Baking method, device, electronic device, and storage medium

Abstract

The application provides a roasting method, a roasting device, an electronic device and a storage medium. In the process of roasting a roasting target according to a first-stage roasting parameter, whether the roasting progress of the roasting target exceeds the roasting progress corresponding to a next node of the first stage is detected. If it is detected that the roasting progress of the roasting target exceeds the roasting progress corresponding to the next node of the first stage, the roasting target is roasted according to a second-stage roasting parameter, wherein the second stage is a next roasting stage of the first stage. In this way, the purpose of automatically adjusting the roasting parameter is achieved, the influence of the experience and level of roasting personnel on the roasting quality is avoided, and the quality of the roasting target is ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic control, and in particular to a baking method and device, electronic equipment and a storage medium. BACKGROUND

[0002] For some products, baking and dehydration treatment of raw materials is a necessary process in the production process of these products. For example, tobacco leaf baking is a necessary process for cigarette processing. By baking the tobacco leaves, the moisture content in the tobacco leaves is reduced to meet the requirements of subsequent cigarette packaging and other production steps.

[0003] Currently, in the process of baking and dehydration treatment of the baking target, in order to ensure the baking quality of the baking target, the baking personnel need to check the baking target regularly and adjust the drying temperature, humidity and other parameters according to experience. However, this method makes the baking quality of the baking target greatly affected by the experience and level of the baking personnel, resulting in uneven baking quality and affecting product quality. SUMMARY

[0004] Therefore, the present application provides a baking method, device, electronic equipment and storage medium to solve the problem that the baking quality of the baking target is greatly affected by the experience and level of the baking personnel in the prior art, resulting in uneven baking quality and affecting product quality.

[0005] The technical solution provided by the present application is as follows:

[0006] In a first aspect, the present application provides a baking method, comprising:

[0007] In the process of baking the baking target according to the baking parameters of the first stage, it is detected whether the baking progress of the baking target exceeds the baking progress corresponding to the advancement node of the first stage;

[0008] If the baking progress of the baking target exceeds the baking progress corresponding to the advancement node of the first stage, the baking target is baked according to the baking parameters of the second stage, and the second stage is the next baking stage of the first stage.

[0009] In a second aspect, the present application provides a baking device, comprising:

[0010] The detection module is configured to detect whether the baking progress of the baking target exceeds the baking progress corresponding to the advancement node of the first stage in the process of baking the baking target according to the baking parameters of the first stage;

[0011] The adjusting module is configured to, if the baking progress of the baking target exceeds the baking progress corresponding to the advancing node of the first stage, bake the baking target according to the baking parameters of the second stage, the second stage being the next baking stage of the first stage.

[0012] In a third aspect, the present application provides an electronic device, comprising:

[0013] a memory and a processor;

[0014] The memory is configured to store a program.

[0015] The processor is configured to implement the method according to any one of the preceding aspects by running the program in the memory.

[0016] In a fourth aspect, the present application provides a storage medium, the storage medium storing a computer program, the computer program being executed by a processor to implement the method according to any one of the preceding aspects.

[0017] The baking method provided by the present application can detect whether the baking progress of the baking target exceeds the baking progress corresponding to the advancing node of the first stage during the baking of the baking target according to the baking parameters of the first stage. If the baking progress of the baking target exceeds the baking progress corresponding to the advancing node of the first stage, the baking target is baked according to the baking parameters of the second stage, the second stage being the next baking stage of the first stage. In this way, the purpose of automatically adjusting the baking parameters is achieved, the influence of the experience and level of the baking personnel on the baking quality is avoided, and the quality of the baking target is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only embodiments of the present application, and those skilled in the art can obtain other drawings according to the provided drawings without creative labor.

[0019] Figure 1 is a flowchart of a baking method provided by an embodiment of the present application;

[0020] Figure 2 is a baking temperature curve diagram of tobacco leaves in a baking process provided by an embodiment of the present application;

[0021] Figure 3 is a flowchart of detecting whether the baking progress of a baking target exceeds the baking progress corresponding to the advancing node of the first stage provided by an embodiment of the present application;

[0022] Figure 4 is a training process schematic diagram of a baking temperature stage identification model provided by an embodiment of the present application;

[0023] Figure 5 is a process schematic diagram of adjusting humidity parameters provided by an embodiment of the present application;

[0024] Figure 6 is a tobacco baking parameter adjustment process schematic diagram provided by an embodiment of the present application;

[0025] Figure 7 is a structure schematic diagram of a baking device provided by an embodiment of the present application;

[0026] Figure 8 is a structure schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0027] The technical scheme of the present application is applicable to the application scenario of baking the baking target. By using the technical scheme of the present application, the baking parameters can be automatically adjusted during the baking process, and the influence of the baking personnel's experience and level on the baking quality is avoided.

[0028] For some products, baking and dehydrating the baking target used to produce the product is a necessary step in the production process of the product. For example, tobacco leaf baking is an important link in the production process of tobacco leaves, and its purpose is to promote the yellowing and drying of tobacco leaves, reduce the water content in tobacco leaves, and meet the requirements of subsequent tobacco leaf packaging and other production steps.

[0029] At present, semi-automatic baking technology is generally used to bake the baking target to improve the quality of the baking target. Among them, semi-automatic baking technology refers to that the baking personnel can input a baking curve before baking, so that each baking equipment in the baking room can bake the baking target according to the baking curve. However, the above baking curve cannot completely meet the baking requirements, and the baking personnel needs to check the state of the baking target from time to time, and adjust the baking time, baking temperature, baking humidity and other parameters of each stage according to the state of the baking target.

[0030] However, the current baking method not only brings a heavy workload to the baking personnel, but also relies too much on the working experience of the baking personnel. Once the baking personnel makes a mistake in judging the baking stage of the baking target according to the working experience, the leading or lagging phenomenon of the temperature and humidity index adjustment operation will occur, which will cause a lot of economic loss and resource waste.

[0031] Therefore, the present application provides a baking method and device, an electronic device and a storage medium. The technical scheme automatically determines the timing of adjusting the baking parameters by comparing the baking progress of the baking target with the baking progress corresponding to the actual baking parameters, so as to ensure the quality of the baking target.

[0032] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the scope of protection of the present application.

[0033] The present embodiment proposes a roasting method, which can be executed by an electronic device. The electronic device can be any device with data and instruction processing functions, such as a computer, a smart terminal, a server, etc. Referring to FIG. 1, the method comprises the following steps. Figure 1

[0034] S101, detecting whether the roasting progress of the roasting target exceeds the roasting progress corresponding to the advancement node of the first stage during the process of roasting the roasting target according to the roasting parameters of the first stage. If the roasting progress of the roasting target exceeds the roasting progress corresponding to the advancement node of the first stage, step S102 is executed. If the roasting progress of the roasting target does not exceed the roasting progress corresponding to the advancement node of the first stage, step S103 is executed.

[0035] The roasting target refers to the object to be roasted. The roasting target can be placed in a roasting room, and the roasting of the roasting target can be realized by controlling the temperature, humidity, wind speed, and temperature rising speed, etc. in the roasting room. For example, in the production process of tobacco leaves, the tobacco leaves can be used as the roasting target.

[0036] The roasting parameters refer to the parameters affecting the roasting quality set for completing the roasting of the roasting target. The roasting parameters include the temperature, humidity, temperature rising time, constant temperature time, and wind speed, etc. corresponding to each roasting stage of the roasting target. The roasting stages and the roasting parameters such as the temperature, humidity, temperature rising time, constant temperature time, and wind speed, etc. corresponding to each roasting stage can be set by professionals according to the roasting target, which is not limited in the present embodiment. In some embodiments, the roasting curve can be set according to the type of the roasting target, which includes each stage in the roasting process and the parameters such as the temperature, humidity, temperature rising time, constant temperature time, and wind speed, etc. corresponding to each stage. The roasting personnel can input the roasting curve before roasting, so that each roasting device in the roasting room can roast the roasting target according to the roasting curve.

[0037] In some embodiments, the roasting target is tobacco leaves. The roasting of tobacco leaves is a slow temperature rising process, as shown in FIG. 2. Figure 2 ​As shown. In order to facilitate baking, the entire baking process is generally divided into ten baking stages, and during the baking of the tobacco leaves, the corresponding temperature, humidity, temperature rising time, constant temperature time and wind speed and other parameters of each baking stage are recorded. Among them, the temperature corresponding to each baking stage can be controlled by controlling the dry bulb temperature; the humidity corresponding to each baking stage is controlled by controlling the wet bulb temperature; the wind speed corresponding to each baking stage is controlled by controlling the running speed of the fan, for example, by setting "high wind speed" or "low wind speed".

[0038] Generally, in the tobacco leaf baking process, for each baking stage, a temperature rising process needs to be performed first, and then a constant temperature process. Among them, when performing the temperature rising process of any baking stage, the baking temperature needs to be raised to the temperature corresponding to the baking stage according to the temperature rising time corresponding to the baking stage, and when performing the constant temperature process of any baking stage, the baking temperature and humidity need to be kept constant according to the constant temperature time corresponding to the baking stage.

[0039] The first stage refers to any stage that needs to be adjusted in all baking stages of the baking target. Among them, the stage that needs to be adjusted can be set by professionals according to the actual situation, and the embodiment is not limited. For example, when baking tobacco leaves, it is generally divided into ten baking stages, but the change of tobacco leaves in the first baking stage is not obvious, and no parameter adjustment is needed. Therefore, if the baking target is tobacco leaves, the first baking stage of the baking target can not be adjusted, and the second baking stage to the tenth baking stage can be set as the baking stage that needs to be adjusted to reduce the calculation amount. For example, all ten baking stages of the tobacco leaf baking process can also be set as the stage that needs to be adjusted, and the embodiment is not limited.

[0040] That is, in the embodiment of the present application, during the baking process of the baking target according to the baking parameters of any baking stage that needs to be adjusted, it is necessary to detect whether the baking progress of the baking target exceeds the baking progress corresponding to the advanced node of the stage.

[0041] The roasting progress of the roasting target is determined according to the actual state of the roasting target. In some embodiments, images of the roasting target serving as a reference in the roasting process can be obtained in advance, and then the images are grouped by professionals according to different roasting progress, and image features corresponding to each group of images are extracted. When detecting the roasting progress of the roasting target, the image of the roasting target can be obtained, and the features of the image of the roasting target are extracted as the image features of the roasting target. The similarity between the image features of the roasting target and the image features corresponding to each group of images is calculated, and the roasting progress corresponding to the group with the highest similarity to the image features of the roasting target is determined as the roasting progress of the roasting target in this embodiment. It should be noted that the image of the roasting target can be a photo or a video frame, and the present embodiment is not limited in this regard.

[0042] The images of the roasting target serving as a reference can be grouped according to the roasting stages and the roasting progress of each roasting stage. For example, for each roasting stage, a plurality of roasting progress nodes can be divided, and the images in the same roasting stage and the same roasting progress node can be grouped.

[0043] For example, if the roasting target includes three roasting stages, each roasting stage can be evenly divided into 5 roasting progress nodes, and the images of the roasting target serving as a reference need to be divided into 11 groups. Specifically, if the roasting progress at the beginning of the first roasting stage is marked as 1, the roasting progress at the beginning of the second roasting stage is marked as 2, and the roasting progress at the beginning of the third roasting stage is marked as 3, the images of the roasting target serving as a reference can be divided into the following groups: the group corresponding to the roasting progress 1, the group corresponding to the roasting progress 1.2, the group corresponding to the roasting progress 1.4, the group corresponding to the roasting progress 1.6, the group corresponding to the roasting progress 1.8, the group corresponding to the roasting progress 2, the group corresponding to the roasting progress 2.2, the group corresponding to the roasting progress 2.4, the group corresponding to the roasting progress 2.6, the group corresponding to the roasting progress 2.8, and the group corresponding to the roasting progress 3 (at the end of roasting).

[0044] The advancement node of the first stage refers to the node near the end of the first stage, when the first stage is about to advance to the second stage. If the roasting parameters are not adjusted in time after the roasting progress exceeds the roasting progress corresponding to the advancement node of the first stage, and the roasting target is still roasted with the roasting parameters of the first stage for a long period of time, the roasting quality of the roasting target may be reduced. Specifically, the roasting progress corresponding to the advancement node of the first stage can be set according to the actual situation, and the present embodiment is not limited in this regard.

[0045] For example, if the baking target includes three baking stages, and the second and third baking stages are the stages that need to be adjusted, the second and third baking stages can be regarded as the first stage. If the baking progress at the beginning of the second baking stage is 2, and the baking progress at the beginning of the third baking stage is 3, 1.9 can be set as the baking progress corresponding to the progress node of the second baking stage, and 2.9 can be set as the baking progress corresponding to the progress node of the third baking stage.

[0046] In the embodiments of the present application, during the baking of the baking target according to the baking parameters of the first stage, it is detected whether the baking progress of the baking target exceeds the baking progress corresponding to the progress node of the first stage. If the baking progress of the baking target exceeds the baking progress corresponding to the progress node of the first stage, step S102 is performed. If the baking progress of the baking target does not exceed the baking progress corresponding to the progress node of the first stage, step S103 is performed.

[0047] For example, according to the above embodiments, if it is determined that the baking progress of the baking target is 1.8, and the progress node of the first stage is 1.7, it indicates that the baking progress of the baking target exceeds the baking progress corresponding to the progress node of the first stage, and step S102 can be performed. According to the above embodiments, if it is determined that the baking progress of the baking target is 1.8, and the progress node of the first stage is 1.9, it indicates that the baking progress of the baking target does not exceed the baking progress corresponding to the progress node of the first stage, and step S103 can be performed.

[0048] S102, baking the baking target according to the baking parameters of the second stage.

[0049] The second stage refers to the next baking stage adjacent to the first stage. It should be noted that if the first stage is the last baking stage in the baking process, the baking will stop after the first stage, and the second stage is the stage in which the baking is stopped. In the stage in which the baking is stopped, each baking device in the baking room will stop working or run at a low speed according to the set parameters. The baking parameters corresponding to the stage are that each baking device in the baking room is stopped, or each baking device in the baking room runs at a low speed according to the set parameters.

[0050] For example, if the tobacco leaf is the baking target, the second baking stage to the tenth baking stage in the baking process of the tobacco leaf is set as the baking stage that needs to be adjusted, any one of the second baking stage to the tenth baking stage can be the first stage. If the first stage is the second baking stage, the second stage is the third baking stage, if the first stage is the sixth baking stage, the second stage is the seventh baking stage, if the first stage is the tenth baking stage, the second stage is the stage that stops baking.

[0051] If it is detected that the baking progress of the baking target exceeds the baking progress corresponding to the advancing node of the first stage, it indicates that the actual state of the baking target can be determined to have reached the node that needs to be advanced, and if the baking parameter of the baking target is not adjusted in time, the baking quality of the baking target can be reduced. Therefore, when it is detected that the baking progress of the baking target exceeds the baking progress corresponding to the advancing node of the first stage, the baking parameter of the baking target is automatically adjusted, and the baking target is baked according to the baking parameter of the second stage. The setting can automatically adjust the baking parameter of the baking target, and avoid the influence of the experience and level of the baking personnel on the baking quality.

[0052] If the baking target is baked according to the baking parameter of the first stage again, the quality of the baking target can be affected, and the baking target needs to be baked according to the baking parameter of the second stage.

[0053] S103, baking the baking target according to the baking parameter of the first stage.

[0054] If it is detected that the baking progress of the baking target does not exceed the baking progress corresponding to the advancing node of the first stage, it indicates that the actual state of the baking target can be determined to have not reached the node that needs to be advanced, and in order to ensure the baking quality, the baking target can be baked according to the baking parameter of the first stage.

[0055] In the above embodiment, whether the baking progress of the baking target exceeds the baking progress corresponding to the advancing node of the first stage can be detected in the process of baking the baking target according to the baking parameter of the first stage, if it is detected that the baking progress of the baking target exceeds the baking progress corresponding to the advancing node of the first stage, the baking target is baked according to the baking parameter of the second stage, and the second stage is the next baking stage of the first stage. The setting achieves the purpose of automatically adjusting the baking parameter, avoids the influence of the experience and level of the baking personnel on the baking quality, and ensures the quality of the baking target.

[0056] As an optional implementation manner, the baking method in the above embodiment can specifically include the following steps in another embodiment of the present application:

[0057] determine the growth condition of the roasting target; and determine the first-stage roasting parameter and the second-stage roasting parameter according to the growth condition of the roasting target.

[0058] In this embodiment, before step S101 of the above embodiment, the growth condition of the roasting target can be determined first, so as to determine the first-stage roasting parameter and the second-stage roasting parameter according to the growth condition of the roasting target.

[0059] Specifically, a professional can establish a roasting parameter group corresponding to different growth conditions according to different growth conditions of the roasting target. The roasting parameter group includes the roasting stage of the roasting target, and the temperature, humidity, temperature rising time, constant temperature time, and wind speed corresponding to each roasting stage.

[0060] Before roasting the roasting target, the growth condition of the roasting target can be determined first. In some embodiments, a growth condition recognition model can be trained to detect the growth condition of the roasting target through the growth condition recognition model.

[0061] Specifically, a large number of images of sample roasting targets can be obtained. The images of the sample roasting targets can be photos of the sample roasting targets, or videos of the sample roasting targets, which are not limited in this embodiment. The sample roasting target refers to a roasting target used to collect training samples. A large number of images of sample roasting targets before roasting are collected as training samples, and the growth condition of the roasting target in each image is labeled by a professional as a training label, and the growth condition recognition model is trained until the loss function of the growth condition recognition model converges. The growth condition recognition model can use a classification model as a basic model, which is not limited in this embodiment.

[0062] Before roasting the roasting target, an image of the roasting target can be obtained, and the image of the roasting target is input into the growth condition recognition model, so that the growth condition recognition model processes the image of the roasting target to determine the actual growth condition of the roasting target.

[0063] Then, the roasting parameter group corresponding to the actual growth condition of the roasting target is determined from the pre-established roasting parameter groups corresponding to different growth conditions, and the roasting target is roasted according to the roasting parameter group corresponding to the actual growth condition of the roasting target.

[0064] In some embodiments, the roasting target is tobacco leaf, and the growth condition of the roasting target includes the maturity and growth position of the tobacco leaf. The maturity of the tobacco leaf generally includes under-ripe, mature, and over-ripe, and the growth position includes upper, middle, and lower.

[0065] The curing expert can establish a curing parameter group corresponding to different growth positions and ripeness according to the local tobacco leaf variety. That is, a curing parameter group corresponding to “under-ripe + upper part”, a curing parameter group corresponding to “under-ripe + middle part”, a curing parameter group corresponding to “under-ripe + lower part”, a curing parameter group corresponding to “ripe + upper part”, a curing parameter group corresponding to “ripe + middle part”, a curing parameter group corresponding to “ripe + lower part”, a curing parameter group corresponding to “over-ripe + upper part”, a curing parameter group corresponding to “over-ripe + middle part”, and a curing parameter group corresponding to “over-ripe + lower part”.

[0066] For example, the curing parameter group corresponding to “ripe + middle part” is shown in Table 1, and the curing parameter group corresponding to “under-ripe + upper part” is shown in Table 2.

[0067]

[0068] Table 1

[0069]

[0070] Table 2

[0071] Before the tobacco leaves are cured, the ripeness and growth position of the tobacco leaves need to be determined. In some embodiments, a ripeness recognition model can be trained to detect the ripeness of the tobacco leaves through the ripeness recognition model.

[0072] Specifically, a large number of tobacco leaf images can be collected as training samples, and the ripeness of the corresponding tobacco leaves in the tobacco leaf images is labeled by a curing expert as training labels. The ripeness recognition model is trained using the training samples and the training labels until the ripeness recognition model converges. The ripeness recognition model can use a transformer model as a base model, which is not limited in the present embodiment. The image of the curing target is input into the trained ripeness recognition model, so that the ripeness recognition model processes the image of the curing target to determine the ripeness of the curing target.

[0073] The growth position of the tobacco leaves can be directly determined by the naked eye, so the growth position of the tobacco leaves can be manually confirmed by the staff. Alternatively, a tobacco variety recognition model and a tobacco growth position recognition model can be trained. Before the tobacco leaves are cured, the image of the tobacco leaves is input into the tobacco variety recognition model to determine the variety of the tobacco leaves based on the tobacco variety recognition model, and then the image of the tobacco leaves and the variety of the tobacco leaves are input into the tobacco growth position recognition model to determine the growth position of the tobacco leaves based on the tobacco growth position recognition model.

[0074] According to the ripeness and growth position of the tobacco leaves, a corresponding curing parameter group is selected to cure the tobacco leaves according to the curing parameter group.

[0075] In the above embodiments, different baking parameters can be selected according to the growth of the baking target, so that the baking target is baked using the baking parameters that meet the growth of the baking target, thereby effectively improving the baking quality.

[0076] As an optional implementation, in another embodiment of the present application, the baking target of the above embodiments includes a first baking target and a second baking target, and the baking temperature of the first baking target is higher than that of the second baking target.

[0077] The step of detecting whether the baking progress of the baking target exceeds the baking progress corresponding to the advancement node of the first stage in the above embodiments can specifically include the following steps:

[0078] The baking progress of the first baking target and the second baking target is detected respectively to determine whether the baking progress of the first baking target and the second baking target exceeds the baking progress corresponding to the advancement node of the first stage. If it is detected that the baking progress of the first baking target and the second baking target exceeds the baking progress corresponding to the advancement node of the first stage, it is determined that the baking progress of the baking target exceeds the baking progress corresponding to the advancement node of the first stage.

[0079] Specifically, the baking target of the above embodiments includes a first baking target and a second baking target, and the temperature of the first baking target is higher than that of the second baking target. In some embodiments, in order to ensure the baking quality of most of the baking targets in the baking room, the baking target at the highest temperature in the baking room is set as the first baking target, and the baking target at the lowest temperature in the baking room is set as the second baking target. The baking parameters are adjusted according to the first baking target and the second baking target. For example, the baking targets in the baking room are generally arranged in layers, and the uppermost layer, which is farthest from the ground, generally has the highest temperature. The baking target in this layer can be set as the first baking target, and the lowermost layer, which is closest to the ground, generally has the lowest temperature. The baking target in this layer can be set as the second baking target.

[0080] In a specific embodiment, the baking target is tobacco leaves, which are divided into upper tobacco leaves, middle tobacco leaves and lower tobacco leaves for baking. The upper tobacco leaves, which have the highest temperature, are the first baking target, and the lower tobacco leaves, which have the lowest temperature, are the second baking target.

[0081] In the embodiments of this application, when detecting whether the baking progress of the baking target exceeds the baking progress corresponding to the advanced node of the first stage, the baking progress of the first baking target and the second baking target are respectively detected as exceeding the baking progress corresponding to the advanced node of the first stage. It should be noted that the detection of whether the baking progress of the first baking target exceeds the baking progress corresponding to the advanced node of the first stage and whether the baking progress of the second baking target exceeds the baking progress corresponding to the advanced node of the first stage can be performed in the manner described in the above embodiments. Those skilled in the art can refer to the description in the above embodiments, and it will not be repeated here.

[0082] If it is detected that the baking progress of both the first baking target and the second baking target exceeds the baking progress corresponding to the advanced node of the first stage, then it can be determined that the baking progress of the baking target exceeds the baking progress corresponding to the advanced node of the first stage.

[0083] In the above embodiments, when it is detected that the baking progress of both the first baking target and the second baking target exceeds the baking progress corresponding to the advanced node of the first stage, it is determined that the baking progress of the baking target exceeds the baking progress corresponding to the advanced node of the first stage, so as to ensure the baking quality of most of the baking targets in the baking room.

[0084] As an optional implementation method, such as Figure 3 As shown in another embodiment of this application, the steps of the above embodiments are disclosed to detect whether the baking progress of the first baking target and the second baking target both exceed the baking progress corresponding to the advanced node of the first stage. Specifically, the steps may include the following:

[0085] S301. Detect whether the baking progress of the first baking target exceeds the baking progress corresponding to the advanced node of the first stage; if the baking progress of the first baking target exceeds the baking progress corresponding to the advanced node of the first stage, then step S302 can be executed.

[0086] Specifically, since the temperature of the first baking target is greater than that of the second baking target, the baking progress of the first baking target is always greater than that of the second baking target during the actual baking process.

[0087] Based on this, in the embodiments of this application, it can be first detected whether the baking progress of the first baking target exceeds the baking progress corresponding to the advanced node of the first stage. The specific method for detecting whether the baking progress of the first baking target exceeds the baking progress corresponding to the advanced node of the first stage can be referred to the description in the above embodiments, and will not be repeated here.

[0088] S302, detecting whether the roasting progress of the second roasting target exceeds the roasting progress corresponding to the advanced node of the first stage; if it is detected that the roasting progress of the second roasting target exceeds the roasting progress corresponding to the advanced node of the first stage, step S303 can be performed.

[0089] If it is detected that the roasting progress of the first roasting target exceeds the roasting progress corresponding to the advanced node of the first stage, the roasting progress of the second roasting target is further detected to determine whether it exceeds the roasting progress corresponding to the advanced node of the first stage. The specific detection manner of whether the roasting progress of the second roasting target exceeds the roasting progress corresponding to the advanced node of the first stage can refer to the description of the above embodiments, which will not be repeated here.

[0090] S303, determining that the roasting progress of the first roasting target and the roasting progress of the second roasting target both exceed the roasting progress corresponding to the advanced node of the first stage.

[0091] If it is detected that the roasting progress of the first roasting target exceeds the roasting progress corresponding to the advanced node of the first stage, and it is detected that the roasting progress of the second roasting target exceeds the roasting progress corresponding to the advanced node of the first stage, it can be determined that the roasting progress of the first roasting target and the roasting progress of the second roasting target both exceed the roasting progress corresponding to the advanced node of the first stage.

[0092] In the above embodiments, the roasting progress of the first roasting target and the roasting progress of the second roasting target are detected in sequence to determine whether they exceed the roasting progress corresponding to the advanced node of the first stage, so as to ensure the roasting quality of most of the roasting targets in the roasting room.

[0093] As an optional implementation manner, as shown in FIG. 8, in another embodiment of the present application, the roasting method of the above embodiments can further include the following steps: Figure 3

[0094] S304, if it is detected that the roasting progress of the first roasting target does not exceed the roasting progress corresponding to the advanced node of the first stage, detecting whether the remaining roasting time length in the roasting parameter of the first stage is greater than a set detection period time length; if it is detected that the remaining roasting time length of the first stage is less than or equal to the detection period time length, step S305 is performed; if it is detected that the remaining roasting time length of the first stage is greater than the detection period time length, step S306 is performed.

[0095] In some embodiments, when the roasting progress of the first roasting target is detected to determine whether it exceeds the roasting progress corresponding to the advanced node of the first stage in the above embodiments, if it is detected that the roasting progress of the first roasting target does not exceed the roasting progress corresponding to the advanced node of the first stage, the present step can be performed.

[0096] ​The detection period is a period for detecting whether the roasting progress of the roasting target exceeds the roasting progress corresponding to the advancement node of the first stage. That is, in the embodiments of the present application, detection is performed every time interval corresponding to the detection period, and the purpose is to detect whether the roasting progress of the first roasting target exceeds the roasting progress corresponding to the advancement node of the first stage.

[0097] If the roasting progress of the first roasting target exceeds the roasting progress corresponding to the advancement node of the first stage, it can be further detected whether the roasting progress of the second roasting target exceeds the roasting progress corresponding to the advancement node of the first stage.

[0098] If it is detected that the roasting progress of the first roasting target does not exceed the roasting progress corresponding to the advancement node of the first stage, it is necessary to further detect whether the remaining roasting time in the roasting parameter of the first stage is greater than the set detection period time interval, to determine whether there is an opportunity to detect again whether the roasting progress of the first roasting target exceeds the roasting progress corresponding to the advancement node of the first stage during the roasting process of the first stage.

[0099] If it is detected that the remaining roasting time of the first stage is less than or equal to the detection period time interval, it means that there is no opportunity to detect again whether the roasting progress of the first roasting target exceeds the roasting progress corresponding to the advancement node of the first stage. If it is detected that the remaining roasting time of the first stage is greater than the detection period time interval, it means that there is at least one opportunity to detect whether the roasting progress of the first roasting target exceeds the roasting progress corresponding to the advancement node of the first stage.

[0100] S305, the remaining roasting time of the first stage is extended to be greater than the detection period time interval.

[0101] If it is detected that the remaining roasting time of the first stage is less than or equal to the detection period time interval, it means that there is no opportunity to detect again whether the roasting progress of the first roasting target exceeds the roasting progress corresponding to the advancement node of the first stage. In order to avoid the roasting equipment in the roasting room automatically adjusting the roasting parameter to the roasting parameter of the second stage, affecting the roasting quality, the remaining roasting time of the first stage can be appropriately extended so that the remaining roasting time of the first stage is greater than the detection period time interval.

[0102] In some embodiments, if the detection period is 1 hour, in order to make the remaining roasting time greater than the detection period time interval, it can be extended by 2 hours each time.

[0103] S306, when the detection period arrives, detecting again whether the roasting progress of the first roasting target exceeds the roasting progress corresponding to the advancement node of the first stage; if it is detected that the roasting progress of the first roasting target does not exceed the roasting progress corresponding to the advancement node of the first stage, repeating the step S304; if it is detected that the roasting progress of the first roasting target exceeds the roasting progress corresponding to the advancement node of the first stage, executing the step S302.

[0104] If it is detected that the remaining roasting time length of the first stage is greater than the detection period length, or the remaining roasting time length of the first stage is less than or equal to the detection period length but the remaining roasting time length of the first stage is extended to be greater than the detection period length, when the detection period arrives, the roasting progress of the first roasting target can be detected again whether it exceeds the roasting progress corresponding to the advancement node of the first stage.

[0105] If the roasting progress of the first roasting target exceeds the roasting progress corresponding to the advancement node of the first stage, the roasting progress of the second roasting target can be further detected whether it exceeds the roasting progress corresponding to the advancement node of the first stage.

[0106] If the roasting progress of the first roasting target does not exceed the roasting progress corresponding to the advancement node of the first stage, the above process can be repeated from the step S304 to re-detect whether the remaining roasting time length in the roasting parameters of the first stage is greater than the set detection period length, if it is detected that the remaining roasting time length of the first stage is less than or equal to the detection period length, the remaining roasting time length of the first stage is extended to be greater than the detection period length, then when the detection period arrives, the roasting progress of the first roasting target is detected again whether it exceeds the roasting progress corresponding to the advancement node of the first stage, if it is detected that the roasting progress of the first roasting target still does not exceed the roasting progress corresponding to the advancement node of the first stage, the above process can be repeated again from the step S304 until it is detected that the roasting progress of the first roasting target exceeds the roasting progress corresponding to the advancement node of the first stage, then according to the step S302 of the above embodiment, the roasting progress of the second roasting target is further detected whether it exceeds the roasting progress corresponding to the advancement node of the first stage.

[0107] In the above embodiments, when it is detected that the baking progress of the first baking target does not exceed the baking progress corresponding to the advanced node of the first stage, it can be determined whether the remaining baking duration of the first stage is greater than the set detection period duration, and when the remaining baking duration of the first stage is less than or equal to the set detection period duration, the remaining baking duration of the first stage can also be timely extended to avoid that the baking equipment in the baking room automatically adjusts the baking parameter to the baking parameter of the second stage, to strengthen the control of the parameter in the baking room, to ensure that the parameter adjustment is performed when the baking progress of the first baking target exceeds the baking progress corresponding to the advanced node of the first stage, and to improve the baking quality.

[0108] As an optional implementation manner, as shown in FIG. 7, in another embodiment of the present application, it is disclosed that the baking method of the above embodiments can further include the following steps: Figure 3

[0109] S307, if it is detected that the baking progress of the second baking target does not exceed the baking progress corresponding to the advanced node of the first stage, the remaining baking duration of the first stage is extended to the preset duration.

[0110] S308, according to the set detection period, it is detected whether the baking progress of the second baking target exceeds the baking progress corresponding to the advanced node of the first stage; if it is detected that the baking progress of the second baking target exceeds the baking progress corresponding to the advanced node of the first stage, step S303 is performed; if it is detected that the baking progress of the second baking target does not exceed the baking progress corresponding to the advanced node of the first stage, step S309 is performed.

[0111] In some embodiments, when it is detected whether the baking progress of the second baking target exceeds the baking progress corresponding to the advanced node of the first stage in the above embodiments, if it is detected that the baking progress of the second baking target does not exceed the baking progress corresponding to the advanced node of the first stage, the present step can be performed.

[0112] The above detection period is a period for detecting whether the baking progress of the baking target exceeds the baking progress corresponding to the advanced node of the first stage. That is, in the embodiments of the present application, detection is performed once every duration corresponding to the above detection period, and the purpose is to detect whether the baking progress of the second baking target exceeds the baking progress corresponding to the advanced node of the first stage.

[0113] If the baking progress of the second baking target exceeds the baking progress corresponding to the advanced node of the first stage, it indicates that the baking progress of the baking target exceeds the baking progress corresponding to the advanced node of the first stage.

[0114] ​If the roasting progress of the second roasting target does not exceed the roasting progress corresponding to the advanced node of the first stage, the remaining roasting time of the first stage is extended, the roasting of the roasting target is continued with the roasting parameters of the first stage, and the roasting progress of the second roasting target is waited to exceed the roasting progress corresponding to the advanced node of the first stage. It should be noted that the remaining roasting time of the first stage can be extended to a preset time length. The preset time length is generally the maximum time length allowed for roasting according to the roasting parameters of the first stage after the roasting progress of the first roasting target exceeds the roasting progress corresponding to the advanced node of the first stage. After exceeding the time length, the first roasting target may be over-roasted. Therefore, in order to avoid the problem of over-roasting of the first roasting target, the remaining roasting time of the first stage is extended to the above-mentioned set time length.

[0115] The specific time length of the preset time length can be set by professionals, and the embodiment is not limited. In some embodiments, if the roasting target is tobacco, the preset time length is generally 5-10 hours.

[0116] After the remaining roasting time of the first stage is extended to the above-mentioned set time length, when the detection period comes, the roasting progress of the second roasting target can be detected again whether it exceeds the roasting progress corresponding to the advanced node of the first stage.

[0117] If it is detected that the roasting progress of the second roasting target exceeds the roasting progress corresponding to the advanced node of the first stage, step S303 can be performed to determine that the roasting progress of the first roasting target and the second roasting target both exceeds the roasting progress corresponding to the advanced node of the first stage.

[0118] If it is detected that the roasting progress of the second roasting target does not exceed the roasting progress corresponding to the advanced node of the first stage, since the above-mentioned set time length is the maximum waiting time length of the first roasting target, the remaining roasting time of the first stage cannot be extended again. In this case, step S309 can be performed.

[0119] S309, detecting whether the remaining roasting time of the first stage is zero; if the remaining roasting time of the first stage is zero, step S303 is performed, and if the remaining roasting time of the first stage is not zero, step S310 is performed.

[0120] If it is detected that the roasting progress of the second roasting target does not exceed the roasting progress corresponding to the advanced node of the first stage, it may be because the first stage is completed, the remaining roasting time of the first stage is already zero, and the roasting equipment in the roasting room has already roasted the roasting target according to the roasting parameters of the second stage.

[0121] For example, if the detection period is 2 hours, the remaining baking time of the first stage is extended to a set time length of 3 hours. After 2 hours, the detection period arrives, and it is detected whether the baking progress of the second baking target exceeds the baking progress corresponding to the advancement node of the first stage. If it is detected that the baking progress of the second baking target does not exceed the baking progress corresponding to the advancement node of the first stage, the remaining baking time of the first stage cannot be extended again. After another 2 hours, the detection period arrives, at this time, the first stage is executed completely, the remaining baking time of the first stage is already zero, and the second stage has been executed for 1 hour.

[0122] Therefore, in the embodiments of the present application, when it is detected that the baking progress of the second baking target does not exceed the baking progress corresponding to the advancement node of the first stage, it is further detected whether the remaining baking time of the first stage is zero, to determine whether the baking target is currently baked according to the baking parameters of the second stage.

[0123] After waiting for the above set time length, if the baking progress of the second baking target still does not exceed the baking progress corresponding to the advancement node of the first stage, in order to avoid that the first baking target is baked according to the baking parameters of the first stage for too long to reduce the baking quality of the first baking target, the first baking target cannot continue to wait, but should be allowed to enter the second stage when the remaining baking time of the first stage (i.e. the remaining time length of the set time length) is zero, and the baking target is baked according to the baking parameters of the second stage.

[0124] If it is determined through detection that the remaining baking time of the first stage is zero, it indicates that the baking target is currently baked according to the baking parameters of the second stage, and step S303 can be executed to determine that the baking progress of the first baking target and the baking progress of the second baking target both exceed the baking progress corresponding to the advancement node of the first stage.

[0125] S310, when the detection period arrives, it is detected whether the baking progress of the second baking target exceeds the baking progress corresponding to the advancement node of the first stage. If it is detected that the baking progress of the second baking target exceeds the baking progress corresponding to the advancement node of the first stage, step S303 is executed. If it is detected that the baking progress of the second baking target does not exceed the baking progress corresponding to the advancement node of the first stage, step S308 is executed.

[0126] Specifically, if it is detected that the baking progress of the second baking target does not exceed the baking progress corresponding to the advancement node of the first stage and the remaining baking time of the first stage is not zero, the baking progress of the second baking target can be detected again whether it exceeds the baking progress corresponding to the advancement node of the first stage when the next detection period arrives.

[0127] If it is detected that the roasting progress of the second roasting target exceeds the roasting progress corresponding to the advancement node of the first stage, step S303 can be performed to determine that the roasting progress of the first roasting target and the roasting progress of the second roasting target both exceed the roasting progress corresponding to the advancement node of the first stage.

[0128] If it is detected that the roasting progress of the second roasting target still does not exceed the roasting progress corresponding to the advancement node of the first stage, the above process can be repeatedly performed from step S308 until it is detected that the remaining roasting duration of the first stage is zero or the roasting progress of the second roasting target exceeds the roasting progress corresponding to the advancement node of the first stage.

[0129] In the roasting process of a general roasting target, over-roasting can cause irreversible damage to the roasting target and affect the roasting quality, while under-roasting can meet the roasting requirements in the subsequent temperature rising roasting process or will not cause serious quality impact to the roasting target. Therefore, in the embodiments of the present application, the remaining roasting duration of the first stage is set to be extended to a set duration to avoid over-roasting of the first roasting target with a higher temperature, while ensuring that the second roasting target can be roasted to the maximum extent.

[0130] As an optional implementation, in another embodiment of the present application, the step of detecting whether the roasting progress of the roasting target exceeds the roasting progress corresponding to the advancement node of the first stage in the above embodiment can specifically include the following steps:

[0131] The roasting temperature stage of the roasting target is determined through the image of the roasting target; it is detected whether the roasting progress corresponding to the roasting temperature stage of the roasting target exceeds the roasting progress corresponding to the advancement node of the first stage; and if it is detected that the roasting progress corresponding to the roasting temperature stage of the roasting target exceeds the roasting progress corresponding to the advancement node of the first stage, it is determined that the roasting progress of the roasting target exceeds the roasting progress corresponding to the advancement node of the first stage.

[0132] Specifically, in the embodiments of the present application, the roasting temperature stage of the roasting target can be first determined through the image of the roasting target. Since different roasting stages require different roasting temperatures, the roasting temperature stage is used to represent the roasting stage of the roasting target in the embodiments of the present application. For example, if the roasting target is tobacco leaf, the roasting process of the tobacco leaf can be divided into 10 roasting temperature stages, and the roasting temperature stage corresponds to the actual roasting stage one by one.

[0133] In some embodiments, images of the roasting target as a reference in the roasting process can be obtained in advance, and then the images can be grouped by professionals according to different roasting temperature stages, and image features corresponding to each group of images can be extracted for each group of images. When detecting the roasting temperature stage in which the roasting target is located, an image of the roasting target can be obtained, and features extracted from the image of the roasting target can be taken as image features of the roasting target. Similarities between the image features of the roasting target and the image features corresponding to each group of images can be calculated, and the roasting temperature stage corresponding to the group with the highest similarity to the image features of the roasting target can be determined as the roasting temperature stage of the roasting target in this embodiment. It should be noted that the image of the roasting target can be a photo or a video frame of the roasting target, and the present embodiment does not make any limitation.

[0134] Then it is further determined whether the roasting progress corresponding to the roasting temperature stage of the roasting target exceeds the roasting progress corresponding to the advancement node of the first stage. If it is detected that the roasting progress corresponding to the roasting temperature stage in which the roasting target is located exceeds the roasting progress corresponding to the advancement node of the first stage, it can be determined in this embodiment that the roasting progress of the roasting target exceeds the roasting progress corresponding to the advancement node of the first stage.

[0135] When detecting whether the roasting progress of the first roasting target exceeds the roasting progress corresponding to the advancement node of the first stage, an image of the first roasting target can be obtained, and features extracted from the image can be taken as image features of the first roasting target. Similarities between the image features of the first roasting target and the image features corresponding to each group of images can be calculated, and the roasting temperature stage corresponding to the group with the highest similarity to the image features of the first roasting target can be determined as the roasting temperature stage of the first roasting target. If the roasting progress of the roasting temperature stage of the first roasting target exceeds the roasting progress corresponding to the advancement node of the first stage, it indicates whether the roasting progress of the first roasting target exceeds the roasting progress corresponding to the advancement node of the first stage.

[0136] When detecting whether the roasting progress of the second roasting target exceeds the roasting progress corresponding to the advancement node of the first stage, the calculation manner is the same as that when detecting whether the roasting progress of the first roasting target exceeds the roasting progress corresponding to the advancement node of the first stage, which will not be described herein.

[0137] In the above embodiments, whether the roasting progress of the roasting target exceeds the roasting progress corresponding to the advancement node of the first stage can be automatically determined through the image of the roasting target, which is not affected by the experience and level of the roasting personnel, and the product quality can be ensured.

[0138] As an optional implementation manner, in another embodiment of the present application, the steps of the above embodiments for determining the roasting temperature stage of the roasting target through the image of the roasting target can specifically include the following steps:

[0139] inputting the image of the roasting target into the pre-trained roasting temperature stage recognition model, so that the roasting temperature stage recognition model determines the roasting temperature stage in which the roasting target is located according to the image of the roasting target.

[0140] Specifically, in addition to determining the roasting temperature stage in which the roasting target is located according to the above embodiment, the roasting temperature stage in which the roasting target is located can also be determined by training the roasting temperature stage recognition model. The roasting temperature stage recognition model is used to determine the roasting temperature stage in which the roasting target is located based on the image of the roasting target.

[0141] In some embodiments, training samples for training the roasting temperature stage recognition model can be obtained in a specific curing room. For example, if the roasting target is tobacco leaves, the tobacco leaves can be fixed by a tobacco clamp. The tobacco clamp is generally 132 cm long, 10 cm wide and 2 cm high. The tobacco clamp is used to fix the tobacco leaves by piercing the root of the tobacco leaves. When hanging the tobacco, the space reserved at both ends of the tobacco clamp is placed on the tobacco hanging rack.

[0142] In order to improve the efficiency of curing tobacco, the tobacco leaves are usually hung very densely, and it is difficult to have enough space for shooting. Therefore, a set of smoke blocking supports need to be installed in front of the camera to provide space and distance for the camera shooting. Considering the temperature difference between the upper and lower shelves, the tobacco leaves on the upper shelf can be used as the first roasting target, and the tobacco leaves on the lower shelf can be used as the second roasting target. Cameras are installed on the upper and lower shelves respectively. According to the structure characteristics of the current curing room, the camera and the smoke blocking support can be installed on one side of the heat insulation wall or one side of the door. The camera is arranged between the heat insulation wall and the smoke blocking support.

[0143] The camera can be a wide-angle camera, which can completely shoot the whole tobacco leaf and is conducive to the training of the recognition model. In this embodiment, the camera is installed in the curing room, which avoids the problem of unclear image caused by glass reflection and water mist. The smoke blocking support not only provides a shooting distance for the camera, but also processes the shooting space in a closed manner, which avoids the hot air entering the inside to form a heat release short circuit, and has less influence on the curing. The camera shoots a single color object, which often causes the image to be color-biased due to the lack of white color. In this embodiment, the smoke blocking support is painted white, which not only achieves the effect of blocking the tobacco leaves, but also corrects the white balance.

[0144] The quality of the roasting target directly affects the training effect of the roasting temperature stage recognition model. The quality of the roasting target is affected by the growth potential and the roasting level of the roasting target. Therefore, the image shooting location and the curing room need to be selected under the guidance of a roasting target planting expert and a roasting expert.

[0145] As shown in Figure 4 The training process of the roasting temperature stage recognition model can include:

[0146] Obtaining a complete set of roasting target images. During the roasting process of the roasting target, an image of the roasting target is captured by a camera arranged in the roasting room. The number of images is a key factor affecting the training effect of the roasting temperature stage recognition model, so as much as possible high-quality images should be captured under the condition of allowing.

[0147] Image screening and sorting. After obtaining a large number of roasting target images, the roasting target images need to be screened by a roasting expert first, and images with poor roasting quality or abnormal roasting process are removed, so as to avoid the adverse effect of poor roasting target images on the training model.

[0148] The screened roasting target images are saved in folders according to "region-roasting room-roasting bed times-camera position". One folder is a set of roasting target images, and a set of roasting target images is sorted from early to late according to the shooting time. The purpose of image sorting is to facilitate the roasting expert to classify and label the images according to the roasting stage.

[0149] Image labeling. Taking a group of images as an example, the roasting expert continuously observes the images from the beginning of roasting according to the time sequence, finds out the images that should have the state at the end of each roasting stage, and marks the images. The image is the temperature change critical point. It should be noted that in this embodiment, the image of the actual temperature rising moment of the roasting personnel is not directly marked, in order to avoid the inconsistency between the state stage of the roasting target image and the actual roasting stage, and also to avoid the adverse effect of the inconsistency of the roasting technology and method of the roasting personnel on the training model.

[0150] In addition, it should be noted that if the roasting target is tobacco, the constant temperature time of the first roasting stage of the tobacco is short, and there is no obvious boundary between the images of the tobacco in the first roasting stage and the images of the tobacco in the second roasting stage, so the image at the end of the first roasting stage can not be marked, and the first roasting stage can not be adjusted when adjusting the parameters.

[0151] Roasting temperature stage recognition model training. Specifically, the screened roasting target images can be used as training samples, the roasting temperature stage of each roasting target image can be determined as a training label according to the labeling of the roasting expert, and the roasting temperature stage recognition model can be trained to enable the roasting temperature stage recognition model to predict the roasting temperature stage of the roasting target according to the roasting target image.

[0152] Specifically, the training process is that the training sample is input into the roasting temperature stage identification model to enable the roasting temperature stage identification model to predict the roasting temperature stage where the training sample is located, and obtain a prediction result. By comparing the prediction result and the training label, the loss value of the roasting temperature stage identification model is determined, and the parameters of the roasting temperature stage identification model are adjusted to reduce the loss of the roasting temperature stage identification model as the target. The above training process is repeated until the loss value of the roasting temperature stage identification model is less than a set value, and the roasting temperature stage identification model is trained. The set value can be set according to the actual situation, which is not limited here.

[0153] It should be further pointed out that according to the annotation of the roasting expert, when determining the roasting temperature stage where each roasting target image is located, in order to further clarify the corresponding roasting progress of each roasting target image in the roasting temperature stage where it is located, the roasting target images of each roasting temperature stage can be divided into several roasting progress nodes in the order of shooting time, and the roasting temperature stage of each roasting target image and the roasting progress corresponding to the roasting temperature stage are labeled as training labels. So that the above-mentioned roasting temperature stage identification model can have the ability to identify the roasting temperature stage where the roasting target image is located and the corresponding roasting progress of the roasting temperature stage.

[0154] For example, if the roasting target images in the first roasting stage include 1000, the first roasting stage can be divided into 1000 roasting progress nodes. According to the order of shooting time, the first roasting target image in the first roasting stage can be marked as 1.001, indicating that the image corresponds to the first roasting stage and the roasting progress is 0.001. The 100th roasting target image in the first roasting stage is marked as 1.01, indicating that the image corresponds to the first roasting stage and the roasting progress is 0.01.

[0155] The above-mentioned roasting temperature stage model can use a transformer model as a basic model, and the present embodiment is not limited. In some embodiments, a transformer-based FFVT (File Format Verification Tool) is used as a basic model.

[0156] After the roasting temperature stage model is trained, the roasting target image is input into the roasting temperature stage model, and the roasting temperature stage model can determine the roasting temperature stage where the roasting target is located and the corresponding roasting progress according to the roasting target image.

[0157] In the above embodiments, by training the baking temperature stage model, the baking temperature stage model can be used to quickly and accurately determine the baking temperature stage and the baking progress of the baking target, so as to determine whether the baking progress of the baking target exceeds the baking progress corresponding to the advancement node of the first stage.

[0158] Further, when detecting whether the baking progress of the first baking target exceeds the baking progress corresponding to the advancement node of the first stage, when the detection period arrives, the image of the first baking target is acquired and input into the trained baking temperature stage recognition model, and the temperature baking stage of the first baking target output by the model and the baking progress of the temperature baking stage are obtained. If the baking progress of the baking temperature stage of the first baking target exceeds the baking progress corresponding to the advancement node of the first stage, it indicates whether the baking progress of the first baking target exceeds the baking progress corresponding to the advancement node of the first stage.

[0159] When detecting whether the baking progress of the second baking target exceeds the baking progress corresponding to the advancement node of the first stage, the calculation method is the same as that when detecting whether the baking progress of the first baking target exceeds the baking progress corresponding to the advancement node of the first stage, which will not be repeated here.

[0160] In some embodiments, if the baking target is tobacco leaf, and the maturity of the tobacco leaf is identified by training the maturity recognition model, the training samples for training the baking temperature stage recognition model can be used to train the maturity recognition model.

[0161] Specifically, the screened baking target image can be used as a training sample, and the maturity of the fresh tobacco leaf of the screened baking target image is labeled by a tobacco leaf expert (for example, labeled as under-ripe, mature or over-ripe), and the labeling result is used as a training label to train the maturity recognition model. The specific training process is the same as the training process of the baking temperature stage recognition model, and this embodiment will not be repeated.

[0162] In this way, a set of training samples is used to complete the training of multiple models. The amount of data collected for training samples is reduced, and the training efficiency of the model is improved.

[0163] As an optional implementation manner, as shown in Figure 5 It is disclosed that the baking method of the above embodiments can further include the following steps in another embodiment of the present application.

[0164] S501, determine the baking humidity stage of the baking target through the image of the baking target.

[0165] In the embodiments of the present application, the roasting humidity stage of the roasting target can be determined by roasting the image of the roasting target. For example, the image of the roasting target in the roasting process can be obtained in advance as a reference, and then the images are grouped according to the different roasting humidity stages by professionals, and the image features corresponding to each group of images are extracted. When detecting the roasting humidity stage of the roasting target, the image of the roasting target can be obtained, and the features extracted from the image of the roasting target are used as the image features of the roasting target. The similarity between the image features of the roasting target and the image features corresponding to each group of images is calculated, and the roasting humidity stage corresponding to the group with the highest similarity to the image features of the roasting target is determined as the roasting humidity stage of the roasting target in the embodiments. It should be noted that the image of the roasting target mentioned above can be a photo or a video frame, and the embodiments are not limited.

[0166] In some embodiments, the image of the roasting target can be obtained every time interval corresponding to the set humidity detection period, and the roasting humidity stage of the roasting target can be determined according to the image of the roasting target, so as to further determine whether the roasting humidity in the first-stage roasting parameter needs to be adjusted according to the following steps. The humidity detection period can be the same as or different from the period for detecting the roasting temperature stage in the above embodiments, and the embodiments are not limited.

[0167] S502, detecting whether the difference between the roasting humidity stage of the roasting target and the first stage is greater than a set difference; if it is detected that the difference between the roasting humidity stage of the roasting target and the first stage is greater than the set difference, step S503 is performed; if it is detected that the difference between the roasting humidity stage of the roasting target and the first stage is less than or equal to the set difference, step S504 is performed.

[0168] The difference refers to the closeness between the roasting humidity stage of the roasting target and the first stage. The closer the roasting humidity stage of the roasting target is to the first stage, the smaller the difference is. On the contrary, the less close the roasting humidity stage of the roasting target is to the first stage, the greater the difference is.

[0169] In the embodiments of the present application, after determining the roasting humidity stage of the roasting target, it is detected whether the difference between the roasting humidity stage of the roasting target and the first stage is greater than a set difference.

[0170] If the difference degree between the baking humidity stage where the baking target is located and the first stage is greater than the set difference degree, it indicates that the baking humidity stage where the baking target is located is not close enough to the first stage. The baking humidity stage is determined according to the actual state of the baking target, and the baking humidity stage where the baking target is located is not close enough to the first stage, which means that the actual required baking humidity of the baking target does not match the current actual baking humidity. Step S503 can be performed to adjust the baking humidity in the baking parameters of the first stage.

[0171] If the difference degree between the baking humidity stage where the baking target is located and the first stage is less than or equal to the set difference degree, it indicates that the baking humidity stage where the baking target is located is close enough to the first stage, and the actual required baking humidity of the baking target matches the current actual baking humidity. Step S504 can be performed to continue to bake the baking target according to the baking humidity in the baking parameters of the first stage.

[0172] In some embodiments, the baking humidity stage where the baking target is located can be determined according to the baking humidity stage where the first baking target is located and the baking humidity stage where the second baking target is located.

[0173] Specifically, the baking humidity stage where the first baking target is located and the baking humidity stage where the second baking target is located can be determined according to the description of the above embodiments, and then the mean value of the baking humidity stage where the first baking target is located and the baking humidity stage where the second baking target is located is calculated, and the mean value is determined as the baking humidity stage where the baking target is located. The formula is as follows:

[0174]

[0175] In the above formula, X1 is the baking humidity stage where the first baking target is located, and X2 is the baking humidity stage where the second baking target is located.

[0176] Further, in some embodiments, the actual accurate stage corresponding to the first stage can also be calculated, and the difference degree between the baking humidity stage where the baking target is located and the above actual accurate stage, and the difference degree between the baking humidity stage where the baking target is located and the first stage. The actual accurate stage can reflect the actual baking progress of the first stage. The calculation formula of the actual accurate stage is as follows:

[0177]

[0178] Wherein, N represents the actual baking stage value corresponding to the first stage, for example, if the first stage is the actual fifth baking stage, the value of N is 5; T1 represents the time length of the first stage that has been executed, and T2 represents the total time length of the first stage, that is, the sum of the temperature rising time length and the constant temperature time length corresponding to the first stage.

[0179] If the baking humidity stage of the baking target is greater than the actual accurate stage corresponding to the first stage, and the difference between the baking humidity stage of the baking target and the actual accurate stage corresponding to the first stage is less than or equal to the set difference, or the baking humidity stage of the baking target is less than the actual accurate stage corresponding to the first stage, and the difference between the baking humidity stage of the baking target and the actual accurate stage corresponding to the first stage is less than or equal to the set difference, or the baking humidity stage of the baking target is equal to the actual accurate stage corresponding to the first stage, it is indicated that the difference between the baking humidity stage of the baking target and the first stage is less than the set difference.

[0180] If the baking humidity stage of the baking target is greater than the actual accurate stage corresponding to the first stage, and the difference between the baking humidity stage of the baking target and the actual accurate stage corresponding to the first stage is greater than the set difference, or the baking humidity stage of the baking target is less than the actual accurate stage corresponding to the first stage, and the difference between the baking humidity stage of the baking target and the actual accurate stage corresponding to the first stage is greater than the set difference, it is indicated that the difference between the baking humidity stage of the baking target and the first stage is greater than the set difference.

[0181] The set difference can be set according to actual conditions, and the embodiment is not limited. In a specific embodiment, the set difference is 0.5, and it can be determined that:

[0182] If |a1-a2|≤0.5, it is indicated that the difference between the baking humidity stage of the baking target and the first stage is less than the set difference; if |a1-a2|>0.5, it is indicated that the difference between the baking humidity stage of the baking target and the first stage is greater than the set difference. Wherein a1 is the baking humidity stage of the baking target, and a2 is the actual accurate stage corresponding to the first stage.

[0183] S503, adjusting the baking humidity in the baking parameter of the first stage.

[0184] If it is determined that the difference between the baking humidity stage of the baking target and the first stage is greater than the set difference, the baking humidity in the baking parameter of the first stage needs to be adjusted to match the actual baking humidity required by the baking target with the current actual baking humidity.

[0185] S504, baking the baking target according to the baking humidity in the baking parameter of the first stage.

[0186] If it is determined that the difference between the roasting humidity stage where the roasting target is located and the first stage is less than or equal to the set difference, it indicates that the actual roasting humidity required by the roasting target matches the current actual roasting humidity, and adjustment is not required. The roasting target is roasted according to the roasting humidity in the roasting parameters of the first stage.

[0187] In the above embodiment, the roasting parameters can be automatically adjusted according to the actual roasting humidity required by the roasting target, and the roasting quality is high and is not affected by the experience and level of the roasting personnel.

[0188] As an optional implementation, in another embodiment of the present application, if it is detected that the difference between the roasting humidity stage where the roasting target is located and the first stage is greater than the set difference, and the roasting progress corresponding to the roasting humidity stage where the roasting target is located exceeds the roasting progress of the first stage, the roasting humidity in the roasting parameters of the first stage is adjusted according to the steps of the above embodiment, which can specifically include the following steps: increasing the roasting humidity of the first stage.

[0189] Specifically, if it is detected that the difference between the roasting humidity stage where the roasting target is located and the first stage is greater than the set difference, and the roasting progress corresponding to the roasting humidity stage where the roasting target is located exceeds the roasting progress of the first stage, it indicates that the actual drying speed of the roasting target is too fast, and the roasting humidity of the first stage should be increased. Specifically, the purpose of increasing the roasting humidity of the first stage can be achieved by increasing the wet bulb temperature, so as to ensure the roasting quality of the roasting target.

[0190] For example, if the set difference is 0.5, and a1-a2>0.5, the wet bulb temperature needs to be increased. Wherein, a1 is the roasting humidity stage where the roasting target is located, and a2 is the actual accurate stage corresponding to the first stage.

[0191] As an optional implementation, in another embodiment of the present application, if it is detected that the difference between the roasting humidity stage where the roasting target is located and the first stage is greater than the set difference, and the roasting progress corresponding to the roasting humidity stage where the roasting target is located does not exceed the roasting progress of the first stage, the roasting humidity in the roasting parameters of the first stage is adjusted according to the steps of the above embodiment, which can specifically include the following steps: reducing the roasting humidity of the first stage.

[0192] Specifically, if it is detected that the difference between the roasting humidity stage where the roasting target is located and the first stage is greater than the set difference, and the roasting progress corresponding to the roasting humidity stage where the roasting target is located does not exceed the roasting progress of the first stage, it indicates that the actual drying speed of the roasting target is too slow, and the roasting humidity of the first stage should be reduced. Specifically, the purpose of reducing the roasting humidity of the first stage can be achieved by reducing the wet bulb temperature, so as to ensure the roasting quality of the roasting target.

[0193] For example, if the difference degree is set to 0.5, and a2-a1>0.5, the wet bulb temperature needs to be reduced. Wherein, a1 is the baking humidity stage where the baking target is located, and a2 is the actual accurate stage corresponding to the first stage.

[0194] As an optional implementation, in another embodiment of the present application, the step of determining the baking humidity stage where the baking target is located through the image of the baking target of the above embodiment can specifically include the following steps:

[0195] The image of the baking target is input into a pre-trained baking humidity stage recognition model, so that the baking humidity stage recognition model determines the baking humidity stage where the baking target is located according to the image of the baking target.

[0196] Specifically, in addition to determining the baking humidity stage where the baking target is located according to the above embodiment, the baking humidity stage where the baking target is located can also be determined by training the baking humidity stage recognition model. Wherein, the baking humidity stage recognition model is used to determine the baking humidity stage where the baking target is located based on the image of the baking target.

[0197] The training samples for training the baking humidity stage recognition model can be collected in the same way as the training samples for training the baking temperature stage recognition model in the above embodiment. Alternatively, the training samples for training the baking temperature stage recognition model can be directly used as the training samples for training the baking humidity stage recognition model, and the present embodiment is not limited.

[0198] When performing image annotation, the same method as the division of the temperature stage in the above embodiment can be used, and the baking expert can perform morphological division on the baking target image without considering the baking temperature stage. The baking expert finds out the typical image corresponding to each morphology in each set of baking target image and performs annotation, determines the baking target images in the same morphology as the same baking stage, and defines the baking stage determined in this way as the humidity baking stage.

[0199] When training the baking humidity stage recognition model, the baking humidity stage where each baking target image is located can be determined as a training label according to the annotation of the baking expert, and the baking humidity stage recognition model is trained to enable the baking humidity stage recognition model to predict the baking humidity stage where the baking target is located according to the baking target image. The specific training method of the baking humidity stage recognition model can refer to the training method of the above baking temperature stage recognition model, which is not described here.

[0200] The roasting humidity stage model can adopt a transformer model as a base model, and the embodiments are not limited thereto. In some embodiments, a transformer-based FFVT (File Format Verification Tool) is adopted as a base model.

[0201] After the roasting humidity stage model is trained, the image of the roasting target is input into the roasting humidity stage model, and the roasting humidity stage model can determine the roasting humidity stage of the roasting target and the corresponding roasting progress according to the image of the roasting target.

[0202] In the above embodiments, by training the roasting humidity stage model, the roasting humidity stage of the roasting target can be quickly and accurately determined based on the roasting humidity stage model, so as to determine whether the roasting progress of the roasting target exceeds the roasting progress corresponding to the advancement node of the first stage.

[0203] Further, when detecting the roasting humidity stage of the first roasting target, the image of the first roasting target can be acquired when the detection period arrives and input into the trained roasting humidity stage recognition model to obtain the humidity roasting stage of the first roasting target output by the model.

[0204] When detecting the roasting humidity stage of the second roasting target, the image of the second roasting target can be acquired when the detection period arrives and input into the trained roasting humidity stage recognition model to obtain the humidity roasting stage of the second roasting target output by the model.

[0205] In some embodiments, if the roasting target is tobacco, the roasting process of the tobacco can generally be divided into seven roasting humidity stages, and the roasting process of the tobacco can be divided into ten stages. The seven roasting humidity stages include the leaf softening stage, the main muscle softening stage, the full collapse stage, the hooking and edge curling stage, the branch vein half-drying stage, the branch vein drying stage, and the dry muscle stage. The leaf softening stage is the second roasting stage, the main muscle softening stage is the third roasting stage, the full collapse stage is the fourth roasting stage, the hooking and edge curling stage is the fifth roasting stage, the branch vein half-drying stage is the sixth roasting stage, the branch vein drying stage is the eighth roasting stage, and the dry muscle stage is the tenth roasting stage. In the first, seventh, and ninth roasting stages, the humidity adjustment can not be performed due to the unobvious morphological changes.

[0206] In the above embodiments, by training the roasting humidity stage model, the roasting humidity stage of the roasting target can be quickly and accurately determined based on the roasting humidity stage model, so as to determine whether the actual roasting humidity required by the roasting target matches the current actual roasting humidity.

[0207] In some embodiments, each baking stage includes a temperature rising stage and a constant temperature stage, and no adjustment is needed to the parameters in the temperature rising stage. When entering the constant temperature stage, it is detected whether the baking progress of the baking target exceeds the baking progress corresponding to the progress node of the first stage, and if the baking progress of the baking target exceeds the baking progress corresponding to the progress node of the first stage, the baking target is baked according to the baking parameters of the second stage. In addition, when entering the constant temperature stage, the baking humidity stage of the baking target is determined through the image of the baking target, and it is detected whether the difference between the baking humidity stage of the baking target and the first stage is greater than the set difference, and if the difference between the baking humidity stage of the baking target and the first stage is greater than the set difference, the baking humidity in the baking parameters of the first stage is adjusted.

[0208] In a specific embodiment, the baking target is tobacco leaves, and before the tobacco leaves are baked, an image of the tobacco leaves is acquired, and the maturity of the tobacco leaves is determined based on the maturity recognition model. Then, the growth position of the tobacco leaves is determined by relevant staff. According to the maturity and growth position of the tobacco leaves, a corresponding baking parameter group is selected, so that the tobacco leaves are baked according to the baking parameter group. During the baking of the tobacco leaves according to the baking parameter group, the baking parameters can be adjusted according to the flowchart shown in FIG. 8. Figure 6

[0209] S601, when the detection period comes, read the current baking stage value from the baking controller of the baking house, denoted as N.

[0210] S602, judge whether N is equal to 1.

[0211] S603, if N=1, the tobacco leaves can be baked according to the parameters specified by the baking parameter group, and no adjustment is needed.

[0212] Specifically, if N=1 indicates that the current is in the first baking stage, since the state of the tobacco leaves does not change obviously in the first baking stage, no adjustment is needed to the baking parameters.

[0213] S604, if N≠1, judge whether the current is in the temperature rising stage, if the current is in the temperature rising stage, start from the above step S601, if the current is in the constant temperature stage, execute step S605.

[0214] ​Specifically, if N≠1, it indicates that N is a stage that needs to be adjusted, and since parameter adjustment can only be performed in the constant temperature stage, in this embodiment, it is first detected whether the constant temperature stage is entered. If it is detected that the constant temperature stage is not entered, that is, it is still in the warming-up stage, it can be re-executed from the step S601, that is, when the next detection period comes, the detection is performed again according to the above steps; if it is detected that the constant temperature stage is entered, the step S605 can be executed.

[0215] S605, record the baking temperature stage and the baking humidity stage of the upper tobacco leaves and the lower tobacco leaves.

[0216] Specifically, in the embodiment of the present application, the baking target is baked in the baking mode of three layers of upper, middle and lower layers. Since the baking temperature of the upper tobacco leaves is the highest and the baking temperature of the lower tobacco leaves is the lowest, it can be determined that the upper tobacco leaves are the first baking target and the lower tobacco leaves are the second baking target. The images of the upper tobacco leaves and the lower tobacco leaves are respectively acquired, and the baking temperature stage recognition model and the baking humidity stage recognition model trained in advance are used to recognize the baking temperature stage and the baking humidity stage of the upper tobacco leaves and the lower tobacco leaves.

[0217] It should be noted that the training mode of the baking temperature stage recognition model and the baking humidity stage recognition model can refer to the description of the above embodiment, which will not be repeated here.

[0218] S606, judge whether the baking progress corresponding to the baking temperature stage of the upper tobacco leaves exceeds the baking progress corresponding to the progress node of the stage N; if the baking progress corresponding to the baking temperature stage of the upper tobacco leaves does not exceed the baking progress corresponding to the progress node of the stage N, execute the step S607; if the baking progress corresponding to the baking temperature stage of the upper tobacco leaves exceeds the baking progress corresponding to the progress node of the stage N, execute the step S613.

[0219] Specifically, N-0.1 can be set as the baking progress corresponding to the progress node of the stage N. If the baking progress corresponding to the baking temperature stage of the upper tobacco leaves is greater than N-0.1, it indicates that the baking progress corresponding to the baking temperature stage of the upper tobacco leaves exceeds the baking progress corresponding to the progress node of the stage N. If the baking progress corresponding to the baking temperature stage of the upper tobacco leaves is less than or equal to N-0.1, it indicates that the baking progress corresponding to the baking temperature stage of the upper tobacco leaves does not exceed the baking progress corresponding to the progress node of the stage N.

[0220] S607, judge whether the remaining baking duration of the stage N is greater than the detection period; if the remaining baking duration of the stage N is greater than the detection period, execute the step S609; if the remaining baking duration of the stage N is less than or equal to the detection period, execute the step S608.

[0221] S608, extend the remaining roasting time length of stage N to be greater than the detection period length.

[0222] Specifically, the remaining roasting time length can be extended by 2 hours each time. That is, the remaining roasting time length = the remaining roasting time length + 2, and the result is issued to the roasting controller.

[0223] Then step S609 is performed to adjust the humidity.

[0224] S609, detect whether the difference between the roasting humidity stage where the roasting target is located and stage N is greater than the set difference.

[0225] S610, if it is detected that the difference between the roasting humidity stage where the roasting target is located and stage N is less than or equal to the set difference, no humidity adjustment is needed.

[0226] S611, if it is detected that the difference between the roasting humidity stage where the roasting target is located and stage N is greater than the set difference, and the roasting progress corresponding to the roasting humidity stage where the roasting target is located exceeds the roasting progress of stage N, the wet bulb temperature is increased.

[0227] S612, if it is detected that the difference between the roasting humidity stage where the roasting target is located and stage N is greater than the set difference, and the roasting progress corresponding to the roasting humidity stage where the roasting target is located does not exceed the roasting progress of stage N, the wet bulb temperature is decreased.

[0228] After the humidity adjustment is performed, the above step S601 can be performed again, that is, when the next detection period comes, the above steps are performed again to determine whether the roasting progress corresponding to the roasting temperature stage of the upper layer tobacco leaves exceeds the roasting progress corresponding to the progress node of stage N.

[0229] S613, determine whether the roasting progress corresponding to the roasting temperature stage of the lower layer tobacco leaves exceeds the roasting progress corresponding to the progress node of stage N; if the roasting progress corresponding to the roasting temperature stage of the lower layer tobacco leaves does not exceed the roasting progress corresponding to the progress node of stage N, step S615 is performed; if the roasting progress corresponding to the roasting temperature stage of the lower layer tobacco leaves exceeds the roasting progress corresponding to the progress node of stage N, step S614 is performed.

[0230] S614, the tobacco leaves are roasted according to the roasting parameters of stage N+1, and the above step S601 is performed again.

[0231] Since the tobacco leaves are roasted according to the roasting parameters of N+1 at this node, the temperature parameters and the humidity parameters are adjusted, so it is not necessary to detect whether the difference between the roasting humidity stage where the roasting target is located and stage N is greater than the set difference.

[0232] S615, extending the remaining curing time length of stage N to a preset time length X.

[0233] The value of X is determined by a tobacco curing expert, and can be set to 5-10 hours. The instruction of extending the remaining curing time length of stage N to the preset time length X is sent to the curing controller.

[0234] S616, detecting the difference between the curing humidity stage where the curing target is located and stage N, and determining whether the difference is greater than a set difference.

[0235] S617, if the difference between the curing humidity stage where the curing target is located and stage N is less than or equal to the set difference, no humidity adjustment is needed.

[0236] S618, if the difference between the curing humidity stage where the curing target is located and stage N is greater than the set difference, and the curing progress corresponding to the curing humidity stage where the curing target is located exceeds the curing progress of stage N, the wet bulb temperature is increased.

[0237] S619, if the difference between the curing humidity stage where the curing target is located and stage N is greater than the set difference, and the curing progress corresponding to the curing humidity stage where the curing target is located does not exceed the curing progress of stage N, the wet bulb temperature is decreased.

[0238] S620, when a detection period arrives, determining whether the curing progress corresponding to the curing temperature stage of the lower layer of tobacco leaves exceeds the curing progress corresponding to the progress node of stage N; if the curing progress corresponding to the curing temperature stage of the lower layer of tobacco leaves does not exceed the curing progress corresponding to the progress node of stage N, step S621 is executed; if the curing progress corresponding to the curing temperature stage of the lower layer of tobacco leaves exceeds the curing progress corresponding to the progress node of stage N, step S614 is executed.

[0239] S621, detecting whether the remaining curing time length of stage N is zero; if the remaining curing time length of stage N is zero, step S614 is executed; if the remaining curing time length of stage N is not zero, the execution starts from step S616 again.

[0240] Specifically, when the remaining curing time length of stage N is not zero, the humidity parameter needs to be adjusted again, and then continuous detection is performed when the next detection period arrives, until it is detected that the remaining curing time length of stage N is zero, or the curing progress corresponding to the curing temperature stage of the lower layer of tobacco leaves exceeds the curing progress corresponding to the progress node of stage N.

[0241] Corresponding to the above curing method, an embodiment of the present application also discloses a curing device, as shown in Figure 7 The device comprises:

[0242] The detection module 100 is configured to detect whether the roasting progress of the roasting target exceeds the roasting progress corresponding to the advancement node of the first stage during the roasting of the roasting target according to the roasting parameters of the first stage.

[0243] The adjustment module 110 is configured to roast the roasting target according to the roasting parameters of the second stage if the roasting progress of the roasting target exceeds the roasting progress corresponding to the advancement node of the first stage, the second stage being the next roasting stage of the first stage.

[0244] As an optional implementation, in another embodiment of the present application, the roasting device of the above embodiment can further include:

[0245] The first determination module is configured to determine the growth of the roasting target, and determine the roasting parameters of the first stage and the roasting parameters of the second stage according to the growth of the roasting target.

[0246] As an optional implementation, in another embodiment of the present application, the roasting target of the above embodiment includes a first roasting target and a second roasting target, the roasting temperature of the first roasting target being greater than the roasting temperature of the second roasting target.

[0247] The detection module 100 of the above embodiment is configured to:

[0248] respectively detect whether the roasting progress of the first roasting target and the second roasting target both exceeds the roasting progress corresponding to the advancement node of the first stage, and determine that the roasting progress of the roasting target exceeds the roasting progress corresponding to the advancement node of the first stage if it is detected that the roasting progress of the first roasting target and the second roasting target both exceeds the roasting progress corresponding to the advancement node of the first stage.

[0249] As an optional implementation, in another embodiment of the present application, the detection module 100 of the above embodiment is configured to:

[0250] detect whether the roasting progress of the first roasting target exceeds the roasting progress corresponding to the advancement node of the first stage, and detect whether the roasting progress of the second roasting target exceeds the roasting progress corresponding to the advancement node of the first stage if it is detected that the roasting progress of the first roasting target exceeds the roasting progress corresponding to the advancement node of the first stage, and determine that the roasting progress of the first roasting target and the second roasting target both exceeds the roasting progress corresponding to the advancement node of the first stage if it is detected that the roasting progress of the second roasting target exceeds the roasting progress corresponding to the advancement node of the first stage.

[0251] As an optional implementation, the baking device of the above embodiment can further include, in another embodiment of the present application:

[0252] The delay module is configured to: if it is detected that the baking progress of the first baking target does not exceed the baking progress corresponding to the advancement node of the first stage, detect whether the remaining baking duration of the first stage is greater than a set detection period duration; the detection period is a period for detecting whether the baking progress of the baking target exceeds the baking progress corresponding to the advancement node of the first stage; and if it is detected that the remaining baking duration of the first stage is less than or equal to the detection period duration, the remaining baking duration of the first stage is extended to be greater than the detection period duration.

[0253] As an optional implementation, the baking device of the above embodiment can further include, in another embodiment of the present application:

[0254] The second determination module is configured to: if it is detected that the baking progress of the second baking target does not exceed the baking progress corresponding to the advancement node of the first stage, extend the remaining baking duration of the first stage to a preset duration, and detect, according to a set detection period, whether the baking progress of the second baking target exceeds the baking progress corresponding to the advancement node of the first stage; the detection period is a period for detecting whether the baking progress of the baking target exceeds the baking progress corresponding to the advancement node of the first stage; if it is detected that the baking progress of the second baking target exceeds the baking progress corresponding to the advancement node of the first stage, it is determined that the baking progress of the first baking target and the baking progress of the second baking target both exceed the baking progress corresponding to the advancement node of the first stage; if it is detected that the baking progress of the second baking target does not exceed the baking progress corresponding to the advancement node of the first stage, it is detected whether the remaining baking duration of the first stage is zero; and if the remaining baking duration of the first stage is zero, it is determined that the baking progress of the first baking target and the baking progress of the second baking target both exceed the baking progress corresponding to the advancement node of the first stage.

[0255] As an optional implementation, the detection module 100 of the above embodiment can be specifically configured to, when detecting whether the baking progress of the baking target exceeds the baking progress corresponding to the advancement node of the first stage:

[0256] determine the baking temperature stage of the baking target according to the image of the baking target; detect whether the baking progress corresponding to the baking temperature stage of the baking target exceeds the baking progress corresponding to the advancement node of the first stage; and if it is detected that the baking progress corresponding to the baking temperature stage of the baking target exceeds the baking progress corresponding to the advancement node of the first stage, it is determined that the baking progress of the baking target exceeds the baking progress corresponding to the advancement node of the first stage.

[0257] As an optional implementation, in another embodiment of the present application, the detection module 100 of the above embodiment is specifically used for:

[0258] inputting the image of the roasting target into a pre-trained roasting temperature stage identification model, so that the roasting temperature stage identification model determines the roasting temperature stage in which the roasting target is located according to the image of the roasting target.

[0259] As an optional implementation, in another embodiment of the present application, the roasting device of the above embodiment further comprises:

[0260] an adjustment module configured to determine the roasting humidity stage in which the roasting target is located through the image of the roasting target; detect whether the difference between the roasting humidity stage in which the roasting target is located and the first stage is greater than a set difference; and if it is detected that the difference between the roasting humidity stage in which the roasting target is located and the first stage is greater than the set difference, adjust the roasting humidity in the roasting parameter of the first stage.

[0261] As an optional implementation, in another embodiment of the present application, if it is detected that the difference between the roasting humidity stage in which the roasting target is located and the first stage is greater than the set difference, and the roasting progress corresponding to the roasting humidity stage in which the roasting target is located exceeds the roasting progress of the first stage, the adjustment module of the above embodiment is specifically used for increasing the roasting humidity of the first stage when adjusting the roasting humidity in the roasting parameter of the first stage.

[0262] As an optional implementation, in another embodiment of the present application, if it is detected that the difference between the roasting humidity stage in which the roasting target is located and the first stage is greater than the set difference, and the roasting progress corresponding to the roasting humidity stage in which the roasting target is located does not exceed the roasting progress of the first stage, the adjustment module of the above embodiment is specifically used for decreasing the roasting humidity of the first stage when adjusting the roasting humidity in the roasting parameter of the first stage.

[0263] As an optional implementation, in another embodiment of the present application, the adjustment module of the above embodiment is specifically used for:

[0264] inputting the image of the roasting target into a pre-trained roasting humidity stage identification model, so that the roasting humidity stage identification model determines the roasting humidity stage in which the roasting target is located according to the image of the roasting target.

[0265] Specifically, the specific working content of each unit of the above baking device can be seen from the above method embodiment, which will not be repeated here.

[0266] The application also provides a control device, which comprises a processor and an interface circuit, and the processor in the control device is connected with an input and output component through the interface circuit of the control device.

[0267] The input and output component specifically refers to a hardware component capable of inputting information and outputting information to the user, for example, a microphone, a keyboard, a handwriting board, a touch screen, a display, a sound, a printer and the like.

[0268] The interface circuit can be any interface circuit capable of realizing data communication function, for example, a USB interface circuit, a Type-C interface circuit, a serial port circuit, a PCIE circuit and the like.

[0269] The processor in the control device is a circuit with signal processing capability, which can execute any one of the baking methods introduced in the above embodiments.

[0270] When the control device is applied to a device with human-computer interaction function, the input and output components of the control device can be input and output components on the device, for example, a microphone, a keyboard, a handwriting board, a touch screen, a display, an audio player and the like, and the processor of the control device can be a CPU or a GPU and the like provided by the device, and the interface circuit of the control device can be an interface circuit between the information input component and the CPU or the GPU and the like processor of the device.

[0271] Corresponding to the above baking method, the application also discloses an electronic device, which can be seen from Figure 8 The electronic device comprises:

[0272] a memory 200 and a processor 210;

[0273] The memory 200 is connected with the processor 210 and is used for storing programs;

[0274] The processor 210 is used for realizing the baking method disclosed in any one of the above embodiments by running the programs stored in the memory 200.

[0275] Specifically, the above electronic device can further comprise a bus, a communication interface 220, an input device 230 and an output device 240.

[0276] The processor 210, the memory 200, the communication interface 220, the input device 230 and the output device 240 are connected with each other through the bus.

[0277] The bus can include a path for communicating information among the various components of the computer system.

[0278] The processor 210 can be a general purpose processor, such as a central processing unit (CPU), a microprocessor, or the like, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of programs of the present application. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components.

[0279] The processor 210 can include a main processor, and can also include a baseband chip, a modem, and the like.

[0280] The memory 200 stores programs for executing the technical solutions of the present application, and can also store operating systems and other key services. Specifically, the programs can include program codes, and the program codes include computer operation instructions. More specifically, the memory 200 can include read-only memory (ROM), other types of static storage devices that can store static information and instructions, random access memory (RAM), other types of dynamic storage devices that can store information and instructions, disk storage, flash, and the like.

[0281] The input device 230 can include a device that receives data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor, and the like.

[0282] The output device 240 can include a device that allows information to be output to a user, such as a display screen, a printer, a speaker, and the like.

[0283] The communication interface 220 can include a device using any transceiver, such as an Ethernet, a radio access network (RAN), a wireless local area network (WLAN), and the like, to communicate with other devices or communication networks.

[0284] The processor 210 executes the programs stored in the memory 200, and calls other devices, which can be used to implement the steps of the baking method provided by the above-mentioned embodiments of the present application.

[0285] In addition to the above-mentioned methods and devices, the embodiments of the present application can also be computer program products, which include computer program instructions that make the processor execute the steps of the baking method provided by the above-mentioned embodiments when the processor runs.

[0286] The computer program product can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, 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 computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server.

[0287] Furthermore, embodiments of the present application can also be a computer readable storage medium, having stored thereon computer program instructions which, when executed by a processor, cause the processor to carry out the steps described in the above embodiments of the roasting method.

[0288] The computer readable storage medium can be any combination of one or more computer readable media. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. A 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 above. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable disc, 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 above.

[0289] For each method embodiment described above, in order to simply describe, it is expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the action sequence described, because according to the present application, some steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0290] It should be noted that each of the embodiments in the specification is described in a progressive manner, and each embodiment focuses on the difference from other embodiments, and the same and similar parts between each embodiment can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, it is described more simply, and the relevant parts refer to the part of the method embodiment.

[0291] The steps in the method of each embodiment of the present application can be adjusted in sequence, combined and deleted according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.

[0292] The modules and sub-modules in the apparatus and terminal in the embodiments of the present application can be combined, divided, and deleted according to actual needs.

[0293] In several embodiments provided in the present application, it should be understood that the disclosed terminal, apparatus, and method can be implemented in other ways. For example, the terminal embodiments described above are merely schematic. For example, the division of the modules or sub-modules is merely a logical function division. In actual implementation, another division manner can be used. For example, a plurality of sub-modules or modules can be combined or integrated into another module, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed elements can be indirect coupling or communication connection through some interfaces, devices, or modules, and can be electrical, mechanical, or other forms.

[0294] The modules or sub-modules described as separate components can or can not be physically separated, and the components of the modules or sub-modules can or can not be physical modules or sub-modules, that is, can be located in one place or can be distributed on a plurality of network modules or sub-modules. Some or all of the modules or sub-modules can be selected according to actual needs to achieve the purpose of the embodiments.

[0295] In addition, each functional module or sub-module in each embodiment of the present application can be integrated in one processing module, or each module or sub-module can exist physically, or two or more modules or sub-modules can be integrated in one module. The integrated module or sub-module can be realized in the form of hardware or software functional module or sub-module.

[0296] The skilled person can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present application can be realized in electronic hardware, computer software, or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, each example has been described in the above description in general terms in terms of function. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0297] The steps of a method or algorithm described in connection with the embodiments disclosed herein can be embodied directly in hardware, in a software executed by a processor, or in a combination of the two. A software unit can reside in RAM (random access memory), flash memory, ROM (read-only memory), EPROM (erasable programmable ROM), EEPROM (electrically erasable programmable ROM), registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0298] Finally, it should be noted that the terms "first", "second", and the like, herein do not denote any order, quantity, combination, or importance, but rather are used to distinguish one element from another, and are more especially used for the purpose of identification in claims.

[0299] The foregoing description of the disclosed embodiments enables a person skilled in the art to implement or use the application. Numerous modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other embodiments without departing from the spirit or scope of the application. Therefore, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method of baking, characterized by, Comprise: During the process of roasting the roasting target according to the roasting parameters of the first stage, the roasting humidity stage where the roasting target is located is determined through the image of the roasting target; whether the difference between the roasting humidity stage where the roasting target is located and the first stage is greater than the set difference is detected; If it is detected that the difference between the roasting humidity stage where the roasting target is located and the first stage is greater than the set difference, the roasting humidity in the roasting parameters of the first stage is adjusted to match the actual roasting humidity required by the roasting target with the current actual roasting humidity; Whether the roasting progress where the roasting target is located exceeds the roasting progress corresponding to the advancement node of the first stage is detected; If the roasting progress where the roasting target is located exceeds the roasting progress corresponding to the advancement node of the first stage, the roasting target is roasted according to the roasting parameters of the second stage, which is the next roasting stage of the first stage; Wherein, the roasting target comprises a first roasting target and a second roasting target, the difference between the roasting humidity stage where the roasting target is located and the first stage is obtained by calculating the difference between the roasting humidity stage where the roasting target is located and the actual accurate stage of the first stage, the roasting humidity stage where the roasting target is located is determined by the average of the roasting humidity stage where the first roasting target is located and the roasting humidity stage where the second roasting target is located, the actual accurate stage of the first stage is determined based on the sum of the actual roasting stage value corresponding to the first stage and the length ratio of the current execution of the first stage, and the length ratio of the current execution of the first stage is determined by the ratio of the length of the current execution of the first stage to the total length of the first stage.

2. The method of claim 1, wherein, Also include: Determine the growth of the roasting target; According to the growth of the roasting target, the roasting parameters of the first stage and the roasting parameters of the second stage are determined.

3. The method of claim 1, wherein, The roasting temperature of the first roasting target is greater than the roasting temperature of the second roasting target; The detection of whether the roasting progress where the roasting target is located exceeds the roasting progress corresponding to the advancement node of the first stage comprises: Respectively detecting whether the roasting progress where the first roasting target and the second roasting target are located exceeds the roasting progress corresponding to the advancement node of the first stage; If it is detected that the roasting progress where the first roasting target and the second roasting target are located exceeds the roasting progress corresponding to the advancement node of the first stage, it is determined that the roasting progress where the roasting target is located exceeds the roasting progress corresponding to the advancement node of the first stage.

4. The method of claim 3, wherein, The detection of whether the roasting progress where the first roasting target and the second roasting target are located exceeds the roasting progress corresponding to the advancement node of the first stage comprises: Detecting whether the roasting progress where the first roasting target is located exceeds the roasting progress corresponding to the advancement node of the first stage; If it is detected that the roasting progress of the first roasting target exceeds the roasting progress corresponding to the advanced node of the first stage, it is detected whether the roasting progress of the second roasting target exceeds the roasting progress corresponding to the advanced node of the first stage; If it is detected that the roasting progress of the second roasting target exceeds the roasting progress corresponding to the advanced node of the first stage, it is determined that the roasting progress of the first roasting target and the second roasting target both exceeds the roasting progress corresponding to the advanced node of the first stage; If it is detected that the roasting progress of the first roasting target does not exceed the roasting progress corresponding to the advanced node of the first stage, it is detected whether the remaining roasting duration in the roasting parameters of the first stage is greater than a set detection period duration; the detection period is a period for detecting whether the roasting progress of the roasting target exceeds the roasting progress corresponding to the advanced node of the first stage; If it is detected that the remaining roasting duration of the first stage is less than or equal to the detection period duration, the remaining roasting duration of the first stage is extended to be greater than the detection period duration; If it is detected that the roasting progress of the second roasting target does not exceed the roasting progress corresponding to the advanced node of the first stage, the remaining roasting duration of the first stage is extended to a preset duration, and it is detected, according to a set detection period, whether the roasting progress of the second roasting target exceeds the roasting progress corresponding to the advanced node of the first stage; the detection period is a period for detecting whether the roasting progress of the roasting target exceeds the roasting progress corresponding to the advanced node of the first stage; If it is detected that the roasting progress of the second roasting target exceeds the roasting progress corresponding to the advanced node of the first stage, it is determined that the roasting progress of the first roasting target and the second roasting target both exceeds the roasting progress corresponding to the advanced node of the first stage; If it is detected that the roasting progress of the second roasting target does not exceed the roasting progress corresponding to the advanced node of the first stage, it is detected whether the remaining roasting duration of the first stage is zero; If the remaining roasting duration of the first stage is zero, it is determined that the roasting progress of the first roasting target and the second roasting target both exceeds the roasting progress corresponding to the advanced node of the first stage.

5. The method of claim 1, wherein, The detection of whether the roasting progress of the roasting target exceeds the roasting progress corresponding to the advanced node of the first stage comprises: determining, through an image of the roasting target, a roasting temperature stage in which the roasting target is located; detecting whether the roasting progress corresponding to the roasting temperature stage in which the roasting target is located exceeds the roasting progress corresponding to the advanced node of the first stage; If it is detected that the roasting progress corresponding to the roasting temperature stage in which the roasting target is located exceeds the roasting progress corresponding to the advanced node of the first stage, it is determined that the roasting progress of the roasting target exceeds the roasting progress corresponding to the advanced node of the first stage.

6. The method of claim 1, wherein, If it is detected that the baking humidity stage where the baking target is located is different from the first stage by more than a set difference, and the baking progress corresponding to the baking humidity stage where the baking target is located exceeds the baking progress of the first stage, the baking humidity in the baking parameters of the first stage is adjusted, including: increasing the baking humidity of the first stage; If it is detected that the baking humidity stage where the baking target is located is different from the first stage by more than a set difference, and the baking progress corresponding to the baking humidity stage where the baking target is located does not exceed the baking progress of the first stage, the baking humidity in the baking parameters of the first stage is adjusted, including: decreasing the baking humidity of the first stage.

7. A toasting apparatus characterised in that, Comprising: a detection module, configured to detect whether the baking progress of the baking target exceeds the baking progress corresponding to the advancement node of the first stage during the baking of the baking target according to the baking parameters of the first stage; an adjustment module, configured to determine the baking humidity stage where the baking target is located through the image of the baking target, and detect whether the difference between the baking humidity stage where the baking target is located and the first stage is greater than a set difference; If it is detected that the difference between the baking humidity stage where the baking target is located and the first stage is greater than a set difference, the baking humidity in the baking parameters of the first stage is adjusted to match the actual baking humidity required by the baking target with the current actual baking humidity; an adjustment module, configured to bake the baking target according to the baking parameters of a second stage if the baking progress of the baking target exceeds the baking progress corresponding to the advancement node of the first stage, the second stage being the next baking stage of the first stage; wherein the difference between the baking humidity stage where the baking target is located and the first stage is obtained by calculating the difference between the baking humidity stage where the baking target is located and the actual accurate stage of the first stage, the baking humidity stage where the baking target is located being determined by the average of the baking humidity stage where the first baking target is located and the baking humidity stage where the second baking target is located, the actual accurate stage of the first stage being determined based on the sum of the actual baking stage value corresponding to the first stage and the current execution duration ratio of the first stage, the current execution duration ratio of the first stage being determined by the ratio of the current execution duration of the first stage to the total duration of the first stage.

8. An electronic device, comprising: Comprising: a memory and a processor; wherein the memory is used to store programs; the processor is used to realize the method of any one of claims 1 to 6 by running the programs in the memory.

9. A storage medium, characterized by The storage medium has a computer program stored thereon, and the computer program is executed by a processor to realize the method of any one of claims 1 to 6. The storage medium has a computer program stored thereon, and the computer program is executed by a processor to realize the method of any one of claims 1 to 6.

Images