CN113516631A - Material quality data tracing management method based on block chain technology - Google Patents

Material quality data tracing management method based on block chain technology Download PDF

Info

Publication number
CN113516631A
CN113516631A CN202110536020.0A CN202110536020A CN113516631A CN 113516631 A CN113516631 A CN 113516631A CN 202110536020 A CN202110536020 A CN 202110536020A CN 113516631 A CN113516631 A CN 113516631A
Authority
CN
China
Prior art keywords
feature map
classification
region
interest
quality data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
CN202110536020.0A
Other languages
Chinese (zh)
Inventor
王泽松
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jinan Maituo Network Technology Co ltd
Original Assignee
Jinan Maituo Network Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jinan Maituo Network Technology Co ltd filed Critical Jinan Maituo Network Technology Co ltd
Priority to CN202110536020.0A priority Critical patent/CN113516631A/en
Publication of CN113516631A publication Critical patent/CN113516631A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/60—Protecting data
    • G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
    • G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T9/00—Image coding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20092—Interactive image processing based on input by user
    • G06T2207/20104—Interactive definition of region of interest [ROI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30152—Solder

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Bioethics (AREA)
  • Computer Hardware Design (AREA)
  • Computer Security & Cryptography (AREA)
  • Quality & Reliability (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)

Abstract

The present application relates to the field of blockchain, and more particularly, to a traceability management method for material quality data based on blockchain technology. The method aims at the unchangeable characteristic of the block chain, accurately identifies and classifies the material quality data to be managed so as to accurately standard the type of the material quality data to be managed, and is convenient for calling and using the subsequent material quality data. Therefore, the block chain is adopted to store and manage the material quality data, the decentralized distributed storage characteristic and the non-modifiable characteristic of the block chain can be utilized to ensure the convenience and the safety of the management of the material quality data, and the management capability of the material quality data is improved.

Description

Material quality data tracing management method based on block chain technology
Technical Field
The present application relates to the field of blockchain, and more particularly, to a method for tracing to source and managing material quality data based on blockchain technology, a system for tracing to source and managing material quality data based on blockchain technology, and an electronic device.
Background
In recent years, as the technology of blockchain matures and develops, various data management technologies based on blockchain technology and applications thereof are developed due to the unique non-alterable characteristic of blockchain. The blockchain technology has the advantages of decentralization, openness, independence, safety, anonymity and the like, wherein decentralization means that the blockchain does not depend on an additional third-party management mechanism or hardware equipment; openness means that the technical basis of the blockchain is open source, and except that private information of each party of the transaction is encrypted, data of the blockchain is open to all people; independence refers to the fact that the whole blockchain system is independent of third parties based on the agreed specifications and protocols; the security means that network data cannot be manipulated and modified arbitrarily as long as more than half of all data nodes cannot be mastered; anonymity means that unless required by legal specifications, technically, the identity information of each block node does not need to be disclosed or verified.
In the building engineering, for the building material, the impact resistance is important data for judging the material quality, and because the safety of the building engineering is directly concerned, a very strict management system and a quality data traceability mechanism need to be established. In addition, the quality detection of the building materials not only occurs in laboratories, but also can be performed in places such as building sites, so that the data sources are numerous, the problems that the data is repeated for many times easily in the process, the data is artificially and maliciously tampered and the like easily occur, and the challenge is brought to data management.
Therefore, a material quality data traceability management scheme based on the blockchain technology is desired.
Disclosure of Invention
The present application is proposed to solve the above-mentioned technical problems. The embodiment of the application provides a material quality data traceability management method based on a block chain technology, a material quality data traceability management system based on the block chain technology and electronic equipment, aiming at the characteristic that a block chain is not changeable, the material quality data to be managed is accurately identified and classified, so that the type of the material quality data to be managed is accurately standardized, and the follow-up material quality data can be called and used conveniently. Specifically, the method detects the impact resistance of the building material based on deep learning computer vision to identify and classify the quality detection data of the building material, and then stores and manages the detected result by utilizing the non-tamper property of the block chain to ensure the safety and convenience of data management, thereby ensuring the safety of the building engineering.
According to one aspect of the present application, there is provided a material quality data traceability management method based on a blockchain technology, comprising:
acquiring an image of the building material block after the impact test;
inputting the image into a depth convolution neural network to obtain an initial feature map;
determining a region in the initial feature map corresponding to the impacted location as a region of interest based on the location in the image at which the piece of building material was impacted;
applying a mask to the positions of the regions except the region of interest in the initial feature map to obtain a mask feature map and passing the mask feature map through a plurality of convolutional layers to obtain an attention feature map;
respectively calculating a first distance and a second distance between a corresponding first sub-feature map of the region of interest in the initial feature map and a corresponding second sub-feature map of the neighborhood part of the region of interest in the initial feature map and the attention feature map;
for the initial feature map, weighting the feature value of each position of the first sub-feature map and the second sub-feature map by taking the first distance and the second distance as weights respectively to obtain a final feature map;
fusing the final feature map and the attention feature map to obtain a classification feature map;
passing the classification feature map through a classifier to obtain a classification result, wherein the classification result indicates whether the impact resistance of the building material block meets a predetermined standard; and
storing the classification result in a corresponding block of a block chain structure.
In the above method for tracing and managing material quality data based on the blockchain technique, determining a region in the initial feature map corresponding to the impacted position as a region of interest based on the position where the block of building material is impacted in the image includes: identifying a location in the image where the piece of building material was impacted with a candidate box; and mapping the position of the candidate frame in the image to the initial feature map to obtain the region of interest.
In the above method for tracing and managing material quality data based on the block chain technology, the first distance and the second distance are cosine distances.
In the above method for tracing and managing material quality data based on the blockchain technology, fusing the final feature map and the attention feature map to obtain a classification feature map, including: and calculating the mean value of the feature values of all the positions in the final feature map and the attention feature map to obtain the classification feature map.
In the above method for tracing and managing material quality data based on the blockchain technology, the step of passing the classification feature map through a classifier to obtain a classification result includes: passing the classified feature map through one or more fully connected layers to obtain a classified feature vector; and inputting the classification feature vector into a Softmax classification function to obtain the classification result.
In the above method for tracing and managing material quality data based on the blockchain technology, the blockchain structure is a federation chain.
According to another aspect of the present application, there is provided a material quality data traceability management system based on a blockchain technology, comprising:
an image acquisition unit for acquiring an image of the building material block after the impact test;
an initial feature map generation unit, configured to input the image obtained by the image obtaining unit into a deep convolutional neural network to obtain an initial feature map;
a region-of-interest determining unit configured to determine, as a region of interest, a region corresponding to the impacted position in the initial feature map obtained by the initial feature map generating unit, based on the position in the image obtained by the image obtaining unit at which the piece of building material is impacted;
an attention feature map generation unit configured to apply a mask to positions of regions in the initial feature map obtained by the initial feature map generation unit other than the region of interest obtained by the image region-of-interest determination unit to obtain a mask feature map and pass the mask feature map through a plurality of convolution layers to obtain an attention feature map;
a distance calculating unit configured to calculate a first distance and a second distance between a corresponding first sub-feature map of the region of interest obtained by the region of interest determining unit in the initial feature map obtained by the initial feature map generating unit and a corresponding second sub-feature map of the neighborhood portion of the region of interest obtained by the region of interest determining unit in the initial feature map obtained by the initial feature map generating unit and the attention feature map obtained by the attention feature map generating unit, respectively;
a final feature map generating unit configured to weight, with respect to the initial feature map obtained by the initial feature map generating unit, feature values of each position of the first sub-feature map obtained by the distance calculating unit and the second sub-feature map obtained by the distance calculating unit, respectively, with the first distance obtained by the distance calculating unit and the second distance obtained by the distance calculating unit as weights, so as to obtain a final feature map;
a classification feature map generation unit configured to fuse the final feature map obtained by the final feature map generation unit and the attention feature map obtained by the attention feature map generation unit to obtain a classification feature map;
a classification result generating unit, configured to pass the classification feature map obtained by the classification feature map generating unit through a classifier to obtain a classification result, where the classification result indicates whether the impact resistance of the building material block meets a predetermined standard; and
a storage unit, configured to store the classification result obtained by the classification result generation unit in a corresponding block of a block chain structure.
In the above system for tracing and managing material quality data based on the blockchain technique, the unit for determining a region of interest includes: a candidate box identification subunit for identifying, with a candidate box, a location in the image where the piece of building material was impacted; and a region-of-interest generating subunit, configured to map, into the initial feature map, the position of the candidate frame in the image, which is obtained by the candidate frame identifying subunit, so as to obtain the region of interest.
In the above system for tracing to the source of the material quality data based on the block chain technology, the first distance and the second distance are cosine distances.
In the above system for tracing and managing material quality data based on the blockchain technology, the classification feature map generating unit is further configured to: and calculating the mean value of the feature values of all the positions in the final feature map and the attention feature map to obtain the classification feature map.
In the above system for tracing and managing material quality data based on the blockchain technology, the classification result generating unit includes: the classification feature vector generation subunit is used for enabling the classification feature map to pass through one or more full-connection layers to obtain a classification feature vector; and a classification result calculation subunit configured to input the classification feature vector obtained by the classification feature vector generation subunit into a Softmax classification function to obtain the classification result.
In the above-mentioned material quality data traceability management system based on the blockchain technology, the blockchain structure is a federation chain.
According to still another aspect of the present application, there is provided an electronic apparatus including: a processor; and a memory having stored therein computer program instructions which, when executed by the processor, cause the processor to perform the method of traceability management of material quality data based on blockchain techniques as described above.
Compared with the prior art, the embodiment of the application provides a material quality data traceability management method based on a blockchain technology, a material quality data traceability management system based on the blockchain technology and an electronic device, aiming at the characteristic that a blockchain cannot be changed, the material quality data to be managed is accurately identified and classified, so that the type of the material quality data to be managed is accurately standardized, and the follow-up material quality data can be called and used conveniently. Specifically, the method detects the impact resistance of the building material based on deep learning computer vision to identify and classify the quality detection data of the building material, and then stores and manages the detected result by utilizing the non-tamper property of the block chain to ensure the safety and convenience of data management, thereby ensuring the safety of the building engineering.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing in more detail embodiments of the present application with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings, like reference numbers generally represent like parts or steps.
Fig. 1 is a block chain architecture according to an embodiment of the present application.
Fig. 2 is an application scenario diagram of a traceability management method for material quality data based on a blockchain technology according to an embodiment of the present application.
Fig. 3 is a flowchart of a traceability management method of material quality data based on a blockchain technique according to an embodiment of the present application.
Fig. 4 is a schematic system architecture diagram of a traceability management method of material quality data based on a blockchain technology according to an embodiment of the present application.
Fig. 5 is a flowchart of determining, in the method for tracing and managing material quality data based on the blockchain technique according to the embodiment of the present application, an area in the initial feature map corresponding to an impacted position as an area of interest based on the impacted position of the block of building material in the image.
Fig. 6 is a flowchart of passing the classification feature map through a classifier to obtain a classification result in the traceability management method of material quality data based on the blockchain technology according to the embodiment of the present application.
Fig. 7 is a block diagram of a traceability management system of material quality data based on a blockchain technique according to an embodiment of the present application.
Fig. 8 is a block diagram of a region of interest determination unit in a block chain technology-based material quality data traceability management system according to an embodiment of the present application.
Fig. 9 is a block diagram of a classification result generation unit in the material quality data traceability management system based on the blockchain technology according to an embodiment of the present application.
Fig. 10 is a block diagram of an electronic device according to an embodiment of the application.
Detailed Description
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be understood that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and that the present application is not limited by the example embodiments described herein.
Block chain architecture overview
Fig. 1 is a block chain architecture according to an embodiment of the present application. As shown in fig. 1, the material quality data based on the blockchain technology according to the embodiment of the present application employs a typical blockchain architecture, and the material quality data, for example, P1, P2, …, Pn (impact resistance, abrasion resistance, bending strength, deformability, etc.) is stored in each of the memory blocks B1, B2, …, Bn configured in a blockchain.
Of course, it will be understood by those skilled in the art that different types of material quality data may be stored separately in separate blocks, e.g., one block dedicated to storing impact resistance data for material quality and another block dedicated to storing wear resistance data for material quality.
According to a typical blockchain storage architecture, each block B1, B2, …, Bn includes pointers H1, H2, …, Hn and data portions D1, D2, …, Dn. The pointers H1, H2, …, Hn may be various types of hash pointers, such as SHA-256 hash functions commonly used in blockchain storage architectures, that point to the last chunk.
In the embodiment of the present application, the value of the hash pointer of the next chunk is based on the value of the hash pointer of the previous chunk and the hash function value of the data portion, for example, H2 ═ H1 × H (D1), and H (D1) represents the hash function value of the data portion D1. The value of the hash pointer for the first chunk may be a random value. In this way, any modification to the portion of data within a block will react on the value of the hash pointer of the next block and further change the values of the hash pointers of all subsequent blocks, making modifications to the portion of data virtually impossible.
Also, in each data portion D1, D2, …, Dn, the hash function value for that data portion may be based on a hash function value generated separately for each type of material quality data in that data portion. For example, all impact resistance data in the data portion may be stored in a hash pointer based data structure of a merkel tree, thereby facilitating the backtracking of specific material quality data through the hash pointer and establishing appropriate membership between the respective material quality data.
Here, those skilled in the art can understand that the material quality data based on the blockchain technology according to the embodiment of the present application may adopt any general blockchain architecture, and the embodiment of the present application is not intended to limit the specific implementation of the blockchain architecture.
Moreover, in the embodiment of the present application, the blockchain preferably adopts a private chain or a federation chain, so as to facilitate distributed storage management of the material quality data inside a security service provider or a company or an enterprise of a security service provider federation, and accordingly, each storage block for storing the material quality data may be configured in advance without being generated based on a consensus algorithm, so that consumption of computing resources caused by the consensus algorithm may be avoided.
That is to say, the blockchain architecture of the material quality data based on the blockchain technology according to the embodiment of the present application focuses on storage management of the material quality data, and does not relate to a value transfer function based on the blockchain like electronic money, so that the blockchain architecture can be configured in advance in a cloud by a management department inside a company or an enterprise, and accessed from a terminal by each technical department, and performs uploading of a security rule file, and performs unified storage and management in the cloud. Therefore, since the technical departments are likely to be distributed in different geographic locations, the application of the blockchain architecture can conveniently realize the distributed storage of the security rule file.
On the other hand, each block in the block chain architecture according to the embodiment of the present application may also be associated with a block of the public chain, so that each block has time stamp information corresponding to the associated block of the public chain. Thus, the chronological attribute of each block in the block chain can be utilized when information requiring a temporal attribute, such as the sampling time of the material quality data, needs to be recorded to determine whether the material quality data is an earlier version.
Overview of a scene
As described above, for the building material, the impact resistance is an important data for evaluating the quality of the material, and since the safety of the building engineering is directly concerned, a very strict management system and a quality data traceability mechanism need to be established. In addition, the quality detection of the building materials not only occurs in laboratories, but also can be performed in places such as building sites, so that the data sources are numerous, the problems that the data is repeated for many times easily in the process, the data is artificially and maliciously tampered and the like easily occur, and the challenge is brought to data management.
The applicant of the present application considers that the block chain technique has great advantages in handling distributed data storage and management, and can play a key role in data traceability management due to the non-tamper property of the stored data, so that the above technical problems can be well solved if the block chain technique is applied to traceability management of quality data of building materials.
Also, the applicant of the present application considers that, when applying the blockchain technique to the traceability management of the quality data of the building material, due to the non-modifiable nature of the data thereof, it is necessary to obtain an accurate detection index for the impact resistance of the building material, such as concrete. However, at present, especially in construction sites such as construction sites, the impact resistance of the building materials is usually detected by manual observation, which obviously is not favorable for obtaining accurate detection results.
Therefore, the applicant of the present application further considers the use of computer vision techniques based on deep learning instead of manual observation to check the impact resistance of the building material. That is, by acquiring an image of the building material block after the impact test, and extracting high-dimensional features of the image via a convolutional neural network, a classification result is finally obtained by a classifier based on the high-dimensional features. Furthermore, considering that the high-dimensional image features of the impacted area of the building material block need to be focused on the high-dimensional image features of the image of the impacted building material block, in the embodiment of the present application, the high-dimensional image features of the area are focused on by a focusing mechanism.
In addition, since the current classifier usually includes one or more fully connected layers, in the process of fitting the feature map through the fully connected layers, in addition to the high-dimensional image features of the impacted area of the building material block as described above, the image features of the neighborhood of the building material block need to be considered to some extent, so in the embodiment of the present application, in addition to the high-dimensional image features of the key area, the neighborhood of the building material block is also appropriately processed based on the attention result.
Specifically, after obtaining the initial feature map, an attention map is first obtained by determining a region of interest in the initial feature map based on the impact position in the input image, and by applying a mask to the position of the feature map outside the region of interest and then passing through a plurality of convolution layers. Then, the distance between the attention map and the first sub-feature map and the second sub-feature map corresponding to the region of interest and the neighborhood part thereof, respectively, is calculated, and is denoted as d1 and d2, where the size of the neighborhood part of the region of interest, i.e. two values in the image width and height directions, can be trained in the training process as a hyper-parameter. Then, the feature value of each position of the region of interest and its neighborhood is weighted with d1 and d2 as weights, respectively, to obtain a final feature map, that is, the overall proportional relationship between the distribution of the feature values of the region of interest and its neighborhood in the final feature map is adjusted.
And then, fusing the final characteristic diagram with the attention diagram, obtaining a classification result through a classifier, wherein the classification result represents whether the impact resistance of the building material block meets a preset standard or not, and storing the classification result into a corresponding block in the block chain architecture, thereby realizing the traceability management of the quality data of the building material.
Based on this, the present application provides a material quality data traceability management method based on a block chain technology, which includes: acquiring an image of the building material block after the impact test; inputting the image into a depth convolution neural network to obtain an initial feature map; determining a region in the initial feature map corresponding to the impacted location as a region of interest based on the location in the image at which the piece of building material was impacted; applying a mask to the positions of the regions except the region of interest in the initial feature map to obtain a mask feature map and passing the mask feature map through a plurality of convolutional layers to obtain an attention feature map; respectively calculating a first distance and a second distance between a corresponding first sub-feature map of the region of interest in the initial feature map and a corresponding second sub-feature map of the neighborhood part of the region of interest in the initial feature map and the attention feature map; for the initial feature map, weighting the feature value of each position of the first sub-feature map and the second sub-feature map by taking the first distance and the second distance as weights respectively to obtain a final feature map; fusing the final feature map and the attention feature map to obtain a classification feature map; passing the classification feature map through a classifier to obtain a classification result, wherein the classification result indicates whether the impact resistance of the building material block meets a predetermined standard; and storing the classification result in a corresponding block of a block link structure.
Fig. 2 illustrates an application scenario of a traceability management method for material quality data based on a blockchain technology according to an embodiment of the present application. As shown in fig. 2, in this application scenario, an image of a building material block after impact testing acquired by a camera (e.g., C as illustrated in fig. 2) is first acquired, and then the image is input into a server (e.g., cloud server S as illustrated in fig. 2) deployed with a material quality data traceability management algorithm based on a blockchain technique, wherein the server is capable of processing the acquired image with the material quality data traceability management algorithm based on the blockchain technique to generate a classification result for indicating whether the impact resistance of the building material block meets a predetermined criterion, and storing the material quality data of the building material block in a blockchain architecture (e.g., T as illustrated in fig. 2) based on the classification result.
Having described the general principles of the present application, various non-limiting embodiments of the present application will now be described with reference to the accompanying drawings.
Exemplary method
Fig. 3 illustrates a flowchart of a traceability management method of material quality data based on a blockchain technology according to an embodiment of the present application. As shown in fig. 3, a method for tracing and managing material quality data based on a blockchain technology according to an embodiment of the present application includes: s110, acquiring an image of the building material block subjected to the impact test; s120, inputting the image into a depth convolution neural network to obtain an initial feature map; s130, determining a region corresponding to the impacted position in the initial feature map as a region of interest based on the impacted position of the building material block in the image; s140, applying a mask to the positions of the regions except the region of interest in the initial feature map to obtain a mask feature map, and enabling the mask feature map to pass through a plurality of convolution layers to obtain an attention feature map; s150, respectively calculating a first distance and a second distance between a corresponding first sub-feature map of the region of interest in the initial feature map and a corresponding second sub-feature map of the neighborhood part of the region of interest in the initial feature map and the attention feature map; s160, weighting the feature value of each position of the first sub-feature map and the second sub-feature map by taking the first distance and the second distance as weights respectively for the initial feature map to obtain a final feature map; s170, fusing the final feature map and the attention feature map to obtain a classification feature map; s180, enabling the classification characteristic diagram to pass through a classifier to obtain a classification result, wherein the classification result represents whether the impact resistance of the building material block meets a preset standard or not; and S190, storing the classification result in a corresponding block of a block link structure.
Fig. 4 is a schematic system architecture diagram illustrating a traceability management method of material quality data based on a blockchain technique according to an embodiment of the present application. As shown IN fig. 4, IN the network architecture of the block chain technology-based material quality data traceability management method, an acquired image of a building material block after impact testing (e.g., IN0 as illustrated IN fig. 4) is first input into a deep convolutional neural network (e.g., CNN as illustrated IN fig. 4) to obtain an initial feature map (e.g., Fi as illustrated IN fig. 4); then, based on the position in the image where the piece of building material is impacted, determining a region in the initial feature map corresponding to the impacted position as a region of interest (e.g., a ROI as illustrated in fig. 4); then, applying a mask to the positions of the regions of the initial feature map except the region of interest to obtain a mask feature map (e.g., Fm as illustrated in fig. 4) and passing the mask feature map through a plurality of convolutional layers (e.g., Cl as illustrated in fig. 4) to obtain an attention feature map (e.g., Fa as illustrated in fig. 4); next, respectively calculating a first distance (e.g., D1 as illustrated in fig. 4) and a second distance (e.g., D2 as illustrated in fig. 4) between a corresponding first sub-feature map of the region of interest in the initial feature map (e.g., F1 as illustrated in fig. 4) and a corresponding second sub-feature map of the neighborhood portion of the region of interest in the initial feature map (e.g., F2 as illustrated in fig. 4) and the attention feature map; then, for the initial feature map, weighting feature values of each position of the first sub-feature map and the second sub-feature map with the first distance and the second distance as weights, respectively, to obtain a final feature map (e.g., Ff as illustrated in fig. 4); then, fusing the final feature map and the attention feature map to obtain a classification feature map (e.g., Fc as illustrated in fig. 4); then, passing the classification feature map through a classifier (e.g., a classifier as illustrated in fig. 4) to obtain a classification result, which indicates whether the impact resistance of the piece of building material meets a predetermined criterion; finally, the classification results are stored in the corresponding blocks of a block-chain structure (e.g., T as illustrated in fig. 4).
In step S110, an image of the impact-tested piece of building material is acquired. As described above, when the blockchain technique is applied to the traceability management of the quality data of the building material, due to the non-modifiable characteristic of the data, it is necessary to obtain an accurate detection index for the impact resistance of the building material, such as concrete. Specifically, in the technical scheme of the application, the computer vision technology based on deep learning is adopted to replace manual observation to detect the impact resistance of the building material, that is, the computer vision technology is used to convert the impact resistance of the building material detected by manual observation into intelligent computer detection, so that the detection result is more accurate.
Specifically, in the embodiment of the present application, an image of the building material block after the impact test may be acquired by the camera. It will be appreciated by a person skilled in the art that during the impact of a piece of building material, the piece of building material to be detected is impacted with a hammer head perpendicular to the piece of building material, and accordingly the material quality property of the piece of building material can be represented on the basis of the image characteristics of the piece of building material after impact.
In step S120, the image is input to a deep convolutional neural network to obtain an initial feature map. That is, the obtained image of the building block after the impact test is processed by a deep convolutional neural network to extract a feature distribution representation of local features in the building block image in a high-dimensional space. That is, a deep convolutional neural network based on deep learning is utilized to extract the feature representation of the post-impact image of the block of building material in a high-dimensional hidden space.
Those skilled in the art will appreciate that the deep convolutional neural network has excellent performance in extracting local spatial features of an image. In one particular example of the present application, the convolutional neural network may be implemented as a deep residual network, e.g., ResNet 150. Compared with the traditional convolutional neural network, the deep residual error network is an optimized network structure provided on the basis of the traditional convolutional neural network, and mainly solves the problem that the gradient disappears in the training process. The depth residual error network introduces a residual error network structure, the network layer can be made deeper through the residual error network structure, and the problem of gradient disappearance can not occur. The residual error network uses the cross-layer link thought of a high-speed network for reference, breaks through the convention that the traditional neural network only can provide N layers as input from the input layer of the N-1 layer, enables the output of a certain layer to directly cross several layers as the input of the later layer, and has the significance of providing a new direction for the difficult problem that the error rate of the whole learning model is not reduced and inversely increased by superposing multiple layers of networks.
The convolutional neural network includes a convolutional layer, a pooling layer, and an activation layer in its network construction. Specifically, the process of passing the image of the block of building material through a depth convolution neural network to obtain a feature map corresponding to the image of the block of building material includes: firstly, the building material block image passes through the convolution layer to carry out convolution processing on the building material block image so as to generate a convolution characteristic map. Here, by performing convolution processing on the building material block image, data dimensionality reduction on the building material block image and extraction of features in the building material block image, which are matched with a convolution kernel, can be achieved. And then activating the convolution characteristic map by a nonlinear activation function to obtain an activation characteristic map, wherein the characterization capability of the convolution neural network can be enhanced through the activation processing of the activation layer. Then, the activation characteristic map is subjected to pooling processing through a pooling layer to generate a pooled characteristic map. Here, the essence of the pooling process is "down-sampling", i.e., the data can be further reduced in dimension by pooling the activation feature map and useful information in the activation feature map can be retained, thereby enhancing the generalization processing capability of the convolutional neural network. Here, in the present embodiment, the feature map may be selected from any one of the convolution feature map, the pooling feature map, and the activation feature map.
In step S130, based on the position in the image where the piece of building material was impacted, a region in the initial feature map corresponding to the impacted position is determined as a region of interest. It will be appreciated that of the high dimensional features of the image of the block of building material after impact, the high dimensional image features of the impacted region of the block of building material need to be of great concern and therefore need to be taken into account by a mechanism of attention.
Specifically, in the embodiment of the present application, determining, as a region of interest, a region in the initial feature map corresponding to the impacted position based on the position in the image where the piece of building material is impacted, includes: firstly, identifying a position in the image where the piece of building material is impacted with a candidate frame; then, the position of the candidate frame in the image is mapped into the initial feature map to obtain the region of interest. That is, the region of interest in the feature map is determined based on the location of the candidate box in the source image region. Here, the characteristic that the convolutional neural network keeps the spatial mapping position unchanged when extracting the features is fully utilized, so after the position of the candidate frame in the image is determined, the position of the region of interest in the initial feature map can be determined based on the position of the candidate frame in the image to obtain the region of interest.
Fig. 5 illustrates a flowchart of determining, in a material quality data traceability management method based on a blockchain technique according to an embodiment of the present application, a region in the initial feature map corresponding to an impacted position as a region of interest based on the impacted position of the block of building material in the image. As shown in fig. 5, in the embodiment of the present application, determining a region in the initial feature map corresponding to the impacted position as a region of interest based on the position of the impacted position of the piece of building material in the image includes: s210, identifying a position of the building material block impacted in the image by a candidate frame; and S220, mapping the position of the candidate frame in the image to the initial feature map to obtain the region of interest.
In step S140, a mask is applied to the positions of the regions of the initial feature map except the region of interest to obtain a mask feature map, and the mask feature map is passed through a plurality of convolutional layers to obtain an attention feature map. That is, an attention feature map is obtained by applying a mask to locations of the feature map outside the region of interest and passing through a plurality of convolutional layers, wherein the attention feature map focuses on image features of non-impact regions in the piece of building material.
In step S150, a first distance and a second distance between a corresponding first sub-feature map of the region of interest in the initial feature map and a corresponding second sub-feature map of the neighborhood portion of the region of interest in the initial feature map and the attention feature map are respectively calculated. Here, since the current classifier usually includes one or more fully connected layers, in the process of fitting the feature map through the fully connected layers, in addition to the high-dimensional image features of the impacted region of the building material block as described above, the image features of its neighborhood need to be considered to some extent, so in the embodiment of the present application, in addition to the high-dimensional image features of the key region, the neighborhood is also appropriately processed based on the attention result.
That is, in addition to focusing on the location of the impacted area in the piece of building material (i.e. the region of interest, or the first sub-feature map), it is also necessary to focus on the transition area of the impacted area to a completely non-impacted area (i.e. the second sub-feature map) in order to improve the accuracy of the classification of the material quality of the piece of building material by both.
Specifically, in this implementation, the distances between the first sub-feature map and the second sub-feature map corresponding to the region of interest and the neighborhood thereof, respectively, and the attention map are calculated, denoted as d1 and d2, respectively, where the sizes of the neighborhood of the region of interest, i.e., two values in the image width and height directions, may be trained as the hyper-parameters in the training process. In a physical sense, d1 represents the associated feature between the first sub-feature map and the attention map in a high-dimensional hidden space, and d2 represents the associated feature between the second sub-feature map and the attention map in a high-dimensional hidden space.
In one implementation, the first distance and the second distance are set to be cosine distances, i.e., d1 represents the degree of similarity between the first sub-feature map and the attention map in the high-dimensional implicit space, and d2 represents the degree of similarity between the second sub-feature map and the attention map in the high-dimensional implicit space. It will be appreciated by those skilled in the art that cosine similarity is often used to represent similarity between two feature vectors. The cosine similarity has a value range of [ -1, 1], and the similarity between two identical vectors is 1. If a distance-like representation is desired, the cosine distance is determined by subtracting the cosine similarity from 1. Therefore, the cosine distance has a value range of [0, 2], and the cosine distance of the same two vectors is 0.
In step S160, for the initial feature map, weighting feature values of each position of the first sub-feature map and the second sub-feature map respectively by using the first distance and the second distance as weights to obtain a final feature map. That is, the feature value of each position of the region of interest and its neighborhood is weighted with d1 and d2 as weights, respectively, to obtain a final feature map to adjust the overall proportional relationship between the distribution of the feature values of the region of interest and its neighborhood in the final feature map, so that the obtained result is more accurate.
In step S170, the final feature map and the attention feature map are fused to obtain a classification feature map. As described above, in the technical solution of the present application, when the blockchain technique is applied to the traceability management of the quality data of the building material, due to the non-modifiable characteristic of the data, it is necessary to obtain an accurate detection index for the impact resistance of the building material, such as concrete. That is, the final feature map and the attention feature map are fused to obtain a classification feature map, so that the obtained classification result for indicating whether the impact resistance of the piece of building material meets the predetermined criterion is more accurate.
Specifically, in the embodiment of the present application, fusing the final feature map and the attention feature map to obtain a classification feature map, including: and calculating the mean value of the feature values of all the positions in the final feature map and the attention feature map to obtain the classification feature map.
In step S180, the classification feature map is passed through a classifier to obtain a classification result, which indicates whether the impact resistance of the building material block meets a predetermined standard. As described above, when the blockchain technique is applied to the traceability management of the quality data of the building material, due to the non-modifiable characteristic of the data, it is necessary to obtain an accurate detection index for the impact resistance of the building material, such as concrete. However, at present, especially in construction sites such as construction sites, the impact resistance of the building materials is usually detected by manual observation, which obviously is not favorable for obtaining accurate detection results. Therefore, there is a need to convert the detection of the impact resistance of building materials into a classification problem based on high-dimensional image features.
Specifically, in the embodiment of the present application, passing the classification feature map through a classifier to obtain a classification result includes: firstly, the classification feature map is passed through one or more full-connection layers to obtain a classification feature vector, that is, firstly, the classification feature map is encoded by one or more full-connection layers to fully utilize the information of each position in the classification feature map to obtain the classification feature vector; then, the classification feature vector is input into a Softmax classification function to obtain the classification result, that is, the classification feature vector is input into the Softmax classification function to obtain probability values of the classification feature vector belonging to the classification labels, and then the classification result is determined based on the probability values.
Fig. 6 is a flowchart illustrating that the classification feature map passes through a classifier to obtain a classification result in the traceability management method of material quality data based on the blockchain technology according to an embodiment of the present application. As shown in fig. 6, in the embodiment of the present application, passing the classification feature map through a classifier to obtain a classification result includes: s310, enabling the classification feature map to pass through one or more full-connection layers to obtain a classification feature vector; and S320, inputting the classification feature vector into a Softmax classification function to obtain the classification result.
In step S190, the classification result is stored in the corresponding block of the block chain structure. It should be understood that, since the data stored in the blockchain technology has non-tamper-ability, which can play a key role in data traceability management, in the technical solution of the present application, the blockchain technology is applied to traceability management of the quality data of the building material, so that management of building material quality detection is more orderly and convenient.
In summary, the traceability management method of material quality data based on the block chain technology is clarified based on the embodiments of the present application, which detects the impact resistance of the building material based on deep learning computer vision to obtain an accurate detection result, and thus stores and manages the detection result by utilizing the non-removable property of the block chain to ensure the safety and convenience of data management, and further can ensure the safety of the building engineering.
Exemplary System
Fig. 7 illustrates a block diagram of a material quality data traceability management system based on a blockchain technique according to an embodiment of the present application. As shown in fig. 7, a traceability management system 700 for material quality data based on blockchain technology according to an embodiment of the present application includes: an image acquisition unit 710 for acquiring an image of the building material block after the impact test; an initial feature map generating unit 720, configured to input the image obtained by the image obtaining unit 710 into a deep convolutional neural network to obtain an initial feature map; a region-of-interest determining unit 730, configured to determine, as a region of interest, a region corresponding to the impacted position in the initial feature map obtained by the initial feature map generating unit 720, based on the position where the piece of building material is impacted in the image obtained by the image obtaining unit 710; an attention feature map generating unit 740, configured to apply a mask to positions of regions in the initial feature map obtained by the initial feature map generating unit 720 except the region of interest obtained by the image region of interest determining unit 730 to obtain a mask feature map, and pass the mask feature map through multiple convolutional layers to obtain an attention feature map; a distance calculating unit 750, configured to calculate a first distance and a second distance between a corresponding first sub-feature map of the region of interest obtained by the region of interest determining unit 730 in the initial feature map obtained by the initial feature map generating unit 720 and a corresponding second sub-feature map of a neighborhood portion of the region of interest obtained by the region of interest determining unit 730 in the initial feature map obtained by the initial feature map generating unit 720, and the attention feature map obtained by the attention feature map generating unit 740, respectively; a final feature map generating unit 760, configured to weight, with respect to the initial feature map obtained by the initial feature map generating unit 720, feature values of each position of the first sub-feature map obtained by the distance calculating unit 720 and the second sub-feature map obtained by the distance calculating unit 720 by using the first distance obtained by the distance calculating unit 750 and the second distance obtained by the distance calculating unit 750 as weights, respectively, to obtain a final feature map; a classification feature map generation unit 770, configured to fuse the final feature map obtained by the final feature map generation unit 760 and the attention feature map obtained by the attention feature map generation unit 740 to obtain a classification feature map; a classification result generating unit 780, configured to pass the classification feature map obtained by the classification feature map generating unit 770 through a classifier to obtain a classification result, where the classification result indicates whether the impact resistance of the building material block meets a predetermined criterion; and a storage unit 790 for storing the classification result obtained by the classification result generation unit 780 in a corresponding block of a block chain structure.
In an example, in the above-mentioned material quality data traceability management system 700 based on the blockchain technique, as shown in fig. 8, the region of interest determination unit 730 includes: a candidate box identification subunit 731 for identifying the position in the image where the piece of building material is impacted with a candidate box; and a region-of-interest generating subunit 732, configured to map the position of the candidate frame in the image, obtained by the candidate frame identifying subunit 731, into the initial feature map to obtain the region of interest.
In one example, in the above-described material quality data traceability management system 700 based on a block chain technique, the first distance and the second distance are cosine distances.
In an example, in the above-mentioned material quality data traceability management system 700 based on the blockchain technique, the classification feature map generating unit 770 is further configured to: and calculating the mean value of the feature values of all the positions in the final feature map and the attention feature map to obtain the classification feature map.
In an example, in the above-mentioned material quality data traceability management system 700 based on the blockchain technique, as shown in fig. 9, the classification result generating unit 780 includes: a classification feature vector generation subunit 781, configured to pass the classification feature map through one or more fully connected layers to obtain a classification feature vector; and a classification result calculation subunit 782, configured to input the classification feature vector obtained by the classification feature vector generation subunit 781 into a Softmax classification function to obtain the classification result.
In one example, in the above block chain technology-based material quality data traceability management system 700, the block chain structure is a federation chain.
Here, it will be understood by those skilled in the art that the specific functions and operations of the respective units and modules in the above-described material quality data traceability management system 700 based on the blockchain technology have been described in detail in the above description of the material quality data traceability management method based on the blockchain technology with reference to fig. 1 to 6, and therefore, a repetitive description thereof will be omitted.
As described above, the traceability management system 700 for material quality data based on the blockchain technology according to the embodiment of the present application can be implemented in various terminal devices, such as a traceability management server for material quality data based on the blockchain technology. In one example, the material quality data traceability management system 700 based on the blockchain technology according to the embodiment of the present application can be integrated into a terminal device as a software module and/or a hardware module. For example, the traceability management system 700 for material quality data based on the blockchain technology may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the traceability management system 700 for material quality data based on the blockchain technology can also be one of many hardware modules of the terminal device.
Alternatively, in another example, the blockchain technology-based material quality data traceability management system 700 and the terminal device may be separate devices, and the blockchain technology-based material quality data traceability management system 700 may be connected to the terminal device through a wired and/or wireless network and transmit the interactive information according to an agreed data format.
Exemplary electronic device
Next, an electronic apparatus according to an embodiment of the present application is described with reference to fig. 10.
As shown in fig. 10, the electronic device 10 includes at least one processor 11 and at least one memory 12.
The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.
The memory 12 may include at least one computer program product that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc. At least one computer program instruction may be stored on the computer readable storage medium and executed by the processor 11 to implement the material quality data traceability management method based on the blockchain technology of the various embodiments of the present application described above and/or other desired functions. Various contents such as the first distance, the second distance, etc. may also be stored in the computer readable storage medium.
In one example, the electronic device 10 may further include: an input device 13 and an output device 14, which are interconnected by a bus system and/or other form of connection mechanism (not shown).
The input device 13 may include, for example, a keyboard, a mouse, and the like.
The output device 14 can output various information including the classification result to the outside. The output devices 14 may include, for example, a display, speakers, a printer, and a communication network and its connected remote output devices, among others.
Of course, for simplicity, only some of the components of the electronic device 10 relevant to the present application are shown in fig. 10, and components such as buses, input/output interfaces, and the like are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.

Claims (10)

1. A material quality data tracing management method based on a block chain technology is characterized by comprising the following steps:
acquiring an image of the building material block after the impact test;
inputting the image into a depth convolution neural network to obtain an initial feature map;
determining a region in the initial feature map corresponding to the impacted location as a region of interest based on the location in the image at which the piece of building material was impacted;
applying a mask to the positions of the regions except the region of interest in the initial feature map to obtain a mask feature map and passing the mask feature map through a plurality of convolutional layers to obtain an attention feature map;
respectively calculating a first distance and a second distance between a corresponding first sub-feature map of the region of interest in the initial feature map and a corresponding second sub-feature map of the neighborhood part of the region of interest in the initial feature map and the attention feature map;
for the initial feature map, weighting the feature value of each position of the first sub-feature map and the second sub-feature map by taking the first distance and the second distance as weights respectively to obtain a final feature map;
fusing the final feature map and the attention feature map to obtain a classification feature map;
passing the classification feature map through a classifier to obtain a classification result, wherein the classification result indicates whether the impact resistance of the building material block meets a predetermined standard; and
storing the classification result in a corresponding block of a block chain structure.
2. The method for traceability management of material quality data based on blockchain technology according to claim 1, wherein determining an area in the initial feature map corresponding to the impacted position as an area of interest based on the position of the impacted position of the block of building material in the image comprises:
identifying a location in the image where the piece of building material was impacted with a candidate box; and
and mapping the position of the candidate frame in the image into the initial feature map to obtain the region of interest.
3. The method for traceability management of material quality data based on block chain technology as claimed in claim 1, wherein said first distance and said second distance are cosine distances.
4. The method for traceability management of material quality data based on blockchain technology as claimed in claim 1, wherein fusing the final feature map and the attention feature map to obtain a classification feature map comprises:
and calculating the mean value of the feature values of all the positions in the final feature map and the attention feature map to obtain the classification feature map.
5. The method for traceability management of material quality data based on blockchain technology as claimed in claim 1, wherein passing the classification feature map through a classifier to obtain a classification result comprises:
passing the classified feature map through one or more fully connected layers to obtain a classified feature vector; and
inputting the classification feature vector into a Softmax classification function to obtain the classification result.
6. The method for traceability management of material quality data based on blockchain technology as claimed in claim 1, wherein the blockchain structure is a federation chain.
7. A traceability management system for material quality data based on a block chain technology is characterized by comprising:
an image acquisition unit for acquiring an image of the building material block after the impact test;
an initial feature map generation unit, configured to input the image obtained by the image obtaining unit into a deep convolutional neural network to obtain an initial feature map;
a region-of-interest determining unit configured to determine, as a region of interest, a region corresponding to the impacted position in the initial feature map obtained by the initial feature map generating unit, based on the position in the image obtained by the image obtaining unit at which the piece of building material is impacted;
an attention feature map generation unit configured to apply a mask to positions of regions in the initial feature map obtained by the initial feature map generation unit other than the region of interest obtained by the image region-of-interest determination unit to obtain a mask feature map and pass the mask feature map through a plurality of convolution layers to obtain an attention feature map;
a distance calculating unit configured to calculate a first distance and a second distance between a corresponding first sub-feature map of the region of interest obtained by the region of interest determining unit in the initial feature map obtained by the initial feature map generating unit and a corresponding second sub-feature map of the neighborhood portion of the region of interest obtained by the region of interest determining unit in the initial feature map obtained by the initial feature map generating unit and the attention feature map obtained by the attention feature map generating unit, respectively;
a final feature map generating unit configured to weight, with respect to the initial feature map obtained by the initial feature map generating unit, feature values of each position of the first sub-feature map obtained by the distance calculating unit and the second sub-feature map obtained by the distance calculating unit, respectively, with the first distance obtained by the distance calculating unit and the second distance obtained by the distance calculating unit as weights, so as to obtain a final feature map;
a classification feature map generation unit configured to fuse the final feature map obtained by the final feature map generation unit and the attention feature map obtained by the attention feature map generation unit to obtain a classification feature map;
a classification result generating unit, configured to pass the classification feature map obtained by the classification feature map generating unit through a classifier to obtain a classification result, where the classification result indicates whether the impact resistance of the building material block meets a predetermined standard; and
a storage unit, configured to store the classification result obtained by the classification result generation unit in a corresponding block of a block chain structure.
8. The traceability management system of material quality data based on a blockchain technique according to claim 7, wherein the region of interest determination unit comprises:
a candidate box identification subunit for identifying, with a candidate box, a location in the image where the piece of building material was impacted; and
a region-of-interest generating subunit, configured to map, into the initial feature map, the position of the candidate frame in the image, which is obtained by the candidate frame identifying subunit, so as to obtain the region of interest.
9. The traceability management system of material quality data based on the blockchain technology as claimed in claim 7, wherein the classification result generating unit comprises:
the classification feature vector generation subunit is used for enabling the classification feature map to pass through one or more full-connection layers to obtain a classification feature vector; and
a classification result calculation subunit configured to input the classification feature vector obtained by the classification feature vector generation subunit into a Softmax classification function to obtain the classification result.
10. An electronic device, comprising:
a processor; and
a memory having stored therein computer program instructions which, when executed by the processor, cause the processor to perform the method of traceability management of material quality data based on a blockchain technique according to any one of claims 1 to 6.
CN202110536020.0A 2021-05-17 2021-05-17 Material quality data tracing management method based on block chain technology Withdrawn CN113516631A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110536020.0A CN113516631A (en) 2021-05-17 2021-05-17 Material quality data tracing management method based on block chain technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110536020.0A CN113516631A (en) 2021-05-17 2021-05-17 Material quality data tracing management method based on block chain technology

Publications (1)

Publication Number Publication Date
CN113516631A true CN113516631A (en) 2021-10-19

Family

ID=78064428

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110536020.0A Withdrawn CN113516631A (en) 2021-05-17 2021-05-17 Material quality data tracing management method based on block chain technology

Country Status (1)

Country Link
CN (1) CN113516631A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114648646A (en) * 2022-05-20 2022-06-21 合肥英特灵达信息技术有限公司 Image classification method and device
CN116258947A (en) * 2023-03-07 2023-06-13 浙江研几网络科技股份有限公司 Industrial automatic processing method and system suitable for home customization industry
CN116797248A (en) * 2023-08-22 2023-09-22 厦门瞳景智能科技有限公司 Data traceability management method and system based on block chain

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114648646A (en) * 2022-05-20 2022-06-21 合肥英特灵达信息技术有限公司 Image classification method and device
CN116258947A (en) * 2023-03-07 2023-06-13 浙江研几网络科技股份有限公司 Industrial automatic processing method and system suitable for home customization industry
CN116258947B (en) * 2023-03-07 2023-08-18 浙江研几网络科技股份有限公司 Industrial automatic processing method and system suitable for home customization industry
CN116797248A (en) * 2023-08-22 2023-09-22 厦门瞳景智能科技有限公司 Data traceability management method and system based on block chain
CN116797248B (en) * 2023-08-22 2024-01-30 厦门瞳景智能科技有限公司 Data traceability management method and system based on block chain

Similar Documents

Publication Publication Date Title
CN113516631A (en) Material quality data tracing management method based on block chain technology
Arietta et al. City forensics: Using visual elements to predict non-visual city attributes
CN111818198B (en) Domain name detection method, domain name detection device, equipment and medium
CN111177507B (en) Method and device for processing multi-mark service
CN111626367A (en) Countermeasure sample detection method, apparatus, device and computer readable storage medium
CN116630100B (en) Travel data processing method, device, equipment and storage medium
Wang et al. Video object matching across multiple non-overlapping camera views based on multi-feature fusion and incremental learning
CN115456789A (en) Abnormal transaction detection method and system based on transaction pattern recognition
CN111221960A (en) Text detection method, similarity calculation method, model training method and device
JP2008065544A (en) Classifier and classification method
Lechgar et al. Detection of cities vehicle fleet using YOLO V2 and aerial images
Pavaskar et al. Real-time vehicle-type categorization and character extraction from the license plates
Ilina et al. Robustness study of a deep convolutional neural network for vehicle detection in aerial imagery
CN113011961B (en) Method, device, equipment and storage medium for monitoring risk of company-related information
CN111353514A (en) Model training method, image recognition method, device and terminal equipment
Sun et al. Vehicle classification approach based on the combined texture and shape features with a compressive DL
CN117217929A (en) Registered object risk identification method, device, computer equipment and storage medium
CN111738213B (en) Person attribute identification method and device, computer equipment and storage medium
CN114741697A (en) Malicious code classification method and device, electronic equipment and medium
Brunner et al. Leveraging semantic embeddings for safety-critical applications
CN114418767A (en) Transaction intention identification method and device
Fatkhulin et al. Analysis of the Basic Image Generation Methods by Neural Networks
Fadili et al. A one-stage modified Tiny-YOLOv3 method for Real time Moroccan license plate recognition
Dhar et al. Detecting deepfake images using deep convolutional neural network
Khripunov et al. Anomalies detection in social services data in the sphere of digital economy

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20211019