CN113553609A - Method and system for predicting service by combining multiple parties based on privacy protection - Google Patents
Method and system for predicting service by combining multiple parties based on privacy protection Download PDFInfo
- Publication number
- CN113553609A CN113553609A CN202111094201.9A CN202111094201A CN113553609A CN 113553609 A CN113553609 A CN 113553609A CN 202111094201 A CN202111094201 A CN 202111094201A CN 113553609 A CN113553609 A CN 113553609A
- Authority
- CN
- China
- Prior art keywords
- cloud center
- service
- data
- fuzzy
- center
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- 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
Abstract
In the method for predicting the service, any first party in a plurality of parties sends a service prediction request to a cloud center, wherein the service prediction request at least indicates a service scene of a current service event and an object identifier of a target service object belonging to a second party, and the object identifier relates to the current service event. And the cloud center responds to the service prediction request and acquires a second privacy contract signed by a second party. And the cloud center judges whether the service scene is matched with the use scene agreed in the second privacy contract or not, and acquires fuzzy characteristic data which is uploaded by the second participant and is subjected to fuzzification processing on the target service object on the basis of the object identification under the condition of matching. The cloud center performs service prediction based on the fuzzy feature data and a target prediction model corresponding to a service scene, and provides a service prediction result to the first participant.
Description
Technical Field
One or more embodiments of the present disclosure relate to the field of computer technologies, and in particular, to a method and a system for performing business prediction based on privacy protection by combining multiple parties.
Background
In the big data era, with the large-scale collection of data, the maturity of a super-large-scale distributed computing cluster technology and the continuous iterative updating of a machine learning algorithm, the value of the data is explored unprecedentedly and is applied to aspects of social production and daily life of people. However, as a double-edged knife is used, while the data has great value to people, the privacy of the data is revealed, and the normal and safe life of people is seriously threatened. This makes individual data holders (also called participants) becoming islands of data one after another.
Therefore, a solution is urgently needed, which enables sharing of data while ensuring that information of each party is not leaked.
Disclosure of Invention
One or more embodiments of the present specification describe a method and a system for performing business prediction by combining multiple parties based on privacy protection, which can ensure that data sharing is achieved without information leakage of the parties.
In a first aspect, a method for performing service prediction based on privacy protection multiparty federation is provided, including:
any first participant in the multiple participants sends a service prediction request to the cloud center, wherein the service prediction request at least indicates a service scene of a current service event and an object identifier of a target service object belonging to a second participant, and the object identifier relates to the current service event;
the cloud center responds to the service prediction request, and acquires a second privacy contract signed by the second party;
the cloud center judges whether the service scene is matched with the use scene agreed in the second privacy contract or not, and acquires fuzzy characteristic data which is uploaded by the second participant and is subjected to fuzzification processing on the basis of the object identification under the condition of matching;
and the cloud center performs service prediction based on the fuzzy feature data and a target prediction model corresponding to the service scene, and provides a service prediction result for the first participant.
In a second aspect, a method for performing service prediction based on privacy protection multiparty federation is provided, including:
in response to the triggering of the current payment event, the second payment platform pulls a signed second privacy contract from the cloud center, wherein the second privacy contract appoints a use scene of uploaded data of the second payment platform and a plurality of fields contained in the uploaded data;
the second payment platform judges whether the use scene agreed in the second privacy contract is matched with the payment scene, and under the condition of matching, field values of the second user corresponding to fields agreed in the second privacy contract are extracted from original feature data of the second user;
the second payment platform fuzzifies the field values of the fields to obtain fuzzy feature data of the second user;
the second payment platform uploads the fuzzy feature data of the second user to the cloud center;
the first payment platform sends a service prediction request to the cloud center, wherein the service prediction request at least indicates a payment scene of a current payment event and a user identifier of the second user related to the current payment event;
the cloud center acquires fuzzy feature data of the second user, which is uploaded by the second payment platform, based on the user identification;
and the cloud center performs service prediction based on the fuzzy feature data and a target prediction model corresponding to the payment scene, and provides a service prediction result for the first payment platform.
In a third aspect, a system for performing service prediction based on privacy protection multiparty federation is provided, including:
any first participant in the multiple participants is used for sending a service prediction request to the cloud center, wherein at least a service scene of a current service event is indicated, and an object identifier of a target service object belonging to a second participant and related to the current service event;
the cloud center is used for responding to the service prediction request and acquiring a second privacy contract signed by the second party;
the cloud center is further configured to determine whether the service scene is matched with a use scene agreed in the second privacy contract, and acquire fuzzy feature data of the target service object, which is uploaded by the second party and subjected to fuzzification processing, based on the object identifier under the condition that the service scene is matched with the use scene agreed in the second privacy contract;
the cloud center is further configured to perform service prediction based on the fuzzy feature data and a target prediction model corresponding to the service scene, and provide a service prediction result to the first participant.
In a fourth aspect, a system for performing service prediction based on privacy protection by combining multiple parties is provided, which includes:
the second payment platform is used for responding to the trigger of the current payment event, pulling a signed second privacy contract from the cloud center, wherein the second privacy contract appoints a use scene of uploaded data of the second payment platform and a plurality of fields contained in the uploaded data;
the second payment platform is further configured to determine whether the usage scenario agreed in the second privacy contract matches the payment scenario, and extract field values of the second user corresponding to fields agreed in the second privacy contract from the original feature data of the second user in the case of matching;
the second payment platform is further configured to perform obfuscation processing on the field values of the fields to obtain obfuscated feature data of the second user;
the second payment platform is further used for uploading the fuzzy feature data of the second user to the cloud center;
the first payment platform is used for sending a service prediction request to the cloud center, wherein at least a payment scene of a current payment event and a user identifier of the second user related to the current payment event are indicated;
the cloud center is used for acquiring fuzzy feature data of the second user uploaded by the second payment platform based on the user identification;
the cloud center is further used for conducting service prediction based on the fuzzy feature data and a target prediction model corresponding to the payment scene, and providing a service prediction result for the first payment platform.
In a fifth aspect, there is provided a computer storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method of the first or second aspect.
In a sixth aspect, there is provided a computing device comprising a memory having stored therein executable code, and a processor that when executing the executable code, implements the method of the first or second aspect.
According to the method and the system for multi-party combined service prediction based on privacy protection provided by one or more embodiments of the specification, firstly, a plurality of participants upload respective fuzzified data to a cloud center, so that the privacy disclosure problem caused by direct sharing of original data among the participants can be avoided. In addition, the participants and the cloud center agree on the use scene of the uploaded data in advance, and the data of each participant can be prevented from being abused. Finally, when any first participant wants to use the uploaded data of other participants to perform service prediction, the cloud center obtains a service prediction result based on the uploaded data of other participants and returns the service prediction result to the first participant, so that the uploaded data of each participant can be always kept in the cloud center without being disclosed to the participants, and privacy protection of data of each participant can be further realized.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
Fig. 1 is a schematic diagram of an implementation scenario provided in an embodiment of the present specification;
fig. 2 is an interaction diagram of a data uploading method provided in an embodiment of the present specification;
FIG. 3 is a schematic view of a feature storage hub provided herein;
FIG. 4 is an interaction diagram of a method for predicting a service based on privacy protection multi-party federation according to an embodiment of the present specification;
FIG. 5 is an interaction diagram of a method for predicting business based on privacy protection multi-party federation according to another embodiment of the present disclosure;
FIG. 6 is a schematic diagram of a system for predicting business based on privacy protection multiparty federation according to an embodiment of the present disclosure;
fig. 7 is a schematic diagram of a system for predicting business based on privacy protection multi-party federation according to another embodiment of the present disclosure.
Detailed Description
The scheme provided by the specification is described below with reference to the accompanying drawings.
Before describing the solutions provided in the embodiments of the present specification, the following description will be made on the inventive concept of the present solution.
As previously mentioned, in order to break data islands, data sharing is often required between the participants. However, since the data itself contains a lot of user privacy, industry confidentiality and the like, if the original data is directly shared between the participating parties, the data security is threatened, and privacy disclosure is caused.
Therefore, the inventor of the present application proposes that each participant uploads the respective fuzzified data to the cloud center, and the cloud center performs isolated storage on the uploaded data (also referred to as shared data) of each participant. In addition, in order to avoid misuse of the uploaded data of each participant by the cloud center, each participant can sign a privacy contract with the cloud center, and the use scene of the uploaded data of the corresponding participant is agreed in the privacy contract. Finally, for any uploaded data of the first participant stored in the cloud center, when other participants want to perform service prediction based on the uploaded data, the other participants can send service prediction requests to the cloud center, then the cloud center performs service prediction based on the uploaded data of the first participant, and returns service prediction results to the other participants.
The present invention will be described in detail with reference to the following embodiments.
Fig. 1 is a schematic view of an implementation scenario provided in an embodiment of the present specification. In fig. 1, the participants may be implemented as any computing, processing capable device, platform, server, or cluster of devices. In one example, each participant may be a payment platform in a different country, with the multiple payment platforms comprising a payment network.
In fig. 1, the structures of the participants are similar, and for example, any first participant may be integrated with a first SDK and a second SDK provided by the cloud center. The first SDK is also called a service prediction SDK, and is configured to perform standardized processing on a service prediction request sent by the first party cloud center. The normalization process includes at least one of parameter assembly and business scenario mapping. The second SDK, also referred to as the feature channel SDK, is used to fuzzify the raw feature data of the first participant. In addition, the method can also be used for preprocessing the original characteristic data before fuzzification processing, such as characteristic cleaning, and the like, and encrypting the fuzzified characteristic data after the fuzzification processing, and the like.
The cloud center may include a feature storage center, a model center, and a policy center, where the feature storage center corresponds to the second SDK and is configured to store upload data of each participant and privacy contracts signed by each participant. The privacy contract appoints the use scene of the uploaded data of the corresponding participant. In addition, each field, encryption mode, fuzzification mode, storage requirement and the like contained in the uploading data of the corresponding participant are also agreed in the privacy contract. The model center is used for storing a plurality of service prediction models trained in advance, wherein each service prediction model corresponds to one service scene. The strategy center corresponds to the first SDK and is used for acquiring fuzzy characteristic data of a target service object from the characteristic storage center based on the received service prediction request and inputting the fuzzy characteristic data into a target service prediction model in the model center for service prediction. In addition, the strategy center is also used for returning the service prediction result to the participant who sends the service prediction request.
It should be understood that fig. 1 is only an exemplary illustration, and in practical applications, each participant and the cloud center may further include other modules. Taking the cloud center as an example, the cloud center may further include a monitoring center, and the monitoring center may be configured to perform at least one of the following monitoring operations: shared data auditing monitoring, shared data use monitoring, decision path monitoring, model snapshot monitoring, business prediction service monitoring and the like.
For easy understanding, a practical application scenario of the present solution is introduced first.
In one example, the target business object may be a user and the target business prediction model may be a user classification or regression model. The uploaded data for each participant may include at least one of age, gender, occupation, and credit score of the user; and/or at least one of geographic location, transaction frequency, and registration duration. The user classification or regression model may be specifically used for predicting the risk level (e.g., high, medium or low) of the user, or the belonged consumer group (low-consumption group, high-consumption group, etc.), or the loanable amount.
In another example, the target business object may be a commodity, and the target business prediction model may be a commodity classification or regression model. The uploaded data for each participant may include at least one of a place of origin, a cost, a selling price, and a sales volume. The product classification or regression model may be specifically used for predicting the hot grade (such as cold or hot) and the recommended goods amount of the product.
In yet another example, the target business object may be a merchant, and the target business prediction model may be a merchant classification or regression model.
In yet another example, the target business object may be an event. The event here may include a transaction event, a login event, a click event, or a purchase event. The target business prediction model may be an event classification or regression model. The uploaded data of each participant may include at least one of a representation of the user, behavioral information, and descriptive information of alternative recommended objects (e.g., advertisements, etc.). The event regression model is used for predicting whether the user clicks the alternative recommendation object.
As can be seen from the related description of fig. 1, the cloud center stores the upload data of each participant. The upload data of any second participant can be uploaded by the second participant in response to the triggering of the business event, namely, uploaded in real time; or may be uploaded offline by the second party. The following describes an upload process of upload data of the second party, taking offline upload as an example.
Fig. 2 is an interaction diagram of a data uploading method provided in an embodiment of the present specification. As shown in fig. 2, the method may include:
in step 202, the second party pulls the second privacy contract signed by the second party from the cloud center.
In particular, the second party may pull the second privacy contract that it signed from a feature storage center in the cloud center.
In one example, the second privacy contract is configured by the second party based on a contract configuration page of the cloud center prior to uploading data. Wherein the usage scenario of the uploaded data of the second participant and several fields contained in the uploaded data are agreed. For example, the business object is a user, and the fields may be, for example, a user identifier, an age, a registration duration, and the like.
In addition, the second privacy contract also stipulates an encryption mode (such as DES, RSA or RHA algorithm and the like) of uploading data, storage requirements, whether the second party shares blacklist data to other parties and the like.
It should be understood that, in this embodiment of the present specification, a manner in which a participant configures a privacy contract based on a contract configuration page may implement flexible configuration of information such as a field (for short, a shared field) and an encryption manner in shared data, for example, the shared field may be increased or decreased flexibly without code development, which reduces optimization cost of the shared field.
In step 204, the second party extracts field values corresponding to fields agreed in the second privacy contract from the original feature data of the service object.
Optionally, before performing step 204, the second party may perform a pre-process such as feature cleaning on the raw feature data of the business object. And then, extracting field values of all fields from the preprocessed original feature data.
And step 206, the second party fuzzifies the field values of the fields to obtain fuzzy characteristic data of the business object.
Here, if the second privacy contract specifies the obfuscation method, the field value of each field may be obfuscated based on the specified obfuscation method. The fuzzification process may include at least one of a hash operation, a section mapping, and a boolean value conversion. The hash operation may be processing on the user identifier, for example, the user identifier may be mapped to a hash value with a fixed length by the hash operation. The interval mapping may be processed for discrete values with a fixed value range, for example, the user age may be mapped to the age group through the interval mapping. The boolean value translation may be processed for a variety of field types, for example, a registration duration may be translated to 1 if the user's registration duration exceeds 7 days, otherwise to 0, and so on.
In summary, the field value processed by fuzzification can play a role of privacy protection for the original feature data.
It should be understood that after the processing of step 204 and step 206 are performed on each of the business objects belonging to the second participant, fuzzy feature data corresponding to each of the business objects can be obtained. And then, the second participant can upload the fuzzy characteristic data corresponding to each business object to the cloud center. Since the uploading manner of each piece of fuzzy feature data is similar, the following description will also take the example of uploading fuzzy feature data of one business object.
And step 208, the second participant uploads the fuzzy characteristic data of the business object to the cloud center.
In order to further ensure the security of the uploaded data of the second party, before step 208 is executed, the second party may encrypt the fuzzy feature data of the business object according to an encryption mode agreed in the second privacy contract, and then upload the encrypted fuzzy feature data of the business object to the cloud center.
Specifically, the second participant may send the fuzzy characteristic data of the business object to the cloud center. And then, the characteristic storage center performs audit compliance check on the received fuzzy characteristic data, and stores the fuzzy characteristic data after the check is passed.
In one particular example, the audit compliance check may include at least one of data decryption, data classification, and audit trails. Wherein the decryption of the data may be performed based on the encryption scheme agreed upon in the second privacy contract.
In another specific example, for the uploaded data of each participant, the cloud center may further perform standardization processing on the object identifier in the uploaded data to obtain an internally used standard identifier. And then storing the standard identifier while storing the uploaded data, so that the uploaded data of the participants can be read based on the standard identifier in the process of service prediction.
In addition, in one example, the feature storage center may store, for a plurality of tenants, upload data corresponding to each tenant in a manner of isolation among the tenants by using a plurality of parties. That is, the storing the fuzzy feature data specifically may include: and storing the fuzzy characteristic data into an isolated storage area of the tenant corresponding to the second party.
Of course, in practical applications, each participant may sign multiple privacy contracts with the cloud center, where different fields and usage scenarios thereof are agreed in different privacy contracts.
For example, suppose that party a signs privacy contract 1 and privacy contract 2 with the cloud center, where the content of privacy contract 1 may be, for example: field: user identification, age, gender, and occupation, etc. The use scenario is as follows: payment scenarios and marketing scenarios. The content of the privacy contract 2 may be, for example: field: user identification, geographic location, etc. The use scenario is as follows: marketing scenarios.
It should be appreciated that when any party signs multiple privacy contracts with the cloud center, it typically uploads multiple shares of data. The feature storage center also stores the multiple copies of data in an isolated manner.
Fig. 3 is a schematic diagram of a feature storage center provided in the present specification. In fig. 3, the feature storage center stores the uploaded data corresponding to two tenants (i.e., two parties) in a manner of isolation between tenants. The uploaded data corresponding to each tenant comprises two pieces of data, and the two pieces of data of the same tenant are stored in an isolation mode. For example, tenant 1, one piece of data includes fields such as user identification, age, gender, and academic calendar. Another piece of data contains fields for user identification, geographic location, etc. In addition, the two pieces of data correspond to two privacy contracts, respectively. Each privacy contract is agreed with fields contained in a corresponding piece of data and a use scene thereof.
It should be noted that, in a preferred implementation, the above steps 202-208 may be performed by the second party invoking a built-in second SDK (i.e., a feature channel SDK) provided by the cloud center. It should be appreciated that the second SDK may establish a connection with the feature storage center through the gateway. Thereafter, based on the connection, a second privacy contract may be pulled and fuzzy feature data of the business object uploaded. That is to say, in the scheme, each participant does not need to additionally develop processing logic such as fuzzification processing of data, but only needs to integrate the SDKs with the fuzzification processing and other functions, which are uniformly provided by the cloud center, so that the data sharing cost of each participant is reduced, and the lightweight design of each participant is realized.
It should be further noted that, in this specification, the feature storage center may be regarded as an independent third-party data storage main body, and each participant uploads respective data to the storage main body, so that peer-to-peer data sharing among multiple participants can be avoided, and further, the service joint prediction cost can be reduced.
It should be understood that, similarly to the data uploading method of the second party, other parties may also upload data to be shared to the cloud center. And the cloud center stores the uploaded data of each participant in a mode of isolation among tenants.
The above is an explanation of the upload process of the upload data of each participant, and the following is an explanation of the traffic prediction process performed based on the upload data of each participant.
Fig. 4 is an interaction diagram of a method for predicting a service based on a multi-party federation of privacy protection according to an embodiment of the present specification. As shown in fig. 4, the method may include:
step 402, any first participant in the multiple participants sends a service prediction request to the cloud center.
The service prediction request at least indicates a service scenario of the current service event and an object identifier of a target service object belonging to the second party, which is related to the current service event.
The current traffic event here may be any one of the following: payment events, marketing events, and money transfer events, among others. The corresponding service scenario may be, for example: a payment scenario, a marketing scenario, or a remittance scenario. In addition, the target business object may be, for example, a user, a merchant, a commodity, an event, or the like.
In one example, the first participant invokes a built-in first SDK (i.e., a traffic prediction SDK) provided by the cloud center to standardize the traffic prediction request. And then sending a standardized service prediction request to the cloud center.
The normalization process herein may include at least one of parameter assembly and business scenario mapping. Wherein, parameter assembling refers to mapping the incoming parameters into standard parameters. Scenario routing refers to mapping a current service prediction request to a specific service scenario.
It should be appreciated that the first SDK may establish a connection with the policy center through the gateway. The traffic prediction request may then be sent based on the connection. That is to say, in the scheme, it is only necessary to integrate the SDK with the standard processing function provided by the cloud center without additionally developing a standardized processing logic of the service prediction request for each participant, thereby reducing the operation and maintenance cost of each participant and realizing a lightweight design of each participant.
In step 404, the cloud center obtains a second privacy contract signed by a second party in response to the service prediction request.
Specifically, a second privacy contract signed by the second party is obtained from the feature storage center by a policy center in the cloud center in response to the traffic prediction request.
In one example, the second party may be determined by the cloud center according to the object identifier of the target business object. For example, by analyzing the identifier of the target business object, the participant to which the target business object belongs can be determined.
In step 404, if the second party uploads a plurality of shares of data in advance, that is, signs a plurality of shares of the second privacy contract with the cloud center in advance, the plurality of shares of the second privacy contract may be obtained.
And 406, the cloud center judges whether the service scene indicated in the service prediction request is matched with the use scene agreed in the second privacy contract, and acquires fuzzy characteristic data of the target service object uploaded by the second participant after fuzzification processing based on the object identification under the condition of matching.
It should be noted that, in the case that multiple copies of the second privacy contracts are acquired, it may be determined sequentially whether the service scenario indicated in the service prediction request matches the usage scenario in each copy of the second privacy contracts. When the first privacy contract is matched with the use scene in any one of the second privacy contracts, the fuzzy feature data of the target business object can be obtained from the corresponding piece of data.
It should be understood that when the service scenario indicated in the service prediction request matches the usage scenario in more than one second privacy contract, then multiple copies of the fuzzy feature data of the target service object may be obtained.
Further, the matching of the business scenario in step 406 with the usage scenario agreed upon in the second privacy contract may include: the former is the same as the latter, or the latter comprises the former. For example, assume a business scenario is: a payment scenario, wherein the usage scenario agreed in the second privacy contract is as follows: and the payment scene and the marketing scene are judged to be matched. For another example, assume that the service scenario is: a payment scenario, wherein the usage scenario agreed in the second privacy contract is as follows: pay the scene, then judge as matching too.
In an example, the obtaining of the fuzzy feature data of the target business object specifically may include: and reading fuzzy characteristic data which are uploaded by the second party and are subjected to fuzzification processing on the target business object from the characteristic storage center by the strategy center. More specifically, the isolated storage area of the tenant corresponding to the second participant may be determined first. And then, reading fuzzy characteristic data of the target business object after fuzzification processing from the determined isolated storage area.
Of course, if multiple pieces of data are stored in the determined isolated storage area, after the isolated storage area is determined, a sub-isolation area corresponding to the matched second privacy contract may be further determined, and then the fuzzy feature data of the target business object is read from the sub-isolation area.
Finally, it should be noted that, for the object identifier, the cloud center may also convert the object identifier into a standard identifier used in the cloud center, and then obtain the fuzzy feature data of the target service object based on the standard identifier.
And step 408, the cloud center performs service prediction based on the fuzzy feature data and the target prediction model corresponding to the service scene, and provides a service prediction result to the first participant.
As previously described, the model center may store business prediction models corresponding to a plurality of business scenarios. After the fuzzy characteristic data of the target service object is obtained, the strategy center can input the fuzzy characteristic data into a target service prediction model corresponding to a service scene in the model center for service prediction, so as to obtain a service prediction result. In addition, the policy center may also return the business prediction results to the first participant.
It should be noted that, if it is also agreed in the second privacy contract that the second party agrees to share the blacklist data thereof to the first party, here, the target service prediction model may also obtain the service prediction result based on the shared blacklist data.
In an example, if the target business prediction model is a user classification or regression model and is used for predicting whether the user is a risk user, that is, the business prediction result includes a risk user and a normal user, the business prediction result may be obtained by, after the user is scored by the target business prediction model, comparing the score with a predetermined threshold corresponding to the model. For example, if the score of the user is greater than the predetermined threshold, the user is a risk user, otherwise, the user is a normal user.
It should be understood that, in the present scheme, the cloud center does not expose the upload data of the second party to the first party, but only returns the service prediction result obtained based on the upload data of the second party to the first party, so that privacy protection of the data of the second party can be achieved.
In summary, according to the method for performing service prediction based on multi-party federation of privacy protection provided by the embodiments of the present specification, first, a plurality of participants upload respective fuzzified data to a cloud center, so that the problem of privacy disclosure caused by directly sharing original data among the participants can be avoided. In addition, the participants and the cloud center agree on the use scene of the uploaded data in advance, and the data of each participant can be prevented from being abused. Finally, when any first participant wants to use the uploaded data of other participants to perform service prediction, the cloud center obtains a service prediction result based on the uploaded data of other participants and returns the service prediction result to the first participant, so that the uploaded data of each participant can be always kept in the cloud center without being disclosed to the participants, and privacy protection of data of each participant can be further realized.
The scheme provided by the embodiment of the present disclosure is described below by taking as an example that multiple parties include a cloud center, a first payment platform, and a second payment platform, and a service event is a payment event and a service scene is a payment scene.
Fig. 5 is an interaction diagram of a method for predicting a service based on a multi-party federation of privacy protection according to another embodiment of the present disclosure. As shown in fig. 5, the method may include:
step 502, in response to the trigger of the current payment event, the second payment platform pulls the signed second privacy contract from the cloud center.
In particular, the second payment platform may invoke a built-in second SDK provided by the cloud center, pulling its signed second privacy contract from the feature storage center. The second privacy contract promises a usage scenario of the upload data of the second payment platform and a plurality of fields contained in the usage scenario.
Step 504, the second payment platform determines whether the usage scenario agreed in the second privacy contract matches the payment scenario, and extracts field values corresponding to fields agreed in the second privacy contract from the original feature data of the second user in the case of matching.
The second user here is the user who triggered the current payment event.
In one example, the extracted fields may include user information, device information, and environment information, among others.
Step 506, the second payment platform performs fuzzification processing on the field values of the fields to obtain fuzzy feature data of the second user.
As described above, the obfuscation process may include at least one of a hash operation, a section mapping, and a boolean value conversion.
And step 508, the second payment platform uploads the fuzzy feature data of the second user to the cloud center.
Specifically, the cloud center may store the fuzzy feature data of the second user in the isolated storage area of the tenant corresponding to the second payment platform.
It should be noted that, the above steps 504-508 may be executed by the second payment platform invoking the built-in second SDK.
Thus, the real-time uploading of the fuzzy characteristic data of the second user triggering the payment event is completed.
Step 510, the first payment platform sends a service prediction request to the cloud center.
The service prediction request at least indicates a payment scene of the current payment event and a user identifier of a second user related to the current payment event.
Specifically, the first payment platform may call a built-in first SDK provided by the cloud center, and send a service prediction request to the cloud center.
And step 512, the cloud center acquires fuzzy feature data of the second user, which is uploaded by the second payment platform, based on the user identifier.
For example, the cloud center may read the fuzzy feature data of the second user from the isolated storage area of the tenant corresponding to the second payment platform.
And 514, the cloud center performs service prediction based on the fuzzy feature data and the target prediction model corresponding to the payment scene, and provides a service prediction result to the first payment platform.
The cloud center can input the fuzzy feature data into a target service prediction model corresponding to the payment scene in the model center for service prediction, and a service prediction result is obtained. In addition, the service prediction result can be returned to the first payment platform.
Therefore, real-time sharing and real-time use of data among payment platforms are achieved, and further the service prediction effect can be improved.
Corresponding to the above method for performing business prediction based on multi-party federation of privacy protection, an embodiment of the present specification further provides a system for performing business prediction based on multi-party federation of privacy protection, as shown in fig. 6, the system may include a cloud center 602 and a plurality of participants. The cloud center 602 maintains privacy contracts signed by a plurality of participants, wherein usage scenarios of uploaded data of the corresponding participants are agreed.
A first participant 604 of any of the multiple participants is configured to send a business prediction request to the cloud center 602, where at least a business scenario of a current business event and an object identifier of a target business object belonging to a second participant are indicated in the business scenario.
The first participant 604 is specifically configured to:
calling a first SDK which is built in and provided by a cloud center, and carrying out standardization processing on a service prediction request, wherein the standardization processing comprises at least one item of parameter assembly and service scene mapping;
and sending the standardized service prediction request to the cloud center 602.
And the cloud center 602 is configured to obtain a second privacy contract signed by the second party 606 in response to the service prediction request.
The cloud center 602 is further configured to determine whether a service scene indicated in the service prediction request matches a usage scene agreed in the second privacy contract, and acquire fuzzy feature data of the target service object, which is uploaded by the second participant 606 and is subjected to fuzzification processing, based on the object identifier in the case of matching.
The cloud center 602 includes a feature storage center, and is configured to store upload data of each participant.
The cloud center 602 is specifically configured to:
and reading fuzzy feature data which are uploaded by the second party 606 and are subjected to fuzzification processing on the target business object from the feature storage center.
In one example, the feature storage center takes a plurality of participants as a plurality of tenants, and stores upload data corresponding to each tenant in a manner of isolation among the tenants.
The cloud center 602 is further specifically configured to:
determining an isolated storage area of a tenant corresponding to the second party 606;
and reading fuzzy characteristic data of the target business object after fuzzification processing from the determined isolated storage area.
The cloud center 602 is further configured to perform service prediction based on the fuzzy feature data and a target prediction model corresponding to the service scenario, and provide a service prediction result to the first participant 604.
The target prediction model is used for predicting a classification or regression value of a business object, and the business object comprises any one of the following components: users, merchants, goods, and events.
In addition, the second participant 606 is configured to upload the fuzzy feature data of the target business object to the cloud center 602.
The second party 606 is specifically configured to:
in response to the trigger of the current business event, the fuzzy feature data of the target business object is uploaded to the cloud center 602.
In one particular example, several fields are also agreed upon in the second privacy contract, and the second party 606 is specifically configured to:
pull a second privacy contract from cloud center 602;
extracting field values corresponding to fields agreed in the second privacy contract from original characteristic data of the target business object;
fuzzifying the field value of each field to obtain fuzzy characteristic data of a target business object; the fuzzification processing includes at least one of hash operation, interval mapping, and boolean value conversion.
And uploading the fuzzy characteristic data of the target business object to the cloud center 602.
The step of the second participant 606 performing the fuzzification processing on the field values of the fields includes:
the second party 606 invokes a built-in second SDK provided by the cloud hub 602 to obfuscate the field values of the fields.
It is noted that cloud center 602 may include a feature store;
the second participant 606 is further configured to send the fuzzy feature data to the cloud center 602;
and the characteristic storage center is used for carrying out audit compliance inspection on the received fuzzy characteristic data and storing the fuzzy characteristic data after the inspection is passed.
More specifically, the feature storage center takes a plurality of participants as a plurality of tenants, and stores uploaded data corresponding to each tenant in an isolation manner among the tenants;
the feature storage center is specifically configured to:
and storing the fuzzy characteristic data into an isolated storage area of the tenant corresponding to the second party 606.
The functions of each functional module of the system in the above embodiments of the present description may be implemented through each step of the above method embodiments, and therefore, a specific working process of the system provided in one embodiment of the present description is not repeated herein.
The system for performing business prediction by combining multiple parties based on privacy protection, provided by an embodiment of the present specification, can ensure that data sharing is achieved without information of each party being leaked.
Corresponding to the above method for predicting a service based on a multi-party federation of privacy protection, an embodiment of the present specification further provides a system for predicting a service based on a multi-party federation of privacy protection, as shown in fig. 7, the system may include a cloud center 702, a first payment platform 704, and a second payment platform 706.
The second payment platform 706 is configured to pull, in response to a trigger of the current payment event, a second privacy contract signed by the cloud center 702, where the second privacy contract specifies a usage scenario of upload data of the second payment platform 706 and a number of fields included in the upload data.
The second payment platform 706 is further configured to determine whether the usage scenario agreed in the second privacy contract matches the payment scenario, and if so, extract field values of the second user corresponding to fields agreed in the second privacy contract from the original feature data of the second user.
The second payment platform 706 is further configured to perform obfuscation processing on field values of the fields to obtain obfuscated feature data of the second user.
The second payment platform 706 is further configured to upload the fuzzy feature data of the second user to the cloud center 702.
The first payment platform 704 is configured to send a service prediction request to the cloud center 702, where at least a payment scenario of a current payment event and a user identifier of a second user involved in the current payment event are indicated.
And the cloud center 702 is configured to obtain the fuzzy feature data of the second user, which is uploaded by the second payment platform 706, based on the user identifier.
The cloud center 702 is further configured to perform service prediction based on the fuzzy feature data and a target prediction model corresponding to the payment scenario, and provide a service prediction result to the first payment platform 704.
The functions of each functional module of the system in the above embodiments of the present description may be implemented through each step of the above method embodiments, and therefore, a specific working process of the system provided in one embodiment of the present description is not repeated herein.
The system for performing service prediction by combining multiple parties based on privacy protection, provided by one embodiment of the present specification, can implement real-time sharing and real-time use of data between payment platforms, and thus can improve a service prediction effect.
According to an embodiment of another aspect, there is also provided a computer-readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method described in connection with fig. 2, 4 or 5.
According to an embodiment of yet another aspect, there is also provided a computing device comprising a memory having stored therein executable code, and a processor that, when executing the executable code, implements the method described in conjunction with fig. 2, fig. 4, or fig. 5.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The steps of a method or algorithm described in connection with the disclosure herein may be embodied in hardware or may be embodied in software instructions executed by a processor. The software instructions may consist of corresponding software modules that may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an ASIC. Additionally, the ASIC may reside in a server. Of course, the processor and the storage medium may reside as discrete components in a server.
Those skilled in the art will recognize that, in one or more of the examples described above, the functions described in this invention may be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The above-mentioned embodiments, objects, technical solutions and advantages of the present specification are further described in detail, it should be understood that the above-mentioned embodiments are only specific embodiments of the present specification, and are not intended to limit the scope of the present specification, and any modifications, equivalent substitutions, improvements and the like made on the basis of the technical solutions of the present specification should be included in the scope of the present specification.
Claims (25)
1. A method for predicting business based on privacy protection multiparty union, wherein the multiparty comprises a cloud center and a plurality of participants; the cloud center maintains privacy contracts signed by the participants respectively; the usage scenario of the uploaded data of the corresponding participants is appointed; the method comprises the following steps:
any first participant in the multiple participants sends a service prediction request to the cloud center, wherein the service prediction request at least indicates a service scene of a current service event and an object identifier of a target service object belonging to a second participant, and the object identifier relates to the current service event;
the cloud center responds to the service prediction request, and acquires a second privacy contract signed by the second party;
the cloud center judges whether the service scene is matched with the use scene agreed in the second privacy contract or not, and acquires fuzzy characteristic data which is uploaded by the second participant and is subjected to fuzzification processing on the basis of the object identification under the condition of matching;
and the cloud center performs service prediction based on the fuzzy feature data and a target prediction model corresponding to the service scene, and provides a service prediction result for the first participant.
2. The method of claim 1, wherein the cloud center comprises a feature storage center for storing upload data of each participant;
the acquiring fuzzy feature data of the target business object uploaded by the second participant after the fuzzification processing includes:
and reading fuzzy feature data which are uploaded by the second party and are subjected to fuzzification processing on the target business object from the feature storage center.
3. The method according to claim 2, wherein the feature storage center stores upload data corresponding to each tenant in a manner of isolation among tenants, with the plurality of participants being a plurality of tenants;
the reading, from the feature storage center, the fuzzy feature data of the target business object, which is uploaded by the second party and is subjected to the fuzzification processing, includes:
determining an isolated storage area of a tenant corresponding to the second party;
and reading fuzzy characteristic data of the target business object after fuzzification processing from the isolated storage area.
4. The method of claim 1, wherein the target prediction model is used to predict classification or regression values of business objects; the business object comprises any one of the following: users, merchants, goods, and events.
5. The method of claim 1, wherein prior to said sending a traffic prediction request to the cloud center, further comprising:
the first participant calls a built-in first SDK provided by the cloud center to standardize the service prediction request; the standardization processing comprises at least one item of parameter assembly and business scene mapping;
the sending of the service prediction request to the cloud center includes:
and sending a service prediction request after standardized processing to the cloud center.
6. The method of claim 1, further comprising:
and the second participating direction uploads the fuzzy characteristic data of the target business object to the cloud center.
7. The method of claim 6, wherein the uploading, by the second party, the fuzzy feature data of the target business object to the cloud center comprises:
and the second participant responds to the trigger of the current business event and uploads the fuzzy characteristic data of the target business object to the cloud center.
8. The method of claim 6, wherein a number of fields are also agreed upon in the second privacy contract; the second participating direction uploads the fuzzy feature data of the target business object to the cloud center, and the fuzzy feature data comprises:
the second party pulling the second privacy contract from the cloud center;
the second party extracts field values corresponding to fields agreed in the second privacy contract from original characteristic data of the target business object;
the second party fuzzifies the field values of the fields to obtain fuzzy characteristic data of the target business object;
and the second party uploads the fuzzy characteristic data of the target business object to the cloud center.
9. The method of claim 8, wherein the obfuscation process includes at least one of a hash operation, a span mapping, and a boolean translation.
10. The method of claim 8, wherein the obfuscating of the field values of the fields by the second participant comprises:
and the second participant calls a built-in second SDK provided by the cloud center to fuzzify the field value of each field.
11. The method of claim 6, wherein the cloud center comprises a feature store center; the second participating direction uploads the fuzzy feature data of the target business object to the cloud center, and the fuzzy feature data comprises:
the second participation direction sends the fuzzy feature data to the cloud center;
and the characteristic storage center performs audit compliance check on the received fuzzy characteristic data, and stores the fuzzy characteristic data after the check is passed.
12. The method of claim 11, wherein the feature storage center stores upload data corresponding to each tenant in an inter-tenant isolation manner with the plurality of participants as a plurality of tenants;
the storing the fuzzy feature data comprises:
and storing the fuzzy characteristic data into an isolated storage area of the tenant corresponding to the second party.
13. A method for predicting business by combining multiple parties based on privacy protection is disclosed, wherein the multiple parties comprise a cloud center, a first payment platform and a second payment platform;
in response to the triggering of the current payment event, the second payment platform pulls a signed second privacy contract from the cloud center, wherein the second privacy contract appoints a use scene of uploaded data of the second payment platform and a plurality of fields contained in the uploaded data;
the second payment platform judges whether the use scene agreed in the second privacy contract is matched with the payment scene, and under the condition of matching, field values of the second user corresponding to fields agreed in the second privacy contract are extracted from original feature data of the second user;
the second payment platform fuzzifies the field values of the fields to obtain fuzzy feature data of the second user;
the second payment platform uploads the fuzzy feature data of the second user to the cloud center;
the first payment platform sends a service prediction request to the cloud center, wherein the service prediction request at least indicates a payment scene of a current payment event and a user identifier of the second user related to the current payment event;
the cloud center acquires fuzzy feature data of the second user, which is uploaded by the second payment platform, based on the user identification;
and the cloud center performs service prediction based on the fuzzy feature data and a target prediction model corresponding to the payment scene, and provides a service prediction result for the first payment platform.
14. A multi-party combined service prediction system based on privacy protection comprises a cloud center and a plurality of participants; the cloud center maintains privacy contracts signed by the participants respectively; the usage scenario of the uploaded data of the corresponding participants is appointed;
any first participant in the multiple participants is used for sending a service prediction request to the cloud center, wherein at least a service scene of a current service event is indicated, and an object identifier of a target service object belonging to a second participant and related to the current service event;
the cloud center is used for responding to the service prediction request and acquiring a second privacy contract signed by the second party;
the cloud center is further configured to determine whether the service scene is matched with a use scene agreed in the second privacy contract, and acquire fuzzy feature data of the target service object, which is uploaded by the second party and subjected to fuzzification processing, based on the object identifier under the condition that the service scene is matched with the use scene agreed in the second privacy contract;
the cloud center is further configured to perform service prediction based on the fuzzy feature data and a target prediction model corresponding to the service scene, and provide a service prediction result to the first participant.
15. The system of claim 14, wherein the cloud center comprises a feature storage center for storing upload data of each participant;
the cloud center is specifically configured to:
and reading fuzzy feature data which are uploaded by the second party and are subjected to fuzzification processing on the target business object from the feature storage center.
16. The system of claim 15, wherein the feature storage center stores upload data corresponding to each tenant in an inter-tenant isolation manner with the plurality of participants as a plurality of tenants;
the cloud center is further specifically configured to:
determining an isolated storage area of a tenant corresponding to the second party;
and reading fuzzy characteristic data of the target business object after fuzzification processing from the isolated storage area.
17. The system of claim 14, wherein the first party is specifically configured to:
calling a built-in first SDK provided by the cloud center, and carrying out standardized processing on the service prediction request; the standardization processing comprises at least one item of parameter assembly and business scene mapping;
and sending a service prediction request after standardized processing to the cloud center.
18. The system of claim 14, wherein,
and the second participant is used for uploading the fuzzy characteristic data of the target business object to the cloud center.
19. The system of claim 18, wherein the second party is specifically configured to:
and responding to the trigger of the current business event, and uploading the fuzzy characteristic data of the target business object to the cloud center.
20. The system of claim 18, wherein a number of fields are also agreed upon in the second privacy contract; the second party is specifically configured to:
pulling the second privacy contract from the cloud hub;
extracting field values corresponding to fields agreed in the second privacy contract from original feature data of the target business object;
fuzzifying the field value of each field to obtain fuzzy characteristic data of the target business object;
and uploading the fuzzy characteristic data of the target business object to the cloud center.
21. The system of claim 18, wherein the cloud center comprises a feature store center;
the second participant is further configured to send the fuzzy feature data to the cloud center;
and the characteristic storage center is used for carrying out audit compliance inspection on the received fuzzy characteristic data and storing the fuzzy characteristic data after the inspection is passed.
22. The system of claim 21, wherein the feature storage center stores upload data corresponding to each tenant in an inter-tenant isolation manner with the plurality of participants as a plurality of tenants;
the feature storage center is specifically configured to:
and storing the fuzzy characteristic data into an isolated storage area of the tenant corresponding to the second party.
23. A multi-party combined service prediction system based on privacy protection comprises a cloud center, a first payment platform and a second payment platform;
the second payment platform is used for responding to the trigger of the current payment event, pulling a signed second privacy contract from the cloud center, wherein the second privacy contract appoints a use scene of uploaded data of the second payment platform and a plurality of fields contained in the uploaded data;
the second payment platform is further configured to determine whether the usage scenario agreed in the second privacy contract matches the payment scenario, and extract field values of the second user corresponding to fields agreed in the second privacy contract from the original feature data of the second user in the case of matching;
the second payment platform is further configured to perform obfuscation processing on the field values of the fields to obtain obfuscated feature data of the second user;
the second payment platform is further used for uploading the fuzzy feature data of the second user to the cloud center;
the first payment platform is used for sending a service prediction request to the cloud center, wherein at least a payment scene of a current payment event and a user identifier of the second user related to the current payment event are indicated;
the cloud center is used for acquiring fuzzy feature data of the second user uploaded by the second payment platform based on the user identification;
the cloud center is further used for conducting service prediction based on the fuzzy feature data and a target prediction model corresponding to the payment scene, and providing a service prediction result for the first payment platform.
24. A computer-readable storage medium, on which a computer program is stored, wherein the computer program causes a computer to carry out the method of any one of claims 1-13 when the computer program is carried out in the computer.
25. A computing device comprising a memory and a processor, wherein the memory has stored therein executable code that when executed by the processor implements the method of any of claims 1-13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111094201.9A CN113553609B (en) | 2021-09-17 | 2021-09-17 | Method and system for predicting service by combining multiple parties based on privacy protection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111094201.9A CN113553609B (en) | 2021-09-17 | 2021-09-17 | Method and system for predicting service by combining multiple parties based on privacy protection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113553609A true CN113553609A (en) | 2021-10-26 |
| CN113553609B CN113553609B (en) | 2022-08-02 |
Family
ID=78134654
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111094201.9A Active CN113553609B (en) | 2021-09-17 | 2021-09-17 | Method and system for predicting service by combining multiple parties based on privacy protection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113553609B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115879650A (en) * | 2023-02-21 | 2023-03-31 | 北京航空航天大学 | Multi-task joint prediction method and system based on credible block chain multi-state separation |
| CN116226928A (en) * | 2023-05-09 | 2023-06-06 | 京东科技控股股份有限公司 | Combined computing method, device, equipment and medium for multiparty business privacy data |
| CN116226928B (en) * | 2023-05-09 | 2024-04-16 | 京东科技控股股份有限公司 | Combined computing method, device, equipment and medium for multiparty business privacy data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190130322A1 (en) * | 2017-11-01 | 2019-05-02 | Google Llc | Wait time prediction |
| CN111767097A (en) * | 2020-08-31 | 2020-10-13 | 支付宝(杭州)信息技术有限公司 | Method and device for calling intelligent contract, electronic equipment and storage medium |
| CN112818023A (en) * | 2021-01-26 | 2021-05-18 | 龚世燕 | Big data analysis method and cloud computing server in associated cloud service scene |
-
2021
- 2021-09-17 CN CN202111094201.9A patent/CN113553609B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190130322A1 (en) * | 2017-11-01 | 2019-05-02 | Google Llc | Wait time prediction |
| CN111767097A (en) * | 2020-08-31 | 2020-10-13 | 支付宝(杭州)信息技术有限公司 | Method and device for calling intelligent contract, electronic equipment and storage medium |
| CN112818023A (en) * | 2021-01-26 | 2021-05-18 | 龚世燕 | Big data analysis method and cloud computing server in associated cloud service scene |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115879650A (en) * | 2023-02-21 | 2023-03-31 | 北京航空航天大学 | Multi-task joint prediction method and system based on credible block chain multi-state separation |
| CN116226928A (en) * | 2023-05-09 | 2023-06-06 | 京东科技控股股份有限公司 | Combined computing method, device, equipment and medium for multiparty business privacy data |
| CN116226928B (en) * | 2023-05-09 | 2024-04-16 | 京东科技控股股份有限公司 | Combined computing method, device, equipment and medium for multiparty business privacy data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113553609B (en) | 2022-08-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20150379510A1 (en) | Method and system to use a block chain infrastructure and Smart Contracts to monetize data transactions involving changes to data included into a data supply chain. | |
| Möser et al. | The price of anonymity: empirical evidence from a market for Bitcoin anonymization | |
| US20160246981A1 (en) | Data secrecy statistical processing system, server device for presenting statistical processing result, data input device, and program and method therefor | |
| CN111159534A (en) | User portrait based aid decision making method and device, equipment and medium | |
| CN111340558B (en) | Online information processing method, device, equipment and medium based on federal learning | |
| CN112200382B (en) | Training method and device for risk prediction model | |
| CN110225032B (en) | Business data transaction method and equipment | |
| US11593513B2 (en) | Information processing system, data provision system, and related method | |
| CN111353554B (en) | Method and device for predicting missing user service attributes | |
| CN113553609B (en) | Method and system for predicting service by combining multiple parties based on privacy protection | |
| Ing et al. | Intention to use e-wallet amongst the university students in Klang Valley | |
| Ali-Eldin et al. | A risk evaluation approach for authorization decisions in social pervasive applications | |
| CN114238397A (en) | User data processing method, device, equipment, storage medium and program product | |
| Verma et al. | TECHNOLOGY ACCEPTANCE MODEL REVISITED FOR MOBILE BASED AGRICULTURAL EXTENSION SERVICES IN INDIA. | |
| Zhang et al. | Secure big data collection and processing: Framework, means and opportunities | |
| CN112948883A (en) | Multi-party combined modeling method, device and system for protecting private data | |
| US20120136883A1 (en) | Automatic Dynamic Multi-Variable Matching Engine | |
| Krontiris et al. | Privacy-ABCs as a case for studying the adoption of PETs by users and service providers | |
| Siyal et al. | A novel trust service provider for Internet based commerce applications | |
| Linh et al. | Factors affecting the intention to use Fintech services in Vietnam | |
| KR20200036643A (en) | Fashion platform system based on CCTV image and method for providing information using the system | |
| CN112468556B (en) | Service product information pushing method and device, computer equipment and medium | |
| US20210012421A1 (en) | Method and device for trading on an electronic trading platform | |
| CN114118823A (en) | Risk identification method, device and system in resource transfer process | |
| Suprapto | Analysis of factors affecting the use of cashless mobile payment in millenial generations of Batam City |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |