CN118229963B

CN118229963B - Metal content identification method, device, equipment and medium based on alloy material

Info

Publication number: CN118229963B
Application number: CN202410650849.7A
Authority: CN
Inventors: 周媛; 谭天
Original assignee: Hangzhou Tianyan Zhilian Technology Co ltd
Current assignee: Hangzhou Tianyan Zhilian Technology Co ltd
Priority date: 2024-05-24
Filing date: 2024-05-24
Publication date: 2024-07-30
Anticipated expiration: 2044-05-24
Also published as: CN118229963A

Abstract

The embodiment of the disclosure discloses a metal content identification method, a device, equipment and a medium based on alloy materials. One embodiment of the method comprises the following steps: controlling each camera included in a preset camera group to shoot a target area; the following processing steps are performed: inputting an alloy material image into a pre-trained material labeling model; dividing the marked material image; classifying each segmented material image in the segmented material image group; generating a material occupation ratio group according to the classified material image group set; determining a metal content information group corresponding to each preset metal information according to the obtained material ratio groups; according to the metal content information set, determining a metal predicted value corresponding to each preset metal information; and transporting the alloy materials corresponding to the alloy material image group to a preset material storage position. The embodiment avoids the waste of spectrometer resources and reduces the time for analyzing the alloy materials.

Description

Metal content identification method, device, equipment and medium based on alloy material

Technical Field

The embodiment of the disclosure relates to the technical field of computers, in particular to a metal content identification method, device, equipment and medium based on alloy materials.

Background

The recycled material of the alloy species may be used for recovery. Before recycling, it is necessary to determine the alloy type and metal content of the material, and how to determine the alloy type and metal content of the material is an important research topic. Currently, in determining the type of alloy and the metal content, the following methods are generally adopted: and analyzing the alloy materials by a spectrometer.

However, in practice, it has been found that when the alloy type and metal content are determined in the above manner, there are often the following technical problems:

First, when alloy kind and metal content are confirmed through the spectrum appearance, the value attribute value (cost) of spectrum appearance is higher, and the life of spectrum appearance is lower, leads to the waste of spectrum appearance resource, and need consume longer time and carry out the analysis to alloy class material.

Secondly, before the alloy materials are analyzed through the semantic segmentation model, the trained semantic segmentation model cannot accurately identify the alloy with lower occurrence proportion due to different occurrence proportion of different types of alloys, so that the waste of regenerated material resources is caused.

Thirdly, when the content of a certain alloy in the material is determined, the existence of non-metal materials in the material is not considered, so that the determined alloy content is smaller, and a required transportation vehicle is erroneously determined when the material is transported, so that the waste of transportation resources is caused.

Fourth, in determining the metal content in an alloy, since there may be a difference in the percentage of the same metal content in the same kind of alloy, the metal content is determined only by a fixed percentage of the metal content, resulting in inconsistent determined metal content with actual metal content and waste of regenerated material resources.

The above information disclosed in this background section is only for enhancement of understanding of the background of the inventive concept and, therefore, may contain information that does not form the prior art that is already known to those of ordinary skill in the art in this country.

Disclosure of Invention

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

Some embodiments of the present disclosure propose methods, apparatus, electronic devices, and computer-readable media for identifying metal content based on alloy materials to address one or more of the technical problems mentioned in the background section above.

In a first aspect, some embodiments of the present disclosure provide a method for identifying metal content based on an alloy material, the method comprising: in response to receiving the shooting request information, controlling each camera included in the preset camera group to shoot a target area to obtain an alloy material image group, wherein the target area is an area for placing materials; for each alloy material image in the above alloy material image group, the following processing steps are performed: inputting the alloy material image into a material labeling model trained in advance to obtain a labeled material image; dividing the marked material images to generate a plurality of divided material images, and obtaining a divided material image group; classifying each segmented material image in the segmented material image group to generate a classified material image group set, wherein the classified material image group in the classified material image group set corresponds to material category information; generating a material occupation ratio group according to the classified material image group set; according to the obtained ratio groups of the materials, determining a metal content information group corresponding to each preset metal information to obtain a metal content information group set; determining a metal predicted value corresponding to each preset metal information according to the metal content information set; and transporting the alloy materials corresponding to the alloy material image group to a preset material storage position.

In a second aspect, some embodiments of the present disclosure provide a metal content identification apparatus based on an alloy material, the apparatus comprising: the control unit is configured to respond to receiving shooting request information, and control each camera included in the preset camera group to shoot a target area to obtain an alloy material image group, wherein the target area is an area for placing materials; an execution unit configured to execute, for each alloy material image in the above alloy material image group, the following processing steps: inputting the alloy material image into a material labeling model trained in advance to obtain a labeled material image; dividing the marked material images to generate a plurality of divided material images, and obtaining a divided material image group; classifying each segmented material image in the segmented material image group to generate a classified material image group set, wherein the classified material image group in the classified material image group set corresponds to material category information; generating a material occupation ratio group according to the classified material image group set; the first determining unit is configured to determine a metal content information group corresponding to each preset metal information according to the obtained material ratio groups, so as to obtain a metal content information group set; a second determining unit configured to determine a metal prediction value corresponding to each preset metal information according to the metal content information set; and the transporting unit is configured to transport the alloy materials corresponding to the alloy material image group to a preset material storage position.

In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors causes the one or more processors to implement the method described in any of the implementations of the first aspect above.

In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

The above embodiments of the present disclosure have the following advantages: by the metal content identification method based on the alloy materials, waste of spectrometer resources is avoided, and analysis time of the alloy materials is shortened. Specifically, the spectrometer resource is wasted, and the analysis of the alloy material takes a long time because: when the alloy type and the metal content are determined through the spectrometer, the value attribute value (cost) of the spectrometer is higher, the service life of the spectrometer is lower, the spectrometer resource is wasted, and the alloy materials are required to be analyzed in a longer time. Based on this, according to some embodiments of the present disclosure, the metal content identification method based on the alloy material first controls each camera included in the preset camera group to shoot the target area in response to receiving the shooting request information, so as to obtain an alloy material image group. Thus, the alloy material can be photographed from a plurality of angles. Next, for each alloy material image in the above alloy material image group, the following processing steps are performed: firstly, inputting the alloy material image into a material labeling model trained in advance to obtain a labeled material image. Therefore, the materials in the alloy material image can be marked. Secondly, the marked material images are subjected to segmentation processing to generate a plurality of segmented material images, and a segmented material image group is obtained. Therefore, the marked materials can be divided. Thirdly, classifying each segmented material image in the segmented material image group to generate a classified material image group set. Thus, the material category of the segmented material image can be determined. Fourth, according to the classified material image group set, a material occupation ratio group is generated. From this, the material ratio of each material can be determined. And then, determining a metal content information group corresponding to each piece of preset metal information according to the obtained material ratio groups to obtain a metal content information group set. Thus, the content of the metal in the alloy can be determined. And then, according to the metal content information set, determining a metal predicted value corresponding to each piece of preset metal information. Therefore, the metal content of each metal can be determined, and the alloy type and the metal content are not determined through a spectrometer, but the alloy material is analyzed through a deep learning method, so that the value attribute value (cost) of the analyzed alloy material can be reduced, the waste of spectrometer resources is avoided, and the time for analyzing the alloy material is shortened. And finally, transporting the alloy materials corresponding to the alloy material image group to a preset material storage position. Therefore, analysis of the alloy Jin Wuliao is completed, waste of spectrometer resources is avoided, and analysis time of alloy materials is shortened.

Drawings

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

FIG. 1 is a flow chart of some embodiments of a method of identifying metal content based on an alloy material according to the present disclosure;

FIG. 2 is a schematic view of an alloy material image according to some embodiments of the alloy material-based metal content identification method of the present disclosure;

FIG. 3 is a schematic diagram of annotated material images according to some embodiments of the alloy material-based metal content identification method of the present disclosure;

FIG. 4 is a schematic illustration of a marked material image in accordance with some embodiments of the alloy material-based metal content identification method of the present disclosure;

FIG. 5 is a background portion labeled pictorial intent of some embodiments of alloy material-based metal content identification methods according to the present disclosure;

FIG. 6 is a schematic structural view of some embodiments of an alloy material based metal content identification device according to the present disclosure;

fig. 7 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.

Detailed Description

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

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

It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.

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

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

FIG. 1 illustrates a flow 100 of some embodiments of a method for identifying metal content based on an alloy material according to the present disclosure. The metal content identification method based on the alloy material comprises the following steps:

And step 101, in response to receiving the shooting request information, controlling each camera included in the preset camera group to shoot the target area, and obtaining an alloy material image group.

In some embodiments, an executing body (for example, a server) of the metal content identification method based on the alloy material may control each camera included in the preset camera group to shoot the target area in response to receiving the shooting request information, so as to obtain an alloy material image group. The target area may be an area where the material is placed. The shooting request information may be request information indicating that shooting is performed on the target area. The shooting request information may be request information generated by various methods. For example, the photographing request information may be generated by detecting a change in the weight of the target area. Each camera in the preset camera group is installed around the target area and used for shooting the target area at multiple angles.

As an example, the alloy material image in the above alloy material image group is shown in fig. 2. Wherein fig. 2 shows a plurality of alloy materials and a plurality of non-alloy materials. The alloy material in the plurality of alloy materials is copper alloy. The alloy materials described above may include, but are not limited to: brass, tin bronze, silicon bronze and copper.

Step 102, for each alloy material image in the alloy material image group, performing the following processing steps:

And 1021, inputting the alloy material image into a pre-trained material labeling model to obtain a labeled material image.

In some embodiments, the execution body may input the alloy material image into a pre-trained material labeling model, so as to obtain a labeled material image. The material labeling model can be a classification model taking an alloy material image as input and taking a labeled material image as output. The alloy materials with the same category in the noted material image can be noted with the same color.

As an example, the noted material image may be as shown in fig. 3. Wherein fig. 3 shows a plurality of color-coded materials. Here, the same color materials are of the same kind. For example, the green area shown in fig. 3 identifies tin bronze and the blue area identifies silicon bronze.

Optionally, the material labeling model may be obtained through training:

First, a sample set is obtained.

In some embodiments, the execution body may obtain a sample set. The samples in the sample set comprise sample alloy material images and sample marked material images corresponding to the sample alloy material images.

And a second step of selecting samples from the sample set.

In some embodiments, the execution body may select a sample from the sample set. Here, the execution subject may randomly select a sample from the sample set.

And thirdly, inputting the sample into an initial network model to obtain a labeled material image corresponding to the sample.

In some embodiments, the execution body may input the sample into an initial network model to obtain a labeled material image corresponding to the sample. The initial neural network may be a classification model capable of obtaining a labeled material image according to an alloy material image. The initial neural network may be a semantic segmentation model.

And step four, determining a loss value between the marked material image and a sample marked material image included in the sample.

In some embodiments, the execution body may determine a loss value between the annotated material image and a sample annotated material image included by the sample. In practice, the loss value between the noted annotated material image and the noted sample annotated material image comprised by the noted sample may be determined based on a preset loss function. For example, the predetermined loss function may be a cross entropy loss function.

In some optional implementations of some embodiments, the loss value between the noted annotated material image and the noted sample annotated material image that the sample comprises may be determined by the following loss function:。。。。

Wherein, The number of material categories (material category information) included in the alloy material image is indicated.Representing the real label.The base of the natural logarithm is represented.AndRespectively representing the output of the full connection layer of the initial network model.Representing either a foreground value or a background value.Indicating the rareness of the material category.The constant threshold is represented, and the value is (0, 1).Represent the firstThe number of pixels of each material class.Representing the length of the alloy material image.Representing the width of the alloy material image.

The related content in the fourth step is taken as an invention point of the present disclosure, which solves the second technical problem mentioned in the background art, namely, before the alloy materials are analyzed by the semantic segmentation model, the trained semantic segmentation model cannot accurately identify the alloy with lower occurrence ratio due to different occurrence ratios of different types of alloys, so that the waste of regenerated material resources is caused. The factors that cause the waste of regenerated material resources are often as follows: before the alloy materials are analyzed through the semantic segmentation model, the trained semantic segmentation model cannot accurately identify the alloy with lower occurrence proportion due to different occurrence proportion of different types of alloys, so that the waste of regenerated material resources is caused. If the above factors are solved, the effect of reducing the waste of regenerated material resources can be achieved. To achieve this effect, some embodiments of the present disclosure consider the problem of unbalanced alloy type distribution by improving the loss function of the material labeling model, and by determining the rarity of different alloy types and using the rarity as a part of the loss function, it is possible to avoid that the alloy with a lower occurrence ratio cannot be accurately identified due to unbalanced alloy type distribution, so that the waste of regenerated material resources can be reduced.

And fifthly, adjusting network parameters of the initial network model in response to the loss value being greater than or equal to a preset threshold.

In some embodiments, the executing entity may adjust the network parameters of the initial network model in response to the loss value being greater than or equal to a preset threshold. Here, the setting of the preset threshold is not limited. For example, the loss value and the preset threshold may be differenced to obtain a loss difference. On this basis, the error value is transmitted forward from the last layer of the model by using back propagation, random gradient descent and the like to adjust the parameters of each layer. Of course, a network freezing (dropout) method may be used as needed, and network parameters of some layers therein may be kept unchanged and not adjusted, which is not limited in any way.

Optionally, in response to the loss value being less than the preset threshold, determining the initial network model as a material labeling model.

In some embodiments, the executing entity may determine the initial network model as a material labeling model in response to the loss value being less than the preset threshold.

Step 1022, performing segmentation processing on the marked material images to generate a plurality of segmented material images, thereby obtaining segmented material image groups.

In some embodiments, the executing body may perform segmentation processing on the noted material image to generate a plurality of segmented material images, so as to obtain segmented material images.

In practice, the labeled material image can be subjected to segmentation processing through the following steps:

and firstly, carrying out material contour detection processing on each material displayed by the marked material image so as to mark the material contour of each material and obtain a marked material image. The material contour detection process may be an OpenCV-based target contour detection process.

As an example, the above-described marked material image may be as shown in fig. 4. As can be seen from fig. 4, taking the yellow area as an example, the outline of the yellow area may be marked, so as to obtain a marked material image. Thus, the yellow region can be cut according to the contour of the material. Here, the contour of the material for marking can be freely adjusted in the contour pixel size, for example, the contour pixel can be set to 1, so that the problem of shielding the material due to the large contour pixel can be avoided.

And secondly, dividing the marked material image according to the material outline displayed by the marked material image to generate a divided material image group. The dividing process may be cutting process according to the material profile of each material.

Step 1023, classifying each segmented material image in the segmented material image group to generate a classified material image group set.

In some embodiments, the executing body may perform classification processing on each segmented material image in the segmented material image group to generate a classified material image group set. Wherein, the classified material image group in the classified material image group corresponds to the material category information. The classifying process may be to divide the segmented material images with the same color as the labels into one type to obtain a classified material image group set. The material category information may be used to characterize the category of the material.

As an example, as can be seen from fig. 3, the respective areas of the same color in the drawing can be divided into one type.

Step 1024, generating a material occupation ratio group according to the classified material image group set.

In some embodiments, the executing entity may generate the material occupation ratio set according to the classified material image set.

In practice, the material ratio set may be generated by:

the first step is to divide each classified material image group in the classified material image group into a first material image group set and a second material image group set according to the material category information corresponding to each classified material image group in the classified material image group. Wherein, the material category information corresponding to the first material image group in the first material image group represents alloy materials. And the material category information corresponding to the second material image group in the second material image group represents the non-alloy material.

And secondly, determining the total area value of the alloy material image. The total area value may be determined as a total area value of the alloy material image by multiplying a pixel value included in a width of the alloy material image by a pixel value included in a length of the alloy material image.

As an example, the total area value may be 2073600 (i.e., 1920×1080).

And thirdly, determining a background area value corresponding to the background part of the alloy material image. The background portion may be a portion of the alloy material image from which the classified material image group set is removed.

As an example, the above background portion may be as shown in fig. 5. Wherein the yellow frame selection part is a background part.

And step four, determining the total material area value of each second material image group in the second material image group. In practice, the total material area value of each second material image group in the second material image group set can be determined by the number of pixels covered by each second material image.

As an example, the above-described second physical image group may be shown as a cyan region and a light purple region in fig. 3.

And fifthly, for each first material image group in the first material image group, determining a material occupation ratio corresponding to the first material image group according to the total area value, the background area value and the total material area value. In practice, first, the difference between the total area value, the background area value and the total material area value is determined as an alloy material area value. And secondly, for each first material image group in the first material image group, determining the ratio of the area of each first material image included in the first material image group to the area value of the alloy material as a material ratio.

The related matters in the first step to the fifth step are taken as an invention point of the present disclosure, and the following step 105 is combined, so that the technical problem three mentioned in the background art is solved: when the content of an alloy in a material is determined, the fact that nonmetallic materials exist in the material is not considered, so that the determined content of the alloy is smaller, and when the material is transported, a needed transportation vehicle is erroneously determined, so that transportation resources are wasted. Factors that cause waste of transportation resources are often as follows: when the content of an alloy in a material is determined, the existence of nonmetallic materials in the material is not considered, so that the determined content of the alloy is smaller, and a required transportation vehicle is erroneously determined when the material is transported, so that the waste of transportation resources is caused. If the above factors are solved, the effect of reducing the waste of regenerated material resources can be achieved. To achieve this effect, first, the respective classified material image groups in the classified material image group are divided into a first material image group set and a second material image group set according to material category information corresponding to each classified material image group in the classified material image group. Thus, alloy materials and non-alloy materials can be distinguished. And secondly, determining the total area value of the alloy material image. Thus, the area of the alloy material image can be determined. Thirdly, determining a background area value corresponding to the background part of the alloy material image. Thus, the area of the background portion of the alloy material image can be determined. Fourth, the total material area value of each second material image group in the second material image group is determined. From this, the area value of the non-alloy material can be determined. Fifthly, for each first material image group in the first material image group set, determining a material occupation ratio corresponding to the first material image group according to the total area value, the background area value and the total material area value. Therefore, the ratio of each alloy material to all alloy materials can be determined, and the problem that the determined alloy content is smaller due to the fact that nonmetallic materials exist in the materials are not considered can be avoided. And combining step 105, transporting the alloy materials corresponding to the alloy material image group to a preset material storage position. Thus, waste of transportation resources can be avoided.

And 103, determining a metal content information group corresponding to each piece of preset metal information according to the obtained material ratio groups to obtain a metal content information group set.

In some embodiments, the executing body may determine a metal content information set corresponding to each preset metal information according to the obtained respective material ratio set, to obtain a metal content information set. The preset metal information may be preset metal element information. For example, the preset metal information may be copper, iron, zinc, or the like.

In practice, the metal content information set corresponding to each preset metal information can be determined by the following steps:

First, for each preset metal information in the respective preset metal information, the following determination step is performed:

And a first determining step, determining the type of the classified material image group corresponding to the preset metal information. Wherein, the type can be material category information.

And a second determining step, wherein the classified material image group is used as a first material image group to obtain the metal content ratio information corresponding to the preset metal information. Wherein, the metal content ratio information may include at least one alloy metal content ratio. The alloy metal content ratio may be a content percentage of a metal element corresponding to preset metal information in the alloy. For example, the preset metal information may be copper element, the alloy material is brass, and the alloy metal content ratio may be 85%.

And a third determining step, for each alloy metal content ratio in at least one alloy metal content ratio included in the metal content ratio information, determining each metal content value corresponding to the alloy metal content ratio as the metal content information according to each material occupation ratio corresponding to the preset metal information. In practice, for each alloy metal content ratio of the at least one alloy metal content ratio included in the above metal content ratio information, the product of the above alloy metal content ratio and the corresponding material ratio may be determined as the metal content value.

And a fourth determining step of combining the determined individual metal content information into a metal content information group.

Step 104, determining a metal predicted value corresponding to each preset metal information according to the metal content information set.

In some embodiments, the executing body may determine the metal prediction value corresponding to each preset metal information according to the metal content information set.

In some optional implementations of some embodiments, the metal prediction value corresponding to each preset metal information may be determined by:

The first step, determining the metal codes corresponding to each piece of preset metal information to obtain a metal code set. The metal code may be a code of preset metal information in the periodic table of elements.

Second, for each metal code in the metal code set, executing the following selection steps:

And a first selection step of selecting at least one metal content information corresponding to the metal code from the metal content information set as a target metal content information set. Wherein the number of the target metal content information in the target metal content information set is equal to the number of the metal content information sets included in the metal content information set. In practice, the metal content information corresponding to the above metal codes may be selected from each of the above metal content information sets as target metal content information.

And a second selecting step, determining the sum of the metal content values included in each piece of target metal content information in the target metal content information set to generate a total metal content value, and obtaining a total metal content value group.

And a third selection step, namely determining the average value of all the metal content total values in the metal content total value group as the metal predicted value corresponding to the metal code.

Optionally, before step 104, the following steps may be further included:

First, for each piece of preset metal information in the respective pieces of preset metal information, the following fitting step is performed:

and a first fitting step, namely acquiring a training data set corresponding to the preset metal information.

In some embodiments, the executing body may acquire a training data set corresponding to the preset metal information. The training data in the training data set comprises at least one material category information and at least one material metal content value corresponding to the at least one material category information.

As an example, the training data set described above may be [ brass: 40, tin bronze 20, copper content 50], [ tin bronze 50, copper 30, copper content 72], [ brass 80, copper 10, copper content 73].

And a second fitting step, wherein the material category information included in each training data in the training data set is combined to generate a combined material category information group.

In some embodiments, the executing body may combine the material category information included in the training data set to generate a combined material category information set.

And a third fitting step, performing de-duplication processing on each piece of combined material category information included in the combined material category information group so as to generate a de-duplicated material category information group.

In some embodiments, the executing entity may perform a deduplication process on each of the consolidated material category information included in the consolidated material category information set to generate a deduplicated material category information set.

And a fourth fitting step, namely generating a metal content fitting formula according to the de-duplicated material category information group.

In some embodiments, the executing body may generate a metal content fitting formula according to the de-duplicated material class information set. Wherein, each parameter in the metal content fitting formula corresponds to a weight parameter. And each parameter is a material occupation ratio corresponding to the de-duplicated material category information in the de-duplicated material category information group.

By way of example, the above described de-duplicated material class information sets may include tin bronze, copper, brass. The above metal content fitting formula may be: α×tin bronze+β×brass+γ×copper=n. Wherein α, β and γ are three weight parameters, respectively. N is copper metal content.

And a fifth fitting step, selecting a preset number of training data from the training data set as a training set, and determining the rest training data as a test set.

In some embodiments, the executing body may select a predetermined number of training data from the training data set as a training set, and determine remaining training data as a test set. In practice, a preset number of training data may be selected from the training data set in a random selection manner to be used as a training set. The preset number may be a preset number of selected training data.

And a sixth fitting step, training the metal content fitting formula according to the training set and the testing set to determine weight values corresponding to the weight parameters corresponding to the metal content fitting formula.

In some embodiments, the execution body may perform training processing on the metal content fitting formula according to the training set and the test set, so as to determine weight values corresponding to the weight parameters corresponding to the metal content fitting formula. The training process may be a solution process for the metal content fitting formula.

As an example, in response to the three training data exemplified by the first fitting step being a training set, α×20+β×30=50, α×50+γ×30=72, β×80+γ×10=73 are generated. Thus, the superpositioning can be solved to determine α=0.9, β=0.8, γ=0.9.

Optionally, the determining, according to the metal content information set, a metal predicted value corresponding to each preset metal information set further includes:

For each piece of preset metal information in the preset metal information, selecting a metal content fitting formula corresponding to the preset metal information from trained metal content fitting formulas to serve as a target fitting formula, and inputting the material occupation ratio corresponding to the preset metal information into the target fitting formula to obtain a metal prediction value.

The first fitting step-the sixth fitting step and the related matters in the optional steps are taken as an invention point of the present disclosure, and the fourth technical problem mentioned in the background art is solved, in determining the metal content in the alloy, since the same metal content percentage in the same kind of alloy may be different, determining the metal content only by the fixed metal content percentage results in that the determined metal content is inconsistent with the actual metal content, resulting in waste of renewable material resources. The factors that cause the waste of regenerated material resources are often as follows: when determining the metal content in an alloy, since the same metal content percentage in the same kind of alloy may be different, the metal content is determined only by a fixed metal content percentage, resulting in inconsistent determined metal content and actual metal content and waste of regenerated material resources. If the above factors are solved, the effect of reducing the waste of regenerated material resources can be achieved. To achieve this effect, first, a training data set corresponding to the above-mentioned preset metal information is acquired. Thus, the training data set in advance can be obtained. Secondly, combining the material category information included in each training data in the training data set to generate a combined material category information group; and carrying out de-duplication treatment on each piece of combined material category information included in the combined material category information group so as to generate a de-duplicated material category information group. Thus, all alloy types corresponding to the preset metal information can be determined. Thirdly, generating a metal content fitting formula according to the de-duplicated material category information group. Thus, a fitting formula corresponding to the preset metal information can be generated. Selecting a preset number of training data from the training data set as a training set, and determining the rest training data as a test set; and training the metal content fitting formula according to the training set and the testing set to determine weight values corresponding to all weight parameters corresponding to the metal content fitting formula. Thus, the respective weight parameters of the fitting formula can be solved by the training data. Fourth, for each preset metal information in each preset metal information, selecting a metal content fitting formula corresponding to the preset metal information from the trained metal content fitting formulas as a target fitting formula, and inputting the material occupation ratio corresponding to the preset metal information into the target fitting formula to obtain a metal predicted value. Thus, the metal prediction value can be determined by a solved formula. And when different alloy material image groups are analyzed, different fitting formulas are solved, so that the condition that the determined metal content is inconsistent with the actual metal content due to the difference of the metal content percentages in the same alloy is avoided, and further the waste of regenerated material resources is avoided.

And 105, transporting the alloy materials corresponding to the alloy material image group to a preset material storage position.

In some embodiments, the executing body may transport the alloy material corresponding to the alloy material image set to a preset material storage location.

With further reference to fig. 6, as an implementation of the method shown in the above figures, the present disclosure provides some embodiments of an alloy material-based metal content recognition device, which correspond to those method embodiments shown in fig. 1, and which may be applied in particular in various electronic devices.

As shown in fig. 6, the alloy material-based metal content recognition apparatus 600 of some embodiments includes: a control unit 601, an execution unit 602, a first determination unit 603, a second determination unit 604, and a transportation unit 605. The control unit 601 is configured to control each camera included in the preset camera group to shoot a target area in response to receiving shooting request information, so as to obtain an alloy material image group, wherein the target area is an area for placing materials; the execution unit 602 is configured to execute, for each alloy material image of the set of alloy material images, the following processing steps: inputting the alloy material image into a material labeling model trained in advance to obtain a labeled material image; dividing the marked material images to generate a plurality of divided material images, and obtaining a divided material image group; classifying each segmented material image in the segmented material image group to generate a classified material image group set, wherein the classified material image group in the classified material image group set corresponds to material category information; generating a material occupation ratio group according to the classified material image group set; the first determining unit 603 is configured to determine a metal content information set corresponding to each preset metal information according to the obtained material ratio sets, so as to obtain a metal content information set; the second determining unit 604 is configured to determine a metal prediction value corresponding to each preset metal information according to the metal content information set; the transporting unit 605 is configured to transport the alloy material corresponding to the above-described alloy material image group to a preset material storage location.

It will be appreciated that the elements described in the alloy material based metal content identification apparatus 600 correspond to the various steps in the method described with reference to fig. 1. Thus, the operations, features and advantages described above with respect to the method are equally applicable to the alloy material-based metal content identification apparatus 600 and the units contained therein, and are not described herein.

Referring now to fig. 7, a schematic diagram of an electronic device 700 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic devices in some embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), car terminals (e.g., car navigation terminals), and the like, as well as stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 7 is only one example and should not impose any limitations on the functionality and scope of use of embodiments of the present disclosure.

As shown in fig. 3, the electronic device 700 may include a processing means 701 (e.g., a central processor, a graphics processor, etc.) that may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 702 or a program loaded from a storage means 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data necessary for the operation of the electronic apparatus 300 are also stored. The processing device 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input/output (I/O) interface 305 is also connected to bus 704.

In general, the following devices may be connected to the I/O interface 705: input devices 706 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, and the like; an output device 707 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 708 including, for example, magnetic tape, hard disk, etc.; and a communication device 709. The communication means 709 may allow the electronic device 700 to communicate wirelessly or by wire with other devices to exchange data. While fig. 7 shows an electronic device 700 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead. Each block shown in fig. 7 may represent one device or a plurality of devices as needed.

In particular, according to some embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via communications device 709, or from storage 708, or from ROM 702. The above-described functions defined in the methods of some embodiments of the present disclosure are performed when the computer program is executed by the processing means 701.

It should be noted that, the computer readable medium described in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, the computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: and in response to receiving the shooting request information, controlling each camera included in the preset camera group to shoot a target area to obtain an alloy material image group, wherein the target area is an area for placing materials. For each alloy material image in the above alloy material image group, the following processing steps are performed: inputting the alloy material image into a material labeling model trained in advance to obtain a labeled material image; dividing the marked material images to generate a plurality of divided material images, and obtaining a divided material image group; classifying each segmented material image in the segmented material image group to generate a classified material image group set, wherein the classified material image group in the classified material image group set corresponds to material category information; generating a material occupation ratio group according to the classified material image group set; and determining a metal content information group corresponding to each piece of preset metal information according to the obtained material ratio groups to obtain a metal content information group set. And determining a metal predicted value corresponding to each piece of preset metal information according to the metal content information set. And transporting the alloy materials corresponding to the alloy material image group to a preset material storage position.

Computer program code for carrying out operations for some embodiments of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

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

The units described in some embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. The described units may also be provided in a processor, for example, described as: a processor includes a control unit, an execution unit, a first determination unit, a second determination unit, and a transport unit. The names of the units do not limit the units themselves in some cases, for example, the control unit may also be described as "a unit that controls each camera included in the above-mentioned preset camera group to shoot the target area in response to receiving shooting request information, so as to obtain an alloy material image group".

The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.

The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above technical features, but encompasses other technical features formed by any combination of the above technical features or their equivalents without departing from the spirit of the invention. Such as the above-described features, are mutually substituted with (but not limited to) the features having similar functions disclosed in the embodiments of the present disclosure.

Claims

1. The metal content identification method based on the alloy material is applied to a preset camera group, wherein the preset camera group comprises a plurality of cameras, and the method comprises the following steps:

In response to receiving the shooting request information, controlling each camera included in the preset camera group to shoot a target area to obtain an alloy material image group, wherein the target area is an area for placing materials;

For each alloy material image in the set of alloy material images, performing the following processing steps:

Inputting the alloy material image into a pre-trained material labeling model to obtain a labeled material image;

Dividing the marked material images to generate a plurality of divided material images, and obtaining a divided material image group;

classifying each segmented material image in the segmented material image group to generate a classified material image group set, wherein the classified material image group in the classified material image group set corresponds to material category information;

generating a material occupation ratio group according to the classified material image group set;

According to the obtained ratio groups of the materials, determining a metal content information group corresponding to each preset metal information to obtain a metal content information group set;

according to the metal content information set, determining a metal predicted value corresponding to each piece of preset metal information;

transporting the alloy materials corresponding to the alloy material image group to a preset material storage position;

wherein, according to the classified material image group set, generating a material occupation ratio group includes:

Dividing each classified material image group in the classified material image group into a first material image group set and a second material image group set according to material category information corresponding to each classified material image group in the classified material image group;

Determining the total area value of the alloy material image;

determining a background area value corresponding to a background part of the alloy material image;

determining the total material area value of each second material image group in the second material image group;

And for each first material image group in the first material image group, determining a material occupation ratio corresponding to the first material image group according to the total area value, the background area value and the material area total value.

2. The method of claim 1, wherein the segmenting the annotated material image to generate a plurality of segmented material images, resulting in a segmented material image set, comprises:

Carrying out material contour detection processing on each material displayed by the marked material image so as to mark the material contour of each material and obtain a marked material image;

and dividing the marked material image according to the material outline displayed by the marked material image to generate a divided material image group.

3. The method of claim 1, wherein the determining the metal content information set corresponding to each preset metal information according to the obtained respective material ratio sets, to obtain the metal content information set, includes:

for each of the respective preset metal information, the following determination step is performed:

determining the type of the classified material image group corresponding to the preset metal information;

Responding to the classified material image group as a first material image group, and acquiring metal content ratio information corresponding to the preset metal information, wherein the metal content ratio information comprises at least one alloy metal content ratio;

For each alloy metal content ratio in at least one alloy metal content ratio included in the metal content ratio information, determining each metal content value corresponding to the alloy metal content ratio as metal content information according to each material occupation ratio corresponding to the preset metal information;

The determined individual metal content information is combined into a metal content information set.

4. The method of claim 1, wherein the determining, according to the set of metal content information sets, a metal prediction value corresponding to each preset metal information includes:

Determining a metal code corresponding to each piece of preset metal information to obtain a metal code set;

For each metal code in the metal code set, performing the following selection steps:

Selecting at least one piece of metal content information corresponding to the metal code from a metal content information group set as a target metal content information set, wherein the number of target metal content information in the target metal content information set is equal to the number of metal content information groups included in the metal content information group set;

Determining the sum of the metal content values included in each piece of target metal content information in the target metal content information set to generate a metal content total value, and obtaining a metal content total value group;

And determining the average value of all the metal content total values in the metal content total value group as a metal predicted value corresponding to the metal code.

5. The method of claim 1, wherein the material labeling model is trained by:

Acquiring a sample set, wherein a sample in the sample set comprises a sample alloy material image and a sample marked material image corresponding to the sample alloy material image;

selecting a sample from the set of samples;

Inputting the sample into an initial network model to obtain a labeled material image corresponding to the sample;

determining a loss value between the marked material image corresponding to the sample and the sample marked material image included in the sample;

And adjusting network parameters of the initial network model in response to the loss value being greater than or equal to a preset threshold.

6. The method of claim 5, wherein the method further comprises:

And determining the initial network model as a material labeling model in response to the loss value being smaller than the preset threshold.

7. A metal content identification device based on alloy materials, comprising:

The control unit is configured to respond to receiving shooting request information, and control each camera included in the preset camera group to shoot a target area to obtain an alloy material image group, wherein the target area is an area for placing materials;

An execution unit configured to execute, for each alloy material image in the set of alloy material images, the following processing steps: inputting the alloy material image into a pre-trained material labeling model to obtain a labeled material image; dividing the marked material images to generate a plurality of divided material images, and obtaining a divided material image group; classifying each segmented material image in the segmented material image group to generate a classified material image group set, wherein the classified material image group in the classified material image group set corresponds to material category information; generating a material occupation ratio group according to the classified material image group set; the execution unit is further configured to:

Determining the total area value of the alloy material image;

For each first material image group in the first material image group, determining a material occupation ratio corresponding to the first material image group according to the total area value, the background area value and the material area total value;

The first determining unit is configured to determine a metal content information group corresponding to each preset metal information according to the obtained material ratio groups, so as to obtain a metal content information group set;

A second determining unit configured to determine a metal prediction value corresponding to each preset metal information according to the metal content information set;

And the transporting unit is configured to transport the alloy materials corresponding to the alloy material image group to a preset material storage position.

8. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon;

When executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1 to 6.

9. A computer readable medium having stored thereon a computer program, wherein the program when executed by a processor implements the method of any of claims 1 to 6.