing acid treatment on the generated filtrate to generate the medlar juice;

adding 0.05% -0.1% of pectinase into the medlar juice for enzyme treatment for 4-6h, and keeping the enzyme treatment temperature at 50-60 ℃;

sterilizing and filtering the medlar juice after enzyme treatment to generate medlar original juice;

adding adjuvants into the fructus Lycii natural juice to obtain fructus Lycii beverage.

2. The method of claim 1, wherein the method further comprises:

and carrying out ultrahigh-temperature instantaneous sterilization on the medlar beverage, filling and sealing with 200ml of specification to prepare the medlar beverage.

3. The method of claim 2, wherein the ultra-high temperature flash sterilization of the wolfberry beverage comprises:

and sterilizing the medlar beverage under the conditions that the temperature is 135-150 ℃ and the sterilization time is 1-60 s.

4. The method of claim 3, wherein the step of soaking the target Lycium barbarum with a preset weight to generate the soaked target Lycium barbarum as the first Lycium barbarum comprises:

soaking the target medlar with the preset weight in warm water at the temperature of 30-40 ℃ for 10-12min, and taking out to obtain primary soaked medlar;

soaking the primary soaked Chinese wolfberry in 0.03% potassium permanganate solution for 10-12min, and taking out to obtain secondary soaked Chinese wolfberry;

rinsing and soaking the twice-soaked Chinese wolfberry by using water, and taking the soaked target Chinese wolfberry as a first Chinese wolfberry.

5. The method of claim 4, wherein said crushing and softening said first wolfberry to form a slurry comprises:

placing the first medlar in a rubber roller for crushing and softening to generate medlar pulp;

and filtering the medlar pulp by a filter screen of 40 meshes to generate pulp.

6. The method of claim 5, wherein said heating the slurry to 30-75 ℃ for further softening of the slurry to produce a mixed liquor comprises:

adding 300-450ml of water into the slurry, heating to 75 ℃ so as to uniformly mix the slurry, and filtering by using a screen to generate primary slurry and primary filter residue;

cooling the primary filter residue to 20-30 ℃, adding 200ml of water, heating to 65 ℃, and filtering by a screen to generate secondary slurry;

and mixing the primary slurry and the secondary slurry, heating to 45 ℃, and filtering by a screen to generate a mixed solution.

7. The method of claim 6, wherein sterilizing and filtering the enzyme-treated juice of Lycium barbarum to produce raw juice of Lycium barbarum comprises:

adding 60-80mg/L mixture of sodium sulfite and sodium bisulfite into enzyme treated fructus Lycii juice, and sterilizing to obtain sterile fructus Lycii juice;

and filtering the sterile medlar raw juice by a 200-mesh screen to generate medlar juice.

8. The method of claim 7, wherein the ingredients comprise at least one of: 1.5% of citric acid, 0.9% of ascorbic acid, 0.7% of vitamin C, 0.5% of radix ophiopogonis, 15-40g of honey, 20-40g of hawthorn, 8-25g of Chinese date, 10-15g of chrysanthemum and 15-30g of honeysuckle.

9. The method of claim 8, wherein the selecting a target wolfberry from the group of wolfberries based on the generated set of classification results comprises:

selecting a classification result from the generated classification result set as a target classification result;

and determining the medlar corresponding to the target classification result as the target medlar.

10. The method of claim 9, wherein the classification model is trained by:

determining a network structure of an initial neural network and initializing network parameters of the initial neural network;

acquiring a training sample set, wherein training samples comprise sample images and sample categories corresponding to the sample images;

selecting samples from the sample set, and performing the following training steps:

inputting a sample image of a selected sample into an initial neural network to obtain the category of the selected sample;

comparing the selected sample category with the corresponding sample category;

determining whether the initial neural network reaches a preset optimization target according to the comparison result;

in response to determining that the initial neural network meets the optimization goal, treating the initial neural network as the classification model for which training is complete;

and in response to determining that the initial neural network is not trained, adjusting relevant parameters in the initial neural network, reselecting samples from the sample set, using the adjusted initial neural network as the initial neural network, and executing the training step again.