CN113051144A - Intelligent contract recommendation method and device - Google Patents
Intelligent contract recommendation method and device Download PDFInfo
- Publication number
- CN113051144A CN113051144A CN202110325675.3A CN202110325675A CN113051144A CN 113051144 A CN113051144 A CN 113051144A CN 202110325675 A CN202110325675 A CN 202110325675A CN 113051144 A CN113051144 A CN 113051144A
- Authority
- CN
- China
- Prior art keywords
- intelligent contract
- user
- similarity
- contract
- intelligent
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3452—Performance evaluation by statistical analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Hardware Design (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Quality & Reliability (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses an intelligent contract recommendation method and device, and the method comprises the following steps: constructing a user contract matrix according to the preset transaction record, wherein the user contract matrix is used for recording the intelligent contract calling times of the user; calculating preset similarity according to the user contract matrix, wherein the preset similarity is user similarity or intelligent contract similarity; and analyzing and calculating the intelligent contract calling times of the user by adopting the preset similarity, and recommending the intelligent contract for the current user according to the calculation result. The method and the device can solve the technical problems that the mass data utilization rate of a block chain platform is low in the prior art, and the self-adaptability is lacked in the intelligent contract selecting process, so that the experience of a user on the block chain platform is poor.
Description
Technical Field
The application relates to the technical field of block chains, in particular to an intelligent contract recommendation method and device.
Background
The block chain is a decentralized accounting technology, and plays a great role in various application scenes by virtue of characteristics of decentralized, privacy protection, difficult tampering and the like since the appearance of the bitcoin in 2008. With the development of technology, representative blockchain platforms such as etherhouse and superhedger Fabric are coming out in succession, and they also represent the explosion in the field of blockchain technology. On the other hand, however, the utilization rate of mass data generated by creating and invoking the intelligent contract for the block chain is not high.
An intelligent contract may autonomously perform all or part of the contract-related operations and generate corresponding proof that may be verified to demonstrate the effectiveness of performing the contract operations. A smart contract, such as on an ethernet house, is a piece of code that can be executed by an ethernet house virtual machine. Intelligent contracts exist on each node of a blockchain network in the form of on-chain scripts, and security and cost of the contracts are of great concern.
The utilization rate of mass data generated by creating and calling the intelligent contract of the block chain is not high, and the process of calling the intelligent contract by a user lacks adaptivity, so that the use of the block chain platform is not personalized and intelligent.
Disclosure of Invention
The application provides an intelligent contract recommendation method and device, which are used for solving the technical problems that the utilization rate of mass data of a block chain platform is low, and the experience of a user on the block chain platform is poor due to the lack of self-adaptability in the intelligent contract selection process in the prior art.
In view of this, a first aspect of the present application provides an intelligent contract recommendation method, including:
constructing a user contract matrix according to a preset transaction record, wherein the user contract matrix is used for recording the intelligent contract calling times of a user;
calculating preset similarity according to the user contract matrix, wherein the preset similarity is user similarity or intelligent contract similarity;
and analyzing and calculating the intelligent contract calling times of the user by adopting the preset similarity, and recommending the intelligent contract for the current user according to the calculation result.
Preferably, when the preset similarity is the user similarity, the calculating the preset similarity according to the user contract matrix includes:
and calculating the included angle of any two row vectors in the user contract matrix in the Euclidean space to obtain the user similarity between two users corresponding to the two row vectors.
Preferably, when the preset similarity is the user similarity, the analyzing and calculating the number of times of calling the intelligent contract of the user by using the preset similarity, and performing intelligent contract recommendation for the current user according to a calculation result specifically include:
selecting a first preset number of similar users for the current user according to the user similarity;
calculating a first weighted average value of the calling times of the non-called intelligent contracts of the similar users aiming at each non-called intelligent contract in a first non-called intelligent contract set to obtain a plurality of first weighted average values, wherein the first non-called intelligent contract set is all intelligent contracts not called by the current user;
selecting the intelligent contract corresponding to the maximum first weighted average value to recommend to the current user
Preferably, when the preset similarity is the intelligent contract similarity, the calculating the preset similarity according to the user contract matrix includes:
and calculating the included angle of any two column vectors in the user contract matrix in the Euclidean space to obtain the intelligent contract similarity between two intelligent contracts corresponding to the two column vectors.
Preferably, when the preset similarity is the intelligent contract similarity, the analyzing and calculating the number of times of calling the intelligent contract of the user by using the preset similarity, and performing intelligent contract recommendation for the current user according to a calculation result specifically include:
selecting a second preset number of similar intelligent contracts for each un-invoked intelligent contract in a second un-invoked intelligent contract set according to the intelligent contract similarity, wherein the second un-invoked intelligent contract set is all intelligent contracts not invoked by the current user;
calculating a second weighted average value of the calling times of the similar intelligent contracts corresponding to each un-called intelligent contract of the current user to obtain a plurality of second weighted average values;
and selecting the intelligent contract corresponding to the maximum second weighted average value and recommending the intelligent contract to the current user.
A second aspect of the present application provides an intelligent contract recommending apparatus, including:
the system comprises a construction module, a contract management module and a contract management module, wherein the construction module is used for constructing a user contract matrix according to a preset transaction record, and the user contract matrix is used for recording the intelligent contract calling times of a user;
the calculation module is used for calculating preset similarity according to the user contract matrix, and the preset similarity is user similarity or intelligent contract similarity;
and the recommending module is used for analyzing and calculating the intelligent contract calling times of the user by adopting the preset similarity and recommending the intelligent contract for the current user according to the calculation result.
Preferably, when the preset similarity is the user similarity, the calculating module is specifically configured to:
and calculating the included angle of any two row vectors in the user contract matrix in the Euclidean space to obtain the user similarity between two users corresponding to the two row vectors.
Preferably, when the preset similarity is the user similarity, the recommending module is specifically configured to:
selecting a first preset number of similar users for the current user according to the user similarity;
calculating a first weighted average value of the calling times of the non-called intelligent contracts of the similar users aiming at each non-called intelligent contract in a first non-called intelligent contract set to obtain a plurality of first weighted average values, wherein the first non-called intelligent contract set is all intelligent contracts not called by the current user;
and selecting the intelligent contract corresponding to the maximum first weighted average value and recommending the intelligent contract to the current user.
Preferably, when the preset similarity is the intelligent contract similarity, the calculation module is specifically configured to:
and calculating the included angle of any two column vectors in the user contract matrix in the Euclidean space to obtain the intelligent contract similarity between two intelligent contracts corresponding to the two column vectors.
Preferably, when the preset similarity is the intelligent contract similarity, the recommending module is specifically configured to:
selecting a second preset number of similar intelligent contracts for each un-invoked intelligent contract in a second un-invoked intelligent contract set according to the intelligent contract similarity, wherein the second un-invoked intelligent contract set is all intelligent contracts not invoked by the current user;
calculating a second weighted average value of the calling times of the similar intelligent contracts corresponding to each un-called intelligent contract of the current user to obtain a plurality of second weighted average values;
and selecting the intelligent contract corresponding to the maximum second weighted average value and recommending the intelligent contract to the current user.
According to the technical scheme, the embodiment of the application has the following advantages:
the application provides an intelligent contract recommendation method, which comprises the following steps: constructing a user contract matrix according to the preset transaction record, wherein the user contract matrix is used for recording the intelligent contract calling times of the user; calculating preset similarity according to the user contract matrix, wherein the preset similarity is user similarity or intelligent contract similarity; and analyzing and calculating the intelligent contract calling times of the user by adopting the preset similarity, and recommending the intelligent contract for the current user according to the calculation result.
According to the intelligent contract recommendation method, the number of times of calling the intelligent contracts of the user is one of mass data generated by creating and calling the intelligent contracts of the block chain, data analysis is carried out on transaction behaviors of the user in a data mining mode, and the intelligent contract calling condition of the user is judged through preset similarity obtained through data calculation, so that the intelligent contracts which meet requirements of the user better are provided for the current user. Therefore, the method and the device can solve the technical problems that the mass data utilization rate of the block chain platform is low, and the experience of a user on the block chain platform is poor due to lack of adaptivity in the intelligent contract selecting process in the prior art.
Drawings
Fig. 1 is a first flowchart illustrating an intelligent contract recommendation method according to an embodiment of the present application;
fig. 2 is a flowchart illustrating a second method for recommending an intelligent contract according to an embodiment of the present application;
fig. 3 is a schematic flowchart third of a method for recommending an intelligent contract according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an intelligent contract recommending apparatus according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, 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 application.
Interpretation of terms:
1. the method comprises the following steps: is an open-source public block chain platform with intelligent contract function, and provides an decentralized Ethernet Virtual Machine (Ethereum Virtual Machine) to process point-to-point contracts through a special encryption currency Ethernet (Ether, abbreviated as 'ETH').
2. Intelligent contract: essentially, a piece of software code, which can be triggered to execute according to a pre-specified condition, is made available to any transaction between users by the joint participation of multiple users in the blockchain.
3. Trading: the minimum unit of state conversion on the block chain is initiated by the signature of a sender, and the specific digital assets are transferred or the operations of influencing the block chain state, such as intelligent contract calling, and the like, are carried out.
The intelligent block chain contract is established and called to generate mass data, so that intelligent contract calling data can be researched by adopting a data mining means, and the use of a block chain platform is more personalized and intelligent.
For easy understanding, referring to fig. 1, a first embodiment of an intelligent contract recommendation method provided in the present application includes:
The preset transaction record is obtained by the transaction process between the blockchain record nodes and the nodes, and specifically comprises transaction details such as transaction node identity, transaction amount and digital signature and information such as transaction times in the blockchain. The preset transaction record in the embodiment of the application mainly refers to the relationship between the user and the called intelligent contract, namely the number of times that the user calls the intelligent contract.
Each row of the user contract matrix refers to the records of the number of times of calling different intelligent contracts by the same user, and each column refers to the number of times of calling different users by the same intelligent contract. For example, the form of the table may be used, please refer to table 1, in which five different users and five different intelligent contracts are listed, and the data in the table is the number of times that the corresponding user invokes the corresponding intelligent contract.
Table 1 example table of user contract matrix structure
| Intelligent contract A | Intelligent contract B | Intelligent contract C | Intelligent contract D | Intelligent contract E | |
| User 1 | 0 | 30 | 0 | 0 | 100 |
| User 2 | 3 | 25 | 0 | 0 | 200 |
| User 3 | 0 | 0 | 100 | 50 | 99 |
| User 4 | 33 | 50 | 83 | 15 | 135 |
| User 5 | 0 | 0 | 0 | 0 | 3 |
And 102, calculating preset similarity according to the user contract matrix, wherein the preset similarity is user similarity or intelligent contract similarity.
The preset similarity can be analyzed from two different aspects, namely user similarity and intelligent contract similarity. If the user similarity is calculated, the similarity between two different users is calculated; if the intelligent contract similarity is calculated, the similarity between two different intelligent contracts is calculated. In summary, the embodiment of the present application needs to calculate the similarity for all elements pairwise.
And 103, analyzing and calculating the intelligent contract calling times of the user by adopting the preset similarity, and recommending the intelligent contract for the current user according to the calculation result.
The analysis of the intelligent contract calling times mainly comprises the steps of analyzing the contract calling characteristics of the current user, and then recommending reasonable intelligent contracts for the current user according to the intelligent contract calling characteristics of the current user; or analyzing the called times of a certain intelligent contract, thereby analyzing the used rule of the intelligent contract, and further carrying out intelligent contract recommendation for the current user with the need.
The data generated in the node transaction process is used for analyzing the contract calling behavior of the user and the use rule of the intelligent contract, the intelligent contract requirements of the user can be more accurately reflected, the data generated in the block chain transaction is reasonably utilized to a certain extent, and the operation method is simple and high in executability.
In the intelligent contract recommendation method provided by the embodiment of the application, the number of times of calling the intelligent contract of the user is one of mass data generated by creating and calling the intelligent contract of the block chain, data analysis is performed on the transaction behavior of the user in a data mining mode, and the intelligent contract calling condition of the user is judged according to the preset similarity obtained by data calculation, so that the intelligent contract which meets the requirements of the user better is provided for the current user. Therefore, the technical problems that the utilization rate of mass data of the block chain platform is low, and the experience of a user on the block chain platform is poor due to lack of adaptivity in the intelligent contract selection process in the prior art can be solved.
The above is an embodiment of an intelligent contract recommendation method provided by the present application, and the following is another embodiment of an intelligent contract recommendation method provided by the present application.
For easy understanding, please refer to fig. 2, the present application provides a second embodiment of an intelligent contract recommendation method, including:
This operation step is similar to the process of step 101, and is not described herein again.
The euclidean space is a special metric space that plays a role in defining manifolds that include both euclidean and non-euclidean geometries.
When the preset similarity is the user similarity, the similarity between every two users is calculated, specifically, any two row vectors are obtained from a user contract matrix, and one row represents the record of the calling times of different intelligent contracts of one user; secondly, calculating the size of an included angle of the two line vectors in the Euclidean space, and reflecting the size of the similarity between the two users through the size of the included angle, wherein in general, the smaller the included angle is, the greater the similarity between the two corresponding users is, and otherwise, the smaller the similarity is; the similarity between the two users is quantified through the size of the included angle, so that the user behavior analysis is facilitated.
And 203, selecting a first preset number of similar users for the current user according to the user similarity.
For the current user, the similarity between the current user and all other users can be obtained through the calculation, the user similarities are sorted in a descending order, and the first preset number of users in the front are obtained to be used as the similar users of the current user, wherein the selected principle is that the similarity with the current user is the highest; each user can do so. The specific first preset number may be configured according to an actual node scale or a setting requirement, and is not limited herein.
And 204, calculating a first weighted average of the calling times of the intelligent contracts which are not called by the similar users aiming at each intelligent contract which is not called in the first intelligent contract set to obtain a plurality of first weighted averages, wherein the first intelligent contract which is not called by the current user is the first intelligent contract which is not called by the current user.
The intelligent contract is not called, namely the number of times of calling the intelligent contract by the current user is 0; the current user does not call the intelligent contract which is not called, but similar users may have calls, the number of calls of the intelligent contract which is not called by all the similar users is calculated, a first weighted average value can be obtained, each intelligent contract which is not called is analyzed and calculated as above, a plurality of first weighted average values can be obtained, and the specific number is consistent with the number of the intelligent contracts which are not called. The weight in the weighted average calculation process may be set according to the actual application, and is not limited herein.
And 205, selecting the intelligent contract corresponding to the maximum first weighted average value and recommending the intelligent contract to the current user.
And performing descending arrangement on all the first weighted average values obtained above, and selecting the intelligent contracts corresponding to the first weighted average value in the sequence to recommend to the current user, wherein the essence is to recommend the un-invoked intelligent contracts with the largest weighted average value used by the user to the current user.
The above is an embodiment of an intelligent contract recommendation method provided by the present application, and the following is another embodiment of an intelligent contract recommendation method provided by the present application.
For easy understanding, please refer to fig. 3, the present application further provides a third embodiment of an intelligent contract recommendation method, including:
This operation step is similar to the process of step 101, and is not described herein again.
And 302, calculating an included angle of any two column vectors in the user contract matrix in the Euclidean space to obtain the intelligent contract similarity between two intelligent contracts corresponding to the two column vectors.
When the preset similarity is the similarity of the intelligent contracts, the similarity between every two intelligent contracts is calculated, specifically, any two column vectors are obtained from a user contract matrix, and one column represents the record of the calling times of one intelligent contract by different users; secondly, calculating the size of an included angle of the two column vectors in the Euclidean space, and reflecting the size of the similarity between the two intelligent contracts through the size of the included angle, wherein in general, the smaller the included angle is, the greater the similarity between the two corresponding intelligent contracts is, and otherwise, the smaller the similarity is; the similarity between the two intelligent contracts is quantified through the size of the included angle, so that the analysis of the use rule of the intelligent contracts is facilitated.
And 303, selecting a second preset number of similar intelligent contracts for each un-invoked intelligent contract in a second un-invoked intelligent contract set according to the similarity of the intelligent contracts, wherein the second un-invoked intelligent contract set is all the intelligent contracts which are not invoked by the current user.
The second is that the intelligent contract calling sets are all intelligent contracts with the current user calling frequency of 0, each intelligent contract can find the intelligent contract with higher relative similarity according to the similarity between every two intelligent contracts, and the second preset number is set according to the scale or the actual requirement of the intelligent contract and is not limited herein. The selection process is also to sort the similarity in descending order and to take the intelligent contracts of the previous preset number.
And step 304, calculating a second weighted average of the calling times of the current user to the similar intelligent contracts corresponding to each un-called intelligent contract to obtain a plurality of second weighted averages.
The similar intelligent contracts are not intelligent contracts which are not called completely, wherein the intelligent contracts which are not called possibly exist, and some intelligent contracts which are called by current users also exist, each intelligent contract which is not called corresponds to a similar intelligent contract number sequence, the calling times of the current users to the similar intelligent contracts in the sequence are analyzed, a second weighted average value is calculated, and the number of the second weighted average value is determined according to the number of the intelligent contracts which are not called; the weight of the weighted average may be set according to the actual weight, which is not limited herein.
And 305, selecting the intelligent contract corresponding to the maximum second weighted average value and recommending the intelligent contract to the current user.
And performing descending arrangement on all the obtained second weighted average values, selecting the intelligent contracts corresponding to the first second weighted average value in the sequence, and recommending the intelligent contracts to the current user, wherein the intelligent contracts are actually analyzed according to the intelligent contract calling habits of the user, and the intelligent contracts possibly existing in the current user are recommended to the current user.
The above is an embodiment of an intelligent contract recommendation method provided by the present application, and the following is an embodiment of an intelligent contract recommendation apparatus provided by the present application.
For ease of understanding, referring to fig. 4, the present application further provides an embodiment of an intelligent contract recommending apparatus, comprising:
the construction module 401 is configured to construct a user contract matrix according to a preset transaction record, where the user contract matrix is used to record the number of times of intelligent contract invocation of a user;
a calculating module 402, configured to calculate a preset similarity according to the user contract matrix, where the preset similarity is a user similarity or an intelligent contract similarity;
and the recommending module 403 is configured to analyze and calculate the number of times of invoking the intelligent contract of the user by using the preset similarity, and recommend the intelligent contract for the current user according to the calculation result.
Further, when the preset similarity is a user similarity, the calculating module 402 is specifically configured to:
and calculating the included angle of any two row vectors in the user contract matrix in the Euclidean space to obtain the user similarity between two users corresponding to the two row vectors.
Further, when the preset similarity is the user similarity, the recommending module 403 is specifically configured to:
selecting a first preset number of similar users for the current user according to the user similarity;
calculating a first weighted average value of the calling times of the intelligent contracts which are not called by similar users aiming at each intelligent contract which is not called in a first intelligent contract set to obtain a plurality of first weighted average values, wherein the first intelligent contract set which is not called by the current user is all intelligent contracts which are not called by the current user;
and selecting the intelligent contract corresponding to the maximum first weighted average value and recommending the intelligent contract to the current user.
Further, when the preset similarity is the intelligent contract similarity, the calculating module 402 is specifically configured to:
and calculating the included angle of any two column vectors in the user contract matrix in the Euclidean space to obtain the intelligent contract similarity between two intelligent contracts corresponding to the two column vectors.
Further, when the preset similarity is the intelligent contract similarity, the recommending module 403 is specifically configured to:
selecting a second preset number of similar intelligent contracts for each un-invoked intelligent contract in a second un-invoked intelligent contract set according to the similarity of the intelligent contracts, wherein the second un-invoked intelligent contract set is all the intelligent contracts not invoked by the current user;
calculating a second weighted average value of the calling times of the current user to the similar intelligent contracts corresponding to each un-called intelligent contract to obtain a plurality of second weighted average values;
and selecting the intelligent contract corresponding to the maximum second weighted average value and recommending the intelligent contract to the current user.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for executing all or part of the steps of the method described in the embodiments of the present application through a computer device (which may be a personal computer, a server, or a network device). And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. An intelligent contract recommendation method, comprising:
constructing a user contract matrix according to a preset transaction record, wherein the user contract matrix is used for recording the intelligent contract calling times of a user;
calculating preset similarity according to the user contract matrix, wherein the preset similarity is user similarity or intelligent contract similarity;
and analyzing and calculating the intelligent contract calling times of the user by adopting the preset similarity, and recommending the intelligent contract for the current user according to the calculation result.
2. The intelligent contract recommendation method according to claim 1, wherein when the preset similarity is the user similarity, the calculating a preset similarity according to the user contract matrix includes:
and calculating the included angle of any two row vectors in the user contract matrix in the Euclidean space to obtain the user similarity between two users corresponding to the two row vectors.
3. The intelligent contract recommendation method according to claim 1, wherein when the preset similarity is the user similarity, the analyzing and calculating the number of times of intelligent contract invocation by the user using the preset similarity, and performing intelligent contract recommendation for the current user according to the calculation result specifically includes:
selecting a first preset number of similar users for the current user according to the user similarity;
calculating a first weighted average value of the calling times of the non-called intelligent contracts of the similar users aiming at each non-called intelligent contract in a first non-called intelligent contract set to obtain a plurality of first weighted average values, wherein the first non-called intelligent contract set is all intelligent contracts not called by the current user;
and selecting the intelligent contract corresponding to the maximum first weighted average value and recommending the intelligent contract to the current user.
4. The intelligent contract recommendation method according to claim 1, wherein when the preset similarity is the intelligent contract similarity, the calculating a preset similarity according to the user contract matrix includes:
and calculating the included angle of any two column vectors in the user contract matrix in the Euclidean space to obtain the intelligent contract similarity between two intelligent contracts corresponding to the two column vectors.
5. The intelligent contract recommendation method according to claim 1, wherein when the preset similarity is the intelligent contract similarity, the analyzing and calculating the number of times of intelligent contract invocation by the user using the preset similarity, and performing intelligent contract recommendation for the current user according to the calculation result specifically includes:
selecting a second preset number of similar intelligent contracts for each un-invoked intelligent contract in a second un-invoked intelligent contract set according to the intelligent contract similarity, wherein the second un-invoked intelligent contract set is all intelligent contracts not invoked by the current user;
calculating a second weighted average value of the calling times of the similar intelligent contracts corresponding to each un-called intelligent contract of the current user to obtain a plurality of second weighted average values;
and selecting the intelligent contract corresponding to the maximum second weighted average value and recommending the intelligent contract to the current user.
6. An intelligent contract recommendation apparatus, comprising:
the system comprises a construction module, a contract management module and a contract management module, wherein the construction module is used for constructing a user contract matrix according to a preset transaction record, and the user contract matrix is used for recording the intelligent contract calling times of a user;
the calculation module is used for calculating preset similarity according to the user contract matrix, and the preset similarity is user similarity or intelligent contract similarity;
and the recommending module is used for analyzing and calculating the intelligent contract calling times of the user by adopting the preset similarity and recommending the intelligent contract for the current user according to the calculation result.
7. The intelligent contract recommending apparatus according to claim 6, wherein when the preset similarity is the user similarity, the calculating module is specifically configured to:
and calculating the included angle of any two row vectors in the user contract matrix in the Euclidean space to obtain the user similarity between two users corresponding to the two row vectors.
8. The intelligent contract recommendation device according to claim 6, wherein when the preset similarity is the user similarity, the recommendation module is specifically configured to:
selecting a first preset number of similar users for the current user according to the user similarity;
calculating a first weighted average value of the calling times of the non-called intelligent contracts of the similar users aiming at each non-called intelligent contract in a first non-called intelligent contract set to obtain a plurality of first weighted average values, wherein the first non-called intelligent contract set is all intelligent contracts not called by the current user;
and selecting the intelligent contract corresponding to the maximum first weighted average value and recommending the intelligent contract to the current user.
9. The intelligent contract recommendation device according to claim 6, wherein when the preset similarity is the intelligent contract similarity, the calculation module is specifically configured to:
and calculating the included angle of any two column vectors in the user contract matrix in the Euclidean space to obtain the intelligent contract similarity between two intelligent contracts corresponding to the two column vectors.
10. The intelligent contract recommendation device according to claim 6, wherein when the preset similarity is the intelligent contract similarity, the recommendation module is specifically configured to:
selecting a second preset number of similar intelligent contracts for each un-invoked intelligent contract in a second un-invoked intelligent contract set according to the intelligent contract similarity, wherein the second un-invoked intelligent contract set is all intelligent contracts not invoked by the current user;
calculating a second weighted average value of the calling times of the similar intelligent contracts corresponding to each un-called intelligent contract of the current user to obtain a plurality of second weighted average values;
and selecting the intelligent contract corresponding to the maximum second weighted average value and recommending the intelligent contract to the current user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110325675.3A CN113051144B (en) | 2021-03-26 | 2021-03-26 | Intelligent contract recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110325675.3A CN113051144B (en) | 2021-03-26 | 2021-03-26 | Intelligent contract recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113051144A true CN113051144A (en) | 2021-06-29 |
| CN113051144B CN113051144B (en) | 2022-02-08 |
Family
ID=76515431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110325675.3A Active CN113051144B (en) | 2021-03-26 | 2021-03-26 | Intelligent contract recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113051144B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105760547A (en) * | 2016-03-16 | 2016-07-13 | 中山大学 | Book recommendation method and system based on user clustering |
| CN106228382A (en) * | 2016-07-07 | 2016-12-14 | 中国联合网络通信集团有限公司 | The recommendation method and system of mobile terminal contract |
| CN108563660A (en) * | 2017-12-29 | 2018-09-21 | 温州大学 | service recommendation method, system and server |
| CN109522474A (en) * | 2018-10-19 | 2019-03-26 | 上海交通大学 | Recommended method based on interaction sequence data mining depth user's similitude |
| CN111158692A (en) * | 2019-12-09 | 2020-05-15 | 华南师范大学 | Method, system and storage medium for ordering similarity of intelligent contract functions |
| WO2020111424A1 (en) * | 2018-11-28 | 2020-06-04 | 주식회사 파이랩테크놀로지 | Automated system for generating and recommending smart contract tag using tag recommendation model |
| CN111596946A (en) * | 2020-04-09 | 2020-08-28 | 山东爱城市网信息技术有限公司 | Recommendation method, device and medium for intelligent contracts of block chains |
| CN111737654A (en) * | 2020-08-14 | 2020-10-02 | 支付宝(杭州)信息技术有限公司 | Infringement detection method and device based on block chain and electronic equipment |
| CN111815372A (en) * | 2020-09-01 | 2020-10-23 | 腾讯科技（深圳）有限公司 | Live broadcast processing method and device based on block chain, electronic equipment and storage medium |
| CN111915409A (en) * | 2020-08-11 | 2020-11-10 | 深圳墨世科技有限公司 | Article recommendation method, device and equipment based on article and storage medium |
| CN112131477A (en) * | 2020-09-27 | 2020-12-25 | 辽宁工程技术大学 | Library book recommendation system and method based on user portrait |
| CN112380454A (en) * | 2021-01-18 | 2021-02-19 | 平安科技（深圳）有限公司 | Training course recommendation method, device, equipment and medium |
-
2021
- 2021-03-26 CN CN202110325675.3A patent/CN113051144B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105760547A (en) * | 2016-03-16 | 2016-07-13 | 中山大学 | Book recommendation method and system based on user clustering |
| CN106228382A (en) * | 2016-07-07 | 2016-12-14 | 中国联合网络通信集团有限公司 | The recommendation method and system of mobile terminal contract |
| CN108563660A (en) * | 2017-12-29 | 2018-09-21 | 温州大学 | service recommendation method, system and server |
| CN109522474A (en) * | 2018-10-19 | 2019-03-26 | 上海交通大学 | Recommended method based on interaction sequence data mining depth user's similitude |
| WO2020111424A1 (en) * | 2018-11-28 | 2020-06-04 | 주식회사 파이랩테크놀로지 | Automated system for generating and recommending smart contract tag using tag recommendation model |
| CN111158692A (en) * | 2019-12-09 | 2020-05-15 | 华南师范大学 | Method, system and storage medium for ordering similarity of intelligent contract functions |
| CN111596946A (en) * | 2020-04-09 | 2020-08-28 | 山东爱城市网信息技术有限公司 | Recommendation method, device and medium for intelligent contracts of block chains |
| CN111915409A (en) * | 2020-08-11 | 2020-11-10 | 深圳墨世科技有限公司 | Article recommendation method, device and equipment based on article and storage medium |
| CN111737654A (en) * | 2020-08-14 | 2020-10-02 | 支付宝(杭州)信息技术有限公司 | Infringement detection method and device based on block chain and electronic equipment |
| CN111815372A (en) * | 2020-09-01 | 2020-10-23 | 腾讯科技（深圳）有限公司 | Live broadcast processing method and device based on block chain, electronic equipment and storage medium |
| CN112131477A (en) * | 2020-09-27 | 2020-12-25 | 辽宁工程技术大学 | Library book recommendation system and method based on user portrait |
| CN112380454A (en) * | 2021-01-18 | 2021-02-19 | 平安科技（深圳）有限公司 | Training course recommendation method, device, equipment and medium |
Non-Patent Citations (1)
| Title |
|---|
| 李昆仑等: "基于改进用户相似性度量和评分预测的协同过滤推荐算法", 《小型微型计算机***》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113051144B (en) | 2022-02-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pinna et al. | A petri nets model for blockchain analysis | |
| CN109063966B (en) | Risk account identification method and device | |
| CN112800466B (en) | Data processing method and device based on privacy protection and server | |
| CN105227352B (en) | A kind of update method and device of user identifier collection | |
| CN106469413B (en) | Data processing method and device for virtual resources | |
| US20150142808A1 (en) | System and method for efficiently determining k in data clustering | |
| CN110570311B (en) | Block chain consensus method, device and equipment | |
| CN111260220B (en) | Group control equipment identification method and device, electronic equipment and storage medium | |
| CN112559301B (en) | Service processing method, storage medium, processor and electronic device | |
| CN108243191A (en) | Risk behavior recognition methods, storage medium, equipment and system | |
| CN107294974A (en) | The method and apparatus for recognizing target clique | |
| CN112700332B (en) | Bit currency account clustering method based on graph calculation | |
| CN109801693B (en) | Medical records grouping method and device, terminal and computer readable storage medium | |
| CN109685336A (en) | Collection task distribution method, device, computer equipment and storage medium | |
| CN110442502A (en) | A kind of method, apparatus buried a little, equipment and storage medium | |
| CN106998314B (en) | Account interaction method and device | |
| CN111930366A (en) | Rule engine implementation method and system based on JIT real-time compilation | |
| CN105426392A (en) | Collaborative filtering recommendation method and system | |
| CN116957112A (en) | Training method, device, equipment and storage medium of joint model | |
| CN112163227B (en) | Multidimensional statistical analysis system and method for user sales of e-commerce platform seller | |
| CN113051144B (en) | Intelligent contract recommendation method and device | |
| CN109213801A (en) | Data digging method and device based on incidence relation | |
| CN113656699A (en) | User feature vector determination method, related device and medium | |
| CN109345252A (en) | A kind of online trading control method, device and computer equipment | |
| CN106215417A (en) | Server and gift bag distributor and method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |