CN113468017A - Online service state detection method applied to block chain and service server - Google Patents

Online service state detection method applied to block chain and service server Download PDF

Info

Publication number
CN113468017A
CN113468017A CN202110666539.0A CN202110666539A CN113468017A CN 113468017 A CN113468017 A CN 113468017A CN 202110666539 A CN202110666539 A CN 202110666539A CN 113468017 A CN113468017 A CN 113468017A
Authority
CN
China
Prior art keywords
service
state
block chain
content
business
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
CN202110666539.0A
Other languages
Chinese (zh)
Inventor
崔恒锋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN202110666539.0A priority Critical patent/CN113468017A/en
Publication of CN113468017A publication Critical patent/CN113468017A/en
Withdrawn legal-status Critical Current

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
    • G06F11/3055—Monitoring arrangements for monitoring the status of the computing system or of the computing system component, e.g. monitoring if the computing system is on, off, available, not available
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
    • G06F11/3006—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems
    • 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
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/60—Protecting data
    • G06F21/64—Protecting data integrity, e.g. using checksums, certificates or signatures

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Security & Cryptography (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Quality & Reliability (AREA)
  • Mathematical Physics (AREA)
  • Health & Medical Sciences (AREA)
  • Bioethics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Hardware Design (AREA)
  • Software Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The embodiment of the application discloses an online service state detection method and a service server applied to a block chain, service item contents are considered in the attribution classification process of the service states of block chain link points, so that the classification judgment dimensionality of the service states can be increased, the influence of the detection error of a single classification judgment dimensionality on the service state detection result is avoided as much as possible in the process of determining the service states of the same block chain link points, the reliability of the service state detection result aiming at the same block chain node is further ensured, the service states of the block chain link points of other block chain nodes are prevented from being wrongly classified, and accurate and reliable analysis basis can be provided for subsequent block chain link point state analysis. Therefore, by adopting the scheme, the technical problems of low classification accuracy and poor reliability of the service state of the block link points in the related technology can be solved.

Description

Online service state detection method applied to block chain and service server
Technical Field
The present application relates to the field of block chains and online service technologies, and in particular, to an online service state detection method and a service server applied to a block chain.
Background
The blockchain is also called a distributed ledger, and the safety of the ledger is ensured by means of redundantly storing ledger data in all participating nodes. In general, the blockchain technique may involve peer-to-peer (P2P), cryptography, and distributed consensus algorithms. With the development of the block chain technology, the service application field of the block chain is more and more extensive except the financial service field, and the handling efficiency and the safety of various services are effectively improved.
At present, the intelligent and digital degree of business handling can be improved by deeply combining the block chain and the cloud business, so that the digital transformation of social production and life is ensured. In general, due to the distributed computing nature of blockchains, the business transactions of different blockchain link points (devices) are relatively independent. In some cases, the service state of different blockchain nodes needs to be classified under the condition that comprehensive analysis needs to be performed on service handling. However, the related art has the technical problems of low accuracy and poor reliability of classification of the service states of the block link nodes.
Disclosure of Invention
One aspect of the present embodiment is to provide an online service status detection method applied to a block chain, including:
acquiring service states of two groups of block chain link points to be detected; respectively identifying service items aiming at the service state of each group of block link nodes to obtain service item contents corresponding to the service state of the block link nodes;
performing relevance analysis on the business item contents to obtain relevant business item contents; the related business affair content represents the related condition among all the business affair contents;
inputting the content of the associated business transaction into: a state relevance analysis network which is trained based on the relevant service item content samples is obtained in advance, and an output result which represents the relevance condition between the service states of the block chain nodes is obtained;
and obtaining a service state detection result whether the service state of the block chain node belongs to the same block chain node according to the comparison relation between the output result and a preset detection condition.
Preferably, the business transaction content includes: multidimensional dynamic business item content; the associated business transaction content comprises: globally associating business item content;
the method for respectively identifying the service items aiming at the service state of each group of block chain nodes to obtain the service item content corresponding to the service state of the block chain node comprises the following steps: analyzing and obtaining the multidimensional dynamic service item content of the service state of each block chain node based on the service interaction object and the service interaction period information of the service state fragment contained in the service state of each group of block chain nodes;
the step of analyzing the relevance of each business item content to obtain the relevant business item content comprises the following steps: performing relevance analysis on the multidimensional dynamic service item contents of the service states of the two groups of block link nodes to obtain overall relevant service item contents;
the input of the associated business transaction content to: obtaining an output result representing the correlation condition between the service states of the block chain nodes based on a state correlation analysis network which is trained based on the related service item content samples in advance, wherein the output result comprises the following steps: inputting the global associated business transaction content into: and analyzing the network based on the state relevance of the overall relevant service event content sample training to obtain an output result representing the relevance condition between the service states of the block chain nodes.
Preferably, the business transaction content includes: signing the business item content and the multidimensional dynamic business item content; the associated business transaction content comprises: local associated service item content and global associated service item content;
the step of respectively performing service item identification on the service state of each group of block link nodes to obtain the service item content corresponding to the service state of the block link node comprises the following steps: respectively acquiring block link point signatures corresponding to the service states of all block link points; carrying out signature service item identification on the block chain node signature corresponding to the service state of each group of block chain nodes to obtain the signature service item content of the service state of the block chain node; analyzing and obtaining the multidimensional dynamic service item content of the service state of each block chain node based on the service interaction object and the service interaction period information of the service state fragment contained in the service state of each group of block chain nodes;
the analyzing the relevance of each business item content to obtain the relevant business item content includes: performing relevance analysis on the signature service item contents of the service states of the two groups of block chain nodes to obtain local relevance service item contents; performing relevance analysis on the multidimensional dynamic service item contents of the service states of the two groups of block link nodes to obtain overall relevant service item contents;
the input of the associated business transaction content to: obtaining an output result representing the correlation condition between the service states of the block chain nodes based on a state correlation analysis network which is trained based on the related service item content samples in advance, wherein the output result comprises the following steps: inputting the local associated business transaction content and the global associated business transaction content to: and obtaining an output result representing the correlation condition between the service states of the block chain nodes based on a state correlation analysis network trained by local correlation service item content and global correlation service item content samples in advance.
Preferably, the business transaction content includes: signing the business item content, the multidimensional dynamic business item content and the node relation business item content; the associated business transaction content comprises: local associated service item content and global associated service item content;
the step of respectively performing service item identification on the service state of each group of block link nodes to obtain the service item content corresponding to the service state of the block link node comprises the following steps: respectively acquiring block link point signatures corresponding to the service states of all block link points; carrying out signature service item identification on the block chain node signature corresponding to the service state of each group of block chain nodes to obtain the signature service item content of the service state of the block chain node; analyzing and obtaining the multidimensional dynamic service item content of the service state of each block chain node based on the service interaction object and the service interaction period information of the service state fragment contained in the service state of each group of block chain nodes; acquiring node relation service transaction contents corresponding to the service states of the two groups of block chain nodes, wherein the node relation service transaction contents represent that: extracting service interaction object information of the central management node of the block chain node signature corresponding to the service states of the two groups of block chain nodes in the current cloud service scene; or, the node relation service transaction content indicates: the same block chain node respectively extracts the prediction information of the switching between the central management nodes of the block chain node signatures corresponding to the service states of the two groups of block chain nodes;
the analyzing the relevance of each business item content to obtain the relevant business item content includes: performing relevance analysis on the signature service item contents of the service states of the two groups of block chain nodes to obtain local relevance service item contents; performing relevance analysis on the multidimensional dynamic service item contents of the service states of the two groups of block link nodes to obtain overall relevant service item contents;
the input of the associated business transaction content to: obtaining an output result representing the correlation condition between the service states of the block chain nodes based on a state correlation analysis network which is trained based on the related service item content samples in advance, wherein the output result comprises the following steps: inputting the local associated service transaction contents, the global associated service transaction contents and the node relation service transaction contents corresponding to the service states of the two groups of block chain nodes into: and obtaining an output result representing the correlation condition among the service states of the block chain nodes in advance based on a state correlation analysis network which is trained by the local correlation service item content samples, the global correlation service item content samples and the node relation service item samples.
Preferably, the multidimensional dynamic business transaction content includes: hot service item content and cold service item content;
the analyzing and obtaining the multidimensional dynamic service item content of the block chain node service state based on the service interaction object and the service interaction period information of the service state segment contained in the service state of each group of block chain node points comprises the following steps:
analyzing and obtaining hot service item contents of the service state of each group of block chain node points based on the service interaction objects and service interaction period information of the service state segments contained in the service state of each group of block chain node points;
and converting the block link node service state into a plurality of candidate service states, and analyzing and obtaining the cold service item content of each candidate service state based on the service interaction object and the service interaction period information of the service state segment contained in each candidate service state.
Preferably, the hot service event content and the cold service event content each include at least one preset type of service event content: dynamically requesting, responding, calling, cooperating and expanding the business item content;
the global associated business transaction content comprises: scene associated service item content and object associated service item content; the performing relevance analysis on the multidimensional dynamic service item content of the service states of the two groups of block link nodes to obtain global relevance service item content includes:
respectively carrying out preset content identification on each preset type service item content contained in hot service item contents of the service states of the two groups of block chain nodes to obtain scene associated service item contents;
and respectively carrying out preset content identification on each preset type service item content contained in the cold service item contents of the service states of the two groups of block chain nodes to obtain object associated service item contents.
Preferably, the step of training the network model of the state correlation analysis network includes:
acquiring a training sample set containing related business item content samples and training sample description values corresponding to the related business item content samples;
inputting the related business affair content sample into a state relevance analysis network to obtain a sample output result which represents the correlation condition between two business state samples corresponding to the related business affair content sample;
judging whether the difference result between the sample output result and the training sample description value meets the set model performance evaluation condition or not;
if so, judging that the training of the network model is finished, and obtaining a trained state correlation analysis network;
if not, adjusting the network model parameters in the state relevance analysis network, returning to the step of inputting the related business item content sample into the state relevance analysis network to obtain a sample output result representing the correlation condition between the two business state samples corresponding to the related business item content sample, and continuing to perform the next network model training.
Preferably, after obtaining the trained state association analysis network, the method further includes:
respectively inputting all the related business item content samples which are not used in the training sample set into the state relevance analysis network after the training is finished to obtain output results of all the samples;
aiming at each sample output result, respectively obtaining a service state detection result of whether two service state samples corresponding to the sample output result belong to the same block chain node according to the comparison relation between the sample output result and a preset alternative detection condition;
analyzing the state detection matching degree of the service state detection result based on the training sample description value corresponding to each sample output result;
judging whether the state detection matching degree is larger than a preset state detection matching degree threshold value or not;
if yes, determining the alternative detection conditions as preset detection conditions to be used;
if not, adjusting the alternative detection conditions, returning the output result of each sample, and obtaining the service state detection result whether the two service state samples corresponding to the output result of the sample belong to the same block chain node or not according to the comparison relation between the output result of the sample and the preset alternative detection conditions respectively until the state detection matching degree of the service state detection result is greater than the preset state detection matching degree threshold value; and determining the alternative detection condition which enables the state detection matching degree of the service state detection result to be larger than the preset state detection matching degree threshold value as the preset detection condition to be used.
Preferably, the obtaining of the training sample description value including the training sample set including the associated business event content sample and corresponding to each associated business event content sample includes:
respectively obtaining a plurality of service state samples corresponding to different block chain link points;
respectively identifying service items aiming at each service state sample to obtain a service item content sample corresponding to each service state sample;
performing relevance analysis on any two business item content samples to obtain a group of relevant business item content samples in a training sample set;
determining a training sample description value corresponding to the associated business item content sample according to whether the two business item content samples belong to the same block chain node; when the two business item content samples belong to the same block chain node, determining that the training sample description value corresponding to the associated business item content sample is a first set value, otherwise, determining that the training sample description value corresponding to the associated business item content sample is a second set value; wherein the associated business transaction content sample represents an association between the two business transaction content samples.
One aspect of the embodiments of the present application is to provide a service server, including a processing engine, a network module, and a memory; the processing engine and the memory communicate through the network module, and the processing engine reads the computer program from the memory and operates to perform the above-described method. In the description that follows, additional features will be set forth, in part, in the description. These features will be in part apparent to those skilled in the art upon examination of the following and the accompanying drawings, or may be learned by production or use. The features of the present application may be realized and attained by practice or use of various aspects of the methodologies, instrumentalities and combinations particularly pointed out in the detailed examples that follow.
Drawings
The present application will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and in these embodiments like numerals are used to indicate like structures, wherein:
FIG. 1 is a flow diagram illustrating an exemplary online traffic status detection method and/or process applied to blockchains, according to some embodiments of the invention;
FIG. 2 is a block diagram illustrating an exemplary on-line traffic status detection apparatus applied to a blockchain in accordance with some embodiments of the present invention;
FIG. 3 is a block diagram illustrating an exemplary on-line traffic status detection system applied to a blockchain, according to some embodiments of the invention, an
Fig. 4 is a diagram illustrating hardware and software components in an exemplary service server according to some embodiments of the invention.
Detailed Description
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments will be briefly introduced below. It is obvious that the drawings in the following description are only examples or embodiments of the application, from which the application can also be applied to other similar scenarios without inventive effort for a person skilled in the art. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.
It should be understood that "system", "device", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.
As used in this application and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.
Flow charts are used herein to illustrate 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 the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.
Aiming at the technical problems described in the background art, the inventor innovatively provides an online service state detection method and a cloud server applied to a block chain, which can perform service item identification on service states of different block chain link points to obtain service item contents, further realize relevance analysis of the service item contents to obtain relevant service item contents, and analyze and process the relevant service item contents by using a pre-trained state relevance analysis network to obtain an output result representing the relevance condition between the service states of the block chain link points, so that a service state detection result of whether the service states of the block chain nodes belong to the same block chain node can be obtained according to a comparison relation between the output result and a preset detection condition.
It can be understood that, since the service item content is considered in the process of belonging and classifying the service state of the block link point, the classification judgment dimension of the service state can be increased, so that in the process of determining the service state of the same block link point, the influence of the detection error of a single classification judgment dimension on the service state detection result is avoided as much as possible, and the reliability of the service state detection result for the same block link node is further ensured. Therefore, by adopting the scheme, the technical problems of low classification accuracy and poor reliability of the service state of the block link points in the related technology can be solved.
Referring to fig. 1, a flowchart of an exemplary online service state detection method and/or process applied to a blockchain is shown, and the online service state detection method applied to a blockchain may include the technical solutions described in step S1-step S4 in one of the following embodiments.
Example one
Step S1, acquiring service states of two groups of block chain link points to be detected; and respectively identifying service items aiming at the service state of each group of block chain nodes to obtain the service item content corresponding to the service state of the block chain node.
In this embodiment, the service state of the block link point to be detected may be understood as the service state of the block link point to be classified, and the service state of the block link point is used to record various types of state information of the corresponding block link point in the service interaction process, and when the block link point is applied to different service scenes, the various types of state information corresponding to the service state of the block link point may be different. Generally, scenarios for block-linked point applications include, but are not limited to, cross-border payments, teleworking, smart medicine, smart parks, cloud gaming, big data mining, and the like.
For example, when the scenario in which the blob is applied is a cross-border payment scenario, the blob service state may include payment state information, collection state information, identity verification state information, or network test state information.
In addition, the service transaction identifies service transaction contents corresponding to service states of different blockchain nodes, and the service transaction contents may include different types/dimensions of transaction contents, such as multidimensional dynamic service transaction contents, signature service transaction contents, node relation service transaction contents, and the like, and the service transaction contents will be further described based on different embodiments.
Step S2, performing relevance analysis on each business item content to obtain relevant business item content.
In this embodiment, the related service item content represents a correlation between the service item contents, and performing correlation analysis on the service item contents may deeply analyze the correlation of different service item contents on multiple feature dimension levels to obtain the related service item contents. Furthermore, the association between different service event contents can be used as a classification and division basis for the service state of the block chain node, and the association between different service event contents is obtained by performing association analysis on each service event content, so that the consideration of the association between different service event contents is wide, and the accuracy and reliability of classification and division of the service state of the block chain node can be ensured.
Step S3, inputting the content of the related business transaction to: and analyzing the network based on the state relevance of the training completion of the related service item content sample in advance to obtain an output result representing the correlation condition between the service states of the block link nodes.
In the present embodiment, the state association analysis network may be a Neural Network (NN) model or a Classifier model (Classifier) based on Machine Learning (Machine Learning). The state relevance analysis network is trained based on the associated service item content samples, and the associated service item content samples can be continuously optimized, updated and iterated according to actual service state detection results, so that the model performance of the state relevance analysis network can be ensured.
On one hand, the output result may be represented by a numerical value, such as an association probability value representing an association between the service states of the block chain nodes. On the other hand, the output result may also be represented in a vector form, such as an association degree evaluation vector (a 1, a2, a 3.., ai) representing the association between the service states of the blockchain nodes, where i is a positive integer. Each vector value in the relevance evaluation vector can evaluate the relevance between the block chain node service states from different dimensions, for example, the vector value a1 can evaluate the relevance between the block chain node service states from a service interaction object dimension, the vector value a2 can evaluate the relevance between the block chain node service states from a service interaction scene dimension, and the vector value a3 can evaluate the relevance between the block chain node service states from a service interaction period dimension. The larger the vector value is, the higher the association degree between the block link point service states in the corresponding dimension is, and the smaller the vector value is, the higher the association degree between the block link point service states in the corresponding dimension is.
And step S4, obtaining a service state detection result whether the service state of the block chain node belongs to the same block chain node according to the comparison relation between the output result and a preset detection condition.
In the present embodiment, the preset detection condition may be matched with the type of the output result. If the output result is a numerical value, for example, an association probability value representing an association condition between the service states of the block chain nodes, the preset detection condition may be a preset probability value. If the output result is a vector, for example, an association degree evaluation vector representing an association condition between the service states of the block chain nodes, the preset detection condition may be a reference evaluation vector.
On the basis, the comparison relationship between the output result and the preset detection condition may be a difference value between the association probability value and the preset probability value, or a cosine distance between the association degree evaluation vector and the reference evaluation vector, but is not limited thereto.
Further, a service state detection result of whether the service state of the blockchain node belongs to the same blockchain node can be obtained according to the comparison relationship. And then integrating the service states of the block chain nodes based on the service state detection result so as to obtain an integration result of the service states of the block chain nodes of the same block chain node, thereby providing accurate and reliable analysis basis for subsequent analysis of the block chain node state.
Therefore, according to the first embodiment, the service item identification can be performed on different block chain node service states to obtain the service item content, and further, the relevance analysis of the service item content is realized to obtain the relevant service item content, and the relevant service item content is analyzed and processed by using the state relevance analysis network trained in advance to obtain the output result indicating the relevance between the block chain node service states, so that the service state detection result indicating whether the block chain node service states belong to the same block chain node can be obtained according to the comparison relationship between the output result and the preset detection condition.
It can be understood that, since the business item content is considered in the process of belonging and classifying the business state of the block link point, the classification judgment dimensionality of the business state can be increased, so that in the process of determining the business state of the same block link point, the influence of the detection error of a single classification judgment dimensionality on the business state detection result is avoided as much as possible, the reliability of the business state detection result for the same block link node is further ensured, the wrong classification of the business states of the block link points of other block link nodes is avoided, and thus, an accurate and reliable analysis basis can be provided for the subsequent block link point state analysis. Therefore, by adopting the scheme, the technical problems of low classification accuracy and poor reliability of the service state of the block link points in the related technology can be solved.
In the following, some alternative embodiments will be described, which should be understood as examples and not as technical features essential for implementing the present solution.
Example two
On the basis of this embodiment, the content of the possible business transaction includes: the multidimensional dynamic business transaction content, further, the associated business transaction content may include: globally associating business transaction content. The multidimensional dynamic business item content is used for representing business item contents with different dimensions and real-time changes, such as transaction amount and transaction amount in cross-border payment business, network delay or business cooperation state in remote office business, and the like. Further, the global associated business items may reflect the content of the associated business items from the overall business level, such as the identity relationship between the buyer and the seller in the cross-border payment business, and the logical relationship between the business items in the remote office business.
On the basis of the above contents, the "performing service item identification respectively for each group of block link node service states to obtain the service item content corresponding to the block link node service state" described in the above steps may include the following contents: and analyzing and obtaining the multidimensional dynamic business item content of the block chain node business state based on the business interaction object and the business interaction time period information of the business state segment contained in the business state of each group of block chain node points.
For example, the traffic state segment may be obtained by splitting the block link node traffic state according to a set rule, where the set rule may be an event splitting-based rule or a time-interval splitting-based rule, for example, a group of block link node traffic states may be split into a traffic state segment p1, a traffic state segment p2, a traffic state segment p3, a traffic state segment p4, and a traffic state segment p 5.
In addition, the service interaction object can be other block chain nodes, and can also be other types of intelligent equipment. In this embodiment, the block link point may be an intelligent device with data information interaction function, such as a personal PC, an enterprise server, and the like. The service interaction period information is used to record periods of different service state segments, for example, the service interaction period information of the service state segment p1 is t1, the service interaction period information of the service state segment p2 is t2, the service interaction period information of the service state segment p3 is t3, the service interaction period information of the service state segment p4 is t4, and the service interaction period information of the service state segment p5 is t 5.
Furthermore, the deep mining of the dynamic business item content can be carried out based on the business interaction object and the business interaction period information of the business state fragment, so that the multidimensional dynamic business item content of the block chain node business state is completely determined to serve the subsequent business state classification.
On the basis of the above contents, the step of "performing relevance analysis on each business transaction content to obtain relevant business transaction content" described in the above steps may include the following contents: and performing relevance analysis on the multidimensional dynamic service item contents of the service states of the two groups of block link nodes to obtain overall relevant service item contents.
For example, relevance analysis is performed on the multidimensional dynamic service item contents of the service states of the two groups of block chain nodes, the relevance between different multidimensional dynamic service item contents can be used as a basis for classifying and dividing the service states of the block chain nodes, and since the relevance between different multidimensional dynamic service item contents is obtained by performing relevance analysis on each multidimensional dynamic service item content, the considered layer of the relevance between different multidimensional dynamic service item contents is wider, and analysis is performed in combination with the dynamic change conditions of different service item contents, so that the classification and division of the service states of the block chain nodes can be ensured to be matched with the actual service state change.
On the basis of the above, the above steps describe "inputting the content of the associated service event into: the obtaining of an output result indicating the correlation between the service states of the block link points based on the state correlation analysis network trained based on the correlated service event content samples in advance may include the following: inputting the global associated business transaction content into: and analyzing the network based on the state relevance of the overall relevant service event content sample training to obtain an output result representing the relevance condition between the service states of the block chain nodes.
It can be understood that the associated service item content can be reflected from the overall service level through the overall associated service item content, so that the influence of individual errors in the output result of the determined association between the service states of the block link nodes on the precision and the reliability of the output result can be improved, and the precision of the output result of the association between the service states of the block link nodes can be ensured. For example, the influence of the vector value with deviation in the relevance degree evaluation vector on the relevance description of the relevance degree evaluation vector can be weakened by analyzing the content of the global relevance business affairs.
EXAMPLE III
On the basis of this embodiment, the business transaction content may include: signing the business transaction content and the multidimensional dynamic business transaction content, and based on the content, the related business transaction content comprises: local associated business transaction content and global associated business transaction content. For example, the signature service transaction content may be used to represent the service transaction content corresponding to the signature behavior of the blockchain node, and may be used to check the security of the blockchain node.
On the basis of the above contents, the step "respectively perform service item identification for each group of block link node service states to obtain the service item contents corresponding to the block link node service states" can be implemented by the following embodiments: respectively acquiring block link point signatures corresponding to the service states of all block link points; carrying out signature service item identification on the block chain node signature corresponding to the service state of each group of block chain nodes to obtain the signature service item content of the service state of the block chain node; and analyzing and obtaining the multidimensional dynamic business item content of the block chain node business state based on the business interaction object and the business interaction time period information of the business state segment contained in the business state of each group of block chain node points.
In actual implementation, the block link point signature can be obtained through block link point communication corresponding to the service state of each block link point, and the block link point signature can be a digital signature for preventing data information from being maliciously tampered, and can also be used for checking the security of the block link node. Furthermore, by carrying out signature service item identification, the signature service item content of the service state of the block chain node can be determined based on the digital signature layer.
On the basis of the above contents, the step "performing relevance analysis on each business transaction content to obtain a relevant business transaction content" can be implemented by the following embodiments: performing relevance analysis on the signature service item contents of the service states of the two groups of block chain nodes to obtain local relevance service item contents; and performing relevance analysis on the multidimensional dynamic service item contents of the service states of the two groups of block link nodes to obtain overall relevant service item contents.
On the basis of the above contents, the local associated service transaction contents may focus on the relevance of the digital signature of the block chain node service state, and since the relevance of the digital signature has independence compared with the multidimensional dynamic service transaction contents, the local associated service transaction contents and the global associated service transaction contents can be respectively determined by the above method, thereby facilitating subsequent service state classification.
On the basis of the above, the step "inputs the content of the related business affairs into: the state relevance analysis network trained based on the relevant service event content samples in advance to obtain an output result representing the relevance condition between the service states of the block link nodes can be realized by the following implementation modes: inputting the local associated business transaction content and the global associated business transaction content to: and obtaining an output result representing the correlation condition between the service states of the block chain nodes based on a state correlation analysis network trained by local correlation service item content and global correlation service item content samples in advance.
It can be understood that when determining the output result of the correlation between the service states of the block chain nodes, the local correlation service item content and the global correlation service item content can be considered at the same time, and since the state correlation analysis network is trained based on the local correlation service item content and the global correlation service item content, it can be ensured that the analysis and identification of the correlation between the service states of the block chain nodes can be matched with the actual input content, and further the reliability of the output result of the correlation between the service states of the block chain nodes is ensured. For example, after consideration of contents of local associated business matters is introduced, a vector dimension of the relevance evaluation vector can be increased to ensure the credibility of the relevance evaluation vector.
Example four
On the basis of this embodiment, the business transaction content may include: the signature service transaction content, the multidimensional dynamic service transaction content and the node relation service transaction content, and the associated service transaction content may include: local associated business transaction content and global associated business transaction content.
Based on the above, the step "respectively perform service item identification for each group of block link node service states to obtain service item contents corresponding to the block link node service states" may include the following contents: respectively acquiring block link point signatures corresponding to the service states of all block link points; carrying out signature service item identification on the block chain node signature corresponding to the service state of each group of block chain nodes to obtain the signature service item content of the service state of the block chain node; analyzing and obtaining the multidimensional dynamic service item content of the service state of each block chain node based on the service interaction object and the service interaction period information of the service state fragment contained in the service state of each group of block chain nodes; and acquiring the node relation service item content corresponding to the service states of the two groups of block chain nodes.
In some examples, the node relationship service transaction content may be used to represent: and extracting service interaction object information of the central management node of the block chain node signature corresponding to the service states of the two groups of block chain nodes in the current cloud service scene.
For example, the service server may communicate with the central management node, and extract, by the central management node, the signature of the block link point corresponding to the service states of the two groups of block link nodes, so that the service server can be prevented from being involved in the distributed processing architecture of the block link points, and the stability of the distributed processing architecture of the block link points can be ensured. The current cloud service scene can be one of the cross-border payment scene, the remote office scene and the intelligent medical scene, and correspondingly, the service interaction object information can be determined according to the actual scene. The node relation of the service states of the two groups of block chain nodes on the equipment level can be determined through the service interaction object information of the central management node in the current cloud service scene, so that the subsequent service state classification is facilitated.
In other examples, the node relationship business transaction content may also be used to represent: and the same block chain node respectively extracts the prediction information of switching between the central management nodes of the block chain node signatures corresponding to the service states of the two groups of block chain nodes.
For example, the node0 may be a central management node, the node0 may be configured to extract the signatures of the blockchain nodes (node 2 and node 3) corresponding to the service statuses of the two sets of blockchain nodes, respectively, and the prediction information may be understood as the handover situation between the same blockchain node1 and the central management node0, and in general, if the prediction information is "m 1", it may be understood as extracting the signatures of the blockchain nodes (node 2 and node 3) corresponding to the service statuses of the two sets of blockchain nodes, respectively, through the node0, and if the prediction information is "m 2", it may be understood as extracting the signatures of the blockchain nodes (node 2 and node 3) corresponding to the service statuses of the two sets of blockchain nodes, respectively, so designed that the node relation between the blockchain nodes can be determined according to the handover situation of the central management node, to facilitate subsequent traffic state classification.
On the basis of the above contents, the step "performing relevance analysis on each business transaction content to obtain a relevant business transaction content" may include the following contents: performing relevance analysis on the signature service item contents of the service states of the two groups of block chain nodes to obtain local relevance service item contents; and performing relevance analysis on the multidimensional dynamic service item contents of the service states of the two groups of block link nodes to obtain overall relevant service item contents. The description of this step can refer to the description of the above embodiments, and will not be described here.
On the basis of the above, the step "inputs the content of the related business affairs into: the state relevance analysis network trained based on the relevant service event content samples in advance to obtain an output result representing the relevance condition between the service states of the block link nodes can be realized by the following implementation modes: inputting the local associated service transaction contents, the global associated service transaction contents and the node relation service transaction contents corresponding to the service states of the two groups of block chain nodes into: and obtaining an output result representing the correlation condition among the service states of the block chain nodes in advance based on a state correlation analysis network which is trained by the local correlation service item content samples, the global correlation service item content samples and the node relation service item samples.
It can be understood that when the state relevance analysis network is used for determining the output result for representing the relevance condition between the service states of the block chain nodes, corresponding samples can be adopted for training according to different input information, so that the model performance and the output accuracy of the state relevance analysis network are ensured.
In some alternative embodiments, the multidimensional dynamic business transaction content comprises: hot service transaction content and cold service transaction content. The hot service item content and the cold service item content can be obtained through the update frequency of the item content, the hot service item content is used for representing the dynamic service item content with higher update frequency, and the cold service item content is used for representing the dynamic service item content with lower update frequency.
On the basis of this alternative embodiment, the step "analyzing and obtaining the multidimensional dynamic service transaction content of the block link point service state based on the service interaction object and the service interaction period information of the service state segment included in the service state of each group of block link points" may include the following steps: analyzing and obtaining hot service item contents of the service state of each group of block chain node points based on the service interaction objects and service interaction period information of the service state segments contained in the service state of each group of block chain node points; and converting the block link node service state into a plurality of candidate service states, and analyzing and obtaining the cold service item content of each candidate service state based on the service interaction object and the service interaction period information of the service state segment contained in each candidate service state.
For example, the hot service item content of the service state of each group of block link nodes may be determined by the matching result (update frequency) of the service interaction object information and the service interaction period information, for example, the hot service item content may be determined according to a service state segment with a higher matching degree (higher update frequency) between the service interaction object information and the service interaction period information.
Further, the block link point service state is converted into a plurality of candidate service states, which may be divided according to the hot service item content of each group of block link point service states, for example, the block link point service states may be divided according to the hot service item content of each group of block link point service states, so as to obtain a plurality of candidate service states, where the plurality of candidate service states are unrelated to the hot service item content, so that the cold service item content of each candidate service state may be obtained through analysis based on the service interaction object and the service interaction period information of the service state segment included in each candidate service state.
Because the hot service item content and the cold service item content are determined to be in sequence, the interference of the hot service item content determined in advance to the cold service item content determined in the later can be avoided, and the hot service item content and the cold service item content can be accurately distinguished.
In some further embodiments, the hot-end transaction content and the cold-end transaction content each include at least one of the following predetermined types of transaction content: dynamic request service item content, dynamic response service item content, dynamic call service item content, dynamic cooperation service item content and dynamic expansion service item content. The dynamic request service event content is used for initiating service interaction, the dynamic response service event content is used for receiving service interaction, the dynamic call service event content is used for skipping service interaction, the dynamic cooperation service event content is used for assisting service interaction, and the dynamic expansion service event content is used for optimizing service interaction.
In some further embodiments, the global associated business transaction content may include: scene associated business transaction content and object associated business transaction content. It can be understood that the scene-related service transaction contents and the object-related service transaction contents respectively focus on the scene level and the object level. Based on this, the step of "performing relevance analysis on the multidimensional dynamic service transaction content of the service states of the two groups of block chain nodes to obtain the global relevance service transaction content" may include the following contents: respectively carrying out preset content identification on each preset type service item content contained in hot service item contents of the service states of the two groups of block chain nodes to obtain scene associated service item contents; and respectively carrying out preset content identification on each preset type service item content contained in the cold service item contents of the service states of the two groups of block chain nodes to obtain object associated service item contents. For example, the predetermined type of service event may be selected according to service requirements.
In the actual implementation process, the scene-related business item content can be determined from the perspective of a business scene by respectively carrying out preset content identification on each preset type business item content contained in the popular business item content, and the completeness and the accuracy of the scene-related business item content can be ensured because the scene features in the popular business item content occupy higher weight. The method has the advantages that the preset content identification is respectively carried out on each preset type of service item content contained in the cold service item content, the object associated service item content can be determined in a service object angle, and the integrity and the accuracy of the object associated service item content can be ensured because the weight occupied by the service object characteristics in the cold service item content is large.
In an actual implementation process, the network model training process of the state relevance analysis network can be realized by the following steps: acquiring a training sample set containing related business item content samples and training sample description values corresponding to the related business item content samples; inputting the related business affair content sample into a state relevance analysis network to obtain a sample output result which represents the correlation condition between two business state samples corresponding to the related business affair content sample; judging whether the difference result between the sample output result and the training sample description value meets the set model performance evaluation condition or not; if so, judging that the training of the network model is finished, and obtaining a trained state correlation analysis network; if not, adjusting the network model parameters in the state relevance analysis network, returning to the step of inputting the related business item content sample into the state relevance analysis network to obtain a sample output result representing the correlation condition between the two business state samples corresponding to the related business item content sample, and continuing to perform the next network model training.
For example, the training sample description value may be understood as an actual value of the training sample, and the actual value is used for describing the association condition of the traffic state. Further, the difference result between the sample output result and the training sample description value may be a numerical result, and the set model performance evaluation condition may be a preset numerical range. The network model parameter adjustment may refer to the related art, and is not described herein.
In some other embodiments, after obtaining the trained state association analysis network, the method may further include: respectively inputting all the related business item content samples which are not used in the training sample set into the state relevance analysis network after the training is finished to obtain output results of all the samples; aiming at each sample output result, respectively obtaining a service state detection result of whether two service state samples corresponding to the sample output result belong to the same block chain node according to the comparison relation between the sample output result and a preset alternative detection condition; analyzing the state detection matching degree of the service state detection result based on the training sample description value corresponding to each sample output result; judging whether the state detection matching degree is larger than a preset state detection matching degree threshold value or not; if yes, determining the alternative detection conditions as preset detection conditions to be used; if not, adjusting the alternative detection conditions, returning the output result of each sample, and obtaining the service state detection result whether the two service state samples corresponding to the output result of the sample belong to the same block chain node or not according to the comparison relation between the output result of the sample and the preset alternative detection conditions respectively until the state detection matching degree of the service state detection result is greater than the preset state detection matching degree threshold value; and determining the alternative detection condition which enables the state detection matching degree of the service state detection result to be larger than the preset state detection matching degree threshold value as the preset detection condition to be used.
For example, the comparison relationship between the sample output result and the preset candidate detection condition may be a numerical comparison relationship, and the state detection matching degree of the service state detection result is used to represent the degree of association between service states of different block chain nodes. The larger the matching degree of state detection is, the higher the correlation degree between different block link point service states is. Therefore, the preset detection conditions to be used can be ensured to be in accordance with the actual service conditions, and the accuracy of subsequent service state classification is further ensured.
In some possible embodiments, the step of "obtaining a training sample description value corresponding to a training sample set containing associated business event content samples and each associated business event content sample" may include the following steps: respectively obtaining a plurality of service state samples corresponding to different block chain link points; respectively identifying service items aiming at each service state sample to obtain a service item content sample corresponding to each service state sample; performing relevance analysis on any two business item content samples to obtain a group of relevant business item content samples in a training sample set; determining a training sample description value corresponding to the associated business item content sample according to whether the two business item content samples belong to the same block chain node; when the two business item content samples belong to the same block chain node, determining that the training sample description value corresponding to the associated business item content sample is a first set value, otherwise, determining that the training sample description value corresponding to the associated business item content sample is a second set value; wherein the associated business transaction content sample represents an association between the two business transaction content samples. In this embodiment, the first setting value may be 1, and the second setting value may be 0.
In other embodiments, the training sample description value may also be determined by linear expression, for example, the training sample description value may be determined as a value interval.
In some alternative embodiments, the business transaction content samples include: the multidimensional dynamic business item content sample, based on which the business item is identified for each business state sample to obtain the business item content sample corresponding to each business state sample, may include the following contents: and analyzing and obtaining a multi-dimensional dynamic business item content sample of each business state sample based on the business interaction object and the business interaction period information of the business state fragment contained in each business state sample. The above-mentioned correlation analysis of any two service item content samples to obtain a group of correlated service item content samples in the training sample set may include the following contents: and performing relevance analysis on the multidimensional dynamic business item content samples of any two business state samples to obtain a group of global relevance business item content samples in the training sample set. The above-mentioned inputting the sample of the related service transaction content into the state relevance analysis network to obtain the sample output result indicating the relevance between the two service state samples corresponding to the sample of the related service transaction content may include the following contents: and inputting the global associated service item content sample into a state association analysis network to obtain a sample output result representing the association condition between any two service state samples.
In some alternative embodiments, the business transaction content samples include: signing a business item content sample and a multidimensional dynamic business item content sample; the associated business transaction content comprises: a local associated business transaction content sample and a global associated business transaction content sample. Based on this, the above-mentioned performing service item identification for each service state sample to obtain the service item content sample corresponding to each service state sample may include the following contents: respectively obtaining signature samples corresponding to the service state samples; performing signature service item identification on the signature sample corresponding to each service state sample to obtain a signature service item content sample of the service state sample; and analyzing and obtaining a multi-dimensional dynamic business item content sample of each business state sample based on the business interaction object and the business interaction period information of the business state fragment contained in each business state sample. The above-mentioned correlation analysis of any two service item content samples to obtain a group of correlated service item content samples in the training sample set may include the following contents: performing relevance analysis on signature service item content samples of any two service state samples to obtain local relevance service item content samples; and carrying out relevance analysis on the multidimensional dynamic business item content samples of any two business state samples to obtain a global relevance business item content sample. The above-mentioned inputting the sample of the related service transaction content into the state relevance analysis network to obtain the sample output result indicating the relevance between the two service state samples corresponding to the sample of the related service transaction content may include the following contents: and inputting the local associated service item content sample and the global associated service item content sample into a state association analysis network to obtain a sample output result representing the association condition between any two service state samples.
In some alternative embodiments, the business transaction content samples include: signing a business item content sample, a multidimensional dynamic business item content sample and a node relation business item content sample; the sample of associated business transaction content comprises: a local associated business transaction content sample and a global associated business transaction content sample. Based on this, the above-mentioned performing service item identification on each service status sample to obtain the service item content sample corresponding to each service status sample can be implemented by the following embodiments: respectively obtaining signature samples corresponding to the service state samples; performing signature service item identification on the signature sample corresponding to each service state sample to obtain a signature service item content sample of the service state sample; analyzing and obtaining a multi-dimensional dynamic business item content sample of each business state sample based on the business interaction object and the business interaction period information of the business state fragment contained in each business state sample; aiming at any two service state samples, acquiring node relation service item content samples corresponding to the two service state samples, wherein the node relation service item content samples represent that: extracting service interaction object information of the central management node of the signature sample corresponding to the two service state samples in the current cloud service scene; or, the node relation service transaction content indicates: and the same block chain node respectively extracts the switching prediction information between the central management nodes of the signature samples corresponding to the two service state samples. Based on this, the above-mentioned correlation analysis is performed on any two business transaction content samples to obtain a group of correlated business transaction content samples in the training sample set, which can be implemented by the following implementation manners: performing relevance analysis on signature service item content samples of any two service state samples to obtain local relevance service item content samples; and carrying out relevance analysis on the multidimensional dynamic business item content samples of any two business state samples to obtain a global relevance business item content sample. Based on this, the above-mentioned inputting the related business affair content sample into the state relevance analysis network to obtain the sample output result indicating the relevance between the two business state samples corresponding to the related business affair content sample can be realized by the following embodiments: and inputting the local associated service item content sample, the global associated service item content sample and the node relation service item content sample corresponding to any two service state samples into a state association analysis network to obtain a sample output result representing the association condition between the local associated service item content sample and any two service state samples.
It should be understood that the above description of different training modes for the state association analysis network may refer to the related contents of the previous embodiments, and will not be described herein again.
In other alternative embodiments, after the service state detection result in S4 indicates whether the service state of the blockchain node belongs to the same blockchain node, the method may further include the following steps: and integrating the service states of the block chain nodes to obtain the service state track of the target block chain node corresponding to the service state of the block chain node.
In this embodiment, the traffic state trajectory may be a knowledge graph or graph data. By analyzing the service state track, portrait information of the target block chain service node in the service interaction process can be mined, so that the service is optimized and upgraded based on the portrait information, and the service interaction efficiency between subsequent block chain service nodes is improved.
In other optional embodiments, after integrating the service states of the blockchain nodes to obtain the service state trajectory of the target blockchain node corresponding to the service state of the blockchain node, the method may further include the contents described in the following steps (1) to (3).
(1) Acquiring a service portrait data record according to the service state track, wherein the service portrait data record comprises a plurality of groups of uninterrupted service portrait data; and acquiring an interference portrait data record according to the service portrait data record, wherein the interference portrait data record comprises a plurality of uninterrupted groups of interference portrait data.
For example, the service profile data is used to describe profile characteristics of the target tile link node, such as preference information or evaluation information of the target tile link node during service interaction. The interference image data is relative to the business image data, i.e., inaccurate image data.
(2) Based on the service portrait data record, acquiring a service portrait label distribution record through a first label extraction network included in a service portrait identification model, wherein the service portrait label distribution record comprises a plurality of service portrait label distributions; and acquiring an interference portrait label distribution record through a second label extraction network included in the service portrait identification model based on the interference portrait data record, wherein the interference portrait label distribution record comprises a plurality of interference portrait label distributions.
For example, the portrait label distribution may be a distribution list or a distribution map, but is not limited thereto. The business image recognition model may be a neural network model.
(3) Acquiring portrait intention skip information corresponding to the service portrait data record through a portrait intention analysis network included in the service portrait identification model based on the service portrait label distribution record and the interference portrait label distribution record; and determining the service requirement portrait information recorded by the service portrait data according to the portrait intention skip information.
For example, the image intent skip information is used to represent the change information of the service portrait data record, and the service demand portrait information can be understood as various service demands of the target block chain node, such as an interactive interface demand, an interactive time consumption demand, and the like.
By means of the design, based on the content described in the steps (1) to (3), portrait intention skip information corresponding to the business portrait data record can be obtained based on different functional layers of the determined business portrait data record, interference portrait data record and business portrait recognition model, and due to the fact that the portrait intention skip information records the change information of the business portrait data record, the latest business demand portrait information of the business portrait data record can be determined through the portrait intention skip information, so that the business service can be optimized and upgraded based on the business demand portrait information, and the business interaction efficiency between subsequent block chain business nodes is improved.
In other alternative embodiments, the step "obtaining portrait intent skip information corresponding to the service portrait data record through the portrait intent analysis network included in the service portrait identification model based on the service portrait tag distribution record and the interference portrait tag distribution record" may include the following steps (31) to (35).
(31) And acquiring a plurality of first label classification characteristics through a first global portrait analysis layer included in the service portrait identification model based on the service portrait label distribution record, wherein each first label classification characteristic corresponds to service portrait label distribution.
(32) And acquiring a plurality of second label classification characteristics through a second global portrait analysis layer included in the service portrait identification model based on the interference portrait label distribution record, wherein each second label classification characteristic corresponds to interference portrait label distribution.
(33) And performing feature matching processing on the plurality of first label classification features and the plurality of second label classification features to obtain a plurality of target label classification features, wherein each target label classification feature comprises a first label classification feature and a second label classification feature.
(34) And acquiring label classification fusion features through a time sequence feature fusion layer included by the service portrait identification model based on the target label classification features, wherein the label classification fusion features are determined according to the target label classification features and time sequence classification weights, and each target label classification feature corresponds to one time sequence classification weight.
(35) And acquiring portrait intention skip information corresponding to the service portrait data record through a portrait intention analysis network included in the service portrait identification model based on the label classification fusion characteristics.
It can be understood that, through the steps (31) to (35), when the image intention skipping information corresponding to the business image data record is acquired, the time sequence characteristics can be taken into consideration, and therefore the real-time performance of the image intention skipping information is ensured.
For the above method for detecting an online service state applied to a block chain, an exemplary apparatus for detecting an online service state applied to a block chain is further provided in the embodiment of the present application, and as shown in fig. 2, the apparatus 200 for detecting an online service state applied to a block chain may include the following functional modules.
The service item identification module 210 is configured to obtain service states of two groups of block link points to be detected; and respectively identifying service items aiming at the service state of each group of block chain nodes to obtain the service item content corresponding to the service state of the block chain node.
The content association analysis module 220 is configured to perform association analysis on each service item content to obtain an associated service item content; the related business affair content shows the relation between the business affair contents.
The associated service processing module 230 is configured to input the associated service transaction content into: and analyzing the network based on the state relevance of the training completion of the related service item content sample in advance to obtain an output result representing the correlation condition between the service states of the block link nodes.
And the service state detection module 240 is configured to obtain a service state detection result of whether the service state of the blockchain node belongs to the same blockchain node according to a comparison relationship between the output result and a preset detection condition.
Based on the above method embodiment and apparatus embodiment, the embodiment of the present invention further provides a system embodiment, that is, an online service status detection system applied to a block chain, please refer to fig. 3, where an online service status detection system 30 applied to a block chain may include a service server 10 and a block link point 20. Wherein the service server 10 and the block link point 20 communicate to implement the above method, further, the functionality of the online service status detection system 30 applied to the block chain is described as follows.
The service server 10 acquires service states of two groups of block link points to be detected; respectively identifying service items aiming at the service state of each group of block link nodes to obtain service item contents corresponding to the service state of the block link nodes; performing relevance analysis on the business item contents to obtain relevant business item contents; the related business affair content represents the related condition among all the business affair contents; inputting the content of the associated business transaction into: a state relevance analysis network which is trained based on the relevant service item content samples is obtained in advance, and an output result which represents the relevance condition between the service states of the block chain nodes is obtained; and obtaining a service state detection result of whether the service state of the block chain node belongs to the same block chain node 20 according to the comparison relation between the output result and a preset detection condition.
Further, referring to fig. 4 in combination, the service server 10 may include a processing engine 110, a network module 120 and a memory 130, wherein the processing engine 110 and the memory 130 communicate through the network module 120.
Processing engine 110 may process the relevant information and/or data to perform one or more of the functions described herein. For example, in some embodiments, processing engine 110 may include at least one processing engine (e.g., a single core processing engine or a multi-core processor). By way of example only, the Processing engine 110 may include a Central Processing Unit (CPU), an Application-Specific Integrated Circuit (ASIC), an Application-Specific Instruction Set Processor (ASIP), a Graphics Processing Unit (GPU), a Physical Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller Unit, a Reduced Instruction Set Computer (RISC), a microprocessor, or the like, or any combination thereof.
Network module 120 may facilitate the exchange of information and/or data. In some embodiments, the network module 120 may be any type of wired or wireless network or combination thereof. Merely by way of example, the Network module 120 may include a cable Network, a wired Network, a fiber optic Network, a telecommunications Network, an intranet, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Public Switched Telephone Network (PSTN), a bluetooth Network, a Wireless personal Area Network, a Near Field Communication (NFC) Network, and the like, or any combination thereof. In some embodiments, the network module 120 may include at least one network access point. For example, the network module 120 may include wired or wireless network access points, such as base stations and/or network access points.
The Memory 130 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The memory 130 is used for storing a program, and the processing engine 110 executes the program after receiving the execution instruction.
It will be appreciated that the architecture shown in fig. 4 is merely illustrative and that the service server 10 may also include more or fewer components than shown in fig. 4, or have a different configuration than shown in fig. 4. The components shown in fig. 4 may be implemented in hardware, software, or a combination thereof.
It should be appreciated that the system and its modules shown above may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory for execution by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided, for example, on a carrier medium such as a diskette, CD-or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, for example, or by a combination of the above hardware circuits and software (e.g., firmware).
It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.
Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered merely illustrative and not restrictive of the broad application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.
Also, this application uses specific language to describe embodiments of the application. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the present application is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the present application may be combined as appropriate.
Moreover, those skilled in the art will appreciate that aspects of the present application may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereon. Accordingly, various aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.
The computer storage medium may comprise a propagated data signal with the computer program code embodied therewith, for example, on baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, etc., or any suitable combination. A computer storage medium may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated over any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or any combination of the preceding.
Computer program code required for the operation of various portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, a conventional programming language such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages, and the like. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).
Additionally, the order in which elements and sequences of the processes described herein are processed, the use of alphanumeric characters, or the use of other designations, is not intended to limit the order of the processes and methods described herein, unless explicitly claimed. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.
Similarly, it should be noted that in the preceding description of embodiments of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.
Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the numbers allow for adaptive variation. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.
The entire contents of each patent, patent application publication, and other material cited in this application, such as articles, books, specifications, publications, documents, and the like, are hereby incorporated by reference into this application. Except where the application is filed in a manner inconsistent or contrary to the present disclosure, and except where the claim is filed in its broadest scope (whether present or later appended to the application) as well. It is noted that the descriptions, definitions and/or use of terms in this application shall control if they are inconsistent or contrary to the statements and/or uses of the present application in the material attached to this application.
Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present application. Other variations are also possible within the scope of the present application. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the present application can be viewed as being consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to only those embodiments explicitly described and depicted herein.

Claims (10)

1. An online service state detection method applied to a block chain is characterized by comprising the following steps:
acquiring service states of two groups of block chain link points to be detected; respectively identifying service items aiming at the service state of each group of block link nodes to obtain service item contents corresponding to the service state of the block link nodes;
performing relevance analysis on the business item contents to obtain relevant business item contents; the related business affair content represents the related condition among all the business affair contents;
inputting the content of the associated business transaction into: a state relevance analysis network which is trained based on the relevant service item content samples is obtained in advance, and an output result which represents the relevance condition between the service states of the block chain nodes is obtained;
and obtaining a service state detection result whether the service state of the block chain node belongs to the same block chain node according to the comparison relation between the output result and a preset detection condition.
2. The method of claim 1, wherein the business transaction content comprises: multidimensional dynamic business item content; the associated business transaction content comprises: globally associating business item content;
the method for respectively identifying the service items aiming at the service state of each group of block chain nodes to obtain the service item content corresponding to the service state of the block chain node comprises the following steps: analyzing and obtaining the multidimensional dynamic service item content of the service state of each block chain node based on the service interaction object and the service interaction period information of the service state fragment contained in the service state of each group of block chain nodes;
the step of analyzing the relevance of each business item content to obtain the relevant business item content comprises the following steps: performing relevance analysis on the multidimensional dynamic service item contents of the service states of the two groups of block link nodes to obtain overall relevant service item contents;
the input of the associated business transaction content to: obtaining an output result representing the correlation condition between the service states of the block chain nodes based on a state correlation analysis network which is trained based on the related service item content samples in advance, wherein the output result comprises the following steps: inputting the global associated business transaction content into: and analyzing the network based on the state relevance of the overall relevant service event content sample training to obtain an output result representing the relevance condition between the service states of the block chain nodes.
3. The method of claim 1, wherein the business transaction content comprises: signing the business item content and the multidimensional dynamic business item content; the associated business transaction content comprises: local associated service item content and global associated service item content;
the step of respectively performing service item identification on the service state of each group of block link nodes to obtain the service item content corresponding to the service state of the block link node comprises the following steps: respectively acquiring block link point signatures corresponding to the service states of all block link points; carrying out signature service item identification on the block chain node signature corresponding to the service state of each group of block chain nodes to obtain the signature service item content of the service state of the block chain node; analyzing and obtaining the multidimensional dynamic service item content of the service state of each block chain node based on the service interaction object and the service interaction period information of the service state fragment contained in the service state of each group of block chain nodes;
the analyzing the relevance of each business item content to obtain the relevant business item content includes: performing relevance analysis on the signature service item contents of the service states of the two groups of block chain nodes to obtain local relevance service item contents; performing relevance analysis on the multidimensional dynamic service item contents of the service states of the two groups of block link nodes to obtain overall relevant service item contents;
the input of the associated business transaction content to: obtaining an output result representing the correlation condition between the service states of the block chain nodes based on a state correlation analysis network which is trained based on the related service item content samples in advance, wherein the output result comprises the following steps: inputting the local associated business transaction content and the global associated business transaction content to: and obtaining an output result representing the correlation condition between the service states of the block chain nodes based on a state correlation analysis network trained by local correlation service item content and global correlation service item content samples in advance.
4. The method of claim 1, wherein the business transaction content comprises: signing the business item content, the multidimensional dynamic business item content and the node relation business item content; the associated business transaction content comprises: local associated service item content and global associated service item content;
the step of respectively performing service item identification on the service state of each group of block link nodes to obtain the service item content corresponding to the service state of the block link node comprises the following steps: respectively acquiring block link point signatures corresponding to the service states of all block link points; carrying out signature service item identification on the block chain node signature corresponding to the service state of each group of block chain nodes to obtain the signature service item content of the service state of the block chain node; analyzing and obtaining the multidimensional dynamic service item content of the service state of each block chain node based on the service interaction object and the service interaction period information of the service state fragment contained in the service state of each group of block chain nodes; acquiring node relation service transaction contents corresponding to the service states of the two groups of block chain nodes, wherein the node relation service transaction contents represent that: extracting service interaction object information of the central management node of the block chain node signature corresponding to the service states of the two groups of block chain nodes in the current cloud service scene; or, the node relation service transaction content indicates: the same block chain node respectively extracts the prediction information of the switching between the central management nodes of the block chain node signatures corresponding to the service states of the two groups of block chain nodes;
the analyzing the relevance of each business item content to obtain the relevant business item content includes: performing relevance analysis on the signature service item contents of the service states of the two groups of block chain nodes to obtain local relevance service item contents; performing relevance analysis on the multidimensional dynamic service item contents of the service states of the two groups of block link nodes to obtain overall relevant service item contents;
the input of the associated business transaction content to: obtaining an output result representing the correlation condition between the service states of the block chain nodes based on a state correlation analysis network which is trained based on the related service item content samples in advance, wherein the output result comprises the following steps: inputting the local associated service transaction contents, the global associated service transaction contents and the node relation service transaction contents corresponding to the service states of the two groups of block chain nodes into: and obtaining an output result representing the correlation condition among the service states of the block chain nodes in advance based on a state correlation analysis network which is trained by the local correlation service item content samples, the global correlation service item content samples and the node relation service item samples.
5. The method according to any of claims 2-4, wherein the multi-dimensional dynamic business transaction content comprises: hot service item content and cold service item content;
the analyzing and obtaining the multidimensional dynamic service item content of the block chain node service state based on the service interaction object and the service interaction period information of the service state segment contained in the service state of each group of block chain node points comprises the following steps:
analyzing and obtaining hot service item contents of the service state of each group of block chain node points based on the service interaction objects and service interaction period information of the service state segments contained in the service state of each group of block chain node points;
and converting the block link node service state into a plurality of candidate service states, and analyzing and obtaining the cold service item content of each candidate service state based on the service interaction object and the service interaction period information of the service state segment contained in each candidate service state.
6. The method of claim 5, wherein the hot-end transaction content and the cold-end transaction content each comprise at least one of the following predetermined types of transaction content: dynamically requesting, responding, calling, cooperating and expanding the business item content;
the global associated business transaction content comprises: scene associated service item content and object associated service item content; the performing relevance analysis on the multidimensional dynamic service item content of the service states of the two groups of block link nodes to obtain global relevance service item content includes:
respectively carrying out preset content identification on each preset type service item content contained in hot service item contents of the service states of the two groups of block chain nodes to obtain scene associated service item contents;
and respectively carrying out preset content identification on each preset type service item content contained in the cold service item contents of the service states of the two groups of block chain nodes to obtain object associated service item contents.
7. The method of claim 1, wherein the step of training a network model for the state dependency analysis network comprises:
acquiring a training sample set containing related business item content samples and training sample description values corresponding to the related business item content samples;
inputting the related business affair content sample into a state relevance analysis network to obtain a sample output result which represents the correlation condition between two business state samples corresponding to the related business affair content sample;
judging whether the difference result between the sample output result and the training sample description value meets the set model performance evaluation condition or not;
if so, judging that the training of the network model is finished, and obtaining a trained state correlation analysis network;
if not, adjusting the network model parameters in the state relevance analysis network, returning to the step of inputting the related business item content sample into the state relevance analysis network to obtain a sample output result representing the correlation condition between the two business state samples corresponding to the related business item content sample, and continuing to perform the next network model training.
8. The method of claim 7, wherein after obtaining the trained state association analysis network, further comprising:
respectively inputting all the related business item content samples which are not used in the training sample set into the state relevance analysis network after the training is finished to obtain output results of all the samples;
aiming at each sample output result, respectively obtaining a service state detection result of whether two service state samples corresponding to the sample output result belong to the same block chain node according to the comparison relation between the sample output result and a preset alternative detection condition;
analyzing the state detection matching degree of the service state detection result based on the training sample description value corresponding to each sample output result;
judging whether the state detection matching degree is larger than a preset state detection matching degree threshold value or not;
if yes, determining the alternative detection conditions as preset detection conditions to be used;
if not, adjusting the alternative detection conditions, returning the output result of each sample, and obtaining the service state detection result whether the two service state samples corresponding to the output result of the sample belong to the same block chain node or not according to the comparison relation between the output result of the sample and the preset alternative detection conditions respectively until the state detection matching degree of the service state detection result is greater than the preset state detection matching degree threshold value; and determining the alternative detection condition which enables the state detection matching degree of the service state detection result to be larger than the preset state detection matching degree threshold value as the preset detection condition to be used.
9. The method according to claim 7, wherein the obtaining a training sample description value corresponding to a training sample set containing associated business transaction content samples and each associated business transaction content sample comprises:
respectively obtaining a plurality of service state samples corresponding to different block chain link points;
respectively identifying service items aiming at each service state sample to obtain a service item content sample corresponding to each service state sample;
performing relevance analysis on any two business item content samples to obtain a group of relevant business item content samples in a training sample set;
determining a training sample description value corresponding to the associated business item content sample according to whether the two business item content samples belong to the same block chain node; when the two business item content samples belong to the same block chain node, determining that the training sample description value corresponding to the associated business item content sample is a first set value, otherwise, determining that the training sample description value corresponding to the associated business item content sample is a second set value; wherein the associated business transaction content sample represents an association between the two business transaction content samples.
10. A business server comprising a processing engine, a network module, and a memory; the processing engine and the memory communicate through the network module, the processing engine reading a computer program from the memory and operating to perform the method of any of claims 1-9.
CN202110666539.0A 2021-06-16 2021-06-16 Online service state detection method applied to block chain and service server Withdrawn CN113468017A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110666539.0A CN113468017A (en) 2021-06-16 2021-06-16 Online service state detection method applied to block chain and service server

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110666539.0A CN113468017A (en) 2021-06-16 2021-06-16 Online service state detection method applied to block chain and service server

Publications (1)

Publication Number Publication Date
CN113468017A true CN113468017A (en) 2021-10-01

Family

ID=77870241

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110666539.0A Withdrawn CN113468017A (en) 2021-06-16 2021-06-16 Online service state detection method applied to block chain and service server

Country Status (1)

Country Link
CN (1) CN113468017A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114218565A (en) * 2021-11-23 2022-03-22 赵运岐 Intrusion protection data processing method based on big data and big data server
CN115952555A (en) * 2022-11-29 2023-04-11 广西金教通科技有限公司 Information processing method based on block chain and AI system

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114218565A (en) * 2021-11-23 2022-03-22 赵运岐 Intrusion protection data processing method based on big data and big data server
CN115952555A (en) * 2022-11-29 2023-04-11 广西金教通科技有限公司 Information processing method based on block chain and AI system

Similar Documents

Publication Publication Date Title
US11727705B2 (en) Platform for document classification
US11151573B2 (en) Intelligent chargeback processing platform
US20230099864A1 (en) User profiling based on transaction data associated with a user
AU2021203164A1 (en) Predictive issue detection
CN113468520A (en) Data intrusion detection method applied to block chain service and big data server
CN110852881A (en) Risk account identification method and device, electronic equipment and medium
US20230186668A1 (en) Polar relative distance transformer
US20210233087A1 (en) Dynamically verifying a signature for a transaction
CN113408897A (en) Data resource sharing method applied to big data service and big data server
CN113468017A (en) Online service state detection method applied to block chain and service server
CN112214402B (en) Code verification algorithm selection method, device and storage medium
Ramasubramanian et al. Machine learning model evaluation
CN114661994A (en) User interest data processing method and system based on artificial intelligence and cloud platform
CN113472860A (en) Service resource allocation method and server under big data and digital environment
CN113313463A (en) Data analysis method and data analysis server applied to big data cloud office
CN114186607A (en) Big data processing method and artificial intelligence server applied to cloud office
US20210044864A1 (en) Method and apparatus for identifying video content based on biometric features of characters
CN116883181A (en) Financial service pushing method based on user portrait, storage medium and server
CN112463778B (en) Information processing method based on big data and application program and big data server
CN114443834A (en) Method and device for extracting license information and storage medium
CN113409014A (en) Big data service processing method based on artificial intelligence and artificial intelligence server
CN113901817A (en) Document classification method and device, computer equipment and storage medium
CN113407835A (en) User portrait processing method and server applied to big data online service
CN112801644A (en) Information management method for block chain payment mode and block chain financial server
US20230410575A1 (en) Systems and methods for qr code battery health based tracking

Legal Events

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

Application publication date: 20211001