CN117540935A - DAO operation management method based on block chain technology - Google Patents
DAO operation management method based on block chain technology Download PDFInfo
- Publication number
- CN117540935A CN117540935A CN202410030530.4A CN202410030530A CN117540935A CN 117540935 A CN117540935 A CN 117540935A CN 202410030530 A CN202410030530 A CN 202410030530A CN 117540935 A CN117540935 A CN 117540935A
- Authority
- CN
- China
- Prior art keywords
- user behavior
- semantic
- sequence
- training
- coding feature
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 53
- 238000005516 engineering process Methods 0.000 title claims abstract description 31
- 239000013598 vector Substances 0.000 claims abstract description 151
- 238000013507 mapping Methods 0.000 claims abstract description 25
- 230000006399 behavior Effects 0.000 claims description 213
- 238000012549 training Methods 0.000 claims description 89
- 238000000034 method Methods 0.000 claims description 27
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000011161 development Methods 0.000 abstract description 7
- 230000008520 organization Effects 0.000 description 20
- 230000006870 function Effects 0.000 description 14
- 238000010586 diagram Methods 0.000 description 7
- 230000018109 developmental process Effects 0.000 description 6
- 230000003993 interaction Effects 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000002708 enhancing effect Effects 0.000 description 4
- 230000001965 increasing effect Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000001737 promoting effect Effects 0.000 description 3
- 230000004888 barrier function Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 238000011278 co-treatment Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000012447 hatching Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009440 infrastructure construction Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000007493 shaping process Methods 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
Abstract
A DAO operation management method based on block chain technology is disclosed. Firstly, carrying out semantic coding on each user behavior data in a user behavior data time sequence to obtain a sequence of user behavior semantic coding feature vectors, then carrying out attention space mapping on the sequence of user behavior semantic coding feature vectors to obtain a sequence of mapped user behavior semantic coding feature vectors, then calculating semantic attention weights of the whole feature distribution of each mapped user behavior semantic coding feature vector relative to the sequence of mapped user behavior semantic coding feature vectors to obtain a sequence of semantic attention weights, then calculating the weighted sum of the sequence of user behavior semantic coding feature vectors to obtain a user behavior global semantic understanding feature vector, and finally determining a type tag of a recommended digital honor badge based on the user behavior global semantic understanding feature vector. In this way, the development and operation of DAOs may be facilitated.
Description
Technical Field
The present application relates to the field of intelligent operations management, and more particularly, to a DAO operations management method based on blockchain technology.
Background
Blockchain technology is a distributed, decentralized, non-tamperable data storage and transaction technology that can enable trust and collaboration among multiple parties, thereby promoting innovation and efficiency in social organization and economic activities. The core characteristics of the blockchain include decentralization, non-tampering, transparency and anonymity, so that the blockchain has wide application potential in various fields. An important application area of blockchain technology is de-centralized autonomous organization (DAO), which is an organization form of self-management, self-execution and self-regulation based on intelligent contracts, and can realize consensus and coordination among organization members and allocation and management of organization resources so as to realize automation and de-centralized management of organization.
The traditional organization operation mode is more prone to a top-down management mechanism, and lower staff can cause the consequences of insufficient execution force, low efficiency and poor results due to the problems of information barriers, communication barriers, decision errors and the like according to the command of the upper lead. In order to solve the problem, the DAO operation mode is introduced based on the blockchain technology, so that the traditional top-down hierarchical management mode can be eliminated, organization members can manage the organization through a decentralization decision mechanism, a novel management mode with transparent disclosure and autonomy is formed, and the defect of the traditional management mode is overcome. However, there are problems in the current DAO operation management, such as how to motivate the active participation and contribution of the members to increase the participation and cohesiveness of the organization members, and how to evaluate the contribution of the organization members.
Accordingly, an optimized DAO operation management scheme based on blockchain technology is desired.
Disclosure of Invention
The present application has been made in order to solve the above technical problems. The embodiment of the application provides a DAO operation management method based on a blockchain technology, which can increase the participation degree and loyalty of users and promote the interaction and cooperation among the users, thereby promoting the development and operation of DAO.
According to one aspect of the present application, there is provided a DAO operation management method based on a blockchain technique, including:
extracting a user behavior data time sequence from the blockchain network;
carrying out semantic coding on each user behavior data in the user behavior data time sequence to obtain a sequence of user behavior semantic coding feature vectors;
performing attention space mapping on the sequence of the user behavior semantic coding feature vectors to obtain a sequence of mapped user behavior semantic coding feature vectors;
calculating the semantic attention weight of the whole feature distribution of each mapped user behavior semantic coding feature vector in the sequence of mapped user behavior semantic coding feature vectors relative to the sequence of mapped user behavior semantic coding feature vectors so as to obtain a sequence of semantic attention weights;
taking the sequence of semantic attention weights as weights, and calculating the weighted sum of the sequence of the user behavior semantic coding feature vectors to obtain a user behavior global semantic understanding feature vector as a user behavior global semantic understanding feature; and
based on the user behavior global semantic understanding feature, a type tag of a recommended digital honor badge is determined.
Compared with the prior art, the DAO operation management method based on the blockchain technology comprises the steps of firstly carrying out semantic coding on each user behavior data in a user behavior data time sequence to obtain a sequence of user behavior semantic coding feature vectors, then carrying out attention space mapping on the sequence of user behavior semantic coding feature vectors to obtain a sequence of mapped user behavior semantic coding feature vectors, then calculating semantic attention weights of the feature distribution whole of each mapped user behavior semantic coding feature vector relative to the sequence of mapped user behavior semantic coding feature vectors to obtain a sequence of semantic attention weights, then calculating weighted sum of the sequence of user behavior semantic coding feature vectors to obtain a user behavior global semantic understanding feature vector, and finally determining a type tag of a recommended digital reputation badge based on the user behavior global semantic understanding feature vector. In this way, the development and operation of DAOs may be facilitated.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly introduced below, which are not intended to be drawn to scale in terms of actual dimensions, with emphasis on illustrating the gist of the present application.
Fig. 1 is a flowchart of a DAO operation management method based on a blockchain technique according to an embodiment of the present application.
Fig. 2 is a schematic architecture diagram of a DAO operation management method based on a blockchain technique according to an embodiment of the present application.
Fig. 3 is a block diagram of a DAO operations management system based on blockchain technology in accordance with an embodiment of the present application.
Fig. 4 is an application scenario diagram of a DAO operation management method based on a blockchain technique according to an embodiment of the present application.
Fig. 5 is a schematic diagram of DAO operation modes according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present application without making any inventive effort, are also within the scope of the present application.
As used in this application and in the claims, the terms "a," "an," "the," and/or "the" are not specific to the singular, but may include the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.
Flowcharts are used in this application to describe the operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
In view of the above technical problems, in the technical solution of the present application, a DAO operation management method based on a blockchain technology is provided, which can stimulate user behavior by means of a digital honor badge to improve participation and cohesive force of organization members, wherein medals represent contributions and achievements of users in DAO, and records of various meaningful behaviors. Through giving the user recommended digital honor badge, the participation degree and loyalty of the user can be increased, and interaction and cooperation between the users are promoted, so that the development and operation of DAO are promoted.
Accordingly, evaluating the user's contribution and behavior to recommend different types of digital honor medals is a critical issue, as different users may have different interests, skills and contribution patterns in the DAO. By evaluating the contribution and behavior of users, they can learn about their features and advantages in DAO and recommend corresponding digital honor badges based on their personalized performance. This may better motivate users to perceive their own contributions as being recognized and appreciated, thereby increasing their engagement and loyalty.
Based on this, the technical idea of the application is to perform semantic association analysis of the user behavior data time sequence by extracting the user behavior data time sequence from the blockchain network and introducing a data processing and semantic understanding algorithm at the back end, so as to perform appropriate digital honor badge type recommendation to motivate the user behavior. Thus, the participation degree and contribution degree of the users can be improved, thereby enhancing the attribution sense and the acceptance sense of the users, promoting the interaction and cooperation among the users and enhancing the community vitality and development potential of the DAO.
Fig. 1 is a flowchart of a DAO operation management method based on a blockchain technique according to an embodiment of the present application. Fig. 2 is a schematic architecture diagram of a DAO operation management method based on a blockchain technique according to an embodiment of the present application. As shown in fig. 1 and fig. 2, the DAO operation management method based on the blockchain technology according to the embodiment of the present application includes the steps of: s110, extracting a user behavior data time sequence from a block chain network; s120, carrying out semantic coding on each user behavior data in the user behavior data time sequence to obtain a sequence of user behavior semantic coding feature vectors; s130, performing attention space mapping on the sequence of the user behavior semantic coding feature vectors to obtain a sequence of mapped user behavior semantic coding feature vectors; s140, calculating semantic attention weights of feature distribution integers of each mapped user behavior semantic coding feature vector in the sequence of mapped user behavior semantic coding feature vectors relative to the sequence of mapped user behavior semantic coding feature vectors to obtain a sequence of semantic attention weights; s150, calculating the weighted sum of the sequences of the semantic attention weights of the user behaviors to obtain global semantic understanding feature vectors of the user behaviors as global semantic understanding features of the user behaviors; and S160, determining a type tag of the recommended digital honor badge based on the global semantic understanding feature of the user behavior.
Specifically, in the technical scheme of the application, firstly, a user behavior data time sequence is extracted from a blockchain network. It should be appreciated that user behavior data typically exists as a record of textual data, which itself contains rich semantic information. Therefore, in order to analyze and understand the behavior patterns and features of the user, in the technical scheme of the application, semantic coding is performed on each user behavior data in the time sequence of the user behavior data so as to extract semantic understanding feature information of each user behavior data respectively, thereby obtaining a sequence of semantic coding feature vectors of the user behavior. In this way, the meaning and purpose of the user's behavior can be better captured, thereby analyzing and understanding the user's behavior patterns more accurately.
Accordingly, in step S120, performing semantic coding on each user behavior data in the time sequence of user behavior data to obtain a sequence of user behavior semantic coding feature vectors, including: and carrying out semantic coding on each user behavior data in the user behavior data time sequence through a user behavior semantic coder so as to obtain a sequence of the user behavior semantic coding feature vector.
Then, in order to convert the user behavior semantic coding feature vectors with different dimensions into the same attention space so as to better capture the association and importance among the user behavior semantic features, in the technical scheme of the application, the sequence of the user behavior semantic coding feature vectors is further mapped to the same attention space through an attention space mapper based on a full connection layer to obtain the sequence of the mapped user behavior semantic coding feature vectors. In this way, the full-connection associated feature information between the user behavior semantic features can be captured.
Accordingly, in step S130, performing attention space mapping on the sequence of the semantic coding feature vectors of the user behavior to obtain a sequence of the semantic coding feature vectors of the user behavior after mapping, including: and mapping the sequence of the user behavior semantic coding feature vectors to the same attention space through an attention space mapper based on a full connection layer to obtain the sequence of the mapped user behavior semantic coding feature vectors.
It is worth mentioning that the fully connected layer (Fully Connected Layer), also called dense connected layer or fully connected layer, is a common layer type in deep neural networks, which is a simple neural network layer, wherein each neuron is connected to all neurons of the previous layer. In the fully connected layer, each input feature is connected to each neuron and weighted sum by weights and then nonlinear transformation by an activation function. This allows mapping of the input features to a new representation space for more advanced feature extraction and classification. The function of the fully connected layer is to introduce nonlinear transformations and feature combinations, thereby increasing the expressive power of the model. It can learn complex relationships between input features and encode these relationships into output features. Fully connected layers are typically used for the last few layers of the deep neural network to map high-level features to final output classes or predictors. In the attention space mapping, a fully connected layer based attention space mapper maps sequences of user behavior semantically encoded feature vectors to the same attention space. Such mapping may help the model better understand the associations and importance between user behaviors, thereby improving understanding and predictive capabilities of the user behaviors. By introducing an attention mechanism, the model can automatically learn the weights and the correlations of different behavior features, so that semantic information of user behaviors can be captured more accurately.
Further, it is considered that each mapped user behavior semantic coding feature vector in the sequence of mapped user behavior semantic coding feature vectors contains different semantic information and importance. Therefore, in order to measure the semantic importance and contribution degree of each feature vector in the whole sequence, thereby providing a more targeted basis for recommending a proper digital honor badge. By calculating the semantic attention weight, the importance of each mapped user behavior semantic coding feature vector relative to the overall feature distribution can be measured. And then, the semantic attention weights are weighted by corresponding vectors, so that the relative importance of each feature vector in the user behavior sequence can be more accurately estimated, the overall understanding and analyzing capability of the user behavior sequence is improved, and a more accurate and comprehensive basis is provided for recommending proper digital honor badges.
Accordingly, in step S140, calculating the semantic attention weight of each post-mapping user behavior semantic coding feature vector in the sequence of post-mapping user behavior semantic coding feature vectors with respect to the feature distribution ensemble of the sequence of post-mapping user behavior semantic coding feature vectors to obtain a sequence of semantic attention weights, including: calculating the semantic attention weight of the feature distribution whole of each mapped user behavior semantic coding feature vector in the sequence of mapped user behavior semantic coding feature vectors relative to the sequence of mapped user behavior semantic coding feature vectors by using the following weight calculation formula to obtain the sequence of semantic attention weights; the weight calculation formula is as follows:
wherein,representing the sequence of the mapped user behavior semantic coding feature vectorThe semantic coding feature vectors of the user behaviors after mapping, A and B areIs a matrix of the (c) in the matrix,is the dimension of each mapped user behavior semantic coding feature vector in the sequence of mapped user behavior semantic coding feature vectors, N is the number of mapped user behavior semantic coding feature vectors in the sequence of mapped user behavior semantic coding feature vectors,is a Sigmoid function of the code,is the first semantic attention weight in the sequence of semantic attention weights.
And then, the global semantic understanding feature vector of the user behavior passes through a classifier to obtain the type label of the recommended digital honor badge. Specifically, the classification tag of the classifier is a type tag of a recommended digital honor badge, so that after the classification result is obtained, a suitable digital honor badge type recommendation can be made based on the classification result to encourage user behavior.
Accordingly, in step S160, determining a type tag of the recommended digital reputation badge based on the user behavior global semantic understanding feature, comprising: and passing the user behavior global semantic understanding feature vector through a classifier to obtain a type tag of the recommended digital honor badge.
Specifically, passing the user behavior global semantic understanding feature vector through a classifier to obtain a type tag of a recommended digital honor badge, including: performing full-connection coding on the user behavior global semantic understanding feature vector by using a full-connection layer of the classifier to obtain a coding classification feature vector; and inputting the encoded classification feature vector into a Softmax classification function of the classifier to obtain a classification result for a type tag representing a recommended digital reputation badge.
It should be appreciated that the role of the classifier is to learn the classification rules and classifier using a given class, known training data, and then classify (or predict) the unknown data. Logistic regression (logistics), SVM, etc. are commonly used to solve the classification problem, and for multi-classification problems (multi-class classification), logistic regression or SVM can be used as well, but multiple bi-classifications are required to compose multiple classifications, but this is error-prone and inefficient, and the commonly used multi-classification method is the Softmax classification function.
Further, in the technical solution of the present application, the DAO operation management method based on the blockchain technology further includes a training step: for training the user behavior semantic encoder, the fully connected layer based attention space mapper and the classifier.
In one example, the training step includes: acquiring training data, the training data comprising a training user behavior data time sequence extracted from a blockchain network and a true value of a type tag of a recommended digital honor badge; performing semantic coding on each training user behavior data in the training user behavior data time sequence through the user behavior semantic coder to obtain a training user behavior semantic coding feature vector sequence; mapping the sequence of the training user behavior semantic coding feature vectors to the same attention space through the attention space mapper based on the full connection layer to obtain a sequence of the training mapped user behavior semantic coding feature vectors; calculating semantic attention weights of feature distribution integers of each training mapped user behavior semantic coding feature vector in the training mapped user behavior semantic coding feature vector sequence relative to the training mapped user behavior semantic coding feature vector sequence to obtain a training semantic attention weight sequence; taking the sequence of training semantic attention weights as weights, and calculating the weighted sum of the sequences of training user behavior semantic coding feature vectors to obtain training user behavior global semantic understanding feature vectors; passing the training user behavior global semantic understanding feature vector through the classifier to obtain a classification loss function value; and training the user behavior semantic encoder, the full-connection layer based attention space mapper and the classifier with the classification loss function values, wherein the training user behavior global semantic understanding feature vector is optimized in each iteration of the training.
Wherein passing the training user behavior global semantic understanding feature vector through the classifier to obtain a classification loss function value comprises: processing the training user behavior global semantic understanding feature vector by the classifier according to the following classification training formula to obtain a training classification result, wherein the classification training formula is as follows:
wherein, the method comprises the steps of, wherein,to the point ofAs a matrix of weights, the weight matrix,to the point ofX is the global semantic understanding feature vector of the training user behavior; and calculating a cross entropy value between the training classification result and the true value as the classification loss function value.
In particular, in the above technical solution, each training user behavior semantic coding feature vector in the sequence of training user behavior semantic coding feature vectors is used to represent a semantic association feature of training user behavior data, and considering the initial source data modal difference, although the training user behavior semantic coding feature vectors are mapped to the same attention space by an attention space mapper based on a full connection layer, there is still a feature distribution difference. In addition, after the semantic attention weight is calculated and the sequence of the training semantic attention weight is used for fusing the sequence of the training user behavior semantic coding feature vector, the obtained inconsistency and instability of the overall feature distribution of the training user behavior global semantic understanding feature vector are more remarkable, so that the stability of classification training of the training user behavior global semantic understanding feature vector through a classifier is affected.
Based on the above, the applicant of the present application optimizes the training user behavior global semantic understanding feature vector at each iteration when classifying and training the training user behavior global semantic understanding feature vector by a classifier.
Accordingly, in one example, optimizing the training user behavior global semantic understanding feature vector in each iteration of the training includes: in each iteration of the training, optimizing the training user behavior global semantic understanding feature vector by using the following optimization formula to obtain an optimized training user behavior global semantic understanding feature vector; wherein, the optimization formula is:
wherein,is the training user behavior global semantic understanding feature vector,is the global semantic understanding feature vector of the training user behaviorIs the first of (2)The value of the characteristic is a value of,andis the global semantic understanding feature vector of the training user behaviorIs set to 1-norm and 2-norm of (c),is the vector of the training user behavior global semantic understanding feature vectorLength andis related toIs used for the weight exceeding parameter of the (a),an exponential operation representing a numerical value, the exponential operation representing the calculation of a natural exponential function value that is a power of the numerical value,is the first eigenvalue of the optimized training user behavior global semantic understanding eigenvector.
Here, feature vectors are globally semantically understood by the training user behaviorIs used for carrying out the training of the global semantic understanding feature vector of the user behaviorThe consistency and stability of the global feature distribution of the training user behavior global semantic understanding feature vector under the rigid structure of absolute distance and the non-rigid structure of spatial distance respectively can enable the global feature distribution of the training user behavior global semantic understanding feature vector to have a certain repeatability to the local mode change in the vector distribution direction, thus, when the training user behavior global semantic understanding feature vectorWhen the user is classified by the classifier, the training process carries out global semantic understanding on the feature vector of the training user behaviorGlobal feature classification of (2)The scale and rotation change of the weight matrix of the classifier are distributed to be more robust, so that the stability of the classification training process is improved. In this way, a suitable digital honor badge type recommendation can be made based on a time series sequence of user behavior data extracted from the blockchain network to motivate user behavior, in such a way that user engagement and contribution can be increased, thereby enhancing user attribution and identity, facilitating interactions and collaboration between users, and enhancing DAO's community vitality and development potential.
In summary, a blockchain technology-based DAO operation management method is illustrated that may facilitate the development and operation of DAOs.
Fig. 3 is a block diagram of a DAO operations management system 100 based on blockchain technology in accordance with an embodiment of the present application. As shown in fig. 3, the DAO operation management system 100 based on the blockchain technique according to the embodiment of the present application includes: a data acquisition module 110 for extracting a user behavior data timing sequence from the blockchain network; the semantic coding module 120 is configured to perform semantic coding on each user behavior data in the time sequence of user behavior data to obtain a sequence of user behavior semantic coding feature vectors; an attention space mapping module 130, configured to perform attention space mapping on the sequence of user behavior semantic coding feature vectors to obtain a sequence of mapped user behavior semantic coding feature vectors; the weight calculation module 140 is configured to calculate a semantic attention weight of each mapped user behavior semantic coding feature vector in the sequence of mapped user behavior semantic coding feature vectors relative to a feature distribution entirety of the sequence of mapped user behavior semantic coding feature vectors to obtain a sequence of semantic attention weights; the weighting module 150 is configured to calculate a weighted sum of the sequence of the semantic coding feature vectors of the user behavior by using the sequence of the semantic attention weights as weights, so as to obtain a global semantic understanding feature vector of the user behavior as a global semantic understanding feature of the user behavior; and a type analysis module 160 for determining a type tag for the recommended digital reputation badge based on the user behavior global semantic understanding feature.
In one example, in the DAO operation management system 100 based on the blockchain technique, the semantic encoding module 120 is configured to: and carrying out semantic coding on each user behavior data in the user behavior data time sequence through a user behavior semantic coder so as to obtain a sequence of the user behavior semantic coding feature vector.
Here, it will be understood by those skilled in the art that the specific functions and operations of the respective modules in the above-described blockchain technology-based DAO operation management system 100 have been described in detail in the above description of the blockchain technology-based DAO operation management method with reference to fig. 1 to 2, and thus, repetitive descriptions thereof will be omitted.
As described above, the DAO operation management system 100 based on the blockchain technique according to the embodiment of the present application may be implemented in various wireless terminals, for example, a server or the like having a DAO operation management algorithm based on the blockchain technique. In one example, the blockchain technology-based DAO operation management system 100 according to embodiments of the present application may be integrated into a wireless terminal as one software module and/or hardware module. For example, the blockchain technology-based DAO operation management system 100 may be a software module in the operating system of the wireless terminal, or may be an application developed for the wireless terminal; of course, the DAO operation management system 100 based on the blockchain technique may also be one of a plurality of hardware modules of the wireless terminal.
Alternatively, in another example, the blockchain technology-based DAO operation management system 100 and the wireless terminal may also be separate devices, and the blockchain technology-based DAO operation management system 100 may connect to the wireless terminal through a wired and/or wireless network and transmit the interaction information in a agreed data format.
Fig. 4 is an application scenario diagram of a DAO operation management method based on a blockchain technique according to an embodiment of the present application. As shown in fig. 4, in this application scenario, first, a user behavior data time series sequence (e.g., D illustrated in fig. 4) is extracted from a blockchain network, and then, is input into a server (e.g., S illustrated in fig. 4) in which a blockchain technology-based DAO operation management algorithm is deployed, wherein the server is capable of processing the user behavior data time series sequence using the blockchain technology-based DAO operation management algorithm to obtain a type tag of a recommended digital honor badge.
It should be understood that, in the DAO operation management method based on the blockchain technology in the embodiments of the present application, the DAO operation mode is introduced, the organization management form is optimized, the traditional top-down hierarchical operation management mechanism is changed, through the decentralization concept, the full open and autonomous interaction is performed, and the common organization targets are used as guidance, so as to form a co-creation, co-treatment and sharing co-operation mode of the members, and the enthusiasm and subjective activity of the members are stimulated, so that the organization efficiency is promoted to realize the value circulation.
Further, referring to fig. 5, the dao operation mode includes a protocol layer, a hardware layer, an organization layer, a user layer, and an incentive layer. Wherein the protocol layer triggers the automatic allocation of various rights and interests within the DAO using various different types of intelligent contracts, which are written on the blockchain as a set of computer programs for executing various commands, the intelligent contracts being publicly transparent, everyone can see each line of code. The hardware layer ensures that the whole community product can normally run on the chain through the blockchain technology, the user account system can be integrally converted into the chain through the wallet, and the behavior data are reserved on the chain. The organization layer can be divided into functional departments, functional departments and authorities. The functional departments are responsible for financial audit, data summarization, activity organization, meeting record and other DAO internal matters; the functional department takes charge of the value capture and output of the DAO, and is generally related to specific business and projects to be propelled by the DAO, such as parties, project groups and the like related to various interests; the authority is responsible for the passing of the proposal, the money-dialing matters of various parties and project groups, and the like. Each department has no upper and lower level and only has difference in function and function. The user layer sets three levels of primary users, medium-level users and high-level users and corresponding level scales, the users finish specific behaviors in the channels, such as channel speaking, comment posts, praise and the like, experience can be obtained, and the level scales are obtained after the user experience is accumulated to a certain level. The operation convention formulates a first edition of user growth system, the user can be upgraded to a middle grade and a high grade by a primary user after reaching a certain grade, the user can be endowed with a corresponding label of an identity group after upgrading to a corresponding user grade, a new task system is unlocked after the user is upgraded to the high grade, a specific task or a community project is completed, point rewards can be obtained, various digital medals are won, and an administrator can match the user labels for the points and the medals, so that a personalized label system with different everybody is formed. In the incentive layer, the incentive in the DAO is mainly virtual digital assets such as points, digital medals and the like, and specific point issuing rules and flows are automatically formulated by each convention. The committee of governance needs to determine the actual value of the points early in order for the congress to evaluate the staff's labor value and to formulate specific criteria and rules. The consumption of the points can be directly carried out in a physical exchange form or the points are converted into chains, and the external value is introduced through the on-chain point exchange. The excitation is mainly divided into three parts. Medal represents the record of various meaningful actions of a user in a community, points represent rewards of the user for participating in specific activities of the community, the real objects are returned to the user after the value of the community is honored, and the points and medal rewards are generally counted and settled in units of a convention or a project team.
Specifically, based on public blockchain, DID (decentralised digital identity) infrastructure construction is introduced, a foundation is laid for docking with other platforms in the future, the first pass in each platform can be met in the future, and the succession and continuation of the identity value in different platforms are realized. Issuing digital honor badge in NFT (digital collection) form, building user honor system, matching platform excitation mechanism, exciting user achievement sense and identification sense, improving user liveness and loyalty, and simultaneously adding a certain activity threshold and privileges to cause user challenge and conquer desire, improving the driving force. By using the medal, a medal economic model is constructed, the concept of 'wind throwing' is introduced, the user is guided to actively participate in the innovative hatching process, the viscosity of the user is enhanced, and the improvement of the innovative atmosphere is promoted. By introducing a social DAO (decentralized autonomous organization) operation mode, a user can establish an autonomous community organization together with the like-minded partners, freely recruit members and autonomously operate and manage, achieve consensus among the members, form division of work, achieve the aim and accelerate cultivation and shaping of innovative talent teams. Through the realization of the functions, the whole innovation mechanism is continuously perfected, the innovation atmosphere is stimulated, and the innovation work is advanced to develop orderly.
Furthermore, those skilled in the art will appreciate that the various aspects of the invention are illustrated and described in the context of a number of patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The foregoing is illustrative of the present invention and is not to be construed as limiting thereof. Although a few exemplary embodiments of this invention have been described, those skilled in the art will readily appreciate that many modifications are possible in the exemplary embodiments without materially departing from the novel teachings and advantages of this invention. Accordingly, all such modifications are intended to be included within the scope of this invention as defined in the following claims. It is to be understood that the foregoing is illustrative of the present invention and is not to be construed as limited to the specific embodiments disclosed, and that modifications to the disclosed embodiments, as well as other embodiments, are intended to be included within the scope of the appended claims. The invention is defined by the claims and their equivalents.
Claims (8)
1. A DAO operation management method based on a blockchain technique, comprising:
extracting a user behavior data time sequence from the blockchain network;
carrying out semantic coding on each user behavior data in the user behavior data time sequence to obtain a sequence of user behavior semantic coding feature vectors;
performing attention space mapping on the sequence of the user behavior semantic coding feature vectors to obtain a sequence of mapped user behavior semantic coding feature vectors;
calculating the semantic attention weight of the whole feature distribution of each mapped user behavior semantic coding feature vector in the sequence of mapped user behavior semantic coding feature vectors relative to the sequence of mapped user behavior semantic coding feature vectors so as to obtain a sequence of semantic attention weights;
taking the sequence of semantic attention weights as weights, and calculating the weighted sum of the sequence of the user behavior semantic coding feature vectors to obtain a user behavior global semantic understanding feature vector as a user behavior global semantic understanding feature; and
based on the user behavior global semantic understanding feature, a type tag of a recommended digital honor badge is determined.
2. The DAO operation management method based on blockchain technology according to claim 1, wherein semantically encoding each user behavior data in the time sequence of user behavior data to obtain a sequence of user behavior semantically encoded feature vectors comprises:
and carrying out semantic coding on each user behavior data in the user behavior data time sequence through a user behavior semantic coder so as to obtain a sequence of the user behavior semantic coding feature vector.
3. The DAO operation management method based on blockchain technique of claim 2, wherein performing an attention space mapping on the sequence of user behavior semantic coding feature vectors to obtain a sequence of mapped user behavior semantic coding feature vectors comprises:
and mapping the sequence of the user behavior semantic coding feature vectors to the same attention space through an attention space mapper based on a full connection layer to obtain the sequence of the mapped user behavior semantic coding feature vectors.
4. The DAO operation management method based on blockchain technology according to claim 3, wherein calculating the semantic attention weight of each post-mapping user behavior semantic coding feature vector in the sequence of post-mapping user behavior semantic coding feature vectors with respect to the feature distribution ensemble of the sequence of post-mapping user behavior semantic coding feature vectors to obtain the sequence of semantic attention weights comprises:
calculating the semantic attention weight of the feature distribution whole of each mapped user behavior semantic coding feature vector in the sequence of mapped user behavior semantic coding feature vectors relative to the sequence of mapped user behavior semantic coding feature vectors by using the following weight calculation formula to obtain the sequence of semantic attention weights; the weight calculation formula is as follows:
wherein,representing the sequence of the mapped user behavior semantic coding feature vectorThe semantic coding feature vectors of the user behaviors after mapping, A and B areIs a matrix of the (c) in the matrix,is the dimension of each mapped user behavior semantic coding feature vector in the sequence of mapped user behavior semantic coding feature vectors, N is the number of mapped user behavior semantic coding feature vectors in the sequence of mapped user behavior semantic coding feature vectors,is a Sigmoid function of the code,is the first semantic attention weight in the sequence of semantic attention weights.
5. The blockchain technology-based DAO operation management method of claim 4, wherein determining a type tag of a recommended digital reputation badge based on the user behavior global semantic understanding feature comprises:
and passing the user behavior global semantic understanding feature vector through a classifier to obtain a type tag of the recommended digital honor badge.
6. The DAO operation management method based on blockchain technique of claim 5, further comprising a training step of: for training the user behavior semantic encoder, the fully connected layer based attention space mapper and the classifier.
7. The DAO operation management method based on blockchain technique of claim 6, wherein the training step comprises:
acquiring training data, the training data comprising a training user behavior data time sequence extracted from a blockchain network and a true value of a type tag of a recommended digital honor badge;
performing semantic coding on each training user behavior data in the training user behavior data time sequence through the user behavior semantic coder to obtain a training user behavior semantic coding feature vector sequence;
mapping the sequence of the training user behavior semantic coding feature vectors to the same attention space through the attention space mapper based on the full connection layer to obtain a sequence of the training mapped user behavior semantic coding feature vectors;
calculating semantic attention weights of feature distribution integers of each training mapped user behavior semantic coding feature vector in the training mapped user behavior semantic coding feature vector sequence relative to the training mapped user behavior semantic coding feature vector sequence to obtain a training semantic attention weight sequence;
taking the sequence of training semantic attention weights as weights, and calculating the weighted sum of the sequences of training user behavior semantic coding feature vectors to obtain training user behavior global semantic understanding feature vectors;
passing the training user behavior global semantic understanding feature vector through the classifier to obtain a classification loss function value; and
training the user behavior semantic encoder, the full-connection layer-based attention space mapper and the classifier with the classification loss function values, wherein the training user behavior global semantic understanding feature vector is optimized in each iteration of the training.
8. The blockchain technology-based DAO operation management method of claim 7, wherein passing the training user behavior global semantic understanding feature vector through the classifier to obtain a classification loss function value comprises:
by the divisionThe classifier processes the training user behavior global semantic understanding feature vector with the following classification training formula to obtain a training classification result, wherein the classification training formula is as follows:wherein, the method comprises the steps of, wherein,to the point ofAs a matrix of weights, the weight matrix,to the point ofX is the global semantic understanding feature vector of the training user behavior; and
and calculating a cross entropy value between the training classification result and the true value as the classification loss function value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410030530.4A CN117540935B (en) | 2024-01-09 | 2024-01-09 | DAO operation management method based on block chain technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410030530.4A CN117540935B (en) | 2024-01-09 | 2024-01-09 | DAO operation management method based on block chain technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117540935A true CN117540935A (en) | 2024-02-09 |
| CN117540935B CN117540935B (en) | 2024-04-05 |
Family
ID=89790393
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410030530.4A Active CN117540935B (en) | 2024-01-09 | 2024-01-09 | DAO operation management method based on block chain technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117540935B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3166020A1 (en) * | 2015-11-06 | 2017-05-10 | Thomson Licensing | Method and apparatus for image classification based on dictionary learning |
| US20210004691A1 (en) * | 2019-07-03 | 2021-01-07 | Kenneth Neumann | Artificial intelligence advisory systems and methods for behavioral pattern matching and language generation |
| CN112732936A (en) * | 2021-01-11 | 2021-04-30 | 电子科技大学 | Radio and television program recommendation method based on knowledge graph and user microscopic behaviors |
| WO2021159751A1 (en) * | 2020-09-22 | 2021-08-19 | 平安科技（深圳）有限公司 | Semantic and image recognition-based electrocardiography information extraction method and apparatus, computer device, and storage medium |
| US20220367061A1 (en) * | 2021-05-13 | 2022-11-17 | Retain Health, Inc | System and method for text-based conversation with a user, using machine learning |
| CN116168352A (en) * | 2023-04-26 | 2023-05-26 | 成都睿瞳科技有限责任公司 | Power grid obstacle recognition processing method and system based on image processing |
| CN116245513A (en) * | 2023-05-11 | 2023-06-09 | 深圳市联合信息技术有限公司 | Automatic operation and maintenance system and method based on rule base |
| CN116943229A (en) * | 2023-01-03 | 2023-10-27 | 深圳市腾讯计算机系统有限公司 | Data processing method, device, equipment and storage medium |
| CN116992007A (en) * | 2023-09-28 | 2023-11-03 | 北京致远互联软件股份有限公司 | Limiting question-answering system based on question intention understanding |
| CN117197722A (en) * | 2023-10-16 | 2023-12-08 | 北京中科网芯科技有限公司 | User perception and analysis system based on mobile internet video |
-
2024
- 2024-01-09 CN CN202410030530.4A patent/CN117540935B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3166020A1 (en) * | 2015-11-06 | 2017-05-10 | Thomson Licensing | Method and apparatus for image classification based on dictionary learning |
| US20210004691A1 (en) * | 2019-07-03 | 2021-01-07 | Kenneth Neumann | Artificial intelligence advisory systems and methods for behavioral pattern matching and language generation |
| WO2021159751A1 (en) * | 2020-09-22 | 2021-08-19 | 平安科技（深圳）有限公司 | Semantic and image recognition-based electrocardiography information extraction method and apparatus, computer device, and storage medium |
| CN112732936A (en) * | 2021-01-11 | 2021-04-30 | 电子科技大学 | Radio and television program recommendation method based on knowledge graph and user microscopic behaviors |
| US20220367061A1 (en) * | 2021-05-13 | 2022-11-17 | Retain Health, Inc | System and method for text-based conversation with a user, using machine learning |
| CN116943229A (en) * | 2023-01-03 | 2023-10-27 | 深圳市腾讯计算机系统有限公司 | Data processing method, device, equipment and storage medium |
| CN116168352A (en) * | 2023-04-26 | 2023-05-26 | 成都睿瞳科技有限责任公司 | Power grid obstacle recognition processing method and system based on image processing |
| CN116245513A (en) * | 2023-05-11 | 2023-06-09 | 深圳市联合信息技术有限公司 | Automatic operation and maintenance system and method based on rule base |
| CN116992007A (en) * | 2023-09-28 | 2023-11-03 | 北京致远互联软件股份有限公司 | Limiting question-answering system based on question intention understanding |
| CN117197722A (en) * | 2023-10-16 | 2023-12-08 | 北京中科网芯科技有限公司 | User perception and analysis system based on mobile internet video |
Non-Patent Citations (1)
| Title |
|---|
| 胡涛;吴涛;李焱;: "一种基于场景识别的快速语义标注方法", 华中科技大学学报(自然科学版), no. 1, 10 January 2014 (2014-01-10) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117540935B (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pratapa et al. | Benchmarking algorithms for gene regulatory network inference from single-cell transcriptomic data | |
| Heppenstall et al. | Future developments in geographical agent‐based models: Challenges and opportunities | |
| Li et al. | Application of interpretable machine learning models for the intelligent decision | |
| Wang et al. | Predicting construction cost and schedule success using artificial neural networks ensemble and support vector machines classification models | |
| Azadeh et al. | Improved estimation of electricity demand function by integration of fuzzy system and data mining approach | |
| Laatabi et al. | ODD+ 2D: An ODD based protocol for mapping data to empirical ABMs | |
| Thangavel et al. | Student placement analyzer: A recommendation system using machine learning | |
| Azadeh et al. | An adaptive network based fuzzy inference system–genetic algorithm clustering ensemble algorithm for performance assessment and improvement of conventional power plants | |
| CN109767312A (en) | A kind of training of credit evaluation model, appraisal procedure and device | |
| CN112328646B (en) | Multitask course recommendation method and device, computer equipment and storage medium | |
| Ahmed et al. | Discovering diverse, high quality design ideas from a large corpus | |
| Li et al. | Explain graph neural networks to understand weighted graph features in node classification | |
| Azadeh et al. | An integrated artificial neural network fuzzy C-means-normalization algorithm for performance assessment of decision-making units: The cases of auto industry and power plant | |
| CN111639706A (en) | Personal risk portrait generation method based on image set and related equipment | |
| CN115099450A (en) | Family carbon emission monitoring and accounting platform based on fusion model | |
| Liu et al. | Enhancing input parameter estimation by machine learning for the simulation of large-scale logistics networks | |
| CN110310012A (en) | Data analysing method, device, equipment and computer readable storage medium | |
| CN117540935B (en) | DAO operation management method based on block chain technology | |
| Baggio | Agent-based modeling and simulations | |
| Nagaraju et al. | Methodologies used for customer churn detection in customer relationship management | |
| Hollenstein et al. | Unsupervised learning and simulation for complexity management in business operations | |
| Prathan et al. | Determining the best‐fit programmers using Bayes’ theorem and artificial neural network | |
| Gafarov et al. | Analysis of students’ academic performance by using machine learning tools | |
| CN114266394A (en) | Enterprise portrait and scientific service personalized demand prediction method oriented to scientific service platform | |
| Kumar et al. | Selection of evolutionary approach based hybrid data mining algorithms for decision support systems and business intelligence |
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 |