CN113326521A - Data source joint modeling method based on safe multi-party calculation - Google Patents
Data source joint modeling method based on safe multi-party calculation Download PDFInfo
- Publication number
- CN113326521A CN113326521A CN202110656136.8A CN202110656136A CN113326521A CN 113326521 A CN113326521 A CN 113326521A CN 202110656136 A CN202110656136 A CN 202110656136A CN 113326521 A CN113326521 A CN 113326521A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- model
- modeling method
- sends
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000004364 calculation method Methods 0.000 title claims description 11
- 238000004458 analytical method Methods 0.000 claims abstract description 24
- 230000005540 biological transmission Effects 0.000 claims abstract description 16
- 238000013500 data storage Methods 0.000 claims abstract description 8
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a data source joint modeling method based on safe multiparty computation, which comprises the following steps: s1, writing data in the first data input module and the second data input module, and encrypting the data through the first data input module; s2, the receiving module receives the encrypted data and simultaneously receives the public key sent by the public key module, and the decryption module decrypts the data through the public key; s3, the data center processing module processes the decrypted data and sends the processed data to the analysis unit; s4, the analysis unit analyzes the processed data and sends the data to the model generation module after the analysis is finished; s5, the model generation module generates a combined model according to the processed data, and the data storage module stores and backups the generated model; s6, the second encryption module encrypts the model, the transmission module sends the encrypted model to each company, and the private key module sends the private key through the transmission module.
Description
Technical Field
The invention relates to the technical field of modeling, in particular to a data source joint modeling method based on safe multi-party calculation.
Background
The joint prediction model simulates the operation process of an enterprise by applying an enterprise model, dynamically describes the characteristics of a normal financial enterprise and a troubled financial enterprise, classifies enterprise samples according to different characteristics and discrimination rules, requires a basic theoretical framework to effectively reflect and recognize the behavior characteristics and financial characteristics of different enterprises, and has the key point of accurately simulating the operation process of the enterprise, so that the joint prediction model requires a basic theoretical framework to effectively simulate the operation process of the enterprise by the framework, effectively reflect and recognize the behavior characteristics and financial characteristics of different enterprises, distinguishes enterprise samples according to the behavior characteristics and financial characteristics, overcomes the one-sidedness that the financial prediction model only uses financial indexes, dynamically simulates and reflects the aspects of the enterprise operation process, and can perform cooperative modeling between the enterprises, in data modeling, joint modeling is usually required due to the situations of insufficient modeling capability and the like, but in the traditional joint modeling, core data is generally required for modeling, so that data leakage is easily caused, and the threat to information security is caused.
Disclosure of Invention
The invention aims to provide a data source joint modeling method based on safe multi-party calculation so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: a data source joint modeling method based on safe multi-party calculation comprises the following steps:
s1, writing data in the first data input module and the second data input module, and encrypting the data through the first data input module;
s2, the receiving module receives the encrypted data and simultaneously receives the public key sent by the public key module, and the decryption module decrypts the data through the public key;
s3, the data center processing module processes the decrypted data and sends the processed data to the analysis unit;
s4, the analysis unit analyzes the processed data and sends the data to the model generation module after the analysis is finished;
s5, the model generation module generates a combined model according to the processed data, and the data storage module stores and backups the generated model;
s6, the second encryption module encrypts the model, the transmission module sends the encrypted model to each company, and the private key module sends the private key through the transmission module.
As a preferable scheme of the present invention, the encryption mode of the first encryption module in step S1 may be to obtain data locally for encryption, or to obtain data from a cloud for encryption.
As a preferred embodiment of the present invention, the decryption module in step S2 is an external device.
As a preferable scheme of the present invention, the data center processing module in step S3 performs superposition processing on the two sets of data, removes repeated and useless data, and sorts and orders the data.
As a preferable aspect of the present invention, the analysis unit includes a similarity module, a difference module, a correlation module, a loss module, and a gradient module, and the analysis unit in step S4 includes:
the similarity module carries out similarity analysis on the data and calculates similarity values among the data;
the difference degree module performs difference calculation on the data to obtain the difference size;
the relevancy module matches the data and analyzes the relevancy;
the loss module and the gradient module retrieve the data and comprehensively sequence the loss degree and the gradient of the data.
In a preferred embodiment of the present invention, the data storage module in step S5 is a mechanical hard disk.
As a preferable aspect of the present invention, the transmission module in step S6 is a wireless transmission module.
Compared with the prior art, the invention has the beneficial effects that: according to the invention, the data to be transmitted can be encrypted through the first encryption module, so that data leakage is avoided, the generated model can be encrypted again through the second encryption module, so that the safety is improved, the possibility of model leakage is further reduced, the data can be decrypted through the second encryption module, the data can be conveniently processed by the data center processing module, and the data can be analyzed through the similarity module, the difference module, the association module, the loss module and the gradient module, so that the time for the model generation module to produce the model is shorter.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
fig. 2 is a block diagram of the system of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, the present invention provides a technical solution: a data source joint modeling method based on safe multi-party calculation comprises the following steps:
s1, writing data in the first data input module and the second data input module, and encrypting the data through the first data input module;
s2, the receiving module receives the encrypted data and simultaneously receives the public key sent by the public key module, and the decryption module decrypts the data through the public key;
s3, the data center processing module processes the decrypted data and sends the processed data to the analysis unit;
s4, the analysis unit analyzes the processed data and sends the data to the model generation module after the analysis is finished;
s5, the model generation module generates a combined model according to the processed data, and the data storage module stores and backups the generated model;
s6, the second encryption module encrypts the model, the transmission module sends the encrypted model to each company, and the private key module sends the private key through the transmission module.
Further, the encryption mode of the first encryption module in step S1 may be to obtain data locally for encryption, or to obtain data from the cloud for encryption.
Further, the decryption module in step S2 is an external device, which can improve security and simplify the key management step.
Further, in step S3, the data center processing module performs superposition processing on the two sets of data, eliminates repeated and useless data, and sorts and orders the data.
Further, the analysis unit includes a similarity module, a difference module, a correlation module, a loss module and a gradient module, and the analysis unit in step S4 includes:
the similarity module carries out similarity analysis on the data and calculates similarity values among the data;
the difference degree module performs difference calculation on the data to obtain the difference size;
the relevancy module matches the data and analyzes the relevancy;
the loss module and the gradient module retrieve the data and comprehensively sequence the loss degree and the gradient of the data.
Further, the data storage module in step S5 is a mechanical hard disk.
Further, the transmission module in step S6 is a wireless transmission module.
Specifically, a first data input module and a second data input module write data in, a first encryption module obtains the data from the cloud for encryption, a receiving module receives the encrypted data and simultaneously receives a public key sent by a public key module, a decryption module decrypts the data through the public key, a data center processing module processes the decrypted data and sends the processed data to an analysis unit, a similarity module in the analysis unit analyzes the similarity of the data and calculates the similarity value between the data, a difference module performs differential calculation on the data to obtain the difference, a relevance module matches the data and analyzes the relevance, a loss module and a gradient module retrieve the data and comprehensively sort the loss and the gradient of the data, the data is sent to a model generation module after the analysis is finished, the model generation module generates a combined model according to the processed data, the data storage module stores and backups the generated model, the second encryption module encrypts the model, the transmission module sends the encrypted model to each company, and the private key module sends the private key through the transmission module.
In the description of the present invention, it is to be understood that the terms "coaxial", "bottom", "one end", "top", "middle", "other end", "upper", "one side", "top", "inner", "front", "center", "both ends", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, and do not indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention.
Furthermore, the terms "first", "second", "third", "fourth" are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated, whereby the features defined as "first", "second", "third", "fourth" may explicitly or implicitly include at least one such feature.
In the present invention, unless otherwise expressly specified or limited, the terms "mounted," "disposed," "connected," "secured," "screwed" and the like are to be construed broadly, e.g., as meaning fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; the terms may be directly connected or indirectly connected through an intermediate, and may be communication between two elements or interaction relationship between two elements, unless otherwise specifically limited, and the specific meaning of the terms in the present invention will be understood by those skilled in the art according to specific situations.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (7)
1. A data source joint modeling method based on safe multi-party calculation is characterized in that: the method comprises the following steps:
s1, writing data in the first data input module and the second data input module, and encrypting the data through the first data input module;
s2, the receiving module receives the encrypted data and simultaneously receives the public key sent by the public key module, and the decryption module decrypts the data through the public key;
s3, the data center processing module processes the decrypted data and sends the processed data to the analysis unit;
s4, the analysis unit analyzes the processed data and sends the data to the model generation module after the analysis is finished;
s5, the model generation module generates a combined model according to the processed data, and the data storage module stores and backups the generated model;
s6, the second encryption module encrypts the model, the transmission module sends the encrypted model to each company, and the private key module sends the private key through the transmission module.
2. The secure multiparty computing-based data source federation modeling method of claim 1, wherein: the encryption mode of the first encryption module in step S1 may be to obtain data locally for encryption, or to obtain data from the cloud for encryption.
3. The secure multiparty computing-based data source federation modeling method of claim 1, wherein: the decryption module in step S2 is an external device.
4. The secure multiparty computing-based data source federation modeling method of claim 1, wherein: the data center processing module in step S3 performs superposition processing on the two sets of data, eliminates repeated and useless data, and sorts and orders the data.
5. The secure multiparty computing-based data source federation modeling method of claim 1, wherein: the analysis unit includes a similarity module, a difference module, a correlation module, a loss module and a gradient module, and the analysis unit in step S4 includes:
the similarity module carries out similarity analysis on the data and calculates similarity values among the data;
the difference degree module performs difference calculation on the data to obtain the difference size;
the relevancy module matches the data and analyzes the relevancy;
the loss module and the gradient module retrieve the data and comprehensively sequence the loss degree and the gradient of the data.
6. The secure multiparty computing-based data source federation modeling method of claim 1, wherein: the data storage module in step S5 is a mechanical hard disk.
7. The secure multiparty computing-based data source federation modeling method of claim 1, wherein: the transmission module in step S6 is a wireless transmission module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110656136.8A CN113326521A (en) | 2021-06-11 | 2021-06-11 | Data source joint modeling method based on safe multi-party calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110656136.8A CN113326521A (en) | 2021-06-11 | 2021-06-11 | Data source joint modeling method based on safe multi-party calculation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113326521A true CN113326521A (en) | 2021-08-31 |
Family
ID=77420565
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110656136.8A Pending CN113326521A (en) | 2021-06-11 | 2021-06-11 | Data source joint modeling method based on safe multi-party calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113326521A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443067A (en) * | 2019-07-30 | 2019-11-12 | 卓尔智联(武汉)研究院有限公司 | Federal model building device, method and readable storage medium storing program for executing based on secret protection |
| CN111611601A (en) * | 2020-04-30 | 2020-09-01 | 深圳壹账通智能科技有限公司 | Multi-data-party user analysis model joint training method and device and storage medium |
| CN112084307A (en) * | 2020-09-14 | 2020-12-15 | 腾讯科技（深圳）有限公司 | Data processing method and device, server and computer readable storage medium |
| CN112241537A (en) * | 2020-09-23 | 2021-01-19 | 易联众信息技术股份有限公司 | Longitudinal federated learning modeling method, system, medium and equipment |
-
2021
- 2021-06-11 CN CN202110656136.8A patent/CN113326521A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443067A (en) * | 2019-07-30 | 2019-11-12 | 卓尔智联(武汉)研究院有限公司 | Federal model building device, method and readable storage medium storing program for executing based on secret protection |
| CN111611601A (en) * | 2020-04-30 | 2020-09-01 | 深圳壹账通智能科技有限公司 | Multi-data-party user analysis model joint training method and device and storage medium |
| CN112084307A (en) * | 2020-09-14 | 2020-12-15 | 腾讯科技（深圳）有限公司 | Data processing method and device, server and computer readable storage medium |
| CN112241537A (en) * | 2020-09-23 | 2021-01-19 | 易联众信息技术股份有限公司 | Longitudinal federated learning modeling method, system, medium and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2019246903B2 (en) | Method and system for distributed cryptographic key provisioning and storage via elliptic curve cryptography | |
| Shen et al. | Secure SVM training over vertically-partitioned datasets using consortium blockchain for vehicular social networks | |
| CN108681966B (en) | Information supervision method and device based on block chain | |
| CN111934879B (en) | Encryption method, device, equipment and medium for data transmission of internal and external network system | |
| Durham et al. | Composite bloom filters for secure record linkage | |
| US9852306B2 (en) | Conjunctive search in encrypted data | |
| CN111143865B (en) | User behavior analysis system and method for automatically generating label on ciphertext data | |
| CN112183765A (en) | Multi-source multi-modal data preprocessing method and system for shared learning | |
| CN111553443B (en) | Training method and device for referee document processing model and electronic equipment | |
| US20220286275A1 (en) | Method and system for the atomic exchange of blockchain assets using transient key pairs | |
| CN108038128A (en) | A kind of search method, system, terminal device and storage medium for encrypting file | |
| CN110717197A (en) | Credit investigation data sharing method based on block chain | |
| CN117390657A (en) | Data encryption method, device, computer equipment and storage medium | |
| CN116032464A (en) | Property data encryption system based on quantum communication | |
| CN113239401A (en) | Big data analysis system and method based on power Internet of things and computer storage medium | |
| Hidayat et al. | Data encryption algorithm AES by using blockchain technology: a review | |
| CN111475690B (en) | Character string matching method and device, data detection method and server | |
| CN113326521A (en) | Data source joint modeling method based on safe multi-party calculation | |
| CN113935874A (en) | District chain-based book management system for studying income | |
| Sun et al. | Feature engineering framework based on secure multi-party computation in federated learning | |
| CN113051587A (en) | Privacy protection intelligent transaction recommendation method, system and readable medium | |
| CN116484409B (en) | Knowledge graph-based alliance chain block chain management system | |
| Liu et al. | [Retracted] Mathematical Modeling of Static Data Attribute Encryption Based on Big Data Technology | |
| WO2022244129A1 (en) | Management apparatus, financial institution terminal, and management method | |
| CN117786644B (en) | Safe face recognition system with face self-characteristics participating in encryption and decryption |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210831 |