Devices, methods, and computer program product for object tracing

Abstract

Embodiments of the present disclosure provide a registration device, a retrieval device, a cloud device, a respective method, and a computer-readable storage medium for object tracing. The registration device may include: a visual work module configured to: capture an image of a first object to be traced; control a work module configured to: generate an identification code for representing the first object based on an image of the first object; send the identification code of the first object and the serial number of the first object, in a manner corresponding to each other, to a cloud device for storage by the cloud device.

Description

[0001] Devices, Methods, and Computer Program Product for Object Tracing

[0002] Technical Field

[0003] The present disclosure relates to the industrial field, in particular, to registration devices for object tracing, retrieval devices, cloud devices, corresponding methods, and computer program products.

[0004] Background Art

[0005] With the rapid development of Internet technology, the industrial manufacturing process has become more digital, networked, and intelligent, for example, the proposed Industrial 4.0 strategy aims to connect the virtual and physical worlds through cyberphysical system (CPS). Product traceability is an important aspect of modern industrial manufacturing that provides a digital connection between the material flow and the associated information flow. Through product traceability, the product or its physical parts can be traced at various processing stages, thereby facilitating quality control, processing decisions and optimization of the product or its physical parts. Thus, how to optimize traceability is one of the issues that needs to be addressed.

[0006] Summary of Invention

[0007] In view of the need for prior art improvements, examples of the present disclosure provide for registration devices, retrieval devices, cloud devices, respective methods, and computer-readable storage media for object tracing.

[0008] In an aspect, examples of the present disclosure provide for a registration device for object tracing, comprising: a visual work module configured to: capture an image of a first object to be traced; control a work module configured to: generating an identification code for representing the first object based on an image of the first object; sending the identification code of the first object and the serial number of the first object to a cloud device in a manner corresponding to each other for storage by the cloud device.

[0009] In another aspect, examples of the present disclosure provide a retrieval device for object tracing, comprising: a visual work module configured to: capture an image of a second object to be traced; control a work module configured to: generate an identification code for representing the second object based on an image of the second object; send an identification code for the second object to a cloud device so that the cloud device outputs a serial number corresponding to the identification code of the second object as a serial number of the second object.

[0010] In another aspect, an example of the present disclosure provides a cloud device for object tracing, comprising: a cloud database configured to: store serial numbers and identification numbers corresponding to one another; a storage module configured to: receive, from a registration device, an identification code and a serial number of a first object and store the identification code and a serial number of the first object in a manner corresponding to one another to the cloud database; a retrieval module configured to: receive, from a retrieval device, an identification code of a second object, retrieve from the cloud database a serial number corresponding to the identification code of the second object as a serial number of the second object based on the identification code of the second object, and output a serial number of the second object.

[0011] In another aspect, examples of the present disclosure provide a system for object tracing comprising: The above-mentioned registration device, the above-mentioned retrieval device, and the above-mentioned cloud device.

[0012] In another aspect, examples of the present disclosure provide a method for object tracing, the method being performed by a registration device, the method comprising: capture an image of a first object that needs to be traced; generate an identification code for representing the first object based on the image of the first object; send an identification code of the first object and a serial number of the first object to a cloud device in a manner corresponding to each other for storage by the cloud device.

[0013] In another aspect, examples of the present disclosure provide a method for object tracing, the method being performed by a retrieval device, the method comprising: capture an image of a second object to be traced; generate an identification code for representing the second object based on an image of the second object; send an identification code for the second object to a cloud device so that the cloud device outputs a serial number corresponding to the identification code of the second object as a serial number of the second object.

[0014] In another aspect, examples of the present disclosure provide a method for object tracing, the method being performed by a cloud device, the method comprising: receive, from a registration device, an identification number and a serial number of a first object and store the identification number and a serial number of the first object in a corresponding manner to a cloud database; and / or receive, from a retrieval device, a second object identifier, retrieve from the cloud database a serial number corresponding to the identification number of the second object as the serial number of the second object and output a serial number of the second object; wherein the cloud database is used to store serial numbers and identification numbers corresponding to each other.

[0015] In another aspect, examples of the present disclosure provide for a registration device for object tracing, comprising: a visual work module; a control work module comprising: At least one processor, a memory in communication with the at least one processor, wherein the memory stores executable codes, and the executable codes, when executed by the at least one processor, allows the at least one processor to control the visual work module and the control work module for performing the above-mentioned method of the registration device.

[0016] In another aspect, examples of the present disclosure provide a retrieval device for object tracing, comprising: a visual work module; a control work module comprising: At least one processor, a memory in communication with the at least one processor, wherein the memory stores executable codes, and the executable codes, when executed by the at least one processor, allows the at least one processor to control the visual work module and the control work module for performing the above-mentioned method of the retrieval device.

[0017] In another aspect, an example of the present disclosure provides a cloud device for object tracing, comprising: at least one processor; a memory in communication with the at least one processor, wherein the memory stores an executable code, and the executable code, when executed by the at least one processor, allows the at least one processor to perform the above-mentioned method of the cloud device.

[0018] In another aspect, the examples of the present disclosure provide a computer- readable storage medium which stores executable codes that, when executed, implement the above-mentioned method of the registration device, retrieval device, or cloud device.

[0019] In another aspect, examples of the present disclosure provide a computer program product that includes a computer program that when executed implements the method described above with respect to a registration device, a retrieval device, or a cloud device.

[0020] Description of Accompanying Drawings

[0021] A more detailed description of exemplary examples of the present disclosure is provided with reference to the drawings, in which the purposes, features, and advantages of the exemplary examples of the present disclosure and others will become more apparent, wherein in the various drawings, the same reference numerals generally represent the same elements.

[0022] FIG. 1 is a schematic block diagram of a system for object tracing in accordance with some examples.

[0023] FIG. 2A is a schematic block diagram of a registration device in accordance with some examples.

[0024] FIG. 2B is a schematic block diagram of an implementation of a visual work module.

[0025] FIG. 3A is a schematic block diagram of a retrieval device in accordance with some examples.

[0026] FIG. 3B is a schematic block diagram of an implementation of a visual work module. FIG. 4 is a schematic block diagram of a cloud device in accordance with some examples.

[0027] FIG. 5A shows a diagram of an example implementation of a visual work module in a registration device or a retrieval device.

[0028] FIG. 5B shows an example processing process for an image of a magnet.

[0029] FIG. 6 is a schematic diagram of an embodiment of an application scenario for examples of the present disclosure.

[0030] FIG. 7 is a schematic flow diagram of a method for object tracing, in accordance with some examples.

[0031] FIG. 8 is a schematic flow diagram of a method for object tracing, in accordance with some examples.

[0032] FIG. 9 is a schematic flow diagram of a method for object tracing, in accordance with some examples.

[0033] FIG. 10 is a schematic block diagram of a control work module in a registration device or a control work module in a retrieval device, in accordance with some examples.

[0034] FIG. 11 is a schematic block diagram of a cloud device in accordance with some examples. For example, the cloud device 1000 may be an example implementation of the cloud device 400.

[0035] Specific Embodiments

[0036] The subject matter described herein is hereby discussed with reference to various examples. It should be understood that discussions about these examples are provided to aid those skilled in the art in better understanding and realization of the subject matter described herein rather than limiting the scope of protection, applicability, or examples described in the Claims.

[0037] In the industrial field, the traceability of physical components is an important part of the quality management of physical components and the products to which they are assembled. For ease of description, the physical components that will require traceability are collectively referred to herein as physical objects or objects. Tracing may typically include batch tracing, item tracing, or a mix of both. Batch tracing is typically performed on a batch of physical objects, such as adding a lot number for a batch of physical objects. The cost of batch tracing is relatively low, but may not be well suited for single piece flow production. Moreover, since batch tracing is for a batch of physical objects that may have originated from a different batch during the previous processing, it may be difficult to find the root cause through batch tracing if there are subsequent quality issues. In contrast, the item traceability can be a more granular traceability that typically traces a single physical object, thereby providing more accurate traceability information. Currently, for purposes of item tracing, unique identifiers for physical objects are typically added by way of indirect or direct marking. For example, in an indirect marking method, a carrier with its unique identifier (e.g., plain text, barcode, QR code, radio frequency identification code, etc.), such as a printed label, may be pasted or appended on a physical object. In a direct marking mode, the unique identification of the physical object itself may be directly added, such as mechanical engraving, laser marking, inkjet printing, electrochemical marking, etc. Whether it is a direct or indirect way of marking, there are certain requirements for the size or shape of the physical object, and the costs are relatively high. Moreover, for indirect marking modes, carriers with unique identifiers can easily be lost during subsequent shipping, which can result in the inability to trace physical objects. For direct marking, some damage may be caused to the surface of the physical object, which affects the performance of the physical object.

[0038] In view of this, examples of the present disclosure provide a technical solution for object tracing that is image-based and therefore efficiently enabling non-invasive, noncontacting object tracing with relatively low costs. The description is given below with reference to the specific examples.

[0039] FIG. 1 is a schematic block diagram of a system for object tracing in accordance with some examples.

[0040] As shown in FIG. 1 , the system 100 may include a registration device 200, a retrieval device 300, and a cloud device 400.

[0041] The registration device 200 can be connected to the cloud device 400 for communication with the cloud device 400. The communication between the registration device 200 and the cloud device 400 can be achieved in a variety of suitable ways, such as based on wired or wireless communication standards.

[0042] The retrieval device 300 can also be connected to the cloud device 400 to communicate with the cloud device 400. The communication between the retrieval device 300 and the cloud device 400 can also be accomplished by a variety of suitable means, such as wired or wireless communication standards.

[0043] In general, the registration device 200 may capture an image of an object that needs to be traced, generate an identification code for representing the object based on the captured image, and then send the identification code and serial number of the object to the cloud device 400. The identification code of the object corresponds to the serial number of the object. The cloud device 400 may store the received identification numbers and serial numbers in a manner corresponding to each other. This may also be understood as requiring the object to be traced to register with the cloud device 400. In this way, the cloud device 400 may store identification numbers and serial numbers corresponding to each other. The retrieval device 300 may capture an image of an object that needs to be traced, generate an identification code for representing the object based on the captured image, and then send the identification code of the object to the cloud device 400. The cloud device 400 can retrieve the serial numbers corresponding to the serial numbers received from the retrieval device 300 and output the retrieved serial numbers, such as the one that the cloud device 400 can send or store to the manufacturing execution system (MES). After the MES obtains the serial number, more information about the object may be obtained based on the serial number, such as various processing information for the object. In addition, the cloud device 400 can send the retrieved serial number to the retrieval device 300 for recording. Of course, the cloud device 400 can also send the retrieved serial numbers to other production systems associated with the object that needs to be traced for later use.

[0044] For example, for the same target device, the registration device 200 may capture an image of the target object, generate an identification code of the target object, and send the identification code of the target object to the cloud device 400 in a manner corresponding to each other after the processing of the target object is complete on the first production line. The cloud device 400 may store the identification code of the target object and the serial number of the target object in a manner that corresponds to each other.

[0045] The retrieval device 300 may capture an image of a target object, generate an identification code of the target object, and send the identification code of the target object to the cloud device 400 after the target object is transported to a second production line and before the target object is processed on the second production line.

[0046] The cloud device 400 can retrieve the serial number of the target object based on the identification code of the target object received from the retrieval device 300 and send the serial number of the target object to a production system associated with the target object for the production system to perform operations on the target object based on the serial number of the target object. In examples of the present disclosure, the production system may be a system associated with the first and second production lines (e.g., a database system, control system, etc.) that may be used to record processing information associated with the first and second production lines, or control the first and second production lines, etc. The specific form of the production system may be determined based on actual application scenarios and business needs, which are not defined herein.

[0047] It can be seen that such a system enables efficient and reliable tracing of objects without special requirements for the shape or size of the objects, without damaging the surfaces of the objects, and with significant cost reduction. In addition, it can be seen that the technical solutions provided in examples of the present disclosure are image-based tracing, and therefore can also be understood as object tracing based on Natural Fingerprint.

[0048] Embodiments of the present disclosure may apply a variety of scenarios. For example, examples of the present disclosure may be applied to the tracking of physical components in a manufacturing plant, especially where the physical components need to be processed on different production lines that cannot directly share processing information with each other. For example, after the physical components are processed on line A, they need to be transported to line B for processing. Processing information cannot be shared directly between line A and line B. In this instance, the examples of the present disclosure still provide for efficient and reliable traceability of information related to physical components at line B.

[0049] The registration device 200, the cloud device 400, and the retrieval device 300 of the FIG. 1 are described below in conjunction with the specific examples.

[0050] FIG. 2A is a schematic block diagram of a registration device in accordance with some examples.

[0051] As shown in FIG. 2A, the registration device 200 may include a visual work module 210 and a control work module 220.

[0052] The visual work module 210 may capture an image of a first object that needs to be traced. The control work module 220 may generate an identification code for representing the first object based on an image of the first object. The control work module 220 may send the identification code of the first object and the serial number of the first object to the cloud device in a manner corresponding to each other for storage by the cloud device.

[0053] In such examples, the identification code of the object is obtained based on the image and the identification code and serial number of the object is sent to the cloud device in a manner corresponding to each other for storage, thereby enabling the efficient registration of information of the object to the cloud device for subsequent traceability. In this process, there are no special requirements for the shape or size of the object, and the damage to the surface of the object, the loss of the object identification, etc. can be avoided. In addition, this approach greatly reduces costs.

[0054] In some examples, the registration device 200 may be mounted at a location after the last station of the first production line such that the visual work module 210 captures an image of the first object after the first object passes the last station.

[0055] For example, in some examples, the registration device 200 may be installed at a location where the first object processing is complete such that the visual work module 210 captures an image of the first object after the first object processing is complete. For example, the registration device 200 may be installed at a quality check station of the first object.

[0056] In some examples, the visual work module 210 may include various suitable components or units for implementing image capture. For example, FIG. 2B is a schematic block diagram of an implementation of the visual work module 210. As shown in FIG. 2B, the vision work module 210 may include a light source 211 , a lens 212, and an imaging unit 213.

[0057] The light source 211 may provide illumination for the first object. For example, the light source 211 may illuminate the first object, which may be advantageous for improving imaging effects. The light source 211 may be implemented using any suitable light source, such as high-frequency fluorescence, fiber halogen lamp, light-emitting diode (LED) lights, etc.

[0058] The lens 212 and the imaging unit 213 may work together to capture images of the first object under the illumination provided by the light source 211 . The lens 212 can be implemented with any suitable lens. The imaging unit 213 may include any suitable imaging device, such as an imaging device based on a charge coupler device (CCD) or complementary metal oxide semiconductor (CMOS).

[0059] The specific implementation of the light source 211 , lens 212, and imaging unit 213 depends on the actual application scenario, business needs, etc., which is not defined herein.

[0060] In some examples, as shown in FIG. 2B, the visual work module 210 may further include a positioning unit 214. The positioning unit 214 may secure the first object to a preset location. The preset location may be a location that facilitates capturing an image of the first object. The light source 211 may provide illumination for the first object after the positioning unit 214 secures the first object to a preset position. Accordingly, in this instance, the lens 212 and the imaging unit 213 may be triggered to work together to capture an image of the first object under the illumination provided by the light source 211.

[0061] In some implementations, the visual work module 210 may operate under the control of the control work module 220. For example, the control work module 220 may control the positioning unit 214 of the visual work module 210 to secure the first object to a preset location. The control work module 220 may then control the light source 211 to provide illumination for the first object. The control work module 220 may then control the lens 212 and the imaging unit 213 to work together to capture images of the first object under the illumination provided by the light source 211.

[0062] Only some examples of the visual work module 210 are described above, however, it will be understood that the visual work module 210 may also include other units or devices in different embodiments, which are not defined herein.

[0063] The control work module 220 may process the image of the first object to obtain an identification code for representing the first object.

[0064] For example, in some examples, the control work module 220 may extract images of the key area from an image of the first object. An image of a key area includes an image of a key area of the first object that includes the natural texture of the first object. The control work module 220 may process the key area image using a fine particle size texture-based feature extraction algorithm to obtain the identification code.

[0065] The extraction of images of key areas may be accomplished in an applicable manner, for example, the control work module 220 may use the predefined areas of interest (i.e. , key areas) on the first object to crop the images of the first object to obtain images of key areas. Unlike indirect marking and direct marking that the identification needs to be added on the object itself or on the carrier attached to the object. The said key area of the present example is a selected area on the said first object, which includes the natural texture of the said first object in the selected area (natural fingerprint), i.e., the texture characteristics of the said first object itself, without relying on the additional identification added on the first object, so as to achieve non-invasive and contactless object tracing. In some examples, the key area image may be a fine particle size texture area that facilitates unique identification of the first object. The key area image may also be understood as or referred to as a fingerprint area of the first object.

[0066] Obtaining the identification code based on the key area image may be achieved in any suitable manner. For example, the control work module 220 may utilize a convolutional neural network (CNN) to process images of key areas to obtain output results from at least two layers in the CNN, which are combined to generate an identification code.

[0067] In some examples, the surface of the first object may be functionally characteristic, such as having a surface treatment of a special process to provide corrosion resistance, high pressure resistance, wear resistance, etc. As previously noted, traditionally, people may mark directly through the surface of the physical object. However, for a physical object with a functional surface, directly marking on the functional surface may affect the function and quality of the object. For example, laser coding, electrochemical markers, etc. on such surfaces may impair their functional properties. In these examples of the present disclosure, a surface of the object can be effectively avoided by utilizing an image that includes the natural texture of the object to generate an identification code for the object that is traceable. The surface of the first object may be a metallic material or a magnetic material.

[0068] The control work module 220 may send the identification number and serial number of the first object to the cloud device in a manner corresponding to each other. For example, the control work module 220 may combine the serial number of the first object with the identifier of the first object to form a key value pair for the first object, wherein the key may represent the serial number of the first object and the value may represent the identifier of the first object. The control work module 220 may then transmit a key value of the first object to the cloud device for storage by the cloud device.

[0069] In some implementations, the control work module 220 may be implemented by an applicable device such as an industrial control computer.

[0070] FIG. 3A is a schematic block diagram of a retrieval device in accordance with some examples.

[0071] As shown in FIG. 3A, the retrieval device 300 may include a visual work module 310 and a control work module 320.

[0072] The visual work module 310 may capture an image of a second object that needs to be traced.

[0073] The control work module 320 may generate an identification code for representing the second object based on an image of the second object.

[0074] The control work module 320 may send the identification code of the second object to the cloud device so that the cloud device outputs a serial number corresponding to the identification code of the second object as the serial number of the second object.

[0075] In such examples, where tracing of a particular object is desired, an image of the object is captured and then an identification code is generated based on the image of the object, which is sent to the cloud device for the cloud device to output a corresponding serial number, enabling efficient and reliable object tracing.

[0076] In some examples, the retrieval device 300 may be mounted at a location prior to the first station on the second production line such that the visual work module 310 can capture an image of the second object before the second object enters the first station.

[0077] For example, in some examples, the retrieval device 300 may be installed at a location where the second object will be assembled to the final product. In this way, the visual work module 310 may capture an image of the second object prior to assembling the second object to the final product.

[0078] The visual work module 310 in the retrieval device 300 is similar to the visual work module 210 in the registration device 200. For example, FIG. 3B is a schematic block diagram of an implementation of the visual work module 310. As shown in FIG. 3B, the visual work module 310 may include a light source 311 , a lens 312, and an imaging unit 313.

[0079] The light source 311 may provide illumination for the second object. For example, the light source 311 may illuminate the second object, which may be advantageous for improving imaging effects. The light source 311 can be implemented using any suitable light source, such as high-frequency fluorescence, fiber halogen lamp, LED light, etc.

[0080] The lens 312 and the imaging unit 313 may work together to capture images of the second object under the illumination provided by the light source 311. The lens 312 may be implemented with any suitable lens. The imaging unit 313 may include any applicable imaging device, such as a CCD-based, CMOS-based imaging device.

[0081] The specific implementation of the light source 311 , lens 312, and imaging unit 313 depends on the actual application scenario, business need, etc., which is not defined herein.

[0082] In some examples, as shown in FIG. 3B, the visual work module 310 may also include a positioning unit 314. The positioning unit 314 may secure the second object to a preset location. The preset location may be a location that facilitates capturing an image of the second object. The light source 311 may provide illumination for the second object after the positioning unit 314 secures the second object to a preset position. Accordingly, in this instance, the lens 312 and the imaging unit 313 may be triggered to work together to capture an image of the second object under the illumination provided by the light source 311 .

[0083] In some implementations, the visual work module 310 may operate under the control of the control work module 320. For example, the control work module 320 may control the positioning unit 314 of the visual work module 310 to secure the second object to a preset location. The control work module 320 may then control the light source 311 to provide illumination for the second object. The control work module 320 may then control the lens 312 and the imaging unit 313 to work together to capture images of the second object under the illumination provided by the light source 311 .

[0084] Only some examples of the visual work module 310 are described above, however, it will be understood that the visual work module 310 may also include other units or devices in different implementations, which are not defined herein.

[0085] The control work module 320 may process the image of the second object to obtain an identification code of the second object.

[0086] For example, the control work module 320 may extract images of the key area from an image of the second object. The control work module 320 may process the key area image using a fine particle size texture-based feature extraction algorithm to obtain an identification code of the second object.

[0087] The extraction of images of key areas may be accomplished in an applicable manner, for example, the control work module 320 may use the predefined areas of interest (i.e. , key areas) to crop the images of the second object to obtain images of key areas. The key area may be a selected area on the second object that includes the natural texture of the second object in the selected area, i.e., the texture characteristics of the second object itself, without relying on an additional identification added to the second object. For example, the key area image may be a fine particle size texture area that facilitates unique identification of the second object. The key area image may also be understood or referred to as a fingerprint area.

[0088] Obtaining the identification code based on the key area image may be achieved in any suitable manner. For example, the control work module 320 can utilize the CNN to process images of key areas, acquire output results from at least two layers in the CNN, and combine these outputs to generate an identification code.

[0089] The control work module 320 may send the identification code of the second object to the cloud device such that the cloud device outputs a serial number corresponding to the identification code of the second object as the serial number of the second object.

[0090] In some examples, the control work module 320 may also receive a serial number of the second object from the cloud device for storage as a record for subsequent query or use.

[0091] In some implementations, the control work module 320 may be implemented using an applicable device such as an industrial control computer.

[0092] While some of the modules in the registration device and the retrieval device are described above, it should be understood that in practical applications, the registration device or retrieval device may also include other additional modules such as a graphical user interface (GUI), web service module, logging module, resource monitoring module, containerized software module (e.g., Docker), etc., which are not defined herein.

[0093] FIG. 4 is a schematic block diagram of a cloud device in accordance with some examples.

[0094] As shown in FIG. 4, the cloud device 400 may include a storage module 410, a retrieval module 420, and a cloud database 430. Both the storage module 410 and the retrieval module 420 may be connected to the cloud database 430. The cloud database 430 may store serial numbers and identification numbers corresponding to each other.

[0095] The storage module 410 may communicate with the registration device. The storage module 410 may receive the identification number and serial number of the first object from the registration device and store it in a cloud database 430 in a manner corresponding to each other.

[0096] The retrieval module 420 may communicate with the retrieval device. The retrieval module 420 may receive the identification code of the second object from the retrieval device and retrieve the serial number corresponding to the identification code of the second object from the cloud database 430 as the serial number of the second object based on the identification code of the second object. The retrieval module 420 may output a serial number of the second object.

[0097] In such examples, the cloud device may utilize the cloud database to store the identification code and serial number of the object that needs to be traced; when retrieval is required, the cloud device may retrieve the corresponding serial number based on the identification code. As a result, object traceability can be achieved efficiently and reliably, with significant cost savings.

[0098] In some examples, the cloud database 430 may be in the form of key value pairs to store serial numbers and identification numbers corresponding to each other. In each key value pair, the key represents a serial number and the value represents an identification number corresponding to the serial number.

[0099] For example, the cloud database 430 can store multiple entries, each of which is a key value pair. For example, a key value pair may be expressed as: {KEY=Serial Number; VALUE=ldentification Code}.

[0100] In some examples, the storage module 410 may receive a key value pair for the first object from the registration device, wherein in the key value pair for the first object, the key may represent a serial number of the first object and the value may represent an identification number of the first object. The storage module 410 may store a key pair of the first object in the cloud database 430.

[0101] In some examples, the retrieval module 124, after receiving the identification code of the second object from the retrieval device 102, may determine the proximity between the identification code of the second object and each of the identification numbers stored in the cloud database 430, and may use the serial number corresponding to the identification code with the highest proximity to the second object as the serial number of the second object.

[0102] As previously noted, the identification code is generated based on the image, so the identification code is a vector in nature. In this way, determining the proximity between the identification code of the second object and each of the identification codes stored in the cloud database 430 may be understood as determining the distance between the vectors. The distance between the vectors may be measured in a variety of suitable ways. For example, in some examples, the Euclidean distance, i.e., L2 distance, between the identification code of the second object and each of the identification codes stored in the cloud database 430 may be determined. The serial number corresponding to the identification code of minimum Euclidean distance to the second object may be used as the serial number of the second object.

[0103] In some examples, the retrieval module 420 may output the serial number of the second object to any system or device that requires the information. For example, the retrieval module 420 may send a serial number of the second object to a production system associated with the second object for subsequent use. For example, the retrieval module 420 may send a serial number of the second object to the MES. In this way, the MES may conduct subsequent operations on the second object based on the serial number of the second object, such as obtaining prior processing information for the second object, associating the serial number of the second object with the serial number information of the final product to which the second object is assembled, and the like.

[0104] To facilitate understanding, the examples of the present disclosure will be described below with reference to the specific examples. It should be noted that these examples do not impose any restrictions on the scope of the present disclosure.

[0105] In the following example, it is assumed that the object to be traced is a magnet. A magnet can be an important component of a part whose processing parameters and / or status typically have a significant impact on the quality of the part and, therefore, the traceability of the magnet will be effective to improve the quality of the part. However, the magnets are generally small. In this case, it is difficult to effectively achieve the marking of magnets using either the indirect marking method or the direct marking method mentioned above. For example, because the size of the magnet is small, it may not be convenient to attach additional labels; instead, it may be easy to damage the surface of the magnet directly on the magnet, which may affect the performance of the magnet. In view of this, the technical solutions provided by examples of the present disclosure can be utilized to achieve the tracing of magnets. The magnet is, for example, a magnetic iron.

[0106] FIG. 5A shows a diagram of an example implementation of a visual work module in a registration device or a retrieval device. The visual work module 500 in FIG. 5A may be provided in a registration device or a retrieval device to image the magnet.

[0107] In the example of FIG. 5A, the visual work module 500 may include a light source 502, a lens 504, an imaging unit 506, and a positioning unit 508.

[0108] The positioning unit 508 may include a metal bracket and a clip. The clip may secure the magnet on the top of the metal bracket facing the same direction. After the positioning unit 508 secures the magnet, the light source 502 may turn on to provide illumination to the magnet. The lens 504 and the imaging unit 506 may capture images of the magnets.

[0109] Only some of the main units or devices of the visual work module are described above. It will be understood that, as also shown in FIG. 5A, the visual work module may also include some other unit or device, which is not defined herein.

[0110] FIG. 5B shows an example processing process for an image of a magnet.

[0111] In the example of FIG. 5B, stage 540 through stage 542 is performed at the registration device 200 to register the serial number and identification number of the magnet to the cloud device 400. The stage 550 through stage 551 is performed at the retrieval device 300 to retrieve the serial numbers of the magnets from the cloud device 400. At stage 540, the registration device 200 may extract images of the key area, the fingerprint area 521 , from the image 520 of the magnet. For example, the image 520 may be captured from a magnet using the visual work module 500 shown in the FIG. 5A.

[0112] At stage 541 , the registration device 200 may process the fingerprint area 521 with the CNN to obtain the identification code 522 of the magnet. In the example of FIG. 5B, the hypothetical identification code 522 is expressed as: [0.02 0.36 2.56 ... 0.02 -3.5] .

[0113] At stage 542, the registration device 200 may combine the identification code 522 of the magnet with the serial number of the magnet to form a key value pair 523 of the magnet, wherein the key may represent the serial number of the magnet and the value may represent the identifier of the magnet. In the example of FIG. 5B, suppose the key value pair 523 is expressed as {key=20211028312; value=[0.02 0.36 2.56 ... 0.02 -3.5]}. That is, the serial number of the magnet may be 20211028312.

[0114] The registration device 200 may then send a key value pair 523 of the magnet to the cloud device 400 for storage.

[0115] As shown in FIG. 5B, the cloud device 400 may have a cloud database that stores serial numbers and identification numbers corresponding to each other in the form of key value pairs.

[0116] Thereafter, the retrieval device 300 may utilize the visual work module 500 shown in the FIG. 5A to capture a magnet image 530 when a retrieval of the magnet is required at a certain time. At stage 550, the retrieval device 300 may extract the fingerprint area 531 from the magnet image 530. At stage 551 , the retrieval device 300 processes the fingerprint area 531 with the CNN to obtain the identification code 532. For example, suppose the identification number 532 is [0.02 0.36 2.56 ... 0.02 -3.5],

[0117] The retrieval device 300 may then send the identification number 532 to the cloud device 400.

[0118] The cloud device 400 may determine the Euclidean distance between the identification code 532 received from the retrieval device 300 and the various identification numbers stored in the cloud database, and output the serial number corresponding to the identification code having the minimum Euclidean distance as the serial number of the magnet. As shown in Figure 5B, serial number is 20211028312. The cloud device 400 can send this serial number to the MES.

[0119] For ease of understanding, in the example of FIG. 5B, the identifier obtained from the retrieval device and the identifier obtained from the registration device are represented as the same vector. However, it should be understood that in practice, for the same object, the identification code obtained by the retrieval device may not be identical to the identification code obtained by the registration device because image capture and / or selection of the key area image / fingerprint area may not be identical, but in general, the Euclidean distance between the identification code obtained by the retrieval device and the registration device will be minimal for the same object.

[0120] FIG. 6 is a schematic diagram of an example of an application scenario for examples of the present disclosure.

[0121] In the example of FIG. 6, at stage 610, the object enters the test stage upon completion of processing on a line. At this point, the registration device 200 may generate an identification code for the object and register the serial number and the identification code of the object to the cloud device 400. Thereafter, at stage 620, the object may be transported to another line for processing (e.g., the object is transported to another line for product assembly) via in-factory logistics transportation. At this point (e.g., before shipping the object to another production line for product assembly), the retrieval device 300 may generate an identification code for the object and send the identification code for the object to the cloud device 400. The cloud device 400 can retrieve the corresponding serial numbers and send them to the MES 650. The MES 650 may obtain previous processing information about the object based on the serial number, associate the serial number with the serial number information of the product the object is to be assembled to, and the like.

[0122] FIG. 7 is a schematic flow diagram of a method for object tracing, in accordance with some examples. The method of FIG. 7 may be performed by the registration device 200.

[0123] At step 702, an image of the first object that needs to be traced may be captured.

[0124] At step 704, an identification code for representing the first object may be generated based on an image of the first object.

[0125] At step 706, the identification code of the first object and the serial number of the first object may be sent to the cloud device in a manner corresponding to each other for storage by the cloud device.

[0126] The specific process of the method of FIG. 7 may correspond to the functions described above with respect to the registration device 200 and therefore, for simplicity of description, the specific process of the method of FIG. 7 is not repeated here.

[0127] FIG. 8 is a schematic flow diagram of a method for object tracing, in accordance with some examples. The method of FIG. 8 may be performed by the retrieval device 300.

[0128] At step 802, an image of the second object that needs to be traced may be captured.

[0129] At step 804, an identification code for representing the second object may be generated based on an image of the second object.

[0130] At step 806, the identification code of the second object may be sent to the cloud device so that the cloud device outputs a serial number corresponding to the identification code of the second object as the serial number of the second object.

[0131] The specific process of the method of FIG. 8 may correspond to the specific functions described above with respect to the retrieval device 300, and therefore the specific process of the method of FIG. 8 is not repeated here for the sake of simplicity of the description.

[0132] FIG. 9 is a schematic flow diagram of a method for object tracing, in accordance with some examples. The method of FIG. 9 may be performed by the cloud device 400.

[0133] At step 902, the identification code and serial number of the first object are received from the registration device and stored in a cloud database corresponding to each other.

[0134] At step 904, the identification code of the second object is received from the retrieval device, the serial number corresponding to the identification code of the second object is retrieved from the cloud database as the serial number of the second object based on the identification code of the second object, and the serial number of the second object is output.

[0135] Although steps 902 and 904 are illustrated as sequential executions in FIG. 9, in practice, steps 902 and 904 may be performed in parallel, or step 904 may be performed before step 902, which is not defined herein.

[0136] The specific process of the method of FIG. 9 may correspond to the specific functions described above with respect to the cloud device 400 and therefore, for the sake of simplicity of the description, the specific process of the method of FIG. 9 is not repeated here.

[0137] FIG. 10 is a schematic block diagram of a control work module in a registration device or a control work module in a retrieval device, in accordance with some examples. For example, the control work module 1000 shown in FIG. 10 may be an example implementation of the control work module 220 in the registration device 200 or the control work module 320 in the retrieval device 300.

[0138] As shown in Figure 10, the control work module 1000 may include a processor 1002, a memory 1004, an input interface 1006, and an output interface 1008, which are coupled together via a bus 1010. However, it should be understood that Figure 10 is for illustrative purposes only rather than limiting the scope of the present disclosure. For example, in different application scenarios, the control work module 1000 may include more or fewer modules, which is not defined herein.

[0139] The memory 1004 may be used to store various information, executable instructions or codes, etc. related to controlling the functions or operations of the work module 1000. For example, the memory 1004 may include, but is not limited to, Random Access Memory (RAM), Read-Only Memory (ROM), Flash Memory, Programmable ROM (PROM), Erasable PROM (EPROM), register, hard disk, and the like.

[0140] The processor 1002 may be used to perform or implement various functions or operations of the control work module 1000. For example, where the control work module 1000 is set up in the registration device 200, the processor 1002 may execute executable instructions or code stored in the memory 1004 to enable the various functions described above with respect to the registration device 200. With the control work module 1000 disposed in the retrieval device 300, the processor 1002 may execute executable instructions or codes stored in the memory 1004 to enable the various functions described above with respect to the retrieval device 300. The processor 1002 may include various applicable processors, such as a general-purpose processor (e.g., Central Processing Unit, CPU), specialized processors (e.g., digital signal processors, application-specific integrated circuits, etc.).

[0141] The input interface 1006 may receive various forms of data. For example, where the control work module 1000 is set up in the registration device 200, the input interface 1006 may receive an image of a first object that needs to be traced. Where the control work module 1000 is set up in the retrieval device 300, the input interface 1006 may receive an image of a second object that needs to be traced.

[0142] The output interface 1008 may output various forms of data. For example, where the control work module 1000 is set up in the registration device 200, the output interface 1008 may output an identification code and serial number corresponding to each other. With the control work module 1000 set up in the retrieval device 300, the output interface 1008 can output an identification code. The output interface 1008 may communicate with the cloud based on various applicable communication standards.

[0143] FIG. 11 is a schematic block diagram of a cloud device in accordance with some examples. For example, the cloud device 1000 may be an example implementation of the cloud device 400.

[0144] As shown in Figure 11 , the cloud device 1100 may include a processor 1102, a memory 1104, an input interface 1106, and an output interface 1108, which are coupled together via a bus 1110. However, it should be understood that Figure 11 is for illustrative purposes only rather than limiting the scope of the present disclosure. For example, in different application scenarios, the cloud device 1100 may include more or fewer modules, which is not defined herein.

[0145] The memory 1104 may be used to store various information, executable instructions or codes, etc. related to the functionality or operation of the cloud device 1100. For example, the above-described cloud database may be disposed in memory 1104. For example, memory 1104 may include, but is not limited to, RAM, ROM, flash memory, PROM, EPROM, register, hard disk, and the like.

[0146] The processor 1102 can be used to perform or implement various functions or operations of the cloud device 1100. The processor 1102 may execute executable instructions or code stored in the memory 1104 to enable the various functions described above with respect to the cloud device 400. The processor 1102 may include a variety of suitable processors, such as a general-purpose processors (such as a CPU), special purpose processors (such as digital signal processors, application-specific integrated circuits, and the like).

[0147] The input interface 1106 may receive various forms of data. For example, the input interface 1106 may receive a serial number and an identification code of the first object from the registration device 200. The input interface 1106 may receive the identification code of the second object from the retrieval device 300.

[0148] The output interface 1108 may output various forms of data. For example, the output interface 1108 may output a serial number of the second object.

[0149] In some implementations, the cloud device 1100 may be implemented based on an open-source software system, Milvus. Of course, the cloud device 1100 can also be implemented in other ways, which is not defined by this disclosure.

[0150] The examples of the present disclosure further provide a computer-readable storage medium. The computer-readable storage medium may store executable codes that, when executed, implement the specific processes described above regarding registration device, retrieval device, or cloud device.

[0151] For example, the computer-readable storage medium may include, but is not limited to, RAM, ROM, Electrically-Erasable Programmable Read-Only Memory (EEPROM), Static Random Access Memory (SRAM), hard disk, flash memory, and the like.

[0152] Embodiments of the present disclosure also provide for computer program products. Computer program products include computer programs. The computer programs, when executed, implement the specific process described above regarding registration device, retrieval device, or cloud device.

[0153] The above-described specific examples of the present disclosure have been described. Other examples are within the scope of the appended Claims. In some cases, actions or steps described in the Claims can be performed in a different order than that of the examples and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require specific or continuous sequences to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or advantageous. Not all steps and units depicted in the above-mentioned flowcharts and system diagrams are required; certain steps or units may be omitted based on actual needs. The device structures described in the above-mentioned examples can be physical or logical structures, that is, some units may be realized by the same physical entity, while others may be realized by multiple physical entities or may be jointly realized by certain components in multiple separate devices.

[0154] The above, in conjunction with the drawings, details various optional embodiments of the present disclosure. However, the examples of the present disclosure are not limited to the specific details of the examples mentioned above. Within the technical scope of the examples of the present disclosure, various modifications to the technical solutions of the examples of the present disclosure are possible, and these modifications fall within the protection scope of the examples of the present disclosure.

Claims

Claims1 . A registration device for object tracing, comprising: a visual work module configured to: capture an image of a first object to be traced, control a work module configured to: generate, based on an image of the first object, an identification code for representing the first object, send an identification code of the first object and a serial number of the first object, in a manner corresponding to each other, to a cloud device for storage by the cloud device.

2. The registration device according to Claim 1 , wherein the registration device is mounted at a location after the last station on the first production line such that the visual work module captures an image of the first object after the first object passes the last station.

3. The registration device according to Claim 2, wherein the registration device is mounted at a location after the first object processing is complete such that the visual work module captures an image of the first object after the first object processing is complete.

4. The registration device according to Claim 1 , wherein the visual work module comprises a light source, a lens, and an imaging unit,The light source is configured to: provide illumination for the first object,The lens and the imaging unit are configured to: capture an image of the first object under illumination of the light source.

5. The registration device according to Claim 4, wherein the visual work module comprises a positioning unit configured to: secure the first object to a preset location,The light source is controlled as: provide illumination to the first object after the positioning unit secures the first object to the preset position.

6. The registration device according to Claim 1 , wherein the control work module is configured to: extract an image of a key area from an image of the first object, wherein the key area image includes an image of a key area of the first object, the key area including anatural texture of the first object, process the key area image using a fine particle size texture-based feature extraction algorithm to obtain an identification code of the first object.

7. The registration device according to Claim 1 , wherein the control work module is configured to: combine the serial number of the first object with the identification code of the first object to obtain a key value pair of the first object, wherein in the key value pair of the first object, the key represents the serial number of the first object, and the value represents the identification code of the first object, send a key value pair of the first object to the cloud device so that the cloud device stores a key value pair of the first object.

8. The registration device according to Claim 1 , wherein the surface of the first object has functional properties, and / or,The surface of the first object is a metallic material or a magnetic material.

9. A retrieval device for object tracing, comprising: a visual work module configured to: capture an image of a second object to be traced, control a work module configured to: generate an identification code for representing the second object based on an image of the second object, send an identification code of the second object to a cloud device so that the cloud device outputs a serial number corresponding to the identification code of the second object as a serial number of the second object.

10. The retrieval device according to Claim 9, wherein the retrieval device is mounted at a position preceding the first station on the second production line such that the visual work module captures an image of the second object before the second object enters the first station.

11. The retrieval device according to Claim 10, wherein the retrieval device is mounted at a location prior to which the second object is to be assembled to the final product such that the visual work module captures an image of the second object prior to the second object being assembled to the final product.

12. The retrieval device according to Claim 9, wherein the visual work module comprises: a light source, a lens, and an imaging unit,The light source is configured to: provide illumination for the second object,The lens and the imaging unit are configured to: capture an image of the second object under illumination of the light source.

13. The retrieval device according to Claim 12, wherein the visual work module comprises a positioning unit configured to: secure the second object to a preset position,The light source is controlled as: providing illumination to the second object after the positioning unit secures the second object to the preset position.

14. The retrieval device according to Claim 9, wherein the said control work module is configured to: extract an image of a key area from an image of the second object, wherein the image of the key area comprises an image of a key area of the second object, the key area comprising a natural texture of the second object, process the key area image using a fine particle size texture-based feature extraction algorithm to obtain an identification code of the second object.

15. The retrieval device according to Claim 9, wherein the control work module is further configured to: receive, from the cloud device, a serial number of the second object for storage.

16. A cloud device for object tracing, comprising: a cloud database configured to: store serial numbers and identification numbers corresponding to each other, a storage module configured to: receive, from a registration device, an identification code and a serial number of a first object, store the identification number and serial number of the first object in a manner corresponding to each other to the cloud database, a retrieval module configured to: receive, from a retrieval device, an identification code of a second object, retrieve, from the cloud database based on an identification code of the second object, a serial number corresponding to the identification code of the second object as a serial number of the second object,output a serial number of the second object.

17. The cloud device according to Claim 16, wherein the said cloud database stores the serial numbers and identification numbers corresponding to each other in the form of key value pairs, wherein in any key value pair, the key represents the serial number, and the value represents the identification number corresponding to the serial number.

18. The cloud device according to Claim 17, wherein the storage module is configured to: receive, from the registration device, a key value pair of the first object, wherein in a key value pair of the first object, the key represents a serial number of the first object and the value represents an identification code of the first object, store a key value pair of the first object to the cloud database.

19. The cloud device according to Claim 16, wherein the said retrieval module is configured to: determine a proximity between an identification code of the second object and each identification code stored in a cloud database, use the serial number corresponding to the identification number of the second object having the highest degree of proximity to the identification number as the serial number of the second object.

20. The cloud device according to Claim 19, wherein the said retrieval module is configured to: determine a Euclidean distance between an identification code of the second object and each identification code stored in the cloud database, set the serial number corresponding to the identification number with minimum Euclidean distance to the identification code of the second object as the serial number of the second object.

21. The cloud device according to Claim 16, wherein the said retrieval module is configured to: send a serial number of the second object to a production system associated with the second object.

22. A system for object tracing, comprising: the registration unit according to any one of Claims 1 to 8, the retrieval unit according to any one of Claims 9 to 15,the cloud device according to any one of Claims 16 to 21 .

23. The system according to Claim 22, wherein the first object and the second object are the same target object,After the processing of the said target object on the first production line is complete, the said registration device captures an image of the said target object, generates an identification code of the said target object, and sends the identification code of the said target object and the serial number of the said target object, in a manner corresponding to each other, to the said cloud device, the cloud device stores the identification code of the target object and the serial number of the target object in a manner corresponding to each other, the retrieval device captures an image of the target object, generates an identification code of the target object, and sends the identification code of the target object to the cloud device after the target object is transported to a second production line and before the target object is processed on the second production line,The cloud device retrieves the serial number of the target object based on the identification code of the target object and sends the serial number of the target object to a production system associated with the target object so that the production system performs operations on the target object based on the serial number of the target object.

24. A method for object tracing, including: capture an image of a first object to be traced, generate, based on an image of the first object, an identification code for representing the first object, send an identification code of the first object and a serial number of the first object, in a manner corresponding to each other, to a cloud device for storage by the cloud device.

25. A method for object tracing, including: capture an image of a second object to be traced, generate an identification code for representing the second object based on an image of the second object, send an identification code of the second object to a cloud device so that the cloud device outputs a serial number corresponding to the identification code of the second object as a serial number of the second object.

26. A method for object tracing, including:receive, from a registration device, an identification code and a serial number of a first object and store the identification code and a serial number of the first object in a cloud database corresponding to each other, and / or receive, from a retrieval device, an identification code of a second object, retrieve from the cloud database a serial number corresponding to the identification code of the second object as a serial number of the second object based on the identification code of the second object, and output a serial number of the second object, wherein the cloud database is used to store serial numbers and identification numbers corresponding to each other.

27. A registration device for object tracing, comprising: a visual work module, a control work module comprising: at least one processor, a memory in communication with the at least one processor, wherein the memory stores executable codes, and the executable codes, when executed by the at least one processor, allows the at least one processor to perform the method according to Claims 24.

28. A retrieval device for object tracing, comprising: a visual work module, a control work module comprising: at least one processor, a memory in communication with the at least one processor, wherein the memory stores executable codes, and the executable codes, when executed by the at least one processor, allows the at least one processor to perform the method according to Claims 25.

29. A cloud device for object tracing, comprising: at least one processor, a memory in communication with the at least one processor, wherein the memory stores executable codes, and the executable codes, when executed by the at least one processor, allows the at least one processor to perform the method according to Claims 26.

30. A computer program product wherein comprises a computer program that implements the method according to any one of Claims 24 to 26 when executed.

Images