CN114663149A - Product delivery method based on privacy protection and related equipment thereof - Google Patents
Product delivery method based on privacy protection and related equipment thereof Download PDFInfo
- Publication number
- CN114663149A CN114663149A CN202210321222.8A CN202210321222A CN114663149A CN 114663149 A CN114663149 A CN 114663149A CN 202210321222 A CN202210321222 A CN 202210321222A CN 114663149 A CN114663149 A CN 114663149A
- Authority
- CN
- China
- Prior art keywords
- user
- users
- target
- label
- product
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000002716 delivery method Methods 0.000 title claims abstract description 27
- 238000006243 chemical reaction Methods 0.000 claims abstract description 75
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000004364 calculation method Methods 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 125000004122 cyclic group Chemical group 0.000 claims description 9
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000012545 processing Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 3
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application belongs to the field of privacy calculation and artificial intelligence, and relates to a product delivery method based on privacy protection and related equipment thereof. The product delivery method based on privacy protection comprises the following steps: determining overlapped users, label missing users and a target prediction model according to a first data party and a second data party through privacy set intersection; predicting a user label of a label-missing user by using a target prediction model; extracting a preset number of releasing users from the label missing users, and releasing the target products to the releasing users; obtaining a release result, and calculating the user conversion rate of a release user according to the release result; when the user conversion rate is larger than a preset threshold value, acquiring an initial user in the overlapped users; acquiring a user portrait corresponding to an initial user in a first data party, and determining a user with the same portrait as the user portrait as a target user; and releasing the target product to the target user. The method can improve the user conversion rate of the target user.
Description
Technical Field
The application relates to the technical field of privacy computation and artificial intelligence, in particular to a product delivery method based on privacy protection and related equipment thereof.
Background
Insurance refers to the business insurance behavior that the insurance applicant pays insurance fees to the insurance carrier according to contract contracts, the insurance carrier undertakes the responsibility for compensating insurance funds for property loss caused by the occurrence of possible accidents agreed by the contracts, or the insured person undertakes the responsibility for paying insurance funds when the insured person dies, has disabilities and diseases or reaches the agreed ages, deadlines and other conditions. Along with the economic development of the society, the insurance consciousness of people is gradually improved, and meanwhile, an insurance company can obtain a user group in a mode of putting insurance advertisements to target users to realize the conversion of the users.
The current way to target users is usually to make extensive placement of insurance advertisements through internet channels, i.e., all users who enter the internet are considered target users. When the insurance advertisements are delivered to the target users determined in the mode, the customer obtaining cost is high, and the user conversion rate is low.
Disclosure of Invention
The embodiment of the application aims to provide a product delivery method based on privacy protection and related equipment thereof, so as to solve the problem of low user conversion rate of a target user.
In order to solve the above technical problem, an embodiment of the present application provides a product delivery method based on privacy protection, which adopts the following technical solutions:
determining overlapped users, label missing users and a target prediction model according to a first data party and a second data party through privacy set intersection; the overlapping users are overlapping users in a first data party and a second data party; the label missing user is a user without a user label in the overlapped users, and the user label is used for indicating whether the user purchases a target product; the target prediction model is a network model pre-trained by the second data party and used for predicting a user label of a user; predicting a user tag of the tag-missing user using the target prediction model; extracting a preset number of releasing users from the label missing users, and releasing the target products to the releasing users; the releasing user is any user of the user with the lost label, the label of which is predicted to buy the target product; obtaining a release result, and calculating the user conversion rate of the release user according to the release result; the releasing result comprises the number of users of releasing users and the number of users who purchase the target product in the releasing users; when the user conversion rate is larger than a preset threshold value, acquiring an initial user in the overlapped users; the user tags of the initial users are all the target products for purchase; acquiring a user portrait corresponding to the initial user in the first data party, and determining a user same as the user portrait as a target user; and releasing the target product to the target user.
Further, the determining overlapping users according to the first data party and the second data party by privacy set intersection includes: acquiring product purchase information of the user on the product in the second data party; the product comprises the target product; determining a corresponding user corresponding to the product purchase information of the user in the first data party by using privacy set intersection; and determining the corresponding user as an overlapping user.
Further, the determining the target prediction model includes: acquiring user information of a tag user; the label user is a user with a user label in the overlapped users, and the user information comprises user consumption information in the first data party and product purchase information of the product by the user in the second data party; and performing user label prediction training on a preset network model by using a longitudinal federated learning algorithm and the user information of the label user until a loss function is converged to obtain the target prediction model.
Further, after calculating the user conversion rate of the release user according to the release result, the product release method further includes: when the user conversion rate is smaller than or equal to the preset threshold, executing the following cyclic operation on the overlapped users until the user conversion rate is larger than the preset threshold; the cyclic operation includes: acquiring user information of the user with the missing label; updating and training the target prediction model by utilizing a longitudinal federated learning algorithm, the user information of the label user and the user information of the label-missing user until the loss function is converged to obtain an updated target prediction model; the overlapping users comprise the tab users and the tab missing users; predicting the user label of the label-missing user again by using the updated target prediction model; extracting a preset number of circularly releasing users from the label missing users, and releasing the target products to the circularly releasing users; the circularly releasing user is any user of the users with the lost labels, and the label of the user is predicted to buy the target product; and acquiring a circular putting result, and calculating the user conversion rate of the circular putting user according to the circular putting result.
Further, the step of calculating the user conversion rate of the released user according to the release result includes: according to the formula
And calculating the user conversion rate of the releasing user, wherein n is used for representing the user conversion rate of the releasing user, a is used for representing the number of users purchasing the target product in the releasing user, and b is used for representing the number of users of the releasing user.
Further, the obtaining a user representation of the initial user includes: acquiring product purchase information of an initial user on a product in the second data party; the product comprises the target product; and determining a user portrait corresponding to the product purchase information of the initial user in the first data party by utilizing privacy set intersection.
Further, after the target product is released to the target user, the product release method further includes: storing the release data corresponding to the target product to a target block chain; the placement data includes at least a user representation of the target user.
In order to solve the above technical problem, an embodiment of the present application further provides a product delivery device based on privacy protection, which adopts the following technical scheme:
the first determining module is used for determining an overlapped user, a label missing user and a target prediction model according to a first data party and a second data party through privacy set intersection; the overlapping users are overlapping users in a first data party and a second data party; the label missing user is a user without a user label in the overlapped users, and the user label is used for indicating whether the user purchases a target product; the target prediction model is a network model pre-trained by the second data party and used for predicting a user label of a user; a label prediction module for predicting the user label of the label-missing user using the target prediction model; the first releasing module is used for extracting a preset number of releasing users from the label missing users and releasing the target product to the releasing users; the releasing user is any user of the user with the lost label, the label of which is predicted to buy the target product; the calculation module is used for acquiring a release result and calculating the user conversion rate of the release user according to the release result; the releasing result comprises the number of users of releasing users and the number of users who purchase the target product in the releasing users; the user obtaining module is used for obtaining an initial user in the overlapped users when the user conversion rate is greater than a preset threshold value; the user tags of the initial users are all the target products for purchase; the second determining module is used for acquiring a user portrait corresponding to the initial user in the first data party and determining a user identical to the user portrait as a target user; and the second delivery module is used for delivering the target product to the target user.
Further, the first determining module comprises a first obtaining sub-module, a first determining sub-module and a second determining sub-module; the first obtaining submodule is used for obtaining product purchasing information of the user on the product in the second data party; the product comprises the target product; the first determining submodule is used for determining a corresponding user corresponding to the product purchasing information of the user in the first data party by utilizing privacy set intersection; the second determining submodule is configured to determine the corresponding user as an overlapping user.
Further, the first determining module further comprises a second obtaining sub-module and a training sub-module; the second obtaining submodule is used for obtaining the user information of the tag user; the label user is a user with a user label in the overlapped users, and the user information comprises user consumption information in the first data party and product purchase information of the product by the user in the second data party; and the training submodule is used for carrying out user label prediction training on a preset network model by utilizing a longitudinal federated learning algorithm and the user information of the label user until a loss function is converged to obtain the target prediction model.
Further, the product delivery device based on privacy protection further comprises a processing module; the processing module is used for executing the following cyclic operation on the overlapped users when the user conversion rate is smaller than or equal to the preset threshold value until the user conversion rate is larger than the preset threshold value; the cyclic operation includes: acquiring user information of the user with the missing label; updating and training the target prediction model by utilizing a longitudinal federated learning algorithm, the user information of the label user and the user information of the label-missing user until the loss function is converged to obtain an updated target prediction model; the overlapping users comprise the tab users and the tab missing users; predicting the user label of the label-missing user again by using the updated target prediction model; extracting a preset number of circularly releasing users from the label missing users, and releasing the target products to the circularly releasing users; the circularly releasing user is any user of the users with the lost labels, and the label of the user is predicted to buy the target product; and acquiring a circular putting result, and calculating the user conversion rate of the circular putting user according to the circular putting result.
Further, the delivery result includes a number of users who purchased the target product, and the calculation module is specifically configured to calculate the target product according to a formula
ComputingAnd the user conversion rate of the releasing user, wherein n is used for representing the user conversion rate of the releasing user, a is used for representing the number of users purchasing the target product in the releasing user, and b is used for representing the number of users of the releasing user.
Further, the second acquisition module comprises an information acquisition sub-module and an image determination sub-module; the information acquisition submodule is used for acquiring product purchase information of an initial user on a product in the second data party; the product comprises the target product; the portrait determination sub-module is used for determining a user portrait corresponding to the product purchase information of the initial user in the first data party by means of privacy set intersection.
Further, the product delivery device based on privacy protection further comprises a storage module; the storage module is used for storing the release data corresponding to the target product to a target block chain; the placement data includes at least a user representation of the target user.
In order to solve the above technical problem, an embodiment of the present application further provides a computer device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the product delivery method based on privacy protection when executing the computer program.
In order to solve the above technical problem, an embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the product delivery method based on privacy protection are implemented.
Compared with the prior art, the embodiment of the application mainly has the following beneficial effects: determining overlapped users, label missing users and a target prediction model, predicting user labels of the label missing users by using the target prediction model, and extracting a preset number of releasing users from the label missing users. The overlapped users are the overlapped users in the first data party and the second data party, namely, the data of the multiple data parties are utilized to pertinently determine the target users, and the accuracy of the determined target users is improved. And then, delivering the target product to the delivery user, acquiring a delivery result, and calculating the user conversion rate of the delivery user according to the delivery result. And when the user conversion rate is greater than a preset threshold value, acquiring a user portrait of an initial user in the overlapped users, and determining a user with the same portrait as the user portrait as a target user needing to put in a target product. In the method, trial delivery is firstly carried out on part of users (namely delivery users) in overlapped users, and when the user conversion rate in the trial delivery is larger than a preset threshold value, the user portrait of an initial user is determined, so that a target user is determined. The problem of high customer acquisition cost caused by directly taking all users entering the Internet as target users is solved, and the user conversion rate is improved.
Drawings
In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of a privacy preserving based product delivery method according to the present application;
FIG. 3 is a flowchart of one embodiment of step S21 of FIG. 2;
FIG. 4 is a flowchart of another embodiment of step S21 of FIG. 2;
FIG. 5 is a flow diagram of another embodiment of a privacy preserving based product delivery method according to the present application;
FIG. 6 is a schematic block diagram of an embodiment of a privacy preserving based product delivery apparatus according to the present application;
FIG. 7 is a schematic block diagram of one embodiment of a computer device according to the present application.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof, in the description and claims of this application and the description of the above figures are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the above-described drawings are used for distinguishing between different objects and not for describing a particular order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have various communication client applications installed thereon, such as a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture experts Group Audio Layer III, mpeg compression standard Audio Layer 3), MP4 players (Moving Picture experts Group Audio Layer IV, mpeg compression standard Audio Layer 4), laptop portable computers, desktop computers, and the like.
The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.
It should be noted that the product delivery method based on privacy protection provided in this embodiment may be applied to the server device 105, and may also be applied to the terminal devices 101, 102, and 103. The server device 105 and the terminal devices 101, 102, 103 may be collectively referred to as electronic devices. That is, an executive subject of the privacy protection-based product delivery method provided in the embodiment of the present application may be a privacy protection-based product delivery apparatus, and the privacy protection-based product delivery apparatus may be the electronic device (e.g., the server device 105 or the terminal devices 101, 102, and 103).
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for an implementation.
With continued reference to FIG. 2, a flowchart of one embodiment of a privacy-based product delivery method according to the present application is shown. The product release method based on privacy protection comprises the following steps:
and step S21, determining overlapped users, label-missing users and a target prediction model according to the first data party and the second data party through privacy set intersection.
The overlapping users are the overlapping users in the first data party and the second data party; the label missing user is a user without a user label in the overlapped users, and the user label is used for indicating whether the user purchases a target product; the target prediction model is used to predict a user label of a user. The first data party is a data party including consumption information (such as annual consumption amount) of the user, for example, an internet company, an e-commerce company and the like; the second data party is a data party including product purchase information (such as underwriting information and claim settlement information) of the product purchased by the user, for example, when the product is an insurance product, the second data party may be an insurance company. Wherein, the product comprises the target product to be released in the application.
Specifically, fig. 3 is a flowchart of a method for determining an overlapped user according to a first data party and a second data party, and as shown in fig. 3, the method includes the following steps S211 to S213.
And step S211, acquiring product purchase information of the user on the product in the second data party.
Wherein the product comprises a target product.
Step S212, determining a corresponding user corresponding to the product purchase information of the user in the first data party by utilizing the privacy set intersection.
Because the first data side comprises the consumption information of the user, the second user side comprises the product purchase information of the user, and the consumption information and the product purchase information of the user are both the privacy information of the user. Therefore, in order to avoid leakage of the user privacy information, a corresponding user corresponding to the product purchase information of the user in the first data party is determined by using a Privacy Set Interaction (PSI). The PSI means that the first data party and the second data party obtain an intersection of data held by the two parties (i.e. corresponding users) without revealing any additional information.
Specifically, the first data party and the second data party both establish communication connection with the PSI server, and hash the data of the first data party and the second data party according to the salt value (salt) obtained from the PSI server to obtain a hash result. And then, sending a hash result to the PSI server, and carrying out PSI processing on the hash result of the first data party and the hash result of the second data party by the PSI server to obtain the information of the user with intersection in the first data party and the second data party. And finally, determining the corresponding user according to the information of the user with intersection in the first data party and the second data party, which is sent by the PSI server.
In step S213, the corresponding user is determined as an overlapping user.
In the embodiment, the target user is determined in a targeted manner by using the data of a plurality of data parties, so that the accuracy of the determined target user is improved. And overlapping users in the first data party and the second data party are determined by privacy set intersection, so that the privacy of the users can be prevented from being revealed.
And then, determining the users with the labels missing in the overlapped users according to the product purchase information of the overlapped users. Specifically, when the product purchase information of the user does not include the user tag, it is determined that the user is a tag-missing user.
Finally, a target prediction model is determined.
Specifically, fig. 4 is a flowchart of a method for determining a target prediction model, and as shown in fig. 4, the method includes the following steps S214 to S215.
Step S214, user information of the label user is obtained.
The label user is a user with a user label in the overlapped users, and the user information comprises user consumption information in the first data party and product purchase information of the product by the user in the second data party.
And S215, performing user label prediction training on the preset network model by using a longitudinal federated learning algorithm and user information of the label user until the loss function is converged to obtain a target prediction model.
Specifically, a first data party establishes a local network model, and a second data party establishes a preset network model. Then, the first data party and the second data party establish communication connection with a cooperation party (used for cooperating the second data party to train the target prediction model), and obtain a public key from the cooperation party.
The first data party encrypts the data characteristics in the user consumption information by using the public key to obtain a first encryption result, and sends the first encryption result to the second data party. And the second data party encrypts the data characteristics in the product purchase information by using the public key to obtain a second encryption result, and sends the second encryption result to the second data party. Wherein the user personal information of the target tag user (any one of the tag users) in the first data side and the second data side is the same, but the characteristic data is different. For example, the first data party includes the mobile phone number, age, sex, and annual consumption amount of the target tag user, and the second data party includes the mobile phone number, annual premium, and whether to purchase the target product (user tag). The personal information of the target label user in the first data party and the second data party is a mobile phone number; the characteristic data of the target tag user in the first data party are age, gender and annual consumption amount; the characteristic data of the target tag user in the second data party is annual premiums; target tag the user tag of the user in the second data party is whether to purchase the target product.
And after receiving the first encryption result, the second data party calculates the local encryption gradient and the encryption loss corresponding to the second data party according to the first encryption result and the data characteristics in the product purchase information, adds an additional mask to the local encryption gradient and the encryption loss corresponding to the second data party, and sends the additional mask to the cooperative party. And after receiving the second encryption result, the first data party calculates the local encryption gradient corresponding to the first data party according to the second encryption result and the data characteristics in the user consumption information, adds an additional mask code to the local encryption gradient corresponding to the first data party and then sends the added mask code to the cooperative party.
And after receiving the local encryption gradient and the encryption loss corresponding to the second data party and the local encryption gradient corresponding to the first data party, the cooperative party decrypts the local encryption gradient and the encryption loss corresponding to the second data party and the local encryption gradient corresponding to the first data party by using a private key corresponding to the public key to obtain a complete gradient, and transmits the complete gradient back to the first data party and the second data party.
Finally, the first data party removes the additional mask on the complete gradient to obtain the complete gradient, and updates the local network model according to the complete gradient; and the second data side removes the additional mask on the complete gradient to obtain the complete gradient, and updates the preset network model according to the complete gradient until the loss function corresponding to the preset network model converges to obtain the target prediction model.
In the embodiment, a longitudinal federated learning technology is used, a logistic regression mode is adopted to train the target prediction model, and data of the first data party and data of the second data party are stored locally in the whole training process, so that the privacy of a user can be ensured not to be revealed.
In step S22, the user label of the label-missing user is predicted using the target prediction model.
Specifically, user consumption information and product purchase information of the user with the label missing are input into the target prediction model, and the user label of the user with the label missing is obtained.
And step S23, extracting a preset number of releasing users from the users with the missing labels, and releasing the target products to the releasing users.
The released user is any user of which the user label is predicted to buy the target product in the user with the label missing. The preset number value can be a default value or a value set by related personnel according to specific conditions. For example, the preset number is 10% of the number of overlapping users.
And step S24, obtaining the releasing result and calculating the user conversion rate of the releasing user according to the releasing result.
In particular, according to the formula
And calculating the user conversion rate of the releasing user, wherein n is used for representing the user conversion rate of the releasing user, a is used for representing the number of users purchasing the target product in the releasing user, and b is used for representing the number of users of the releasing user.
Optionally, when the user conversion rate is less than or equal to the preset threshold, the following loop operation is performed on the overlapped user until the user conversion rate is greater than the preset threshold. The preset threshold may be a default value or a numerical value set by a relevant person according to a specific situation. For example, the preset threshold is 60%.
Specifically, the cyclic operation includes: and obtaining user information of the label-missing user, and updating and training the target prediction model by utilizing a longitudinal federal learning algorithm, the user information of the label user and the user information of the label-missing user until the loss function is converged to obtain an updated target prediction model. Wherein the overlapped users comprise tagged users and users with missing tags. And then, predicting the user labels of the users with the labels missing again by using the updated target prediction model, and extracting a preset number of circularly delivered users from the users with the labels missing. And then, delivering the target product to the circular delivery user, and acquiring a circular delivery result. And finally, calculating the user conversion rate of the circularly launched user according to the circularly launched result. The circularly releasing user is any user of which the user label is predicted to buy the target product in the label-missing user. The specific implementation process of the loop operation is the same as that of steps S21-S25, and is not described here again.
In this embodiment, when the user conversion rate of the randomly extracted drop users is less than or equal to the preset threshold, the target prediction model is trained and updated until the user conversion rate of the randomly extracted drop users is greater than the preset threshold, so that the prediction accuracy of the updated target prediction model is ensured, and the user conversion rate of the determined target users is improved.
And step S25, when the user conversion rate is greater than a preset threshold value, acquiring an initial user of the overlapped users.
Wherein, the user tags of the initial users are all purchase target products.
In step S26, a user representation corresponding to the first data party of the initial user is obtained, and the user with the same representation is determined as the target user.
Specifically, product purchase information of an initial user on a product in the second data party is obtained, and a user portrait corresponding to the product purchase information of the initial user in the first data party is determined by means of privacy set intersection. The process of determining the user profile is the same as the process of determining the overlapped users in steps S211 to S213, and is not described herein again.
In the embodiment, the user portrait corresponding to the product purchase information of the initial user is determined by using the privacy set intersection, so that the privacy of the user can be ensured not to be leaked.
And step S27, the target product is released to the target user.
Specifically, target products are delivered to target users in batches by using a preset delivery mode. For example, the target product is delivered to the target user by using a marketing short message.
Optionally, fig. 5 is a flowchart of another embodiment of the product delivery method based on privacy protection according to the present application, and referring to fig. 5, after step S27, the method further includes the following step S28.
And step S28, storing the release data corresponding to the target product to the target block chain. Wherein the placement data comprises at least a user representation of the target user. In this embodiment, the delivery data corresponding to the target product is stored in the target block chain, so that the delivery data can be guaranteed to be real and credible, and subsequent statistics and monitoring of the conversion result of delivery of the target product are facilitated.
In this embodiment, an overlapped user, a label-missing user, and a target prediction model are determined, a user label of the label-missing user is predicted by using the target prediction model, and a preset number of released users are extracted from the label-missing users. The overlapped users are the overlapped users in the first data party and the second data party, namely, the data of the multiple data parties are utilized to pertinently determine the target users, and the accuracy of the determined target users is improved. And then, delivering the target product to the delivery user, acquiring a delivery result, and calculating the user conversion rate of the delivery user according to the delivery result. And when the user conversion rate is greater than a preset threshold value, acquiring a user portrait of an initial user in the overlapped users, and determining a user with the same portrait as the user portrait as a target user needing to put in a target product. In the application, trial delivery is firstly carried out on part of users (namely delivery users) in overlapped users, and when the conversion rate of the users in the trial delivery is larger than a preset threshold value, the user portrait of the initial user is determined, so that the target user is determined. The problem of high customer acquisition cost caused by directly taking all users entering the Internet as target users is solved, and the user conversion rate is improved.
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 a computer program, which can be stored in a computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the computer program is executed. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
With further reference to fig. 6, as an implementation of the method shown in fig. 2, the present application provides an embodiment of a product delivery apparatus based on privacy protection, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.
As shown in fig. 6, the privacy-protection-based product delivery apparatus 600 of the present embodiment includes: a first determining module 601, a tag predicting module 602, a first delivering module 603, a calculating module 604, a user obtaining module 605, a second determining module 606 and a second delivering module 607, wherein:
a first determining module 601, configured to determine, according to a first data party and a second data party, an overlapping user, a tag missing user, and a target prediction model through privacy set intersection; the overlapping users are overlapping users in a first data party and a second data party; the label missing user is a user without a user label in the overlapped users, and the user label is used for indicating whether the user purchases a target product; the target prediction model is a network model pre-trained by the second data party and used for predicting a user label of a user; a tag prediction module 602, configured to predict a user tag of the user with the missing tag using the target prediction model; a first releasing module 603, configured to extract a preset number of releasing users from the users with missing tags, and release the target product to the releasing users; the releasing user is any user of the user with the lost label, the label of which is predicted to buy the target product; a calculating module 604, configured to obtain a delivery result, and calculate a user conversion rate of the delivery user according to the delivery result; the releasing result comprises the number of users of releasing users and the number of users who purchase the target product in the releasing users; a user obtaining module 605, configured to obtain an initial user of the overlapping users when the user conversion rate is greater than a preset threshold; the user tags of the initial users are all the target products for purchase; a second determining module 606, configured to obtain a user portrait corresponding to the initial user in the first data party, and determine a user that is the same as the user portrait as a target user; a second releasing module 607, configured to release the target product to the target user.
In this embodiment, an overlapped user, a label missing user, and a target prediction model are determined, a user label of the label missing user is predicted by using the target prediction model, and a preset number of released users are extracted from the label missing user. The overlapped users are the overlapped users in the first data party and the second data party, namely, the data of the multiple data parties are utilized to pertinently determine the target users, and the accuracy of the determined target users is improved. And then, delivering the target product to the delivery user, acquiring a delivery result, and calculating the user conversion rate of the delivery user according to the delivery result. And when the user conversion rate is greater than a preset threshold value, acquiring a user portrait of an initial user in the overlapped users, and determining a user with the same portrait as the user portrait as a target user needing to put in a target product. In the method, trial delivery is firstly carried out on part of users (namely delivery users) in overlapped users, and when the user conversion rate in the trial delivery is larger than a preset threshold value, the user portrait of an initial user is determined, so that a target user is determined. The problem of high customer acquisition cost caused by directly taking all users entering the Internet as target users is solved, and the user conversion rate is improved.
In some possible implementation manners of this embodiment, the first determining module 601 includes a first obtaining sub-module, a first determining sub-module, and a second determining sub-module; the first obtaining submodule is used for obtaining product purchasing information of the user on the product in the second data party; the product comprises the target product; the first determining submodule is used for determining a corresponding user corresponding to the product purchasing information of the user in the first data party by utilizing privacy set intersection; the second determining submodule is configured to determine the corresponding user as an overlapping user.
In the embodiment, the target user is determined in a targeted manner by using the data of a plurality of data parties, so that the accuracy of the determined target user is improved. And the overlapping users in the first data party and the second data party are determined by the privacy set intersection, so that the privacy of the users can be ensured not to be revealed.
In some optional implementations of this embodiment, the first determining module 601 further includes a second obtaining sub-module and a training sub-module; the second obtaining submodule is used for obtaining the user information of the tag user; the label user is a user with a user label in the overlapped users, and the user information comprises user consumption information in the first data party and product purchase information of the product by the user in the second data party; and the training submodule is used for carrying out user label prediction training on a preset network model by utilizing a longitudinal federated learning algorithm and the user information of the label user until a loss function is converged to obtain the target prediction model.
In the embodiment, a longitudinal federated learning technology is used, a logistic regression mode is adopted to train the target prediction model, and data of the first data party and data of the second data party are stored locally in the whole training process, so that the privacy of a user can be ensured not to be revealed.
In some possible implementation manners of this embodiment, the product delivery apparatus based on privacy protection further includes a processing module; the processing module is used for executing the following cyclic operation on the overlapped users when the user conversion rate is smaller than or equal to the preset threshold value until the user conversion rate is larger than the preset threshold value; the cyclic operation includes: acquiring user information of the user with the missing label; updating and training the target prediction model by utilizing a longitudinal federated learning algorithm, the user information of the label user and the user information of the label-missing user until the loss function is converged to obtain an updated target prediction model; the overlapping users comprise the tab users and the tab missing users; predicting the user label of the label-missing user again by using the updated target prediction model; extracting a preset number of circularly releasing users from the label missing users, and releasing the target products to the circularly releasing users; the circularly releasing user is any user of the users with the lost labels, and the label of the user is predicted to buy the target product; and acquiring a circular putting result, and calculating the user conversion rate of the circular putting user according to the circular putting result.
In this embodiment, when the user conversion rate of the randomly extracted drop users is less than or equal to the preset threshold, the target prediction model is trained and updated until the user conversion rate of the randomly extracted drop users is greater than the preset threshold, so that the prediction accuracy of the updated target prediction model is ensured, and the user conversion rate of the determined target users is improved.
In some possible implementations of this embodiment, the delivery result includes a number of users who purchased the target product, and the calculating module 604 is specifically configured to calculate the target product according to a formula
And calculating the user conversion rate of the releasing user, wherein n is used for representing the user conversion rate of the releasing user, a is used for representing the number of users purchasing the target product in the releasing user, and b is used for representing the number of users of the releasing user.
In some possible implementations of this embodiment, the user obtaining module 605 includes an information obtaining sub-module and a portrait determining sub-module; the information acquisition submodule is used for acquiring product purchase information of an initial user on a product in the second data party; the product comprises the target product; the portrait determination submodule is used for determining the user portrait corresponding to the product purchase information of the initial user in the first data party by utilizing privacy set intersection.
In the embodiment, the user portrait corresponding to the product purchase information of the initial user is determined by using the privacy set intersection, so that the privacy of the user can be ensured not to be leaked.
In some possible implementation manners of this embodiment, the product delivery device based on privacy protection further includes a storage module; the storage module is used for storing the release data corresponding to the target product to a target block chain; the placement data includes at least a user representation of the target user.
In this embodiment, the release data corresponding to the target product is stored in the target block chain, so that the release data can be guaranteed to be real and credible, and the subsequent statistics and monitoring of the conversion result of the release of the target product are facilitated.
In order to solve the technical problem, the embodiment of the application further provides computer equipment. Referring to fig. 7, fig. 7 is a block diagram of a basic structure of a computer device according to the present embodiment.
The computer device 7 comprises a memory 71, a processor 72, a network interface 73, which are communicatively connected to each other via a system bus. It is noted that only a computer device 7 having components 71-73 is shown, but it is to be understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead. As will be understood by those skilled in the art, the computer device is a device capable of automatically performing numerical calculation and/or information processing according to instructions set or stored in advance, and the hardware thereof includes but is not limited to a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.
The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer equipment can carry out man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like.
The memory 71 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the storage 71 may be an internal storage unit of the computer device 7, such as a hard disk or a memory of the computer device 7. In other embodiments, the memory 71 may also be an external storage device of the computer device 7, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the computer device 7. Of course, the memory 71 may also comprise both an internal storage unit of the computer device 7 and an external storage device thereof. In this embodiment, the memory 71 is generally used for storing an operating system and various application software installed on the computer device 7, such as computer readable instructions of a product delivery method based on privacy protection, and the like. Further, the memory 71 may also be used to temporarily store various types of data that have been output or are to be output.
The processor 72 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 72 is typically arranged to control the overall operation of the computer device 7. In this embodiment, the processor 72 is configured to execute the computer readable instructions or process data stored in the memory 71, for example, execute the computer readable instructions of the product delivery method based on privacy protection.
The network interface 73 may comprise a wireless network interface or a wired network interface, and the network interface 73 is generally used for establishing a communication connection between the computer device 7 and other electronic devices.
The computer device provided in this embodiment may perform the steps of the product delivery method based on privacy protection. Here, the steps of the product delivery method based on privacy protection may be steps of the product delivery method based on privacy protection of the above embodiments.
In this embodiment, an overlapped user, a label missing user, and a target prediction model are determined, a user label of the label missing user is predicted by using the target prediction model, and a preset number of released users are extracted from the label missing user. The overlapped users are the overlapped users in the first data party and the second data party, namely, the data of the multiple data parties are utilized to pertinently determine the target users, and the accuracy of the determined target users is improved. And then, releasing the target product to the releasing user, acquiring a releasing result, and calculating the user conversion rate of the releasing user according to the releasing result. And when the user conversion rate is greater than a preset threshold value, acquiring a user portrait of an initial user in the overlapped users, and determining a user with the same portrait as the user portrait as a target user needing to put in a target product. In the method, trial delivery is firstly carried out on part of users (namely delivery users) in overlapped users, and when the user conversion rate in the trial delivery is larger than a preset threshold value, the user portrait of an initial user is determined, so that a target user is determined. The problem of high customer acquisition cost caused by directly taking all users entering the Internet as target users is solved, and the user conversion rate is improved.
The present application further provides another embodiment, which is to provide a computer-readable storage medium storing computer-readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the privacy-based product delivery method as described above.
In this embodiment, an overlapped user, a label missing user, and a target prediction model are determined, a user label of the label missing user is predicted by using the target prediction model, and a preset number of released users are extracted from the label missing user. The overlapped users are the overlapped users in the first data party and the second data party, namely, the data of the multiple data parties are utilized to pertinently determine the target users, and the accuracy of the determined target users is improved. And then, delivering the target product to the delivery user, acquiring a delivery result, and calculating the user conversion rate of the delivery user according to the delivery result. And when the user conversion rate is greater than a preset threshold value, acquiring a user portrait of an initial user in the overlapped users, and determining a user with the same portrait as the user portrait as a target user needing to put in a target product. In the method, trial delivery is firstly carried out on part of users (namely delivery users) in overlapped users, and when the user conversion rate in the trial delivery is larger than a preset threshold value, the user portrait of an initial user is determined, so that a target user is determined. The problem that all users entering the Internet are directly regarded as target users, so that customer acquisition cost is high is solved, and user conversion rate is improved.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (such as a ROM/RAM, a magnetic disk, and an optical disk), and includes several instructions for enabling a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
It is to be understood that the above-described embodiments are merely illustrative of some, but not restrictive, of the broad invention, and that the appended drawings illustrate preferred embodiments of the invention and do not limit the scope of the invention. This application is capable of embodiments in many different forms and is provided for the purpose of enabling a thorough understanding of the disclosure of the application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that the present application may be practiced without modification or with equivalents of some of the features described in the foregoing embodiments. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields and are within the protection scope of the present application.
Claims (10)
1. A product release method based on privacy protection is characterized by comprising the following steps:
determining overlapped users, label missing users and a target prediction model according to a first data party and a second data party through privacy set intersection; the overlapping users are overlapping users in a first data party and a second data party; the label missing user is a user without a user label in the overlapped users, and the user label is used for indicating whether the user purchases a target product; the target prediction model is a network model pre-trained by the second data party and used for predicting a user label of a user;
predicting a user tag of the tag-missing user using the target prediction model;
extracting a preset number of releasing users from the label missing users, and releasing the target product to the releasing users; the releasing user is any user of the user with the lost label, the label of which is predicted to buy the target product;
obtaining a release result, and calculating the user conversion rate of the release user according to the release result; the releasing result comprises the number of users of releasing users and the number of users who purchase the target product in the releasing users;
when the user conversion rate is larger than a preset threshold value, acquiring an initial user in the overlapped users; the user tags of the initial users are all the target products for purchase;
acquiring a user portrait corresponding to the initial user in the first data party, and determining a user same as the user portrait as a target user;
and releasing the target product to the target user.
2. The product placement method according to claim 1, wherein the determining overlapping users from the first and second data parties by privacy set intersection comprises:
acquiring product purchase information of a user on a product in the second data party, wherein the product comprises the target product;
determining a corresponding user corresponding to the product purchase information of the user in the first data party by using privacy set intersection;
and determining the corresponding user as an overlapping user.
3. The product delivery method of claim 1, wherein the determining a target predictive model comprises:
acquiring user information of a tag user; the label user is a user with a user label in the overlapped users, and the user information comprises user consumption information in the first data party and product purchase information of the product by the user in the second data party;
and performing user label prediction training on a preset network model by using a longitudinal federated learning algorithm and the user information of the label user until a loss function is converged to obtain the target prediction model.
4. The product delivery method according to claim 3, wherein after calculating a user conversion rate of the delivery user based on the delivery result, the product delivery method further comprises:
when the user conversion rate is smaller than or equal to the preset threshold, executing the following cyclic operation on the overlapped users until the user conversion rate is larger than the preset threshold;
the cyclic operation includes:
acquiring user information of the user with the missing label;
updating and training the target prediction model by utilizing a longitudinal federated learning algorithm, the user information of the label user and the user information of the label-missing user until the loss function is converged to obtain an updated target prediction model; the overlapping users comprise the tab users and the tab missing users;
predicting the user label of the label missing user again by using the updated target prediction model;
extracting a preset number of circularly releasing users from the label missing users, and releasing the target products to the circularly releasing users; the circular releasing user is any user of the users with the lost labels, and the label of the user is predicted to buy the target product;
and acquiring a circular putting result, and calculating the user conversion rate of the circular putting user according to the circular putting result.
5. The product placement method according to claim 1, wherein the placement result includes a number of users who purchased the target product, and the calculating the user conversion rate of the placement user according to the placement result includes:
according to the formula
And calculating the user conversion rate of the releasing user, wherein n is used for representing the user conversion rate of the releasing user, a is used for representing the number of users purchasing the target product in the releasing user, and b is used for representing the number of users of the releasing user.
6. The product delivery method of claim 1, wherein said obtaining a user representation of the initial user comprises:
acquiring product purchase information of an initial user on a product in the second data party; the product comprises the target product;
and determining a user portrait corresponding to the product purchase information of the initial user in the first data party by utilizing privacy set intersection.
7. The product placement method according to claim 1, wherein after the target product is placed to the target user, the product placement method further comprises:
storing the release data corresponding to the target product to a target block chain; the placement data includes at least a user representation of the target user.
8. A product delivery device based on privacy protection, comprising:
the first determining module is used for determining overlapped users, label missing users and a target prediction model according to the first data party and the second data party through privacy set intersection; the overlapping users are overlapping users in a first data party and a second data party; the label missing user is a user without a user label in the overlapped users, and the user label is used for indicating whether the user purchases a target product; the target prediction model is a network model pre-trained by the second data party and used for predicting a user label of a user;
a label prediction module for predicting the user label of the label-missing user using the target prediction model;
the first releasing module is used for extracting a preset number of releasing users from the label missing users and releasing the target product to the releasing users; the releasing user is any user of the users with the lost labels, and the label of the user is predicted to buy the target product;
the calculation module is used for acquiring a release result and calculating the user conversion rate of the release user according to the release result; the releasing result comprises the number of users of releasing users and the number of users who purchase the target product in the releasing users;
the user obtaining module is used for obtaining an initial user in the overlapped users when the user conversion rate is greater than a preset threshold value; the user tags of the initial users are all the target products for purchase;
the second determining module is used for acquiring a user portrait corresponding to the initial user in the first data party and determining a user identical to the user portrait as a target user;
and the second releasing module is used for releasing the target product to the target user.
9. A computer device comprising a memory having computer readable instructions stored therein and a processor that when executed performs the steps of the privacy-based product delivery method of any one of claims 1-7.
10. A computer-readable storage medium, having computer-readable instructions stored thereon, which, when executed by a processor, implement the steps of the privacy-based product delivery method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210321222.8A CN114663149A (en) | 2022-03-24 | 2022-03-24 | Product delivery method based on privacy protection and related equipment thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210321222.8A CN114663149A (en) | 2022-03-24 | 2022-03-24 | Product delivery method based on privacy protection and related equipment thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114663149A true CN114663149A (en) | 2022-06-24 |
Family
ID=82033424
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210321222.8A Pending CN114663149A (en) | 2022-03-24 | 2022-03-24 | Product delivery method based on privacy protection and related equipment thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114663149A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094032A (en) * | 2023-10-17 | 2023-11-21 | 成都乐超人科技有限公司 | User information encryption method and system based on privacy protection |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120323674A1 (en) * | 2009-08-14 | 2012-12-20 | Dataxu, Inc. | Creation and usage of synthetic user identifiers within an advertisement placement facility |
| WO2016100870A1 (en) * | 2014-12-18 | 2016-06-23 | Interdigital Technology Corporation | Methods and systems for reverse auctions and resource pooling for pervasive applications |
| CN106803190A (en) * | 2017-01-03 | 2017-06-06 | 北京掌阔移动传媒科技有限公司 | A kind of ad personalization supplying system and method |
| CN108205766A (en) * | 2016-12-19 | 2018-06-26 | 阿里巴巴集团控股有限公司 | Information-pushing method, apparatus and system |
| CN111652735A (en) * | 2020-04-17 | 2020-09-11 | 世纪保众(北京)网络科技有限公司 | Insurance product recommendation method based on user behavior label characteristics and commodity characteristics |
| 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 |
| CN112381568A (en) * | 2020-11-11 | 2021-02-19 | 苏宁云计算有限公司 | Target crowd circle selection method, target crowd circle selection model construction method and device |
| CN112765482A (en) * | 2020-12-23 | 2021-05-07 | 微民保险代理有限公司 | Product delivery method, device, equipment and computer readable medium |
| CN113032840A (en) * | 2021-05-26 | 2021-06-25 | 腾讯科技（深圳）有限公司 | Data processing method, device, equipment and computer readable storage medium |
| WO2021179720A1 (en) * | 2020-10-12 | 2021-09-16 | 平安科技（深圳）有限公司 | Federated-learning-based user data classification method and apparatus, and device and medium |
| CN113704599A (en) * | 2021-07-14 | 2021-11-26 | 大箴(杭州)科技有限公司 | Marketing conversion user prediction method and device and computer equipment |
| CN113763093A (en) * | 2020-11-12 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | User portrait-based item recommendation method and device |
| CN113793161A (en) * | 2020-07-07 | 2021-12-14 | 北京沃东天骏信息技术有限公司 | Advertisement delivery method, advertisement delivery device, readable storage medium and electronic device |
| CN114077749A (en) * | 2021-11-23 | 2022-02-22 | 润联软件***(深圳)有限公司 | Data processing method based on block chain and related equipment thereof |
-
2022
- 2022-03-24 CN CN202210321222.8A patent/CN114663149A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120323674A1 (en) * | 2009-08-14 | 2012-12-20 | Dataxu, Inc. | Creation and usage of synthetic user identifiers within an advertisement placement facility |
| WO2016100870A1 (en) * | 2014-12-18 | 2016-06-23 | Interdigital Technology Corporation | Methods and systems for reverse auctions and resource pooling for pervasive applications |
| CN108205766A (en) * | 2016-12-19 | 2018-06-26 | 阿里巴巴集团控股有限公司 | Information-pushing method, apparatus and system |
| CN106803190A (en) * | 2017-01-03 | 2017-06-06 | 北京掌阔移动传媒科技有限公司 | A kind of ad personalization supplying system and method |
| CN111652735A (en) * | 2020-04-17 | 2020-09-11 | 世纪保众(北京)网络科技有限公司 | Insurance product recommendation method based on user behavior label characteristics and commodity characteristics |
| 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 |
| CN113793161A (en) * | 2020-07-07 | 2021-12-14 | 北京沃东天骏信息技术有限公司 | Advertisement delivery method, advertisement delivery device, readable storage medium and electronic device |
| WO2021179720A1 (en) * | 2020-10-12 | 2021-09-16 | 平安科技（深圳）有限公司 | Federated-learning-based user data classification method and apparatus, and device and medium |
| CN112381568A (en) * | 2020-11-11 | 2021-02-19 | 苏宁云计算有限公司 | Target crowd circle selection method, target crowd circle selection model construction method and device |
| CN113763093A (en) * | 2020-11-12 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | User portrait-based item recommendation method and device |
| CN112765482A (en) * | 2020-12-23 | 2021-05-07 | 微民保险代理有限公司 | Product delivery method, device, equipment and computer readable medium |
| CN113032840A (en) * | 2021-05-26 | 2021-06-25 | 腾讯科技（深圳）有限公司 | Data processing method, device, equipment and computer readable storage medium |
| CN113704599A (en) * | 2021-07-14 | 2021-11-26 | 大箴(杭州)科技有限公司 | Marketing conversion user prediction method and device and computer equipment |
| CN114077749A (en) * | 2021-11-23 | 2022-02-22 | 润联软件***(深圳)有限公司 | Data processing method based on block chain and related equipment thereof |
Non-Patent Citations (1)
| Title |
|---|
| 申立艳等: "隐私保护集合交集计算技术研究综述", 计算机研究与发展, vol. 54, no. 10, 31 October 2017 (2017-10-31), pages 2153 - 2169 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094032A (en) * | 2023-10-17 | 2023-11-21 | 成都乐超人科技有限公司 | User information encryption method and system based on privacy protection |
| CN117094032B (en) * | 2023-10-17 | 2024-02-09 | 成都乐超人科技有限公司 | User information encryption method and system based on privacy protection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110245510B (en) | Method and apparatus for predicting information | |
| US10558984B2 (en) | Method, apparatus and server for identifying risky user | |
| US11238528B2 (en) | Systems and methods for custom ranking objectives for machine learning models applicable to fraud and credit risk assessments | |
| US20190147430A1 (en) | Customizing payment sessions with machine learning models | |
| CN111210335B (en) | User risk identification method and device and electronic equipment | |
| CN112148987A (en) | Message pushing method based on target object activity and related equipment | |
| CN113761577B (en) | Big data desensitization method, device, computer equipment and storage medium | |
| CN112861662B (en) | Target object behavior prediction method based on face and interactive text and related equipment | |
| CN107911449A (en) | Method and apparatus for pushed information | |
| US20230316129A1 (en) | Auxiliary implementation method and apparatus for online prediction using machine learning model | |
| CN114663149A (en) | Product delivery method based on privacy protection and related equipment thereof | |
| CN114780701A (en) | Automatic question-answer matching method, device, computer equipment and storage medium | |
| CN112507141A (en) | Investigation task generation method and device, computer equipment and storage medium | |
| US11303588B1 (en) | Automating a response to a message communicated to a business entity via an online messaging application | |
| CN112434746A (en) | Pre-labeling method based on hierarchical transfer learning and related equipment thereof | |
| CN117114901A (en) | Method, device, equipment and medium for processing insurance data based on artificial intelligence | |
| US20240095545A1 (en) | Data transmission between two systems to improve outcome predictions | |
| CN116860805A (en) | Data processing method, device, computer equipment and storage medium | |
| CN112348661B (en) | Service policy distribution method and device based on user behavior track and electronic equipment | |
| CN112085469B (en) | Data approval method, device, equipment and storage medium based on vector machine model | |
| CN114781368A (en) | Business requirement safety processing method and device | |
| CN114493850A (en) | Artificial intelligence-based online notarization method, system and storage medium | |
| CN114066603A (en) | Post-loan risk early warning method and device, electronic equipment and computer readable medium | |
| CN112669136A (en) | Financial product recommendation method, system, equipment and storage medium based on big data | |
| CN113742564A (en) | Target resource pushing method and device |
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 | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: Room 801, building 2, Shenzhen new generation industrial park, 136 Zhongkang Road, Meidu community, Meilin street, Futian District, Shenzhen, Guangdong 518000 Applicant after: China Resources Digital Technology Co.,Ltd. Address before: Room 801, building 2, Shenzhen new generation industrial park, 136 Zhongkang Road, Meidu community, Meilin street, Futian District, Shenzhen, Guangdong 518000 Applicant before: Runlian software system (Shenzhen) Co.,Ltd. Country or region before: China |