Precious metal identification method, assembly, equipment, medium and data acquisition device

Abstract

The invention provides a precious metal identification method and assembly, electronic equipment, a computer readable storage medium and a data acquisition device. The method and the assembly can be used in the technical field of precious metal identification and finance. The precious metal identification method is used for a data processing device of the precious metal detection system, the precious metal detection system further comprises a data acquisition device, the data acquisition device is used for acquiring an X-ray image of a precious metal article, and the method comprises the step of identifying the precious metal article according to the X-ray image of the precious metal article acquired from the data acquisition device and a pre-trained material identification model. Determining a material result of the precious metal article; determining the atomic number of the noble metal article according to the thickness of the noble metal article, the energy value of the high-energy ray and the energy value of the low-energy ray of the noble metal article acquired from the data acquisition device, and a pre-constructed atomic number database; and according to the material result and the atomic number, according to a preset identification standard, identifying that the corresponding precious metal is genuine or fake.

Description

Technical Field

[0001] The present disclosure relates to the field of precious metal identification and financial technology, and more specifically, to a precious metal identification method, component, electronic device, computer-readable storage medium, computer program product, and data acquisition device. Background Art

[0002] The agency purchase of physical gold products (i.e. repurchase business) refers to the business behavior of banks acting as agents for third-party physical gold product purchase companies to purchase physical gold products owned by customers and included in the bank's repurchase scope. It supports two modes: self-operated repurchase and agency repurchase. Although banks are important platforms for recycling gold, they do not have professional personnel, lack experience in testing, have limited equipment use, and have many loopholes in gold repurchase services.

[0003] At present, the repurchase detection methods commonly used by banks include the water hanging detection method and the fire melting detection method. Among them, the "water hanging detection method (abbreviated as water hanging method) refers to the detection method of immersing the test sample in a container filled with water and combining the mass value measured by an electronic balance or the displayed density value, and comparing the mass value or density value to identify the authenticity. This detection method requires that the product must be in good condition, without obvious defects, no traces of repair on the surface, and complete surface elements (including brand logo, gram weight and color, etc.), and the weight is consistent with the gram weight marked on the surface. For gold bars with intact surfaces that are suitable for water hanging detection, the internal structure of gold cannot be seen. If someone deliberately mixes metals with a specific gravity and density similar to gold, such as "iridium" or "palladium", the bank cannot find it. Once it is recycled, if it is not recycled, it will be directly transferred back to the market for trading, which will damage the interests of customers and seriously affect the reputation of the bank; the detection method for gold bars with intact appearance is cumbersome and complicated, and there are manual errors, which affect the accuracy of the results.

[0004] The fire fusion test method is a method of testing that uses a melting furnace to melt the sample to be tested, and then uses a spectrometer to detect its composition after solidification. The fire fusion test method is a destructive form of testing. Summary of the invention

[0005] In view of this, the present disclosure provides a precious metal identification method, component, electronic device, computer-readable storage medium, computer program product and data acquisition device that can ensure the integrity of precious metal products, has a high degree of intelligence, is simple to operate and has high result accuracy.

[0006] One aspect of the present disclosure provides a method for identifying precious metals, which is a data processing device for a precious metal detection system. The precious metal detection system also includes a data acquisition device, which is used to acquire X-ray images of precious metal items. The data processing device is communicatively connected to the data acquisition device. The method includes: determining a material result of the precious metal item based on the X-ray image of the precious metal item acquired from the data acquisition device and a pre-trained material recognition model, wherein the material result is one of hollow-with dopants, hollow-without dopants, solid-with dopants, and solid-without dopants; determining the atomic number of the precious metal item based on the thickness of the precious metal item, the energy value of the high-energy ray and the energy value of the low-energy ray of the precious metal item acquired from the data acquisition device, and a pre-constructed atomic number database; and identifying the corresponding precious metal as authentic or counterfeit according to a pre-set identification standard based on the material result and the atomic number.

[0007] In some embodiments, the step of determining the atomic number of the precious metal object based on the thickness of the precious metal object, the energy value of the high-energy ray and the energy value of the low-energy ray of the precious metal object obtained from the data acquisition device, and a pre-constructed atomic number database includes: calculating the ratio between the energy value of the high-energy ray and the energy value of the low-energy ray of the precious metal object obtained from the data acquisition device as a matching value; and matching the thickness of the precious metal object and the matching value with the mapping relationship between the thickness of the precious metal, the ratio of the energy value of the high-energy ray of the precious metal to the energy value of the low-energy ray, and the atomic number of the precious metal in the pre-constructed atomic number database to obtain the atomic number corresponding to the thickness of the precious metal object and the matching value.

[0008] In some embodiments, the step of pre-training a material recognition model includes: obtaining an initial training sample set, wherein the initial training sample set includes m training sample X-ray images of precious metal objects annotated with material results, and m is an integer greater than or equal to 1; adjusting initial model parameters set in a neural network model according to the initial training sample set to obtain training model parameters; and applying the training model parameters as model parameters of the material recognition model.

[0009] In some embodiments, before the step of applying the training model parameters as the model parameters of the material identification model, the step of pre-training the material identification model also includes: obtaining a verification sample set, wherein the verification sample set includes k verification sample X-ray images of precious metal objects marked with material results, and k is an integer greater than or equal to 1; verifying the training model parameters based on the verification sample set; if the verification passes, applying the training model parameters as the model parameters of the material identification model; and if the verification fails, repeating the step of obtaining the initial training sample set until the verification passes.

[0010] In some embodiments, the step of pre-constructing an atomic number database includes: measuring the energy values ​​of high-energy rays and low-energy rays of authentic precious metals of n kinds of thickness respectively, wherein n is an integer greater than or equal to 1; storing the mapping relationship between the thickness of the authentic precious metal, the ratio of the energy value of the high-energy ray to the energy value of the low-energy ray of the authentic precious metal, and the obtained atomic number of the authentic precious metal in the atomic number database; measuring the energy values ​​of high-energy rays and low-energy rays of counterfeit precious metals when each thickness of counterfeit precious metals of n kinds of thicknesses is doped with g kinds of impurities respectively, wherein g is an integer greater than or equal to 1; and storing the mapping relationship between the thickness of the counterfeit precious metal, the ratio of the energy value of the high-energy ray to the energy value of the low-energy ray of the counterfeit precious metal, the proportion of the counterfeit precious metal doped with impurities, and the calculated atomic number of the counterfeit precious metal in the atomic number database.

[0011] Another aspect of the present disclosure provides a precious metal identification component, which is a data processing device for a precious metal detection system. The precious metal detection system also includes a data acquisition device, which is used to collect X-ray images of precious metal items. The component includes: a first determination module, which is used to determine the material result of the precious metal item based on the X-ray image of the precious metal item obtained from the data acquisition device and a pre-trained material recognition model, wherein the material result is one of hollow-with dopants, hollow-without dopants, solid-with dopants and solid-without dopants; a second determination module, which is used to determine the atomic number of the precious metal item based on the thickness of the precious metal item, the energy value of the high-energy ray and the energy value of the low-energy ray of the precious metal item obtained from the data acquisition device, and a pre-constructed atomic number database; and an identification module, which is used to identify the corresponding precious metal as authentic or counterfeit according to the material result and the atomic number and a pre-set identification standard.

[0012] In some examples, the material result of the precious metal item can be determined by using an X-ray image of the precious metal item obtained from a data acquisition device and a pre-trained material recognition model, and the atomic number of the precious metal item can be determined by using the energy value of the high-energy ray and the energy value of the low-energy ray of the precious metal item obtained from the data acquisition device and a pre-constructed atomic number database. According to the material result and the atomic number, the corresponding precious metal can be identified as authentic or counterfeit according to the pre-set identification standard. The precious metal identification method disclosed in the present invention enables banks to detect whether precious metals are authentic or counterfeit without destroying the precious metal products when recycling precious metals, which can ensure the integrity of the precious metal products and does not affect secondary sales. Moreover, the internal structure of precious metals can be seen through X-ray images, and the determination of atomic number can facilitate the determination of whether precious metal products are mixed with impurities. Through comprehensive judgment based on material results and atomic number, it is possible to more accurately identify whether precious metals are genuine or counterfeit. The precious metal products identified by the present disclosure are then returned to the market for trading, which can protect customer interests and the bank's reputation. In addition, the precious metal identification method disclosed in the present disclosure is highly intelligent and easy to operate, so that ordinary bank staff can be competent for recycling business without the need to assign professional identification experts to perform recycling business work, thereby alleviating the bank's personnel pressure.

[0013] Another aspect of the present disclosure provides an electronic device, comprising one or more processors and one or more memories, wherein the memories are used to store executable instructions, and when the executable instructions are executed by the processors, the above-mentioned method is implemented.

[0014] Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the above method when executed.

[0015] Another aspect of the present disclosure provides a computer program product, comprising a computer program, wherein the computer program comprises computer executable instructions, and the instructions are used to implement the method as described above when executed.

[0016] Another aspect of the present disclosure provides a data acquisition device, which is used to acquire X-ray images of precious metal objects, and includes: a box body, the box body having a accommodating cavity, the accommodating cavity having an entrance and an exit; an X-ray machine, the X-ray machine is disposed in the accommodating cavity and is configured to generate X-ray rays; an acquisition detector, the acquisition detector is disposed in the accommodating cavity, and is used to receive X-ray rays emitted by the X-ray machine to generate X-ray images of precious metal objects; a conveyor belt, the conveyor belt is passed through the box body, and is used to send precious metal objects into the box body for detection, and send out the box body after the detection is completed; and a measurement module, the measurement module is disposed in the accommodating cavity, and is used to measure the energy value of high-energy rays and the energy value of low-energy rays of the precious metal objects, and calculate the ratio of the measured energy value of the high-energy rays to the energy value of the low-energy rays as a matching value, wherein the second determination module matches the atomic number database through the matching value to obtain the corresponding atomic number.

[0017] In some embodiments, according to the data acquisition device disclosed in the present invention, through the box, X-ray machine, acquisition detector, conveyor belt and measurement module, it is easy to obtain the X-ray image of the precious metal object, and it is easy to obtain the energy value of the high-energy ray and the energy value of the low-energy ray of the precious metal object.

[0018] In some embodiments, the data acquisition device further includes a warning light, which is disposed on the box and is communicatively connected to the X-ray machine. When the X-ray machine is working, the warning light is on. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0020] Figure 1 Schematically illustrates an exemplary system architecture to which methods and components according to embodiments of the present disclosure may be applied;

[0021] Figure 2 A flow chart of a method for distinguishing precious metals according to an embodiment of the present disclosure is schematically shown;

[0022] Figure 3 A flowchart schematically illustrates the steps of pre-training a material recognition model according to an embodiment of the present disclosure;

[0023] Figure 4 A flowchart schematically illustrates the steps of pre-training a material recognition model according to an embodiment of the present disclosure;

[0024] Figure 5 A flowchart schematically shows the steps of pre-building an atomic number database according to an embodiment of the present disclosure;

[0025] Figure 6 The structure block diagram of the precious metal identification component according to the embodiment of the present disclosure is schematically shown;

[0026] Figure 7 A block diagram of an electronic device according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0027] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0028] In the technical solution of the present disclosure, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0029] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0030] When using expressions such as "at least one of A, B or C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B or C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.). The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, features defined as "first" and "second" may explicitly or implicitly include one or more of the said features.

[0031] The agency purchase of physical gold products (i.e. repurchase business) refers to the business behavior of banks acting as agents for third-party physical gold product purchase companies to purchase physical gold products owned by customers and included in the bank's repurchase scope. It supports two modes: self-operated repurchase and agency repurchase. Although banks are important platforms for recycling gold, they do not have professional personnel, lack experience in testing, have limited equipment use, and have many loopholes in gold repurchase services.

[0032] At present, the repurchase detection methods commonly used by banks include the water hanging detection method and the fire melting detection method. Among them, the "water hanging detection method (abbreviated as water hanging method) refers to the detection method of immersing the test sample in a container filled with water and combining the mass value measured by an electronic balance or the displayed density value, and comparing the mass value or density value to identify the authenticity. This detection method requires that the product must be in good condition, without obvious defects, no traces of repair on the surface, and complete surface elements (including brand logo, gram weight and color, etc.), and the weight is consistent with the gram weight marked on the surface. For gold bars with intact surfaces that are suitable for water hanging detection, the internal structure of gold cannot be seen. If someone deliberately mixes metals with a specific gravity and density similar to gold, such as "iridium" or "palladium", the bank cannot find it. Once it is recycled, if it is not recycled, it will be directly transferred back to the market for trading, which will damage the interests of customers and seriously affect the reputation of the bank; the detection method for gold bars with intact appearance is cumbersome and complicated, and there are manual errors, which affect the accuracy of the results.

[0033] The fire fusion test method is a method of testing that uses a melting furnace to melt the sample to be tested, and then uses a spectrometer to detect its composition after solidification. The fire fusion test method is a destructive form of testing.

[0034] Embodiments of the present disclosure provide a precious metal identification method, component, electronic device, computer-readable storage medium, computer program product, and data acquisition device. The precious metal identification method is used in a data processing device of a precious metal detection system. The precious metal detection system also includes a data acquisition device, which is used to collect X-ray images of precious metal items. The precious metal identification method includes: determining the material result of the precious metal item according to the X-ray image of the precious metal item obtained from the data acquisition device and a pre-trained material recognition model, wherein the material result is one of hollow-with dopants, hollow-without dopants, solid-with dopants, and solid-without dopants; determining the atomic number of the precious metal item according to the thickness of the precious metal item, the energy value of the high-energy ray and the energy value of the low-energy ray of the precious metal item obtained from the data acquisition device, and a pre-constructed atomic number database; and identifying the corresponding precious metal as a genuine or counterfeit according to the material result and the atomic number and the pre-set identification standard.

[0035] It should be noted that the precious metal identification method, components, electronic device, computer-readable storage medium, computer program product and data acquisition device disclosed in the present invention can be used in the field of precious metal identification, and can also be used in any field other than the field of precious metal identification, such as the financial field. The field of the present invention is not limited here.

[0036] Figure 1 The exemplary system architecture 100 to which the precious metal identification method, components, electronic device, computer-readable storage medium and computer program product according to the embodiments of the present disclosure can be applied is schematically shown. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0037] like Figure 1 As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0038] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).

[0039] The terminal devices 101 , 102 , and 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0040] The server 105 may be a server that provides various services, such as a background management server (only an example) that provides support for websites browsed by users using the terminal devices 101, 102, and 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0041] It should be noted that the precious metal identification method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the precious metal identification component provided in the embodiment of the present disclosure can generally be set in the server 105. The precious metal identification method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the precious metal identification component provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0042] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0043] The following will be based on Figure 1 The scene described by Figure 2 to Figure 5 The precious metal identification method of the embodiment of the present disclosure is described in detail.

[0044] Figure 2 The flowchart of the precious metal identification method according to the embodiment of the present disclosure is schematically shown. The precious metal identification method is used in a data processing device of a precious metal detection system, the precious metal detection system also includes a data acquisition device, the data acquisition device is used to collect X-ray images of precious metal objects, and the data processing device is communicatively connected to the data acquisition device.

[0045] like Figure 2 As shown, the precious metal identification method of this embodiment includes operations S210 to S230.

[0046] In operation S210, the material result of the precious metal object is determined based on the X-ray image of the precious metal object obtained from the data acquisition device and the pre-trained material recognition model, wherein the material result is one of hollow-with impurities, hollow-without impurities, solid-with impurities and solid-without impurities.

[0047] In operation S220, the atomic number of the precious metal object is determined according to the thickness of the precious metal object, the energy value of the high-energy ray and the energy value of the low-energy ray of the precious metal object acquired from the data acquisition device, and the pre-constructed atomic number database.

[0048] As a possible implementation method, operation S220 includes a step of determining the atomic number of the precious metal object based on the thickness of the precious metal object, the energy value of the high-energy ray and the energy value of the low-energy ray of the precious metal object obtained from the data acquisition device, and a pre-constructed atomic number database, and includes operation S221 and operation S222.

[0049] In operation S221, a ratio between an energy value of a high-energy ray and an energy value of a low-energy ray of the precious metal object acquired from the data acquisition device is calculated as a matching value.

[0050] In operation S222, the thickness of the precious metal object and the matching value are matched with the mapping relationship between the thickness of the precious metal in a pre-constructed atomic number database, the ratio of the energy value of the high-energy ray of the precious metal to the energy value of the low-energy ray, and the atomic number of the precious metal to obtain the atomic number corresponding to the thickness of the precious metal object and the matching value.

[0051] It is understandable that the atomic number database includes the mapping relationship between the thickness of the genuine precious metal, the ratio of the energy value of the high-energy ray of the genuine precious metal to the energy value of the low-energy ray, and the atomic number of the genuine precious metal, and the mapping relationship between the thickness of the counterfeit precious metal, the ratio of the energy value of the high-energy ray of the counterfeit precious metal to the energy value of the low-energy ray, the proportion of impurities doped in the counterfeit precious metal, and the atomic number of the counterfeit precious metal. When the data acquisition device irradiates the precious metal object with X-rays, the energy value of the high-energy ray and the energy value of the low-energy ray of the precious metal object can be measured, thereby obtaining the ratio of the energy value of the high-energy ray of the precious metal object to the energy value of the low-energy ray as a matching value, and the atomic number of the precious metal object can be determined based on the matching value and the pre-constructed atomic number database.

[0052] Operations S221 and S222 can facilitate the determination of the atomic number of the precious metal object based on the thickness of the precious metal object, the energy value of the high-energy ray and the energy value of the low-energy ray of the precious metal object obtained from the data acquisition device, and a pre-constructed atomic number database.

[0053] In operation S230, the corresponding precious metal is identified as authentic or counterfeit according to the material result and the atomic number and a preset identification standard.

[0054] In some examples, when the material result is hollow-with dopants and the atomic number is the atomic number of the authentic precious metal, the corresponding precious metal product is identified as a fake; when the material result is hollow-with dopants and the atomic number is the atomic number of the fake precious metal, the corresponding precious metal product is identified as a fake.

[0055] In some examples, when the material result is hollow-no dopants and the atomic number is the atomic number of the authentic precious metal, the corresponding precious metal product is identified as authentic; when the material result is hollow-no dopants and the atomic number is the atomic number of the counterfeit precious metal, the corresponding precious metal product is identified as a counterfeit.

[0056] In some examples, when the material result is solid-with dopants and the atomic number is the atomic number of the authentic precious metal, the corresponding precious metal product is identified as a counterfeit; when the material result is solid-with dopants and the atomic number is the atomic number of the counterfeit precious metal, the corresponding precious metal product is identified as a counterfeit.

[0057] In some examples, when the material result is solid-no dopants and the atomic number is the atomic number of the authentic precious metal, the corresponding precious metal product is identified as authentic; when the material result is solid-no dopants and the atomic number is the atomic number of the counterfeit precious metal, the corresponding precious metal product is identified as a counterfeit.

[0058] According to the precious metal identification method of the embodiment of the present disclosure, the material result of the precious metal item can be determined by the X-ray image of the precious metal item obtained from the data acquisition device and the pre-trained material recognition model, and the atomic number of the precious metal item can be determined by the energy value of the high-energy ray and the energy value of the low-energy ray obtained from the data acquisition device, and the pre-constructed atomic number database. According to the material result and the atomic number, according to the pre-set identification standard, the corresponding precious metal can be identified as authentic or counterfeit. The precious metal identification method disclosed in the present disclosure enables banks to detect whether precious metals are authentic or counterfeit without destroying the precious metal products when recycling precious metals, which can ensure the integrity of the precious metal products and does not affect secondary sales. Moreover, the internal structure of precious metals can be seen through X-ray images, and the determination of atomic number can facilitate the determination of whether precious metal products are mixed with impurities. Through comprehensive judgment based on material results and atomic number, it is possible to more accurately identify whether precious metals are genuine or counterfeit. The precious metal products identified by the present disclosure are then returned to the market for trading, which can protect customer interests and the bank's reputation. In addition, the precious metal identification method disclosed in the present disclosure is highly intelligent and easy to operate, so that ordinary bank staff can be competent for recycling business without the need to assign professional identification experts to perform recycling business work, thereby alleviating the bank's personnel pressure.

[0059] Figure 3 The flowchart schematically shows the steps of pre-training a material recognition model according to an embodiment of the present disclosure.

[0060] like Figure 3 As shown, the step of pre-training the material recognition model in this embodiment includes operation S310, operation S320 and operation S350.

[0061] In operation S310, an initial training sample set is obtained, wherein the initial training sample set includes m training sample X-ray images of precious metal objects annotated with material results, where m is an integer greater than or equal to 1.

[0062] In operation S320, initial model parameters set in the neural network model are adjusted according to the initial training sample set to obtain training model parameters.

[0063] In operation S350, the training model parameters are applied as model parameters of the material recognition model.

[0064] The pre-training of the material recognition model may be facilitated through operations S310 , S320 , and S350 .

[0065] Figure 4 The flowchart schematically shows the steps of pre-training a material recognition model according to an embodiment of the present disclosure.

[0066] like Figure 4 As shown, the step of pre-training the material recognition model in this embodiment includes operations S310 to S360.

[0067] In operation S310, an initial training sample set is obtained, wherein the initial training sample set includes m training sample X-ray images of precious metal objects annotated with material results, where m is an integer greater than or equal to 1.

[0068] In operation S320, initial model parameters set in the neural network model are adjusted according to the initial training sample set to obtain training model parameters.

[0069] In operation S330, a verification sample set is obtained, wherein the verification sample set includes k verification sample X-ray images of precious metal objects annotated with material results, where k is an integer greater than or equal to 1.

[0070] In operation S340, the training model parameters are verified based on the verification sample set.

[0071] In operation S350 , if the verification is successful, the training model parameters are applied as model parameters of the material recognition model.

[0072] In operation S360, if the verification fails, the initial training sample set is repeatedly obtained until the verification passes.

[0073] In some examples, a predicted value can be obtained by verifying the material recognition model with a verification sample set, and an actual value can be obtained based on the labeled material results of the verification sample set. A loss function is used to calculate the loss value between the predicted value and the actual value. If the loss value meets the set model threshold, the verification is considered to have passed, and the trained model parameters are used as the model parameters of the material recognition model. If the loss value does not meet the set model threshold, the verification is considered to have failed, and operations S310 to S340 are repeated until the verification passes.

[0074] In some examples, applying the verified training model parameters can make the model parameters of the material recognition model more accurate, thereby making the recognition ability of the material recognition model better and the determined material result more accurate. The pre-training of the material recognition model can be facilitated through operations S310 to S360.

[0075] Figure 5 The flowchart schematically shows the steps of pre-building an atomic number database according to an embodiment of the present disclosure.

[0076] like Figure 5 As shown, the step of pre-building an atomic number database in this embodiment includes operations S410 to S440.

[0077] In operation S410, energy values ​​of high-energy rays and energy values ​​of low-energy rays of authentic precious metals of n thicknesses are measured respectively, where n is an integer greater than or equal to 1.

[0078] In operation S420, a mapping relationship between the thickness of the authentic precious metal, the ratio of the energy value of the high-energy ray to the energy value of the low-energy ray of the authentic precious metal, and the obtained atomic number of the authentic precious metal is stored in the atomic number database.

[0079] In operation S430, when each of n thicknesses of counterfeit noble metals is doped with g proportions of impurities, energy values ​​of high-energy rays and low-energy rays of the counterfeit noble metal are measured respectively, where g is an integer greater than or equal to 1.

[0080] In operation S440, a mapping relationship between the thickness of the counterfeit noble metal, the ratio of the energy value of the high-energy ray to the energy value of the low-energy ray of the counterfeit noble metal, the proportion of impurities doped in the counterfeit noble metal, and the calculated atomic number of the counterfeit noble metal is stored in the atomic number database.

[0081] Operations S410 to S440 may facilitate the pre-construction of an atomic number database.

[0082] Based on the above precious metal identification method, the present disclosure also provides a precious metal identification component. Figure 6 The precious metal identification component is described in detail.

[0083] Figure 6 The structural block diagram of the precious metal identification component according to an embodiment of the present disclosure is schematically shown.

[0084] The precious metal identification component 10 is used as a data processing device of the precious metal detection system. The precious metal detection system also includes a data acquisition device, which is used to collect X-ray images of precious metal objects. The precious metal identification component 10 includes a first determination module 1, a second determination module 2 and an identification module 3.

[0085] The first determination module 1 is used to perform operation S210: determine the material result of the precious metal object according to the X-ray image of the precious metal object obtained from the data acquisition device and the pre-trained material recognition model, wherein the material result is one of hollow-with impurities, hollow-without impurities, solid-with impurities and solid-without impurities.

[0086] The second determination module 2 is used to perform operation S220: determine the atomic number of the precious metal object according to the thickness of the precious metal object, the energy value of the high-energy ray and the energy value of the low-energy ray of the precious metal object obtained from the data acquisition device, and the pre-constructed atomic number database.

[0087] Identification module 3, identification module 3 is used to perform operation S230: according to the material result and the atomic number, according to the preset identification standard, identify the corresponding precious metal as a genuine product or a fake.

[0088] According to the precious metal identification device 10 of the embodiment of the present disclosure, the material result of the precious metal item can be determined through the X-ray image of the precious metal item obtained from the data acquisition device and the pre-trained material recognition model, and the atomic number of the precious metal item can be determined through the energy value of the high-energy ray and the energy value of the low-energy ray of the precious metal item obtained from the data acquisition device, and the pre-constructed atomic number database. According to the material result and the atomic number, according to the pre-set identification standard, the corresponding precious metal can be identified as authentic or counterfeit. The precious metal identification method disclosed in the present disclosure enables banks to detect whether precious metals are authentic or counterfeit without destroying the precious metal products when recycling precious metals, which can ensure the integrity of the precious metal products and does not affect secondary sales. Moreover, the internal structure of precious metals can be seen through X-ray images, and the determination of atomic number can facilitate the determination of whether precious metal products are mixed with impurities. Through comprehensive judgment based on material results and atomic number, it is possible to more accurately identify whether precious metals are genuine or counterfeit. The precious metal products identified by the present disclosure are then returned to the market for trading, which can protect customer interests and the bank's reputation. In addition, the precious metal identification method disclosed in the present disclosure is highly intelligent and easy to operate, so that ordinary bank staff can be competent for recycling business without the need to assign professional identification experts to perform recycling business work, thereby alleviating the bank's personnel pressure.

[0089] In addition, according to an embodiment of the present disclosure, any multiple modules among the first determination module 1, the second determination module 2 and the identification module 3 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module.

[0090] According to an embodiment of the present disclosure, at least one of the first determination module 1, the second determination module 2 and the identification module 3 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or can be implemented in any one of the three implementation methods of software, hardware and firmware, or in an appropriate combination of any of them.

[0091] Alternatively, at least one of the first determination module 1, the second determination module 2 and the identification module 3 may be at least partially implemented as a computer program module, and when the computer program module is executed, the corresponding function may be executed.

[0092] In some embodiments of the present disclosure, the present disclosure further provides a data acquisition device for acquiring X-ray images of precious metal objects, comprising a box, an X-ray machine, a collection detector, a conveyor belt and a measurement module.

[0093] Specifically, the box has a accommodating cavity, which has an entrance and an exit; an X-ray machine is arranged in the accommodating cavity and is configured to generate X-rays; a collection detector is arranged in the accommodating cavity, which is used to receive the X-rays emitted by the X-ray machine and generate X-ray images of precious metal objects; a conveyor belt is passed through the box, which is used to send the precious metal objects into the box for detection and send them out of the box after the detection is completed; a measurement module is arranged in the accommodating cavity, which is used to measure the energy values ​​of high-energy rays and low-energy rays of the precious metal objects, and calculate the ratio of the measured energy values ​​of the high-energy rays and the energy values ​​of the low-energy rays as a matching value, wherein the second determination module obtains the corresponding atomic number by matching the matching value in the atomic number database.

[0094] According to the data acquisition device disclosed in the present invention, through the box, X-ray machine, acquisition detector, conveyor belt and measurement module, it is convenient to obtain the X-ray image of the precious metal object, and it is convenient to obtain the energy value of the high-energy ray and the energy value of the low-energy ray of the precious metal object.

[0095] According to some embodiments of the present disclosure, the data acquisition device may further include a warning light, which is arranged on the box body and is connected to the X-ray machine. When the X-ray machine is working, the warning light is on, thereby notifying outsiders that there are radiation and they should stay away from it, thereby protecting the safety of the personnel.

[0096] Figure 7 A block diagram of an electronic device suitable for implementing the above method according to an embodiment of the present disclosure is schematically shown.

[0097] like Figure 7 As shown, the electronic device 900 according to an embodiment of the present disclosure includes a processor 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage part 908 into a random access memory (RAM) 903. The processor 901 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 901 may also include an onboard memory for caching purposes. The processor 901 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0098] In RAM 903, various programs and data required for the operation of electronic device 900 are stored. Processor 901, ROM 902 and RAM 903 are connected to each other via bus 904. Processor 901 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 902 and / or RAM 903. It should be noted that the program can also be stored in one or more memories other than ROM 902 and RAM 903. Processor 901 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0099] According to an embodiment of the present disclosure, the electronic device 900 may further include an input / output (I / O) interface 905, which is also connected to the bus 904. The electronic device 900 may further include one or more of the following components connected to the I / O interface 905: an input portion 906 including a keyboard, a mouse, etc.; an output portion 907 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 908 including a hard disk, etc.; and a communication portion 909 including a network interface card such as a LAN card, a modem, etc. The communication portion 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the input / output (I / O) interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed, so that a computer program read therefrom is installed into the storage portion 908 as needed.

[0100] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0101] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus, or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 902 and / or RAM 903 described above and / or one or more memories other than ROM 902 and RAM 903.

[0102] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the method of the embodiment of the present disclosure.

[0103] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 901. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0104] In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium, and downloaded and installed through the communication part 909, and / or installed from a removable medium 911. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0105] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 909, and / or installed from the removable medium 911. When the computer program is executed by the processor 901, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0106] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0107] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0108] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0109] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A precious metal identification method, used in a data processing device of a precious metal detection system, wherein the precious metal detection system further comprises a data acquisition device, wherein the data acquisition device is used to acquire X-ray images of precious metal objects, and the data processing device is communicatively connected to the data acquisition device, characterized in that: The method comprises: Determine the material result of the precious metal object according to the X-ray image of the precious metal object obtained from the data acquisition device and the pre-trained material recognition model, wherein the material result is one of hollow-with dopant, hollow-without dopant, solid-with dopant and solid-without dopant; Determine the atomic number of the precious metal object according to the thickness of the precious metal object, the energy value of the high-energy ray and the energy value of the low-energy ray of the precious metal object obtained from the data acquisition device, and a pre-constructed atomic number database; and According to the material result and the atomic number, the corresponding precious metal is identified as genuine or counterfeit according to a pre-set identification standard.

2. The method for identifying precious metals according to claim 1, characterized in that: The step of determining the atomic number of the precious metal object according to the thickness of the precious metal object, the energy value of the high-energy ray and the energy value of the low-energy ray of the precious metal object obtained from the data acquisition device, and the pre-constructed atomic number database includes: calculating a ratio between an energy value of a high-energy ray and an energy value of a low-energy ray of the precious metal object acquired from the data acquisition device as a matching value; and The thickness of the precious metal object and the matching value are matched with the mapping relationship between the thickness of the precious metal in a pre-constructed atomic number database, the ratio of the energy value of the high-energy ray of the precious metal to the energy value of the low-energy ray, and the atomic number of the precious metal to obtain the atomic number corresponding to the thickness of the precious metal object and the matching value.

3. The method for distinguishing precious metals according to claim 1, characterized in that: The steps to pre-train the material recognition model include: Acquire an initial training sample set, wherein the initial training sample set includes m training sample X-ray images of precious metal objects annotated with material results, where m is an integer greater than or equal to 1; Adjusting initial model parameters set in the neural network model according to the initial training sample set to obtain training model parameters; and The training model parameters are applied as model parameters of the material recognition model.

4. The method for distinguishing precious metals according to claim 3, characterized in that: Before the step of applying the training model parameters as the model parameters of the material recognition model, the step of pre-training the material recognition model further includes: Acquire a verification sample set, wherein the verification sample set includes k verification sample X-ray images of precious metal objects annotated with material results, where k is an integer greater than or equal to 1; Verifying the training model parameters according to the verification sample set; If the verification is successful, the training model parameters are applied as model parameters of the material recognition model; and If the verification fails, repeat the process to obtain the initial training sample set until the verification passes.

5. The method for distinguishing precious metals according to claim 1, characterized in that: The steps to pre-build the atomic number database include: Respectively measure the energy values ​​of high-energy rays and low-energy rays of authentic precious metals of n thicknesses, wherein n is an integer greater than or equal to 1; storing a mapping relationship between the thickness of the authentic precious metal, the ratio of the energy value of the high-energy ray to the energy value of the low-energy ray of the authentic precious metal, and the obtained atomic number of the authentic precious metal in an atomic number database; Respectively measuring the energy values ​​of the high-energy rays and the low-energy rays of the counterfeit precious metal when each thickness of the counterfeit precious metal in n thicknesses is doped with impurities in g proportions, wherein g is an integer greater than or equal to 1; and The mapping relationship between the thickness of the counterfeit noble metal, the ratio of the energy value of the high-energy ray of the counterfeit noble metal to the energy value of the low-energy ray, the proportion of impurities doped in the counterfeit noble metal and the calculated atomic number of the counterfeit noble metal is stored in the atomic number database.

6. A precious metal identification component, a data processing device for a precious metal detection system, the precious metal detection system also includes a data acquisition device, the data acquisition device is used to collect X-ray images of precious metal objects, characterized in that: The components include: A first determination module, the first determination module is used to determine the material result of the precious metal object according to the X-ray image of the precious metal object obtained from the data acquisition device and a pre-trained material recognition model, wherein the material result is one of hollow-with dopant, hollow-without dopant, solid-with dopant and solid-without dopant; a second determination module, the second determination module being configured to determine the atomic number of the precious metal object according to the thickness of the precious metal object, the energy value of the high-energy ray and the energy value of the low-energy ray of the precious metal object acquired from the data acquisition device, and a pre-constructed atomic number database; and The identification module is used to identify whether the corresponding precious metal is genuine or counterfeit according to the material result and the atomic number and a preset identification standard.

7. An electronic device, characterized in that: include: one or more processors; One or more memories, used to store executable instructions, wherein when the executable instructions are executed by the processor, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: The storage medium stores executable instructions, which implement the method according to any one of claims 1 to 5 when executed by the processor.

9. A data acquisition device, characterized in that: The data acquisition device is a data acquisition device according to claim 1, comprising: A box body, wherein the box body has a containing cavity, and the containing cavity has an inlet and an outlet; An X-ray machine, which is disposed in the accommodating cavity and is configured to generate X-rays; A collection detector, which is arranged in the accommodating cavity and is used to receive the X-rays emitted by the X-ray machine and generate an X-ray image of the precious metal object; A conveyor belt, which passes through the box and is used to send precious metal objects into the box for testing and send them out of the box after the testing is completed; and A measuring module is arranged in the accommodating cavity, and is used to measure the energy value of the high-energy ray and the energy value of the low-energy ray of the precious metal object, and calculate the ratio of the measured energy value of the high-energy ray to the energy value of the low-energy ray as a matching value, wherein the second determination module matches the atomic number database through the matching value to obtain the corresponding atomic number.

10. The data acquisition device according to claim 9, characterized in that: Also includes: A warning light is arranged on the box body and is communicatively connected with the X-ray machine. When the X-ray machine is working, the warning light is on.

Images