CN113901497A - Talent evaluation method based on block chain and federal learning technology - Google Patents
Talent evaluation method based on block chain and federal learning technology Download PDFInfo
- Publication number
- CN113901497A CN113901497A CN202111203201.8A CN202111203201A CN113901497A CN 113901497 A CN113901497 A CN 113901497A CN 202111203201 A CN202111203201 A CN 202111203201A CN 113901497 A CN113901497 A CN 113901497A
- Authority
- CN
- China
- Prior art keywords
- module
- block chain
- federal learning
- learning
- 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.)
- Pending
Links
Classifications
-
- 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
- G06F21/602—Providing cryptographic facilities or services
-
- 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
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- 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
- G06F21/64—Protecting data integrity, e.g. using checksums, certificates or signatures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Abstract
The invention provides a method for building a 1+ X certificate alliance chain, a cryptography operation module, a federal learning module, a small program, a storage module, an image processing input module, an image processing output module, a sound processing input module, a sound processing output module, a fingerprint identification module, an employment requirement and talent matching degree algorithm and an intelligent contract code based on a micro-banking FISCO-BCOS, an asymmetric key pair is generated by a cryptology operation module, a public key, a coded lock number, learning and practical training record types, purposes, ranges and owner information are registered in a block chain, assets and identity information are bound, performing double certification through CA, using block chain technology and federal learning technology, and equitably evaluating the occupation level of talents through a machine learning algorithm, and storing the federated machine learning model on the federated learning block chain, and carrying out whole-process recording and tracing on the data and the process of the machine learning model. The method has the advantages of accurate evaluation and cheating avoidance.
Description
Technical Field
The invention belongs to the field of computers, and particularly relates to a talent evaluation method based on a block chain and a federal learning technology.
Background
The novel innovative talent culture mode has multiple participation and multiple stages of culture process. Cross-organizational informational intercommunication is required, as well as multi-stage training records and full-range traceability. The method has the advantages that teaching cooperation and data sharing among different organizations are needed, involved parties are numerous, information systems are provided for the parties, trust relationships among the information systems and among different education implementation subjects are established in different learning, teaching and practical training scenes, a training and evaluation organization can call process data of real learning and practical training of multiple parties, real and reliable talent evaluation standards and models are established, evaluation of professional ability levels is given, and professional qualification certificates of corresponding levels are issued.
However, the existing credit learning network is only a academic database and provides a website query function, the organization of training evaluation is an enterprise, evaluation and setting of occupation qualification grade are not transparent, and the cheating phenomenon of selling certificates occurs at present, so that negative influence is caused on implementation of a 1+ X certificate system, and therefore a method capable of avoiding the selling certificates is needed in the existing market, and non-objective evaluation in artificial evaluation is avoided.
Disclosure of Invention
The invention aims to provide a talent evaluation method which is accurate in evaluation and avoids cheating and is based on a block chain and a federal learning technology, and the talent evaluation method is particularly suitable for a 1+ X certificate project.
The technical scheme of the invention is as follows: a talent evaluation method based on a block chain and a federal learning technology comprises the steps of building a 1+ X certificate alliance chain, a cryptography operation module, a federal learning module, a small program, a storage module, an image processing input module, an image processing output module, a sound processing input module, a sound processing output module, a fingerprint identification module, an employment requirement and talent matching degree algorithm and an intelligent contract code based on a micro-banking FISCO-BCOS;
generating an asymmetric key pair through a cryptology operation module, registering public keys, coded lock numbers, learning and practical training record types, purposes, ranges and owner information in a block chain, binding assets and identity information, and performing double authentication through CA;
issuing user data and use restriction to a block chain by adopting an intelligent contract format to write terms;
the federal learning server obtains the intelligent contract clause content by browsing the block chain transaction information;
setting a federal learning server at each block chain node, wherein the federal learning server has local data, the calculation is completed locally, only the calculation result is output, and the learning model and the data exchange information are also registered in the block chain;
the intelligent contract execution result record is synchronized to the intelligent trusted storage device;
the user obtains a key for the right to use the data, which may be for initiating a learning model calculation;
the alliance link points are automatically completed through contracts;
through a small program, a key is used for issuing an application to evaluate the own occupation grade;
the coded lock verifies the signature of the user through the cryptology operation module, and identifies the identity of the user;
and after the verification is passed, the logic control module drives the federal learning execution unit, and outputs an evaluation result to evaluate the professional ability, the post matching degree and the salary level.
Further, the hardware part comprises a storage unit, a video image input unit, a video image output unit, a fingerprint input unit, a sound input unit and a sound output unit.
Further, the federal learning software is updated through the nodes.
Further, the information is encrypted in the block chain by a Hash algorithm
The invention has the advantages and positive effects that:
1. when talent assessment is carried out by using a blockchain technology and a federal learning technology, a plurality of participants, schools, students, personnel selection units, training institutions and training evaluation organizations are involved, actual information islands are caused by data of all parties due to various reasons, the data relate to high privacy, the blockchain technology and the federal learning technology are fused and used on the premise of guaranteeing the privacy of users, all the participants and data owners of 1+ X certificates are added in the federal learning of talent assessment, the occupation level of talents is assessed through a machine learning algorithm, the fairness and the justice of talent assessment are guaranteed, the talent assessment efficiency is improved, the privacy data of users can be protected, and the information safety is improved.
2. The federated machine learning model and the original data index are stored on the federated learning block chain, and the whole process recording and tracing are carried out on the data and the process of the machine learning model, so that the safety of the data and the real-time tracking of the data are improved, and the process retrieval of inquiring the data and the data is facilitated.
3. The federal study mainly can solve information isolated island and train the model of talent evaluation by all parties together and adjust and optimize in real time on the premise of protecting the privacy of sensitive information. Data of all participants can be utilized through a technology called Federal Averaging, so that the talent evaluation model is continuously optimized. This process does not require the transmission of the respective data to a data center location. That is, federal averaging does not require data to be transmitted from any edge termination device to a central location. Through federal learning, the model on each server will be encrypted and uploaded to the cloud. Finally, all the encrypted models are aggregated into an encrypted global model, so that the cloud server cannot know the data or the models of each device, and the cloud aggregated model is still encrypted.
Detailed Description
A talent evaluation method based on a block chain and a federal learning technology comprises the steps of building a 1+ X certificate alliance chain, a cryptography operation module, a federal learning module, a small program, a storage module, an image processing input module, an image processing output module, a sound processing input module, a sound processing output module, a fingerprint identification module, an employment requirement and talent matching degree algorithm and an intelligent contract code based on a micro-banking FISCO-BCOS;
generating an asymmetric key pair through a cryptology operation module, registering public keys, coded lock numbers, learning and practical training record types, purposes, ranges and owner information in a block chain, binding assets and identity information, and performing double authentication through CA;
issuing user data and use restriction to a block chain by adopting an intelligent contract format to write terms;
the federal learning server obtains the intelligent contract clause content by browsing the block chain transaction information;
setting a federal learning server at each block chain node, wherein the federal learning server has local data, the calculation is completed locally, only the calculation result is output, and the learning model and the data exchange information are also registered in the block chain;
the intelligent contract execution result record is synchronized to the intelligent trusted storage device;
the user obtains a key for the right to use the data, which may be for initiating a learning model calculation;
the alliance link points are automatically completed through contracts;
through a small program, a key is used for issuing an application to evaluate the own occupation grade;
the coded lock verifies the signature of the user through the cryptology operation module, and identifies the identity of the user;
and after the verification is passed, the logic control module drives the federal learning execution unit, and outputs an evaluation result to evaluate the professional ability, the post matching degree and the salary level.
The hardware part comprises a storage unit, a video image input unit, a video image output unit, a fingerprint input unit, a sound input unit and a sound output unit.
The federal learning software is updated by the nodes.
The information is encrypted in the block chain by a Hash algorithm.
The working process of the example is as follows:
in the federal learning process, a matrix Di is set to represent data of the ith participant; let each row of the matrix Di represent a data sample and each column represents a specific data feature (feature). Also, some data sets may contain tag information. Let the feature space be X, the data label (label) space be Y, and denote the data sample ID or identity information space by I. The data labels are the academic scores or professional skill information of the students and evaluation standards set by all the parties; the feature space X, the data label space Y and the sample ID space I constitute a training data set (I, X, Y). The feature space and sample ID space of data owned by different parties may be different. In an application scenario, each party participates in evaluation model training, basic data samples are aligned, but data characteristics are different, so a segmentation learning mode is adopted, and a Deep Neural Network (DNN) is trained on a longitudinally divided data set on the basis of longitudinal federal learning.
The working process is as follows:
1) a user applet;
2) generating an asymmetric key pair through a cryptology operation module, registering information such as a public key, a coded lock number, learning and practical training record types, purposes, ranges and the like, an owner and the like in a block chain, and binding assets and identity information;
double authentication is performed by the CA.
3) The user issues the data and the use limit to a block chain for registration by writing terms in an intelligent contract format;
4) the federal learning server obtains the intelligent contract clause content by browsing the block chain transaction information;
5) each block chain node is provided with a federal learning server and local data, calculation is completed locally, only calculation results are output and data are not output, and learning models and data exchange information are also registered in a block chain;
6) the intelligent contract execution result records are synchronized to the intelligent trusted storage device.
7) The user obtains a "key" for the right to use the data, which may be for initiating learning model calculations.
8) The federal learning software is automatically updated, and all nodes of the alliance chain can be downloaded at any time and automatically completed through intelligent contracts.
9) The user can use the key to send an application to evaluate the own occupation grade through the small program;
10) the coded lock verifies the signature of the user through a cryptology operation module, and optionally identifies the identity of the user through a mode;
11) and after the verification is passed, the logic control module drives the federal learning execution unit, and outputs an evaluation result to evaluate the professional ability, the post matching degree and the salary level.
While one embodiment of the present invention has been described in detail, the description is only a preferred embodiment of the present invention and should not be taken as limiting the scope of the invention. All equivalent changes and modifications made within the scope of the present invention shall fall within the scope of the present invention.
Claims (4)
1. A talent evaluation method based on a block chain and a federal learning technology is characterized in that: the method comprises the steps of establishing a 1+ X certificate alliance chain based on the micro-banking FISCO-BCOS, a cryptography operation module, a federal learning module, a small program, a storage module, an image processing input module, an image processing output module, a sound processing input module, a sound processing output module, a fingerprint identification module, an employment requirement and talent matching degree algorithm and an intelligent contract code;
generating an asymmetric key pair through a cryptology operation module, registering public keys, coded lock numbers, learning and practical training record types, purposes, ranges and owner information in a block chain, binding assets and identity information, and performing double authentication through CA;
issuing user data and use restriction to a block chain by adopting an intelligent contract format to write terms;
the federal learning server obtains the intelligent contract clause content by browsing the block chain transaction information;
setting a federal learning server at each block chain node, wherein the federal learning server has local data, the calculation is completed locally, only the calculation result is output, and the learning model and the data exchange information are also registered in the block chain;
the intelligent contract execution result record is synchronized to the intelligent trusted storage device;
the user obtains a key for the right to use the data, which may be for initiating a learning model calculation;
the alliance link points are automatically completed through contracts;
through a small program, a key is used for issuing an application to evaluate the own occupation grade;
the coded lock verifies the signature of the user through the cryptology operation module, and identifies the identity of the user;
and after the verification is passed, the logic control module drives the federal learning execution unit, and outputs an evaluation result to evaluate the professional ability, the post matching degree and the salary level.
2. The talent evaluation method based on blockchain and federal learning techniques as claimed in claim 1, wherein: the hardware part comprises a storage unit, a video image input unit, a video image output unit, a fingerprint input unit, a sound input unit and a sound output unit.
3. The talent evaluation method based on blockchain and federal learning techniques as claimed in claim 1, wherein: the federal learning software is updated by the nodes.
4. The talent evaluation method based on blockchain and federal learning techniques as claimed in claim 1, wherein: the information is encrypted in the block chain by a Hash algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111203201.8A CN113901497A (en) | 2021-10-15 | 2021-10-15 | Talent evaluation method based on block chain and federal learning technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111203201.8A CN113901497A (en) | 2021-10-15 | 2021-10-15 | Talent evaluation method based on block chain and federal learning technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113901497A true CN113901497A (en) | 2022-01-07 |
Family
ID=79192282
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111203201.8A Pending CN113901497A (en) | 2021-10-15 | 2021-10-15 | Talent evaluation method based on block chain and federal learning technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113901497A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114331388A (en) * | 2022-02-08 | 2022-04-12 | 湖南红普创新科技发展有限公司 | Salary calculation method, device, equipment and storage medium based on federal learning |
| CN117217719A (en) * | 2023-11-07 | 2023-12-12 | 湖南海润天恒科技集团有限公司 | Talent information recruitment data intelligent management method and system based on big data |
-
2021
- 2021-10-15 CN CN202111203201.8A patent/CN113901497A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114331388A (en) * | 2022-02-08 | 2022-04-12 | 湖南红普创新科技发展有限公司 | Salary calculation method, device, equipment and storage medium based on federal learning |
| CN114331388B (en) * | 2022-02-08 | 2022-08-09 | 湖南红普创新科技发展有限公司 | Salary calculation method, device, equipment and storage medium based on federal learning |
| CN117217719A (en) * | 2023-11-07 | 2023-12-12 | 湖南海润天恒科技集团有限公司 | Talent information recruitment data intelligent management method and system based on big data |
| CN117217719B (en) * | 2023-11-07 | 2024-02-09 | 湖南海润天恒科技集团有限公司 | Talent information recruitment data intelligent management method and system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sun et al. | Application of blockchain technology in online education. | |
| US20190122161A1 (en) | Real-Time Skills-Based and Competency Assessment System and Method | |
| US10666425B2 (en) | Digital education record management method based on blockchain token technology | |
| CN113901497A (en) | Talent evaluation method based on block chain and federal learning technology | |
| CN108876113B (en) | Assessment management method, assessment management device, terminal equipment and assessment management system | |
| CN111768296A (en) | Block chain-based small and micro enterprise loan approval method and device | |
| CN110490776A (en) | A kind of study authentication method, device and electronic equipment based on block chain | |
| CN109801043A (en) | Life cycle learning records authentication device and authentication method based on block chain | |
| Hsu et al. | Design of an e-diploma system based on consortium blockchain and facial recognition | |
| CN110751585A (en) | Remote learning conversion system | |
| Korepin et al. | Improving supply chain reliability with blockchain technology | |
| Okoye | Strategies to minimize the effects of information security threats on business performance | |
| Sebrek | Open Access: Overlap in external technology search locations and the breadth of IPR assets: lessons from the Security Software Industry | |
| CN113657609B (en) | Data management method and system based on block chain and federation transfer learning | |
| CN113987060A (en) | Innovative entrepreneurship investment and convergence network platform based on block chain technology | |
| Cheng et al. | Stem education-career pathway for emerging forensic analytics: Innovative professional development in multimodal environments | |
| CN115631075A (en) | Master and resource training system based on block chain | |
| Zeroual et al. | A pedagogical orientation system based on blockchain technology and machine learning | |
| Malik et al. | Transforming the competencies of Artificial Intelligence to ensure the Cyber Threats: A Systemic Literture Review of Busniess Sectors | |
| CN113673234A (en) | Recruitment method and system based on block chain | |
| CN111209588A (en) | Teaching and cultivating management method and system based on block chain | |
| Desai | Infusing Blockchain in accounting curricula and practice: expectations, challenges, and strategies | |
| CN111709595A (en) | Method and system for allocating resources based on block chain technology | |
| TWM576703U (en) | Management system for financial records | |
| Lundström et al. | Generating Value Through Blockchain Technology: The Case of Trade Finance |
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 |