CN114021175B - User portrait configuration method and device, computer equipment and medium - Google Patents
User portrait configuration method and device, computer equipment and medium Download PDFInfo
- Publication number
- CN114021175B CN114021175B CN202111402220.3A CN202111402220A CN114021175B CN 114021175 B CN114021175 B CN 114021175B CN 202111402220 A CN202111402220 A CN 202111402220A CN 114021175 B CN114021175 B CN 114021175B
- Authority
- CN
- China
- Prior art keywords
- user
- platform
- ciphertext
- tag
- attribute
- 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.)
- Active
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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Security & Cryptography (AREA)
- Bioethics (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Storage Device Security (AREA)
Abstract
The application relates to the field of user portrayal, and discloses a user portrayal configuration method, a user portrayal configuration device, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring basic data of a user on a plurality of different platforms and platform identifications of the corresponding platforms; acquiring a user identifier of a user, and establishing an incidence relation between the basic data and the user identifier and a platform identifier of a corresponding platform; respectively calculating the basic data of the user under each platform identification based on a machine learning model according to the incidence relation to obtain an attribute label of the user under each platform; carrying out homomorphic encryption on the attribute tag to obtain a ciphertext tag; and acquiring the type of the attribute tag, configuring authorization information of the ciphertext tag according to the type of the attribute tag, and generating a user portrait according to the ciphertext tag and the authorization information. The method and the device can improve the data security and the efficiency of converting the ciphertext tag into the user portrait.
Description
Technical Field
The present application relates to the field of user portraits, and more particularly, to a method and apparatus for configuring a user portraits, a computer device, and a storage medium.
Background
With the development of internet technology, currently, the processing of user portraits on the internet is to obtain different labels representing the user portraits by counting the behavior data of users and then identifying the behavior data of the users, and for data collected by different platforms, data management and authority control are not additionally performed, so that the data leakage risk is high, and the data security and efficiency in the user portraits configuration process are low.
Disclosure of Invention
The present application mainly aims to provide a method and an apparatus for configuring a user portrait, a computer device and a storage medium, and aims to solve the problems of low security and low efficiency of the user portrait configuration process under different platforms at present.
In order to achieve the above object, the present application provides a method for configuring a user portrait, comprising:
acquiring basic data of a user on a plurality of different platforms and platform identifications of the corresponding platforms;
acquiring a user identifier of a user, and establishing an incidence relation between the basic data and the user identifier and a platform identifier of a corresponding platform;
respectively calculating the basic data of the user under each platform identification based on a machine learning model according to the incidence relation to obtain an attribute label of the user under each platform;
carrying out homomorphic encryption on the attribute tag to obtain a ciphertext tag;
and acquiring the type of the attribute tag, configuring authorization information of the ciphertext tag according to the type of the attribute tag, and generating a user portrait according to the ciphertext tag and the authorization information.
Further, the converting the first token into a second token with the same semantic meaning based on a pre-established synonym table, and generating second sample data according to the first sample data and the second token includes:
selecting any word in the first sample data as a first word;
matching the first words with second words with the same semantics based on a pre-established synonym table;
and replacing the first word of the first sample data with the second word to generate second sample data.
Further, before the obtaining of a third word of which the usage frequency satisfies a preset value in the first word, the method further includes:
acquiring an application scene of the first sample data;
acquiring a word library based on big data pre-acquisition in the application scene;
and determining a preset value of the frequency under the application scene from the word bank.
Further, after generating the training sample data of the intention recognition model, the method further includes:
obtaining an intention of the training sample data;
counting the data size of training sample data of each intention;
and acquiring a target intention of the training sample data, wherein the data volume of the training sample data is lower than a preset threshold value, and performing training sample data enhancement on the target intention.
Further, the enhancing the target intention with training sample data comprises:
obtaining sample data to be enhanced of the target intention;
and sequentially transforming the words of the sample data to be enhanced to generate target sample data so as to enhance the training sample data of the target intention.
Further, the enhancing the target intention with training sample data comprises:
acquiring initial sample data of the target intention;
acquiring historical sample data matched with the target intention;
calculating the similarity between the initial sample data and historical sample data, and screening target historical sample data meeting preset requirements according to the similarity;
and establishing association between the target historical sample data and the target intention so as to enhance the training sample data of the target intention.
Further, the performing associated data enhancement on the first sample data, the second sample data, and the third sample data includes:
obtaining a first intent of the first sample data;
configuring the first intent as header information of a tile;
configuring the first sample data, the second sample data and the third sample data as content information of a block;
and performing uplink according to the header information and the content information so as to perform associated data enhancement on the first sample data, the second sample data and the third sample data.
The present application further provides a user portrait configuration device, comprising:
the data acquisition module is used for acquiring basic data of a user on a plurality of different platforms and platform identifications of the corresponding platforms;
the incidence relation module is used for acquiring a user identifier of a user and establishing the incidence relation between the basic data and the user identifier and the platform identifier of the corresponding platform;
the label matching module is used for respectively calculating the basic data of the user under each platform identifier based on a machine learning model according to the incidence relation to obtain an attribute label of the user under each platform;
the label encryption module is used for homomorphic encryption on the attribute label to obtain a ciphertext label;
and the portrait generation module is used for acquiring the type of the attribute tag, configuring authorization information of the ciphertext tag according to the type of the attribute tag, and generating a user portrait according to the ciphertext tag and the authorization information.
The application also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the user portrait configuration method in any one of the above aspects when executing the computer program.
The present application also provides a computer readable storage medium having a computer program stored thereon, which when executed by a processor implements the steps of any of the above-described user representation configuration methods.
The embodiment of the application provides a configuration method of a user picture based on a homomorphic encryption algorithm, which comprises the steps of firstly obtaining basic data of a user on a plurality of different platforms and platform identifications of corresponding platforms, then obtaining user identifications of the user, establishing an incidence relation between the basic data and the user identifications and the platform identifications of the corresponding platforms, respectively calculating the basic data of the user under each platform identification based on a machine learning model according to the incidence relation, carrying out standardized processing on the basic data, then matching the basic data with predefined labels by adopting a proximity analysis, a cluster analysis and a decision tree algorithm to obtain attribute labels of the user under each platform, then carrying out homomorphic encryption on the attribute labels to obtain ciphertext labels, obtaining the types of the attribute labels after obtaining the ciphertext labels, configuring authorization information of the ciphertext labels according to the types of the attribute labels, the method comprises the steps that corresponding authorization information is configured on different types of ciphertext tags, user portraits are generated according to the ciphertext tags and the authorization information, configuration of the user portraits after basic data combination under different platforms is completed, the user portraits are configured and generated based on combination of the ciphertext tags of users under different platforms, therefore, the obtained user portraits are also encrypted user portraits, and data security of the user portraits can be guaranteed. Besides, the ciphertext tags obtained through homomorphic encryption can realize basic encryption configuration and direct calculation among the ciphertext tags, a plurality of ciphertext tags can be calculated and then decrypted, and the situation that each ciphertext tag is decrypted and then calculated to consume a large amount of calculation power is not needed, so that not only is the data security improved, but also the efficiency of converting the ciphertext tags into user portraits is improved on the premise of ensuring the data security.
Drawings
FIG. 1 is a flow chart illustrating an embodiment of a user representation configuration method of the present application;
FIG. 2 is a schematic diagram illustrating an embodiment of a user portrait layout apparatus according to the present application;
FIG. 3 is a block diagram illustrating a computer device according to an embodiment of the present invention.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to FIG. 1, an embodiment of the present application provides a user representation configuring method, including steps S10-S50, and the steps of the user representation configuring method are described in detail as follows.
And S10, acquiring basic data of the user on a plurality of different platforms and platform identifications of the corresponding platforms.
The embodiment is applied to user portrait analysis scenes of content and product platforms, the behavior of the same user on different platforms can reflect the characteristics of the user, data generated by the behavior of the user on the platform is defined as basic data, so that the basic data of the user on a plurality of different platforms can be acquired, and meanwhile, platform identifications of the corresponding platforms are acquired, wherein the basic data comprise user attribute data and user behavior data. In one embodiment, different platforms represent a plurality of different applications or websites, so that basic data of a user on the corresponding applications or websites are obtained from the different applications or websites; in another embodiment, the different platforms represent different function modules in an application, such as shopping function, information function, and social function in the application, or the different platforms represent different function pages in a website, and data generated by a user when using the different functions is defined as basic data corresponding to the different platforms.
S20, obtaining the user identification of the user, and establishing the incidence relation between the basic data and the user identification and the platform identification of the corresponding platform.
In this embodiment, after obtaining basic data of a user on a plurality of different platforms and platform identifiers of corresponding platforms, obtaining a user identifier of the user, representing the same user on different platforms by using the same user identifier, and then establishing an association relationship between the basic data and the user identifier and the platform identifier of the corresponding platform, that is, determining the basic data generated by the user on different platforms, and tracing the basic data according to the association relationship.
And S30, respectively calculating the basic data of the user under each platform identification based on a machine learning model according to the incidence relation to obtain the attribute label of the user under each platform.
In this embodiment, after the association relationship between the basic data and the user identifier and the platform identifier of the corresponding platform is established, the basic data of the user under each platform identifier is calculated based on a machine learning model according to the association relationship, first, for each platform, the basic data generated under the platform is obtained based on the platform identifier and the association relationship, then a cluster analysis model for machine learning is established based on a machine learning sklerann framework to calculate the basic data, an attribute tag of the user is determined according to the basic data, the basic data is normalized, then the normalized basic data is matched with a predefined tag by adopting a proximity analysis, cluster analysis and decision tree algorithm, and a tag with a matching rate higher than a preset value is selected as the attribute tag of the user under the platform, and for other platforms, the above operations are also executed, so that the attribute label of the user under each platform is obtained, and the attribute label comprises a label basic definition and a label hierarchical definition. By defining the tags, including basic tag definition and layered tag definition, different types of tags can configure rules and types of periodic calculation, for example, type division is performed from the perspective of management and control, the tags are divided into general tags and controlled tags, the controlled tags and the general tags are divided, only authorized personnel can access the controlled tags, and management and control on the security of client information are embodied.
And S40, homomorphic encryption is carried out on the attribute tag to obtain a ciphertext tag.
In the embodiment, after the attribute tags of the user under each platform are obtained, homomorphic encryption is performed on the attribute tags to obtain ciphertext tags, namely homomorphic encryption is performed on the attribute tags under different platforms based on an encryption algorithm, each attribute tag is encrypted into the ciphertext tag, the ciphertext tags obtained through homomorphic encryption can realize multiple calculations among ciphertexts besides basic encryption operation, namely multiple calculations among the ciphertext tags, the homomorphic encryption is used for encrypting the attribute tags, the plurality of ciphertext tags can be calculated and then decrypted, and a large amount of computing power is consumed without decrypting and then calculating each ciphertext tag, so that the efficiency of converting the ciphertext tag into the user image is improved; the method can also realize the calculation of the ciphertext label by a non-key party, and the calculation of the ciphertext label does not need to pass through a key party, thereby reducing the communication cost and transferring the calculation task, and further balancing the calculation power resource.
S50, obtaining the type of the attribute label, configuring the authorization information of the ciphertext label according to the type of the attribute label, and generating the user portrait according to the ciphertext label and the authorization information.
In this embodiment, after obtaining the ciphertext tag, the type of the attribute tag, that is, the classification type of the attribute tag is obtained, where the classification type includes a controlled tag and a general tag, then the authorization information of the ciphertext tag is configured according to the type of the attribute tag, the different types of ciphertext tags are configured with corresponding authorization information, and a user portrait is generated according to the ciphertext tag and the authorization information, so as to complete the configuration of a user portrait after combining basic data under multiple different platforms, and the user portrait is configured and generated based on the combination of the ciphertext tags of users under different platforms, so that the obtained user portrait is also an encrypted user portrait, and meanwhile, the ciphertext tag is obtained based on homomorphic encryption, so as to generate a user portrait under the corresponding platform combination through the combination of the ciphertext tags of any multiple platforms, and also output different user portraits at different stages, flexible configuration of the user representation is accomplished.
This embodiment provides a configuration method of a user image based on a homomorphic encryption algorithm, which includes first obtaining basic data of a user on a plurality of different platforms and platform identifiers corresponding to the platforms, then obtaining user identifiers of the user, establishing an association relationship between the basic data and the user identifiers and the platform identifiers corresponding to the platforms, respectively calculating the basic data of the user under each platform identifier based on a machine learning model according to the association relationship, normalizing the basic data, then matching the basic data with predefined tags by using a proximity analysis, a cluster analysis and a decision tree algorithm to obtain attribute tags of the user under each platform, then homomorphic encrypting the attribute tags to obtain ciphertext tags, obtaining types of the attribute tags after obtaining the ciphertext tags, configuring authorization information of the ciphertext tags according to the types of the attribute tags, the method comprises the steps that corresponding authorization information is configured on different types of ciphertext tags, user portraits are generated according to the ciphertext tags and the authorization information, configuration of the user portraits after basic data combination under different platforms is completed, the user portraits are configured and generated based on combination of the ciphertext tags of users under different platforms, therefore, the obtained user portraits are also encrypted user portraits, and data security of the user portraits can be guaranteed. Besides, the ciphertext tags obtained through homomorphic encryption can realize basic encryption configuration and direct calculation among the ciphertext tags, a plurality of ciphertext tags can be calculated and then decrypted, and the situation that each ciphertext tag is decrypted and then calculated to consume a large amount of calculation power is not needed, so that not only is the data security improved, but also the efficiency of converting the ciphertext tags into user portraits is improved on the premise of ensuring the data security.
In an embodiment, before the obtaining the type of the attribute tag and configuring the authorization information of the ciphertext tag according to the type of the attribute tag, the method further includes:
acquiring an application scene of the user portrait;
matching a classification type library of attribute labels according to the application scenes;
and configuring the type of the attribute label according to the classification type library.
In this embodiment, before the type of the attribute tag is obtained and the authorization information of the ciphertext tag is configured according to the type of the attribute tag, the application scenario of the user portrait is obtained, in different application scenarios, the classification type of the same attribute tag is different, then the classification type library of the attribute tag is matched according to the application scenario, and the type of the attribute tag is configured according to the classification type library, for example, in a product push scenario, the classification type of an attribute tag "working address" is a1, the attribute tag cannot be disclosed, in a company meeting scenario, the classification type of the attribute tag "working address" is a2, the attribute tag can be disclosed, the type of the attribute tag is determined by configuring the classification type library in different application scenarios, the authorization information of the ciphertext tag can be configured in different scenarios, so as to improve the display effect of the user portrait in different scenarios, and the universality of application scenes is improved.
In an embodiment, after the homomorphic encrypting the attribute tag to obtain the ciphertext tag, the method further includes:
and acquiring the type of the attribute tag, and performing combined calculation on a plurality of ciphertext tags of the same type according to the type of the attribute tag to obtain a combined ciphertext tag.
In this embodiment, after the attribute tags are homomorphic encrypted to obtain the ciphertext tags, a plurality of ciphertext tags may be combined and calculated to obtain the combined ciphertext tags, specifically, because the attribute tags have different attributes, the type of the attribute tags is obtained in order to facilitate the classification of the key tags, then a plurality of ciphertext tags of the same type are combined and calculated according to the type of the attribute tags to obtain the combined ciphertext tags, for example, the ciphertext tags whose attribute tags are general types are combined and calculated, the ciphertext tags whose attribute tags are controlled types are combined and calculated, the combined ciphertext tags are analyzed to obtain a plurality of ciphertext tags, and then each ciphertext tag is decrypted to obtain the attribute tag corresponding to each ciphertext tag, and the data amount of data transmission is enabled by combining the ciphertext tags, thereby improving the utilization rate of resources.
In one embodiment, the platform comprises a first platform and a second platform; the generating a user representation includes:
a first user representation of a first platform is generated, a second user representation of a second platform is generated, and a combined user representation of the first platform and the second platform is generated.
In this embodiment, the plurality of platforms include different platforms, and the first platform and the second platform represent different platforms, so that when a user portrait is generated, a first user portrait of the first platform and a second user portrait of the second platform can be generated simultaneously, and a combined user portrait of the first platform and the second platform can be generated, thereby improving generation efficiency of user portraits of different platforms and generation efficiency of combined user portraits between different platforms.
In one embodiment, after generating the first user representation of the first platform, further comprising:
acquiring the number of ciphertext tags of a first user portrait of a user on a first platform;
calculating the richness of the first user portrait according to the number of the ciphertext tags;
if the richness is lower than a preset value, acquiring a basic ciphertext tag of the user on a second platform;
and adding the basic ciphertext tag to the first user portrait of the first platform, and updating the first user portrait.
In this embodiment, after a first user portrait of a first platform is generated, that is, after a portrait of a user on one platform is generated, the number of ciphertext tags of the first user portrait of the user on the first platform is obtained, that is, the first user portrait of the user on the first platform is counted, the richness of the first user portrait is calculated according to the ciphertext tags, if the richness is lower than a preset value, it is indicated that the first user portrait on the first platform is not abundant enough to accurately describe user characteristics, at this time, a basic ciphertext tag of the user on a second platform is obtained, the basic ciphertext tag is determined based on a tag type, the basic ciphertext tag represents basic characteristic information of the user, the basic ciphertext tag is added to the first user portrait of the first platform, the first user portrait of the first platform is updated, and thus the first user portrait of the first platform is enriched, the first user portrait of the first platform can be ensured to be used normally, and the flexibility of user portrait configuration is improved.
In one embodiment, after updating the first user representation by adding the base ciphertext tag to the first user representation of the first platform, further comprising:
matching recommendation information of a first platform based on the first user profile;
and pushing the recommendation information of the user to a first platform.
In the embodiment, after the first user portrait is generated, the recommendation information of the first platform is matched based on the first user portrait, so that even if the richness of the user portrait is insufficient under the first platform, the recommendation information with higher relevance degree with the user portrait can be matched, and the ciphertext tags between different platforms cannot be leaked due to the fact that the ciphertext tags are encrypted, and therefore the data security is guaranteed.
In one embodiment, after generating the user representation according to the ciphertext tag and the authorization information, the method further includes:
when a viewing request of a user portrait is received, authority information contained in the viewing request is acquired;
if the authority information is matched with the authorization information, extracting key information in the checking request;
and decrypting the user portrait according to the key information and outputting the decrypted user portrait.
In the embodiment, after the user portrait is generated according to the ciphertext tag and the authorization information, authorization is required to be obtained for checking the user portrait first, and the user portrait can be checked only after the authorization is successful, namely when a checking request of the user portrait is received, authority information contained in the checking request is obtained, if the authority information is matched with the authorization information, the authorization is confirmed to be successful, the user portrait is still an encrypted user portrait, at the moment, key information in the checking request is also extracted, the user portrait is decrypted according to the key information, then the decrypted user portrait is output, and the security of user portrait data is ensured through the authorization information and homomorphic encryption.
Referring to fig. 2, the present application further provides a user portrait configuration apparatus, including:
the data acquisition module 10 is used for acquiring basic data of a user on a plurality of different platforms and platform identifications of the corresponding platforms;
the association relation module 20 is configured to obtain a user identifier of a user, and establish an association relation between the basic data and the user identifier and a platform identifier of a corresponding platform;
the tag matching module 30 is configured to calculate the basic data of the user under each platform identifier based on a machine learning model according to the association relationship, so as to obtain an attribute tag of the user under each platform;
the tag encryption module 40 is configured to perform homomorphic encryption on the attribute tag to obtain a ciphertext tag;
and the portrait generation module 50 is configured to obtain the type of the attribute tag, configure authorization information of the ciphertext tag according to the type of the attribute tag, and generate a user portrait according to the ciphertext tag and the authorization information.
As described above, it is understood that the components of the user representation configuration apparatus proposed in the present application can implement the functions of any of the user representation configuration methods described above.
In an embodiment, before the obtaining the type of the attribute tag and configuring the authorization information of the ciphertext tag according to the type of the attribute tag, the method further includes:
acquiring an application scene of the user portrait;
matching a classification type library of attribute labels according to the application scenes;
and configuring the type of the attribute label according to the classification type library.
In an embodiment, after the homomorphic encrypting the attribute tag to obtain the ciphertext tag, the method further includes:
and acquiring the type of the attribute tag, and performing combined calculation on a plurality of ciphertext tags of the same type according to the type of the attribute tag to obtain a combined ciphertext tag.
In one embodiment, the platform comprises a first platform and a second platform; the generating a user representation includes:
a first user representation of a first platform is generated, a second user representation of a second platform is generated, and a combined user representation of the first platform and the second platform is generated.
In one embodiment, after generating the first user representation of the first platform, further comprising:
acquiring the number of ciphertext tags of a first user portrait of a user on a first platform;
calculating the richness of the first user portrait according to the number of the ciphertext tags;
if the richness is lower than a preset value, acquiring a basic ciphertext tag of the user on a second platform;
and adding the basic ciphertext tag to the first user portrait of the first platform, and updating the first user portrait.
In one embodiment, after updating the first user representation by adding the base ciphertext tag to the first user representation of the first platform, further comprising:
matching recommendation information of a first platform based on the first user profile;
and pushing the recommendation information of the user to a first platform.
In one embodiment, after generating the user representation according to the ciphertext tag and the authorization information, the method further includes:
when a viewing request of a user portrait is received, authority information contained in the viewing request is acquired;
if the authority information is matched with the authorization information, extracting key information in the checking request;
and decrypting the user portrait according to the key information and outputting the decrypted user portrait.
Referring to fig. 3, a computer device, which may be a mobile terminal and whose internal structure may be as shown in fig. 3, is also provided in the embodiment of the present application. The computer equipment comprises a processor, a memory, a network interface, a display device and an input device which are connected through a system bus. Wherein, the network interface of the computer equipment is used for communicating with an external terminal through network connection. The input means of the computer device is for receiving input from a user. The computer designed processor is used to provide computational and control capabilities. The memory of the computer device includes a storage medium. The storage medium stores an operating system, a computer program, and a database. The database of the computer device is used for storing data. The computer program is executed by a processor to implement a method of configuring a user representation.
The processor executing the user portrait configuration method comprises: acquiring basic data of a user on a plurality of different platforms and platform identifications of the corresponding platforms; acquiring a user identifier of a user, and establishing an incidence relation between the basic data and the user identifier and a platform identifier of a corresponding platform; respectively calculating the basic data of the user under each platform identification based on a machine learning model according to the incidence relation to obtain an attribute label of the user under each platform; carrying out homomorphic encryption on the attribute tag to obtain a ciphertext tag; and acquiring the type of the attribute tag, configuring authorization information of the ciphertext tag according to the type of the attribute tag, and generating a user portrait according to the ciphertext tag and the authorization information.
The computer equipment provides a configuration method of a user picture based on a homomorphic encryption algorithm, firstly basic data of a user on a plurality of different platforms and platform identifications of corresponding platforms are obtained, then user identifications of the user are obtained, the incidence relation between the basic data and the user identifications and the platform identifications of the corresponding platforms is established, the basic data of the user under each platform identification are respectively calculated based on a machine learning model according to the incidence relation, the basic data are normalized, then the basic data are matched with predefined labels by adopting proximity analysis, cluster analysis and a decision tree algorithm to obtain attribute labels of the user under each platform, then homomorphic encryption is carried out on the attribute labels to obtain ciphertext labels, and after the ciphertext labels are obtained, the types of the attribute labels are obtained, and configuring authorization information of the ciphertext tags according to the types of the attribute tags, configuring corresponding authorization information for different types of ciphertext tags, generating a user portrait according to the ciphertext tags and the authorization information, configuring corresponding authorization information for different types of ciphertext tags, generating the user portrait according to the ciphertext tags and the authorization information, and completing configuration of the user portrait after basic data under different platforms are combined. Besides, the ciphertext tags obtained through homomorphic encryption can realize basic encryption configuration and direct calculation among the ciphertext tags, a plurality of ciphertext tags can be calculated and then decrypted, and the situation that each ciphertext tag is decrypted and then calculated to consume a large amount of calculation power is not needed, so that not only is the data security improved, but also the efficiency of converting the ciphertext tags into user portraits is improved on the premise of ensuring the data security.
An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by the processor, implements a method for configuring a user representation, including the steps of: acquiring basic data of a user on a plurality of different platforms and platform identifications of the corresponding platforms; acquiring a user identifier of a user, and establishing an incidence relation between the basic data and the user identifier and a platform identifier of a corresponding platform; respectively calculating the basic data of the user under each platform identification based on a machine learning model according to the incidence relation to obtain an attribute label of the user under each platform; carrying out homomorphic encryption on the attribute tag to obtain a ciphertext tag; and acquiring the type of the attribute tag, configuring authorization information of the ciphertext tag according to the type of the attribute tag, and generating a user portrait according to the ciphertext tag and the authorization information.
The computer readable storage medium provides a configuration method of a user picture based on a homomorphic encryption algorithm, which comprises the steps of firstly obtaining basic data of a user on a plurality of different platforms and platform identifications of corresponding platforms, then obtaining user identifications of the user, establishing an incidence relation between the basic data and the user identifications as well as platform identifications of corresponding platforms, respectively calculating the basic data of the user under each platform identification based on a machine learning model according to the incidence relation, carrying out standardization processing on the basic data, then adopting a proximity analysis, a cluster analysis and a decision tree algorithm to match the basic data with predefined labels to obtain attribute labels of the user under each platform, then carrying out homomorphic encryption on the attribute labels to obtain ciphertext labels, and obtaining the types of the attribute labels after obtaining the ciphertext labels, configuring authorization information of the ciphertext tags according to the types of the attribute tags, configuring corresponding authorization information of different types of ciphertext tags, generating a user portrait according to the ciphertext tags and the authorization information, configuring corresponding authorization information of different types of ciphertext tags, generating the user portrait according to the ciphertext tags and the authorization information, completing configuration of the user portrait after basic data under different platforms are combined, and configuring and generating the user portrait based on combination of the ciphertext tags of users under different platforms, so that the obtained user portrait is also an encrypted user portrait, and the data security of the user portrait can be ensured. Besides, the ciphertext tags obtained through homomorphic encryption can realize basic encryption configuration and direct calculation among the ciphertext tags, a plurality of ciphertext tags can be calculated and then decrypted, and the situation that each ciphertext tag is decrypted and then calculated to consume a large amount of calculation power is not needed, so that not only is the data security improved, but also the efficiency of converting the ciphertext tags into user portraits is improved on the premise of ensuring the data security.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above.
Any reference to memory, storage, database, or other medium provided herein and used in the embodiments may include non-volatile and/or volatile memory.
Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above description is only a preferred embodiment of the present application and is not intended to limit the scope of the present application.
All the equivalent structures or equivalent processes performed by using the contents of the specification and the drawings of the present application, or directly or indirectly applied to other related technical fields, are included in the scope of protection of the present application.
Claims (10)
1. A method for user representation configuration, comprising:
acquiring basic data of a user on a plurality of different platforms and platform identifications of the corresponding platforms;
acquiring a user identifier of a user, and establishing an incidence relation between the basic data and the user identifier and a platform identifier of a corresponding platform;
respectively calculating the basic data of the user under each platform identification based on a machine learning model according to the incidence relation to obtain an attribute label of the user under each platform;
carrying out homomorphic encryption on the attribute tag to obtain a ciphertext tag;
and acquiring the type of the attribute tag, configuring authorization information of the ciphertext tag according to the type of the attribute tag, and generating a user portrait according to the ciphertext tag and the authorization information.
2. The method of claim 1, wherein before the obtaining the type of the attribute tag and configuring the authorization information of the ciphertext tag according to the type of the attribute tag, the method further comprises:
acquiring an application scene of the user portrait;
matching a classification type library of attribute labels according to the application scene;
and configuring the type of the attribute label according to the classification type library.
3. A method for configuring a user representation as recited in claim 1, wherein the step of homomorphically encrypting the attribute tag to obtain a ciphertext tag further comprises:
and acquiring the type of the attribute tag, and performing combined calculation on a plurality of ciphertext tags of the same type according to the type of the attribute tag to obtain a combined ciphertext tag.
4. A method as claimed in claim 1, wherein said platform comprises a first platform and a second platform; the generating a user representation includes:
a first user representation of a first platform is generated, a second user representation of a second platform is generated, and a combined user representation of the first platform and the second platform is generated.
5. The method of user representation configuration of claim 4, wherein said generating a first user representation of a first platform further comprises:
acquiring the number of ciphertext tags of a first user portrait of a user on a first platform;
calculating the richness of the first user portrait according to the number of the ciphertext tags;
if the richness is lower than a preset value, acquiring a basic ciphertext tag of the user on a second platform;
and adding the basic ciphertext tag to the first user portrait of the first platform, and updating the first user portrait.
6. The method of claim 5, wherein the step of adding the base ciphertext tag to the first user representation of the first platform further comprises, after updating the first user representation:
matching recommendation information of a first platform based on the first user profile;
and pushing the recommendation information of the user to a first platform.
7. The method of claim 1, wherein after generating a user representation based on the ciphertext tag and the authorization information, further comprising:
when a viewing request of a user portrait is received, authority information contained in the viewing request is acquired;
if the authority information is matched with the authorization information, extracting key information in the checking request;
and decrypting the user portrait according to the key information and outputting the decrypted user portrait.
8. A user representation configuring apparatus, comprising:
the data acquisition module is used for acquiring basic data of a user on a plurality of different platforms and platform identifications of the corresponding platforms;
the incidence relation module is used for acquiring a user identifier of a user and establishing the incidence relation between the basic data and the user identifier and the platform identifier of the corresponding platform;
the label matching module is used for respectively calculating the basic data of the user under each platform identification based on a machine learning model according to the incidence relation to obtain an attribute label of the user under each platform;
the label encryption module is used for homomorphic encryption on the attribute label to obtain a ciphertext label;
and the portrait generation module is used for acquiring the type of the attribute tag, configuring authorization information of the ciphertext tag according to the type of the attribute tag, and generating a user portrait according to the ciphertext tag and the authorization information.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor when executing the computer program implements the steps of the method of configuring a user representation of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for configuring a user representation as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111402220.3A CN114021175B (en) | 2021-11-19 | 2021-11-19 | User portrait configuration method and device, computer equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111402220.3A CN114021175B (en) | 2021-11-19 | 2021-11-19 | User portrait configuration method and device, computer equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114021175A CN114021175A (en) | 2022-02-08 |
| CN114021175B true CN114021175B (en) | 2022-08-02 |
Family
ID=80065929
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111402220.3A Active CN114021175B (en) | 2021-11-19 | 2021-11-19 | User portrait configuration method and device, computer equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114021175B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114996347A (en) * | 2022-06-24 | 2022-09-02 | 中国电信股份有限公司 | User portrait management method and device, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109408746A (en) * | 2018-09-26 | 2019-03-01 | 平安科技（深圳）有限公司 | Portrait information query method, device, computer equipment and storage medium |
| CN109992982A (en) * | 2019-04-11 | 2019-07-09 | 北京信息科技大学 | Big data access authorization methods, device and big data platform |
| CN110334274A (en) * | 2019-05-30 | 2019-10-15 | 平安科技（深圳）有限公司 | Information-pushing method, device, computer equipment and storage medium |
| CN110710190A (en) * | 2017-06-16 | 2020-01-17 | 华为技术有限公司 | Method and terminal for generating user portrait |
| CN111666460A (en) * | 2020-05-27 | 2020-09-15 | 中国平安财产保险股份有限公司 | User portrait generation method and device based on privacy protection and storage medium |
| CN111784301A (en) * | 2020-07-02 | 2020-10-16 | 中国银行股份有限公司 | User portrait construction method and device, storage medium and electronic equipment |
| CN111915366A (en) * | 2020-07-20 | 2020-11-10 | 上海燕汐软件信息科技有限公司 | User portrait construction method and device, computer equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9075981B2 (en) * | 2011-02-15 | 2015-07-07 | Yahoo! Inc. | Non-textual security using portraits |
-
2021
- 2021-11-19 CN CN202111402220.3A patent/CN114021175B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110710190A (en) * | 2017-06-16 | 2020-01-17 | 华为技术有限公司 | Method and terminal for generating user portrait |
| CN109408746A (en) * | 2018-09-26 | 2019-03-01 | 平安科技（深圳）有限公司 | Portrait information query method, device, computer equipment and storage medium |
| CN109992982A (en) * | 2019-04-11 | 2019-07-09 | 北京信息科技大学 | Big data access authorization methods, device and big data platform |
| CN110334274A (en) * | 2019-05-30 | 2019-10-15 | 平安科技（深圳）有限公司 | Information-pushing method, device, computer equipment and storage medium |
| CN111666460A (en) * | 2020-05-27 | 2020-09-15 | 中国平安财产保险股份有限公司 | User portrait generation method and device based on privacy protection and storage medium |
| CN111784301A (en) * | 2020-07-02 | 2020-10-16 | 中国银行股份有限公司 | User portrait construction method and device, storage medium and electronic equipment |
| CN111915366A (en) * | 2020-07-20 | 2020-11-10 | 上海燕汐软件信息科技有限公司 | User portrait construction method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114021175A (en) | 2022-02-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109474578B (en) | Message checking method, device, computer equipment and storage medium | |
| CN111314306A (en) | Interface access method and device, electronic equipment and storage medium | |
| CN110765295A (en) | Graph database-based query method and device, computer equipment and storage medium | |
| CN110535971B (en) | Interface configuration processing method, device, equipment and storage medium based on block chain | |
| CN108090351B (en) | Method and apparatus for processing request message | |
| CN109189367B (en) | Data processing method, device, server and storage medium | |
| CN111931076B (en) | Method and device for carrying out relationship recommendation based on authorized directed graph and computer equipment | |
| CN112367164B (en) | Service request processing method and device, computer equipment and storage medium | |
| CN112328486A (en) | Interface automation test method and device, computer equipment and storage medium | |
| CN114218322B (en) | Data display method, device, equipment and medium based on ciphertext transmission | |
| CN114153626A (en) | Method and device for abstracting service integration process and computer equipment | |
| CN114021175B (en) | User portrait configuration method and device, computer equipment and medium | |
| CN111177794A (en) | City image method, device, computer equipment and storage medium | |
| CN111124421B (en) | Abnormal contract data detection method and device for blockchain intelligent contract | |
| CN112528201A (en) | Method and device for calling third-party platform, computer equipment and storage medium | |
| CN112131471A (en) | Method, device, equipment and medium for relation recommendation based on unauthorized undirected graph | |
| CN115564000A (en) | Two-dimensional code generation method and device, computer equipment and storage medium | |
| CN113360300B (en) | Interface call link generation method, device, equipment and readable storage medium | |
| CN111209061A (en) | Method and device for filling in user information, computer equipment and storage medium | |
| CN113709181A (en) | Website login method, device, equipment and storage medium based on browser plug-in | |
| CN112559526A (en) | Data table export method and device, computer equipment and storage medium | |
| CN112734050A (en) | Text model training method, text model recognition device, text model equipment and storage medium | |
| CN109857748B (en) | Contract data processing method and device and electronic equipment | |
| CN114924783A (en) | Interface calling method, device, equipment and storage medium of application program | |
| CN115203674A (en) | Automatic login method, system, device and storage medium for application program |
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 |