CN117828658A - Block chain-based joint modeling method and device and computer equipment - Google Patents
Block chain-based joint modeling method and device and computer equipment Download PDFInfo
- Publication number
- CN117828658A CN117828658A CN202311726154.4A CN202311726154A CN117828658A CN 117828658 A CN117828658 A CN 117828658A CN 202311726154 A CN202311726154 A CN 202311726154A CN 117828658 A CN117828658 A CN 117828658A
- Authority
- CN
- China
- Prior art keywords
- model
- data
- joint modeling
- initiator
- service data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 239000003999 initiator Substances 0.000 claims abstract description 134
- 238000012549 training Methods 0.000 claims abstract description 91
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 24
- 238000013475 authorization Methods 0.000 claims description 26
- 238000012795 verification Methods 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 16
- 238000004140 cleaning Methods 0.000 claims description 8
- 238000012847 principal component analysis method Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 3
- 238000013500 data storage Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a block chain-based joint modeling method, a block chain-based joint modeling device and computer equipment. The method comprises the following steps: determining a model to be trained according to a model algorithm module deployed by a joint modeling initiator based on intelligent contracts of a blockchain, and determining a model identification of the model to be trained; the model identification is sent to the joint modeling initiator and the joint modeling participant, and historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identification is obtained; and carrying out model training on the model to be trained according to the historical service data, determining an intelligent wind control model, and carrying out uplink evidence storage on the historical service data. According to the scheme, the method for establishing the intelligent wind control model through multiparty joint is provided, the universality of the intelligent wind control model is improved, and the safety of service data is guaranteed in the multiparty joint modeling process.
Description
Technical Field
The present disclosure relates to the field of blockchain technologies, and in particular, to a blockchain-based joint modeling method, apparatus, and computer device.
Background
At present, when an enterprise trains an intelligent wind control model, the model is often trained through business data of the enterprise, so that the intelligent wind control model is limited to data of the enterprise, when the enterprise cooperates with other institutions, the cooperation institutions need to carry out data cleaning and new-round model training on local data of the enterprise, and model result combination is carried out, so that an application mode of the intelligent wind control model in the cooperation period of the enterprise is complicated. On the basis, if enterprises and institutions conduct cooperative modeling, each partner cannot guarantee the safety of data when providing service data for model training, and higher cost is required for adopting a privacy calculation scheme in the process of data interaction. Therefore, how to realize the multi-party joint establishment of the intelligent wind control model, improve the universality of the intelligent wind control model, and ensure the safety of service data in the multi-party joint modeling process is a problem to be solved.
Disclosure of Invention
Based on the above, it is necessary to provide a block chain-based joint modeling method, device and computer equipment capable of realizing multi-party joint establishment of an intelligent wind control model, improving the universality of the intelligent wind control model and ensuring the security of service data in the multi-party joint modeling process.
In a first aspect, the present application provides a blockchain-based joint modeling method, the method comprising:
determining a model to be trained according to a model algorithm module deployed by a joint modeling initiator based on intelligent contracts of a blockchain, and determining a model identification of the model to be trained;
the model identification is sent to the joint modeling initiator and the joint modeling participant, and historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identification is obtained;
and carrying out model training on the model to be trained according to the historical service data, determining an intelligent wind control model, and carrying out uplink evidence storage on the historical service data.
In one embodiment, the blockchain-based joint modeling method further includes:
obtaining model input data deployed by a model application party, and inputting the model input data into an intelligent wind control model;
and obtaining model output data of the intelligent wind control model, sending the model output data to a model application party, and carrying out uplink certification on the model input data and the model output data.
In one embodiment, the sending the model identifier to the joint modeling initiator and the joint modeling participant, and obtaining historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identifier, includes:
The model identification is sent to the joint modeling initiator, and the model identification is sent to a joint modeling participant through the joint modeling initiator;
sending a service data authorization request to the joint modeling initiator and the joint modeling participant, and acquiring authorization feedback information sent by the joint modeling initiator and the joint modeling participant according to the service data authorization request;
and if the authorization feedback information is successful authorization, acquiring historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identifier.
In one embodiment, performing model training on the model to be trained according to the historical service data, and determining the intelligent wind control model includes:
acquiring a sender identity of a data sender of the historical service data;
screening the historical service data according to the sender identity, the initiator identity of the joint modeling initiator and the participant identity of the joint modeling participant, and determining target service data;
and carrying out model training on the model to be trained according to the target business data, and determining an intelligent wind control model.
In one embodiment, performing model training on the model to be trained according to the target service data, and determining the intelligent wind control model includes:
determining whether the target service data meets the model training conditions of the model to be trained according to the data characteristics of the target service data;
if not, based on a preset data synchronization period, reading service association data of the joint modeling initiator and the joint modeling participant through middleware, and carrying out uplink certification on the service association data.
And carrying out model training on the model to be trained according to the target service data and the service association data, and determining an intelligent wind control model.
In one embodiment, the training of the model to be trained according to the target service data and the service association data, and determining the intelligent wind control model includes:
performing data cleaning on the target service data and the service association data to determine effective data;
and carrying out feature extraction on the effective data by adopting a principal component analysis method, determining feature data, carrying out model training on the model to be trained by adopting the feature data, and determining an intelligent wind control model.
In one embodiment, the blockchain-based joint modeling method further includes:
acquiring model verification data sent by the joint modeling initiator and/or the joint modeling participant based on a model verification interface;
verifying the intelligent wind control model according to the model verification data, and determining the prediction accuracy of the intelligent wind control model;
and if the prediction accuracy is smaller than an accuracy threshold, adjusting the model parameters of the intelligent wind control model.
In a second aspect, the present application also provides a blockchain-based joint modeling apparatus, the apparatus comprising:
the model initialization module is used for determining a model to be trained according to a model algorithm module deployed by a joint modeling initiator based on intelligent contracts of a blockchain, and determining a model identification of the model to be trained;
the historical service data acquisition module is used for sending the model identifier to the joint modeling initiator and the joint modeling participant and acquiring historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identifier;
and the model training module is used for carrying out model training on the model to be trained according to the historical service data, determining an intelligent wind control model and carrying out uplink evidence storage on the historical service data.
In a third aspect, the present application also provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
determining a model to be trained according to a model algorithm module deployed by a joint modeling initiator based on intelligent contracts of a blockchain, and determining a model identification of the model to be trained;
the model identification is sent to the joint modeling initiator and the joint modeling participant, and historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identification is obtained;
and carrying out model training on the model to be trained according to the historical service data, determining an intelligent wind control model, and carrying out uplink evidence storage on the historical service data.
In a fourth aspect, the present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
determining a model to be trained according to a model algorithm module deployed by a joint modeling initiator based on intelligent contracts of a blockchain, and determining a model identification of the model to be trained;
The model identification is sent to the joint modeling initiator and the joint modeling participant, and historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identification is obtained;
and carrying out model training on the model to be trained according to the historical service data, determining an intelligent wind control model, and carrying out uplink evidence storage on the historical service data.
According to the block chain-based joint modeling method, the block chain-based joint modeling device and the computer equipment, a model to be trained is determined according to the model algorithm module deployed by the intelligent contract of the joint modeling initiator based on the block chain, and the model identification of the model to be trained is determined; the model identification is sent to a joint modeling initiator and a joint modeling participant, and historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identification is obtained; and carrying out model training on the model to be trained according to the historical service data, determining an intelligent wind control model, and carrying out uplink evidence storage on the historical service data. The method solves the problems that when enterprises have a cooperative relationship, and the intelligent wind control model is shared among the cooperative enterprises, the accuracy and the credibility of the model are limited, whether the data of each enterprise meet the data format specification of the intelligent wind control model cannot be ensured, the application mode of the intelligent wind control model in the enterprise cooperation period is complicated, and the model training data is difficult to trace back and trace the source. According to the scheme, the multi-party joint modeling scheme is provided, the block chain determines the model to be trained according to the mode algorithm module deployed on the block chain by the joint modeling initiator, the intelligent wind control model is determined by carrying out model training on the model to be trained on the chain according to the historical service data sent by the joint modeling initiator and the joint modeling participant based on the model to be trained, the problem that the privacy of the service data is difficult to guarantee when each enterprise adopts the historical service data to carry out model training on the model to be trained is avoided, the universality of the intelligent wind control model is improved, and the safety of the service data is guaranteed in the multi-party joint modeling process.
Drawings
FIG. 1 is an application environment diagram of a blockchain-based joint modeling method in one embodiment;
FIG. 2 is a flow diagram of a blockchain-based joint modeling method in one embodiment;
FIG. 3 is a flow diagram of a blockchain-based joint modeling method in another embodiment;
FIG. 4 is a flow diagram of a blockchain-based joint modeling method in another embodiment;
FIG. 5 is a flow diagram of a blockchain-based joint modeling method in another embodiment;
FIG. 6 is a signaling diagram of a blockchain-based joint modeling method in one embodiment;
FIG. 7 is a block diagram of a block chain based joint modeling apparatus in one embodiment;
fig. 8 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The block chain-based joint modeling method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The server 104 determines a model to be trained according to a model algorithm module deployed by a joint modeling initiator based on intelligent contracts of a blockchain, and determines a model identification of the model to be trained; the model identification is sent to a joint modeling initiator and a joint modeling participant, and historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identification is obtained; and performing model training on the model to be trained according to the historical service data, determining an intelligent wind control model, performing uplink evidence storage on the historical service data, and transmitting an establishment result of the intelligent wind control model to the terminal 102 through a communication network. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
In one embodiment, as shown in fig. 2, a joint modeling method based on a blockchain is provided, and this embodiment is applied to a terminal for illustration by using the method, it is understood that the method may also be applied to a server, and may also be applied to a system including the terminal and the server, and implemented through interaction between the terminal and the server. It should be noted that the above-mentioned joint modeling method based on the blockchain is performed by the blockchain. The blockchain is a storage system of distributed data storage, has the characteristics of decentralization, non-tampering and traceability, and can safely and reliably store data assets. Based on the business data of each participant recorded through the blockchain, the intelligent contracts are utilized to carry out multidimensional statistics and modeling on the data, so that a wind control early warning and marketing system can be enriched, the characteristics of distributed accounting, non-tampering and traceability of the blockchain are relied on, the non-tamper property of the data is ensured, and a trusted mutually trusted digital interfacing cooperation environment is established.
In this embodiment, the method includes the steps of:
s210, determining a model to be trained according to a model algorithm module deployed by the joint modeling initiator based on the intelligent contracts of the blockchain, and determining a model identification of the model to be trained.
The model algorithm module is a data structure corresponding to a model operation rule deployed on the blockchain by a joint modeling initiator according to the intelligent contract of the blockchain, and is an intelligent contract program. Model identification refers to data that can characterize the model to be trained.
Specifically, the joint modeling initiator can deploy an interface according to a model on the blockchain, and a model algorithm module is deployed on the blockchain based on intelligent combination of the blockchain, so that the blockchain initializes the model according to the model algorithm module, determines a model to be trained, and distributes a model identifier for the model to be trained.
S220, the model identification is sent to the joint modeling initiator and the joint modeling participant, and historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identification are obtained.
The historical business data refers to data recorded by a joint modeling initiator and a joint modeling participant in a business process handling process in a historical time period.
Specifically, the blockchain sends the model identification to the joint modeling initiator, and the model identification is sent to the joint modeling participant through the joint modeling initiator. After the joint modeling initiator and the joint modeling participant acquire model identifications, historical service data required by model training is determined according to the model identifications, the historical service data is sent to a blockchain through a data transmission interface, and the blockchain acquires the historical service data sent by the joint modeling initiator and the joint modeling participant through the data interface.
S230, training the model to be trained according to the historical service data, determining an intelligent wind control model, and uploading and verifying the historical service data.
The intelligent wind control model can be a data prediction model, an evaluation model or a classification model.
Specifically, after the blockchain acquires the historical service data, model training data and tag data are determined according to the historical service data, an initialized model to be trained is subjected to model training through the model training data and the tag data to determine an intelligent wind control model, and the historical service data and a sender of the historical service data are subjected to uplink evidence storage so as to facilitate subsequent tracing of the model training data.
In the block chain-based joint modeling method, a model to be trained is determined according to a model algorithm module deployed by a joint modeling initiator based on intelligent contracts of the block chain, and a model identification of the model to be trained is determined; the model identification is sent to a joint modeling initiator and a joint modeling participant, and historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identification is obtained; and carrying out model training on the model to be trained according to the historical service data, determining an intelligent wind control model, and carrying out uplink evidence storage on the historical service data. The method solves the problems that when enterprises have a cooperative relationship, and the intelligent wind control model is shared among the cooperative enterprises, the accuracy and the credibility of the model are limited, whether the data of each enterprise meet the data format specification of the intelligent wind control model cannot be ensured, the application mode of the intelligent wind control model in the enterprise cooperation period is complicated, and the model training data is difficult to trace back and trace the source. According to the scheme, the multi-party joint modeling scheme is provided, the block chain determines the model to be trained according to the mode algorithm module deployed on the block chain by the joint modeling initiator, the intelligent wind control model is determined by carrying out model training on the model to be trained on the chain according to the historical service data sent by the joint modeling initiator and the joint modeling participant based on the model to be trained, the problem that the privacy of the service data is difficult to guarantee when each enterprise adopts the historical service data to carry out model training on the model to be trained is avoided, the universality of the intelligent wind control model is improved, and the safety of the service data is guaranteed in the multi-party joint modeling process.
In one embodiment, as shown in fig. 3, the block chain based joint modeling method further includes, based on the above embodiment:
s310, obtaining model input data deployed by a model application party, and inputting the model input data into the intelligent wind control model.
The model input data refers to service data of a model application party. The model application party can be a joint modeling initiator or a joint modeling participant, and can also be other enterprises needing to use the intelligent wind control model.
Specifically, the blockchain acquires model input data sent by a model application party based on a data transmission interface, and inputs the model input data into an intelligent wind control model.
S320, obtaining model output data of the intelligent wind control model, sending the model output data to a model application party, and performing uplink certification on the model input data and the model output data.
For example, when an enterprise that does not participate in training the intelligent wind control model wants to use the intelligent wind control model, a payment credential of the intelligent wind control model can be uploaded on a blockchain, after the blockchain acquires the payment credential, enterprise business data uploaded by the enterprise is acquired, the enterprise business data is input into the intelligent wind control model, output data of the intelligent wind control model is sent to the enterprise, and when the enterprise determines that the output data of the intelligent wind control model is acquired, the blockchain sends the payment credential to a joint modeling initiator and a joint modeling participant.
According to the method, the intelligent wind control model obtained through joint modeling based on the blockchain is used for realizing the data processing requirement of a model application party through the intelligent wind control model on the chain, so that the data safety of the model application party can be ensured, and meanwhile, the traceability of the input data and the output data of the model can be ensured.
In one embodiment, sending the model identification to the joint modeling initiator and the joint modeling participant, and obtaining historical business data sent by the joint modeling initiator and the joint modeling participant according to the model identification, includes:
the model identification is sent to a joint modeling initiator, and the model identification is sent to a joint modeling participant through the joint modeling initiator; sending a service data authorization request to a joint modeling initiator and a joint modeling participant, and acquiring authorization feedback information sent by the joint modeling initiator and the joint modeling participant according to the service data authorization request; and if the authorization feedback information is successful, acquiring historical service data transmitted by the joint modeling initiator and the joint modeling participant according to the model identification.
Specifically, the blockchain sends the model identifier allocated to the model to be trained to the joint modeling initiator, and the joint modeling initiator sends the model identifier to the joint modeling participant after acquiring the model identifier. After the joint modeling participant obtains the model identifier, information of participation in model training is sent to the blockchain, and the information of participation in model training can comprise the participant identifier of the joint modeling participant and the model identifier, wherein the participant identifier is data of enterprise information of the joint modeling participant. After acquiring information of participation model training sent by a joint modeling participant, the blockchain sends a service data authorization request to a joint modeling initiator and the joint modeling participant, and acquires authorization feedback information sent by the joint modeling initiator and the joint modeling participant according to the service data authorization request. If the authorization feedback information is successful, the blockchain acquires historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identification through the data interface.
It can be appreciated that after the joint modeling initiator and the joint modeling participant authorize the blockchain, the blockchain party can acquire historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identifier, so that the service data can be prevented from being stolen, and the security of the service data of the joint modeling initiator and the joint modeling participant is ensured.
In one embodiment, as shown in fig. 4, performing model training on a model to be trained according to historical service data to determine an intelligent wind control model, including:
s410, acquiring the sender identity of the data sender of the historical service data.
It should be noted that, in order to ensure that the acquired historical service data is the data sent by the joint modeling initiator or the joint modeling participant, the blockchain needs to check the acquired historical service data to ensure that the data source of the acquired historical service data is the joint modeling initiator or the joint modeling participant.
The sender identity is the identity of the data sender of the historical service data acquired by the blockchain.
S420, screening the historical service data according to the sender identity, the initiator identity of the joint modeling initiator and the participant identity of the joint modeling participant, and determining the target service data.
Specifically, whether the data sender of the historical service data is the joint modeling initiator or the joint modeling participant is determined according to the sender identity, the initiator identity of the joint modeling initiator and the participant identity of the joint modeling participant. If yes, determining the historical service data as target service data, and if not, deleting the historical service data sent by the data sender.
S430, performing model training on the model to be trained according to the target business data, and determining an intelligent wind control model.
In this embodiment, after the historical service data is obtained, the data source of the historical service data is checked, so that the data source of the historical service data can be ensured to be a joint modeling initiator or a joint modeling participant, thereby ensuring the reliability of the historical service data.
In one embodiment, as shown in fig. 5, performing model training on a model to be trained according to target service data to determine an intelligent wind control model, including:
s510, determining whether the target business data meets the model training conditions of the model to be trained according to the data characteristics of the target business data.
It should be noted that, when the model to be trained is trained to obtain the intelligent wind control model, the target service data may not meet the data requirement of the model training, so when the target service data does not meet the model training condition of the model to be trained, the supplementary data for the model training needs to be obtained from the joint modeling initiator and the joint modeling participant, and the supplementary data is service association data of the target service data.
Specifically, feature extraction is performed on the target service data, the data features of the target service data are determined, and whether the target service data meet the model training conditions of the model to be trained is determined according to the comparison result of the data features of the target service data and the data features required by model training. If the data characteristics of the target service data do not completely contain the data characteristics required by the model training, determining that the target service data do not meet the model training conditions of the model to be trained.
S520, if not, based on a preset data synchronization period, reading service association data of the joint modeling initiator and the joint modeling participant through middleware, and carrying out uplink certification on the service association data.
The data synchronization period can be set according to actual needs.
Specifically, if the target service data does not meet the model training condition of the model to be trained, the middleware of the blockchain synchronously reads the service association data of the joint modeling initiator and the joint modeling participant based on a preset data synchronization period, and performs uplink certification on the service association data.
And S530, performing model training on the model to be trained according to the target service data and the service association data, and determining an intelligent wind control model.
Exemplary, performing model training on a model to be trained according to target service data and service association data, and determining an intelligent wind control model, including: data cleaning is carried out on the target service data and the service association data, and effective data is determined; and extracting features of the effective data by adopting a principal component analysis method, determining feature data, and carrying out model training on the model to be trained by adopting the feature data to determine an intelligent wind control model.
The data cleaning refers to the last procedure for finding and correcting identifiable errors in a data file, and comprises the steps of checking data consistency, processing invalid values, missing values and the like.
It can be understood that the validity of the model training data can be ensured by performing data cleaning on the target service data and the service association data to determine the valid data, the valid data is subjected to feature extraction by adopting a principal component analysis method, the model to be trained is trained according to the feature data, and the model training efficiency can be improved while the reliability of the model is ensured.
According to the scheme, when the model to be trained is trained, the situation that the target service data determined according to the historical service data possibly has fewer data types and cannot meet the model training requirement is considered, the service association data is read through the middleware at regular time so as to supplement the model training data, the model to be trained is trained according to the service association data and the target service data, the integrity and the reliability of the model training data can be guaranteed, and therefore the reliability of the intelligent wind control model obtained through training is improved.
Illustratively, based on the above embodiment, the blockchain-based joint modeling method further includes:
acquiring model verification data sent by a joint modeling initiator and/or a joint modeling participant based on a model verification interface; verifying the intelligent wind control model according to the model verification data, and determining the prediction accuracy of the intelligent wind control model; and if the prediction accuracy is smaller than the accuracy threshold, adjusting the model parameters of the intelligent wind control model.
The accuracy threshold can be set according to actual requirements.
Specifically, the joint modeling initiator and/or the joint modeling participant can send model verification data to the blockchain at any time through the model verification interface, and after the blockchain receives the model verification data, the intelligent wind control model is verified according to the model verification data, so that the prediction accuracy of the intelligent wind control model is determined. And whether to update parameters of the intelligent wind control model is truly performed according to the comparison result of the prediction accuracy and the accuracy threshold. And if the prediction accuracy is smaller than the accuracy threshold, adjusting the model parameters of the intelligent wind control model.
It can be appreciated that through the scheme, the blockchain can acquire the model verification data which can be uploaded by the joint modeling initiator and the joint modeling participant to verify the intelligent wind control model, and adjust the model parameters of the intelligent wind control model according to the verification result of the intelligent wind control model, so that the prediction precision of the intelligent wind control model is improved.
Illustratively, as shown in fig. 6, the block chain-based joint modeling method further includes, based on the above embodiment:
the joint modeling initiator deploys a model algorithm module on the blockchain based on the intelligent combination of the blockchain according to the model deployment interface on the blockchain, so that the blockchain initializes the model according to the model algorithm module, determines the model to be trained, and distributes model identification for the model to be trained.
The blockchain sends the model identification allocated to the model to be trained to a joint modeling initiator, and the joint modeling initiator sends the model identification to a joint modeling participant after acquiring the model identification. After the joint modeling participant obtains the model identifier, information of participation in model training is sent to the blockchain, and the information of participation in model training can comprise the participant identifier of the joint modeling participant and the model identifier, wherein the participant identifier is data of enterprise information of the joint modeling participant. After acquiring information of participation model training sent by a joint modeling participant, the blockchain sends a service data authorization request to a joint modeling initiator and the joint modeling participant, and acquires authorization feedback information sent by the joint modeling initiator and the joint modeling participant according to the service data authorization request. If the authorization feedback information is successful, the blockchain acquires historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identification through the data interface.
And acquiring the sender identity of the data sender of the historical service data, and determining whether the data sender of the historical service data is the joint modeling initiator or the joint modeling participant according to the sender identity, the initiator identity of the joint modeling initiator and the participant identity of the joint modeling participant. If yes, determining the historical service data as target service data, and if not, deleting the historical service data sent by the data sender.
And extracting the characteristics of the target service data, determining the data characteristics of the target service data, and determining whether the target service data meets the model training conditions of the model to be trained according to the comparison result of the data characteristics of the target service data and the data characteristics required by model training. If the data characteristics of the target service data do not completely contain the data characteristics required by the model training, determining that the target service data do not meet the model training conditions of the model to be trained. If the target service data does not meet the model training conditions of the model to be trained, the middleware of the block chain synchronously reads the service association data of the joint modeling initiator and the joint modeling participant based on a preset data synchronization period, and performs uplink certification on the service association data. Data cleaning is carried out on the target service data and the service association data, and effective data is determined; and extracting features of the effective data by adopting a principal component analysis method, determining feature data, and carrying out model training on the model to be trained by adopting the feature data to determine an intelligent wind control model.
The joint modeling initiator and/or the joint modeling participant can send model verification data to the blockchain at any time through the model verification interface, and after the blockchain receives the model verification data, the intelligent wind control model is verified according to the model verification data, so that the prediction accuracy of the intelligent wind control model is determined. And whether to update parameters of the intelligent wind control model is truly performed according to the comparison result of the prediction accuracy and the accuracy threshold. And if the prediction accuracy is smaller than the accuracy threshold, adjusting the model parameters of the intelligent wind control model.
The block chain acquires model input data sent by a model application party based on a data transmission interface, and inputs the model input data into an intelligent wind control model. And obtaining model output data of the intelligent wind control model, sending the model output data to a model application party, and carrying out uplink certification on the model input data and the model output data.
In the block chain-based joint modeling method, a model to be trained is determined according to a model algorithm module deployed by a joint modeling initiator based on intelligent contracts of the block chain, and a model identification of the model to be trained is determined; the model identification is sent to a joint modeling initiator and a joint modeling participant, and historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identification is obtained; and carrying out model training on the model to be trained according to the historical service data, determining an intelligent wind control model, and carrying out uplink evidence storage on the historical service data. The method solves the problems that when enterprises have a cooperative relationship, and the intelligent wind control model is shared among the cooperative enterprises, the accuracy and the credibility of the model are limited, whether the data of each enterprise meet the data format specification of the intelligent wind control model cannot be ensured, the application mode of the intelligent wind control model in the enterprise cooperation period is complicated, and the model training data is difficult to trace back and trace the source. According to the scheme, the multi-party joint modeling scheme is provided, the block chain determines the model to be trained according to the mode algorithm module deployed on the block chain by the joint modeling initiator, the intelligent wind control model is determined by carrying out model training on the model to be trained on the chain according to the historical service data sent by the joint modeling initiator and the joint modeling participant based on the model to be trained, the problem that the privacy of the service data is difficult to guarantee when each enterprise adopts the historical service data to carry out model training on the model to be trained is avoided, the universality of the intelligent wind control model is improved, and the safety of the service data is guaranteed in the multi-party joint modeling process.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a block chain-based joint modeling device for realizing the block chain-based joint modeling method. The implementation of the solution provided by the apparatus is similar to that described in the above method, so the specific limitations in the embodiments of the one or more blockchain-based joint modeling apparatus provided below may be referred to above as limitations of the blockchain-based joint modeling method, and will not be described herein.
In one embodiment, as shown in FIG. 7, there is provided a blockchain-based joint modeling apparatus, comprising: a model initialization module 701, a historical business data acquisition module 702, and a model training module 703, wherein:
the model initialization module 701 is configured to determine a model to be trained according to a model algorithm module deployed by a joint modeling initiator based on a blockchain intelligent contract, and determine a model identifier of the model to be trained;
the historical service data acquisition module 702 is configured to send the model identifier to the joint modeling initiator and the joint modeling participant, and acquire historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identifier;
the model training module 703 is configured to perform model training on a model to be trained according to the historical service data, determine an intelligent wind control model, and perform uplink evidence storage on the historical service data.
Illustratively, the above-mentioned joint modeling apparatus based on blockchain further includes:
the model input data acquisition module is used for acquiring model input data deployed by a model application party and inputting the model input data into the intelligent wind control model;
the model output data transmitting module is used for acquiring model output data of the intelligent wind control model, transmitting the model output data to a model application party, and carrying out uplink certification on the model input data and the model output data.
Illustratively, the historical service data acquisition module 702 is specifically configured to:
the model identification is sent to a joint modeling initiator, and the model identification is sent to a joint modeling participant through the joint modeling initiator;
sending a service data authorization request to a joint modeling initiator and a joint modeling participant, and acquiring authorization feedback information sent by the joint modeling initiator and the joint modeling participant according to the service data authorization request;
and if the authorization feedback information is successful, acquiring historical service data transmitted by the joint modeling initiator and the joint modeling participant according to the model identification.
Exemplary, the model training module 703 is specifically configured to:
acquiring a sender identity of a data sender of historical service data;
screening historical service data according to the sender identity, the initiator identity of the joint modeling initiator and the participant identity of the joint modeling participant, and determining target service data;
and carrying out model training on the model to be trained according to the target service data, and determining the intelligent wind control model.
The model training module 703 is also specifically used for example:
determining whether the target service data meets the model training conditions of the model to be trained according to the data characteristics of the target service data;
If not, based on a preset data synchronization period, reading service association data of the joint modeling initiator and the joint modeling participant through middleware, and carrying out uplink certification on the service association data.
And carrying out model training on the model to be trained according to the target service data and the service association data, and determining the intelligent wind control model.
The model training module 703 is also specifically used for example:
data cleaning is carried out on the target service data and the service association data, and effective data is determined;
and extracting features of the effective data by adopting a principal component analysis method, determining feature data, and carrying out model training on the model to be trained by adopting the feature data to determine an intelligent wind control model.
Illustratively, the above-mentioned joint modeling apparatus based on blockchain further includes:
the verification data acquisition module is used for acquiring the model verification data sent by the joint modeling initiator and/or the joint modeling participant based on the model verification interface;
the model accuracy determining module is used for verifying the intelligent wind control model according to the model verification data to determine the prediction accuracy of the intelligent wind control model;
and the parameter adjustment module is used for adjusting the model parameters of the intelligent wind control model if the prediction accuracy is smaller than the accuracy threshold.
The various modules in the blockchain-based joint modeling apparatus described above may be implemented in whole or in part in software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure thereof may be as shown in fig. 8. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program, when executed by a processor, implements a blockchain-based joint modeling method. The display unit of the computer device is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be a key, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 8 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
step one, determining a model to be trained according to a model algorithm module deployed by a joint modeling initiator based on intelligent contracts of a blockchain, and determining a model identification of the model to be trained;
step two, the model identification is sent to a joint modeling initiator and a joint modeling participant, and historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identification are obtained;
thirdly, training the model to be trained according to the historical service data, determining an intelligent wind control model, and carrying out uplink evidence storage on the historical service data.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
Step one, determining a model to be trained according to a model algorithm module deployed by a joint modeling initiator based on intelligent contracts of a blockchain, and determining a model identification of the model to be trained;
step two, the model identification is sent to a joint modeling initiator and a joint modeling participant, and historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identification are obtained;
thirdly, training the model to be trained according to the historical service data, determining an intelligent wind control model, and carrying out uplink evidence storage on the historical service data.
In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:
step one, determining a model to be trained according to a model algorithm module deployed by a joint modeling initiator based on intelligent contracts of a blockchain, and determining a model identification of the model to be trained;
step two, the model identification is sent to a joint modeling initiator and a joint modeling participant, and historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identification are obtained;
thirdly, training the model to be trained according to the historical service data, determining an intelligent wind control model, and carrying out uplink evidence storage on the historical service data.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to comply with the related laws and regulations and standards of the related countries and regions.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. A blockchain-based joint modeling method, comprising:
determining a model to be trained according to a model algorithm module deployed by a joint modeling initiator based on intelligent contracts of a blockchain, and determining a model identification of the model to be trained;
the model identification is sent to the joint modeling initiator and the joint modeling participant, and historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identification is obtained;
And carrying out model training on the model to be trained according to the historical service data, determining an intelligent wind control model, and carrying out uplink evidence storage on the historical service data.
2. The method as recited in claim 1, further comprising:
obtaining model input data deployed by a model application party, and inputting the model input data into an intelligent wind control model;
and obtaining model output data of the intelligent wind control model, sending the model output data to a model application party, and carrying out uplink certification on the model input data and the model output data.
3. The method of claim 1, wherein transmitting the model identification to the joint modeling initiator and joint modeling participant and obtaining historical business data transmitted by the joint modeling initiator and joint modeling participant according to the model identification comprises:
the model identification is sent to the joint modeling initiator, and the model identification is sent to a joint modeling participant through the joint modeling initiator;
sending a service data authorization request to the joint modeling initiator and the joint modeling participant, and acquiring authorization feedback information sent by the joint modeling initiator and the joint modeling participant according to the service data authorization request;
And if the authorization feedback information is successful authorization, acquiring historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identifier.
4. The method of claim 1, wherein model training the model to be trained based on the historical business data to determine an intelligent wind control model comprises:
acquiring a sender identity of a data sender of the historical service data;
screening the historical service data according to the sender identity, the initiator identity of the joint modeling initiator and the participant identity of the joint modeling participant, and determining target service data;
and carrying out model training on the model to be trained according to the target business data, and determining an intelligent wind control model.
5. The method of claim 4, wherein model training the model to be trained according to the target business data, determining an intelligent wind control model, comprises:
determining whether the target service data meets the model training conditions of the model to be trained according to the data characteristics of the target service data;
if not, based on a preset data synchronization period, reading service association data of the joint modeling initiator and the joint modeling participant through middleware, and carrying out uplink certification on the service association data;
And carrying out model training on the model to be trained according to the target service data and the service association data, and determining an intelligent wind control model.
6. The method of claim 5, wherein model training the model to be trained based on the target business data and the business-related data, determining an intelligent wind control model, comprises:
performing data cleaning on the target service data and the service association data to determine effective data;
and carrying out feature extraction on the effective data by adopting a principal component analysis method, determining feature data, carrying out model training on the model to be trained by adopting the feature data, and determining an intelligent wind control model.
7. The method as recited in claim 1, further comprising:
acquiring model verification data sent by the joint modeling initiator and/or the joint modeling participant based on a model verification interface;
verifying the intelligent wind control model according to the model verification data, and determining the prediction accuracy of the intelligent wind control model;
and if the prediction accuracy is smaller than an accuracy threshold, adjusting the model parameters of the intelligent wind control model.
8. A blockchain-based joint modeling apparatus, the blockchain-based joint modeling apparatus comprising:
the model initialization module is used for determining a model to be trained according to a model algorithm module deployed by a joint modeling initiator based on intelligent contracts of a blockchain, and determining a model identification of the model to be trained;
the historical service data acquisition module is used for sending the model identifier to the joint modeling initiator and the joint modeling participant and acquiring historical service data sent by the joint modeling initiator and the joint modeling participant according to the model identifier;
and the model training module is used for carrying out model training on the model to be trained according to the historical service data, determining an intelligent wind control model and carrying out uplink evidence storage on the historical service data.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311726154.4A CN117828658A (en) | 2023-12-14 | 2023-12-14 | Block chain-based joint modeling method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311726154.4A CN117828658A (en) | 2023-12-14 | 2023-12-14 | Block chain-based joint modeling method and device and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117828658A true CN117828658A (en) | 2024-04-05 |
Family
ID=90520164
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311726154.4A Pending CN117828658A (en) | 2023-12-14 | 2023-12-14 | Block chain-based joint modeling method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117828658A (en) |
-
2023
- 2023-12-14 CN CN202311726154.4A patent/CN117828658A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112232527B (en) | Safe distributed federal deep learning method | |
| US20190342096A1 (en) | Online identity and credential verification systems and methods protecting user data | |
| US9361450B2 (en) | Authentication using mobile devices | |
| TWI746399B (en) | Information reading and writing method and device based on blockchain | |
| US12008096B2 (en) | Secure authentication | |
| CN117828658A (en) | Block chain-based joint modeling method and device and computer equipment | |
| CN116233847A (en) | Login method, login device, computer equipment and storage medium | |
| US9210147B1 (en) | Method, apparatus and computer program product for assessing risk associated with authentication requests | |
| JP2017152032A (en) | Control method for information processor, information processor, control program, control method for terminal, and terminal control program | |
| US12022281B2 (en) | User authentication | |
| US20190116168A1 (en) | Authentication for computing systems | |
| US20220417744A1 (en) | User authentication | |
| US20240020879A1 (en) | Proof-of-location systems and methods | |
| US11393235B2 (en) | Face image quality recognition methods and apparatuses | |
| US20240007293A1 (en) | Systems and methods for user identification and/or retrieval of user-related data at a local auxiliary system | |
| CN117078263A (en) | Resource transfer method, device, computer equipment and storage medium | |
| CN116707972A (en) | Device authentication method, device, computer device and storage medium thereof | |
| CN117240578A (en) | Flow integrity verification method and device, computer equipment and storage medium thereof | |
| CN117061238A (en) | Service request processing method, device, computer equipment and storage medium | |
| CN116847345A (en) | User authentication method, device, computer equipment and storage medium thereof | |
| CN114444095A (en) | Target data acquisition method, apparatus, device, storage medium, and program product | |
| CN116167073A (en) | Object credit model training method, device, computer equipment and storage medium | |
| CN117611165A (en) | Abnormal object detection method, device, computer equipment and storage medium | |
| CN117436888A (en) | Payment service processing method, device, computer equipment and storage medium | |
| CN117151717A (en) | Device password modification method, device, computer device and storage medium |
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 |