CN111079022A - Personalized recommendation method, device, equipment and medium based on federal learning - Google Patents
Personalized recommendation method, device, equipment and medium based on federal learning Download PDFInfo
- Publication number
- CN111079022A CN111079022A CN201911326853.3A CN201911326853A CN111079022A CN 111079022 A CN111079022 A CN 111079022A CN 201911326853 A CN201911326853 A CN 201911326853A CN 111079022 A CN111079022 A CN 111079022A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- personalized recommendation
- federal learning
- federal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9538—Presentation of query results
Abstract
The application discloses a personalized recommendation method, a personalized recommendation device and a personalized recommendation medium based on federal learning, wherein the personalized recommendation method based on federal learning comprises the following steps: receiving uploaded data, extracting a target recall set corresponding to the uploaded data from a preset recall set storage database, acquiring data to be predicted corresponding to the uploaded data and the target recall set together, inputting the data to be predicted into an individualized recommendation model acquired based on federal learning, acquiring a model output result, and screening the model output result to acquire an individualized recommendation result. The application solves the technical problem of poor personalized recommendation effect in the prior art.
Description
Technical Field
The application relates to the technical field of artificial intelligence of financial technology (Fintech), in particular to a personalized recommendation method, device, equipment and medium based on federal learning.
Background
With the continuous development of financial technologies, especially internet technology and finance, more and more technologies (such as distributed, Blockchain, artificial intelligence and the like) are applied to the financial field, but the financial industry also puts higher requirements on the technologies, such as higher requirements on the distribution of backlog of the financial industry.
With the continuous development of computer software and artificial intelligence, personalized recommendation technology is applied more and more widely, at present, personalized recommendation providers usually predict personalized behaviors or articles of users through data such as user attribute data, user behavior context data and the like acquired by own parties, for example, a mobile phone favored by the user is predicted, the webpage click rate of the user is predicted, and the like, but in the method, the feature richness of user data often has great influence on the prediction result, and along with the strictness of the data privacy protection legislation, the user data cannot be plaintext shared in all parties of different data, so the feature richness of the user data of a single personalized recommendation provider is often low, further the prediction precision of the personalized behaviors or articles of the user is low, further the personalized recommendation effect is poor, therefore, the technical problem of poor personalized recommendation effect exists in the prior art.
Disclosure of Invention
The application mainly aims to provide a method, a device, equipment and a medium for personalized recommendation based on federal learning, and aims to solve the technical problem that personalized recommendation effect is poor in the prior art.
In order to achieve the above object, an embodiment of the present application provides a personalized recommendation method based on federal learning, where the personalized recommendation method based on federal learning is applied to a personalized recommendation device based on federal learning, and the personalized recommendation method based on federal learning includes:
receiving uploaded data, and extracting a target recall set corresponding to the uploaded data from a preset recall set storage database;
acquiring data to be predicted, which corresponds to the uploaded data and the target recall set together, inputting the data to be predicted into an individualized recommendation model acquired based on the federal learning, and acquiring a model output result;
and screening the output result of the model to obtain an individualized recommendation result.
Optionally, the targeted recall set comprises a list of items to be recommended, the upload data comprises user data, item data and behavior data,
the step of obtaining data to be predicted, which corresponds to the uploaded data and the target recall set together, and inputting the data to be predicted into an individualized recommendation model obtained based on the federal learning, and obtaining a model output result includes:
screening the item data based on the item list to be recommended to obtain item data to be recommended, and setting the user data, the item data to be recommended and the behavior data as the data to be predicted;
and inputting the data to be predicted into the personalized recommendation model to grade and sort the articles to be recommended in the article list to be recommended, and obtaining a model output result.
Optionally, the step of inputting the data to be predicted into the personalized recommendation model to score and sort the items to be recommended in the item list to be recommended, and obtaining a model output result includes:
inputting the data to be predicted into the personalized recommendation model to grade the item to be recommended based on the user data and the behavior data to obtain a grading result;
and sequencing the articles to be recommended based on the scoring result to obtain a model output result.
Optionally, the personalized recommendation method based on the federal learning is applied to a first device performing the federal learning,
the step of obtaining the data to be predicted which corresponds to the upload data and the target recall set together, inputting the data to be predicted into an individualized recommendation model which is obtained based on the federal learning, and obtaining a model output result comprises the following steps:
performing sample matching with second equipment associated with the first equipment to obtain a public training sample ID (identity card identification number);
and obtaining the personalized recommendation model by interacting with the second device for federal learning based on the public training sample ID.
Optionally, the personalized recommendation model comprises a logistic regression model,
the step of obtaining the personalized recommendation model by interacting with the second device for federal learning based on the public training sample ID includes:
based on the public training sample ID, extracting first sample data corresponding to the public training sample ID, and calculating a first weight corresponding to the first sample data;
receiving a second weight value sent by the second equipment, calculating a gradient auxiliary variable corresponding to the first weight value and the second weight value together through a preset intermediate parameter formula, and sending the gradient auxiliary variable to the second equipment, wherein the second equipment is used for calculating a second gradient corresponding to the gradient auxiliary variable;
calculating a first gradient based on the gradient auxiliary variable, and sending the first gradient to a preset federal server, wherein the preset federal server is used for calculating a federal model total gradient based on the first gradient and a second gradient sent by the second equipment;
and receiving the total federal model gradient fed back by the federal server, and iteratively updating the local training model of the first device based on the total federal model gradient to obtain the logistic regression model.
Optionally, the step of receiving the uploaded data and extracting the target recall set corresponding to the uploaded data from a preset recall set storage database includes:
receiving upload data and extracting a sample ID in the upload data;
and inquiring a corresponding target recall set in the preset recall set storage database based on the sample ID.
Optionally, the personalized recommendation method based on the federal learning is applied to a first device performing the federal learning,
the step of receiving the uploaded data and extracting the target recalling set corresponding to the uploaded data from the preset recalling set storage database comprises the following steps:
performing federal learning on second equipment associated with the first equipment to obtain a federal recall algorithm model;
acquiring sample uploading data, inputting the sample uploading data into the federal recall algorithm model, acquiring a target recall set, and storing the target recall set in the preset recall set storage database.
The application also provides a personalized recommendation device based on federal learning, which is applied to personalized recommendation equipment based on federal learning, and comprises the following components:
the extraction module is used for receiving the uploaded data and extracting a target recall set corresponding to the uploaded data from a preset recall set storage database;
the prediction module is used for acquiring data to be predicted which corresponds to the uploaded data and the target recall set together, inputting the data to be predicted into an individualized recommendation model acquired based on the federal learning, and acquiring a model output result;
and the screening module is used for screening the output result of the model to obtain an individualized recommendation result.
Optionally, the prediction module comprises:
the screening unit is used for screening the item data based on the item list to be recommended to obtain item data to be recommended and setting the user data, the item data to be recommended and the behavior data as the data to be predicted;
and the prediction unit is used for inputting the data to be predicted into the personalized recommendation model so as to grade and sort the articles to be recommended in the article list to be recommended and obtain a model output result.
Optionally, the prediction unit comprises:
the scoring subunit is used for inputting the data to be predicted into the personalized recommendation model so as to score the item to be recommended based on the user data and the behavior data to obtain a scoring result;
and the sorting subunit is used for sorting the articles to be recommended based on the scoring result to obtain a model output result.
Optionally, the personalized recommendation device based on federal learning further includes:
the sample matching module is used for carrying out sample matching on the second equipment associated with the first equipment to obtain a public training sample ID;
and the first federal learning module is used for obtaining the personalized recommendation model by interacting with the second equipment for federal learning based on the public training sample ID.
Optionally, the federal learning module includes:
a first calculating unit, configured to extract, based on the public training sample ID, first sample data corresponding to the public training sample ID, and calculate a first weight corresponding to the first sample data;
the second calculating unit is configured to receive a second weight sent by the second device, calculate a gradient auxiliary variable corresponding to the first weight and the second weight together through a preset intermediate parameter formula, and send the gradient auxiliary variable to the second device, where the second device is configured to calculate a second gradient corresponding to the gradient auxiliary variable;
the third calculation unit is used for calculating a first gradient based on the gradient auxiliary variable and sending the first gradient to a preset federal server, wherein the preset federal server is used for calculating a federal model total gradient based on the first gradient and a second gradient sent by the second equipment;
and the iterative updating unit is used for receiving the total federal model gradient fed back by the federal server and iteratively updating the local training model of the first device based on the total federal model gradient to obtain the logistic regression model.
Optionally, the extraction module comprises:
the extraction unit is used for receiving the uploading data and extracting the sample ID in the uploading data;
and the query unit is used for querying a corresponding target recall set in the preset recall set storage database on the basis of the sample ID.
Optionally, the personalized recommendation device based on federal learning includes:
the second federated learning module is used for the second equipment associated with the first equipment to carry out federated learning to obtain a federated recall algorithm model;
and the storage module is used for acquiring the sample uploading data, inputting the sample uploading data into the federal recall algorithm model, acquiring a target recall set and storing the target recall set in the preset recall set storage database.
The application also provides personalized recommendation equipment based on federal learning, which comprises: the personalized recommendation method based on the federal learning comprises a memory, a processor and a program of the personalized recommendation method based on the federal learning, wherein the program of the personalized recommendation method based on the federal learning is stored in the memory and can run on the processor, and the program of the personalized recommendation method based on the federal learning can realize the steps of the personalized recommendation method based on the federal learning when being executed by the processor.
The application also provides a medium which is a readable storage medium, the medium is stored with a program for realizing the personalized recommendation method based on the federal learning, and the program for realizing the personalized recommendation method based on the federal learning realizes the steps of the personalized recommendation method based on the federal learning when being executed by a processor.
According to the method and the device, uploading data are received, the target recall set corresponding to the uploading data is extracted from a preset recall set storage database, then the uploading data and the data to be predicted corresponding to the target recall set are obtained, the data to be predicted are input based on the personalized recommendation model obtained through federal learning, a model output result is obtained, then the model output result is screened, and a personalized recommendation result is obtained. That is, according to the method and the device, firstly, uploaded data are received, then a target recall set corresponding to the uploaded data is extracted from a preset recall set storage database, then the uploaded data and the target recall set jointly correspond to data to be predicted, the data to be predicted are input into an individualized recommendation model obtained based on federal learning, a model output result is obtained, then the model output result is screened, and the individualized recommendation result is obtained. That is, according to the present application, after acquiring data to be predicted based on uploaded data and a target recall set, the personalized recommendation result of a user is predicted by inputting the data to be predicted into a personalized recommendation model acquired based on federal learning, wherein the personalized recommendation model is acquired based on federal learning, that is, training of the personalized recommendation model can be performed by combining multi-party data through the federal learning, so that the feature richness of a training sample of the personalized recommendation model is improved, and the data privacy of each data provider and data user is not revealed, so that the robustness and the universality of the personalized recommendation model are improved, the prediction accuracy of the personalized recommendation model is improved, the occurrence of poor personalized recommendation effect due to the prediction accuracy of the personalized recommendation model is avoided, and by inputting the data to be predicted into the personalized recommendation model acquired based on the federal learning, the model prediction effect of predicting by combining multi-party data is achieved under the condition of only using local data for prediction, the calculation amount during personalized recommendation is reduced, the response speed during personalized recommendation is further improved, and the personalized recommendation effect is enhanced, so that the technical problem of poor personalized recommendation effect is solved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a schematic flow chart illustrating a first embodiment of a personalized recommendation method based on federated learning according to the present application;
FIG. 2 is a flowchart illustrating a second embodiment of the personalized recommendation method based on federated learning according to the present application;
fig. 3 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present application.
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
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.
The embodiment of the application provides a personalized recommendation method based on federal learning, which is applied to personalized recommendation equipment based on federal learning, and in a first embodiment of the personalized recommendation method based on federal learning, referring to fig. 1, the personalized recommendation method based on federal learning comprises the following steps:
step S10, receiving the uploaded data, and extracting a target recall set corresponding to the uploaded data from a preset recall set storage database;
in this embodiment, it should be noted that the upload data includes a sample ID, user data, article data, and behavior data, where the upload data is uploaded by a client, the user data includes user natural attribute data, user interest attribute data, and the like, the article data includes data of an article name, an article attribute, and the like of an article to be recommended in a personalized manner, the behavior data includes behavior data of the article by a user and context data when a behavior occurs, for example, the behavior data of the article by the user includes browsing, clicking, and the like, the context data when a behavior occurs includes a geographic location, a network type, and the sample ID includes a user name, a user identification number, a user phone number, and the like.
Receiving upload data, extracting a target recall set corresponding to the upload data from a preset recall set storage database, specifically, receiving the upload data, and querying the target recall set corresponding to the user data in the preset recall set storage database based on the user data in the upload data, wherein the target recall set comprises one or more initial items to be recommended, and the initial items to be recommended refer to items which may be interested by a user.
The steps of receiving the uploaded data and extracting a target recall set corresponding to the uploaded data from a preset recall set storage database comprise:
step S11, receiving the uploaded data and extracting a sample ID in the uploaded data;
in this embodiment, it should be noted that the sample ID includes an identity tag such as a user ID and a character string, the upload data includes one or more data samples, and the data samples are represented by a preset data sample format, for example, "ID, label, user _ a _ feature _ i, item _ feature _ i, action _ i, and other _ a _ i" are a preset data sample format, where ID is a sample ID and label is a sample tag, where the sample tag identifies a type of the user, for example, the user is a good client or a bad client, user _ a _ feature _ i is user data, item _ feature _ i is article data, action _ i is behavior data, and other _ a _ i is other data.
Step S12, based on the sample ID, querying the preset recall set storage database for a corresponding target recall set.
In this embodiment, it should be noted that the sample ID includes an identity tag such as a user ID, a character string, and a phone number, that is, the sample ID may be represented by using a character string or may be directly represented by using a phone number.
And inquiring a corresponding target recall set in the preset recall set storage database based on the sample ID, specifically, taking the sample ID as a keyword, and retrieving in the preset recall set storage database to obtain the target recall set.
Wherein the personalized recommendation method based on the federal learning is applied to a first device for performing the federal learning,
the step of receiving the uploaded data and extracting the target recalling set corresponding to the uploaded data from the preset recalling set storage database comprises the following steps:
step A10, carrying out federal learning on a second device associated with the first device to obtain a federal recall algorithm model;
in this embodiment, it should be noted that the federal learning includes a vertical federal learning and a horizontal federal learning, and the first device and the second device may be communicatively connected.
Performing federal learning on a second device associated with the first device to obtain a federal recall algorithm model, specifically, performing sample alignment on the second device to perform sample alignment on a sample ID of the first device and a sample ID of the second device to obtain a common training sample ID, training a first training model of the first device based on uploaded data corresponding to the common training sample ID to obtain a first training result, calculating an error between the first training result and a theoretical training result, and performing partial derivation on a preset objective function based on the error and a network weight of the first training model to obtain a first gradient, wherein the preset objective function is a function of the error and the network weight, and further sending the first gradient to a preset federal server to advance the first gradient and a second gradient sent by the second device through the preset federal server based on preset federal rules And performing federation, obtaining a federation gradient, further receiving the federation gradient fed back by the preset federation server, and performing iterative update on the first training model based on the federation gradient to obtain the federation recall algorithm model, wherein the preset federation rule comprises a weighted average and the like, and the condition for stopping the iterative update comprises reaching the maximum iteration frequency, converging the model on a preset error threshold value and the like.
Step A20, obtaining sample uploading data, inputting the sample uploading data into the federal recall algorithm model, obtaining a target recall set, and storing the target recall set in the preset recall set storage database.
In this embodiment, it should be noted that the target recall set includes one or more target recalls, where each sample ID corresponds to a target recall.
Obtaining sample upload data, inputting the sample upload data into the federal recall algorithm model, obtaining a target recall set, storing the target recall set in the preset recall set storage database, and specifically obtaining sample upload data, wherein the sample upload data includes upload data of each user stored in the first device, each user corresponds to a sample ID, the upload data includes user data, item data, behavior data and the like, and further inputting the sample upload data into the federal recall algorithm model to predict items that may be interested by the user of the first device, obtain one or more items to be recommended, divide the items to be recommended corresponding to the same sample ID into one target recall set, obtain the target recall set, and store the target recall set in the preset recall set storage database, and the target recalling set is stored in the preset recalling set storage database in the forms of item lists, item sets and the like, and the query keyword corresponding to the target recalling set comprises a sample ID.
Step S20, obtaining data to be predicted which correspond to the uploaded data and the target recall set together, inputting the data to be predicted into an individualized recommendation model obtained based on the federal learning, and obtaining a model output result;
in this embodiment, it should be noted that two or more participants of federal learning are provided, where the participants include a first device and a second device, the personalized recommendation model obtained based on the federal learning includes a logistic regression model trained based on the federal learning, the output result of the model includes items to be recommended and their scores and ranks, and the data to be predicted includes user data, behavior data, and item data corresponding to the target recall set.
And specifically, the data to be predicted, which correspond to the uploaded data and the target recall set together, is input into an individualized recommendation model obtained based on the federal learning to obtain a model output result, and specifically, the data to be predicted, which correspond to the uploaded data and the target recall set together, is input into an individualized recommendation model obtained based on the federal learning to score and sort the articles to be recommended, which correspond to the target recall set, to obtain an article sorting list corresponding to the articles to be recommended and a score corresponding to the articles to be recommended, that is, to obtain a model output result.
Wherein the target recall set comprises a list of items to be recommended, the upload data comprises user data, item data and behavior data,
the step of obtaining data to be predicted, which corresponds to the uploaded data and the target recall set together, and inputting the data to be predicted into an individualized recommendation model obtained based on the federal learning, and obtaining a model output result includes:
step S21, screening the item data based on the item list to be recommended to obtain item data to be recommended, and setting the user data, the item data to be recommended and the behavior data as the data to be predicted;
in this embodiment, it should be noted that the items in the item to be recommended list are associated with the item data to be recommended.
Step S22, inputting the data to be predicted into the personalized recommendation model to grade and sort the items to be recommended in the item list to be recommended, and obtaining a model output result.
In this embodiment, the data to be predicted is input into the personalized recommendation model to score and sort the items to be recommended in the item list to be recommended, so as to obtain a model output result, specifically, the data to be predicted is input into the personalized recommendation model to score the items in the item list to be recommended based on the user data, the behavior data, and the item data to be recommended, so as to obtain a scoring result, and then the items in the item list to be recommended are sorted based on the scoring result, so as to obtain a model output result.
In step S22, the step of inputting the data to be predicted into the personalized recommendation model to score and sort the items to be recommended in the item list to be recommended, and obtaining a model output result includes:
step S221, inputting the data to be predicted into the personalized recommendation model, so as to grade the item to be recommended based on the user data and the behavior data, and obtaining a grading result;
in this embodiment, the data to be predicted is input into the personalized recommendation model to score the item to be recommended based on the user data and the behavior data to obtain a scoring result, specifically, the data to be predicted is input into the personalized recommendation model to score the item to be recommended based on the user data and the behavior data respectively to obtain a first scoring result and a second scoring result, and the scoring result is calculated based on the first scoring result and the second scoring result and according to a preset calculation rule, where the preset calculation rule includes weighted average, summation, product calculation, and the like, for example, if the calculation rule is summation, the first scoring result is 1 point, and the second scoring result is 2 points, the scoring result is 3 points.
Step S222, sequencing the articles to be recommended based on the scoring result, and obtaining a model output result.
In this embodiment, the items to be recommended are sorted based on the scoring result to obtain a model output result, and specifically, the scored items to be recommended are sorted in a preset sorting manner based on the scoring result, where the preset sorting manner includes sorting from small to large, sorting from large to small, and the like, so as to obtain a model output result.
And step S30, screening the output result of the model to obtain a personalized recommendation result.
In this embodiment, the model output result is filtered to obtain an individualized recommendation result, specifically, the model output result is filtered based on a preset service logic, and an article to be recommended in the model output result is extracted as the individualized recommendation result, for example, a preset number of articles with the highest score in the model output result is extracted as the individualized recommendation result.
According to the method, the uploaded data are received, the target recall set corresponding to the uploaded data is extracted from a preset recall set storage database, the data to be predicted which correspond to the uploaded data and the target recall set together are further obtained, the data to be predicted are input into the personalized recommendation model which is obtained based on federal learning, a model output result is obtained, and the model output result is further screened, so that the personalized recommendation result is obtained. That is, in this embodiment, first, the uploaded data is received, then, a target recall set corresponding to the uploaded data is extracted from a preset recall set storage database, then, the data to be predicted, which collectively correspond to the uploaded data and the target recall set, is obtained, the data to be predicted is input into an individualized recommendation model obtained based on the federal learning, a model output result is obtained, and then, the model output result is screened, so that an individualized recommendation result is obtained. That is, in the embodiment, after acquiring data to be predicted based on uploaded data and a target recall set, the data to be predicted is input into the personalized recommendation model acquired based on the federal learning, so as to predict the personalized recommendation result of the user, wherein the personalized recommendation model is acquired based on the federal learning, that is, the personalized recommendation model can be trained by combining multi-party data through the federal learning, so that the feature richness of the training sample of the personalized recommendation model is improved, the data privacy of each data provider and data user is not revealed, the robustness and the universality of the personalized recommendation model are improved, the prediction accuracy of the personalized recommendation model is improved, the occurrence of poor personalized recommendation effect caused by the prediction accuracy of the personalized recommendation model is avoided, and the data to be predicted is input into the personalized recommendation model acquired based on the federal learning, the model prediction effect of predicting by combining multi-party data is achieved under the condition of only using local data for prediction, the calculation amount during personalized recommendation is reduced, the response speed during personalized recommendation is further improved, and the personalized recommendation effect is enhanced, so that the technical problem of poor personalized recommendation effect is solved.
Further, referring to fig. 2, in another embodiment of the personalized recommendation method based on federal learning based on the first embodiment in the present application, the personalized recommendation method based on federal learning is applied to the first device for performing the federal learning,
the step of obtaining the data to be predicted which corresponds to the upload data and the target recall set together, inputting the data to be predicted into an individualized recommendation model which is obtained based on the federal learning, and obtaining a model output result comprises the following steps:
step B10, carrying out sample matching with a second device associated with the first device to obtain a public training sample ID;
in this embodiment, it should be noted that the public training sample ID includes an identity tag such as a user ID and an identification character string.
And performing sample matching on second equipment associated with the first equipment to obtain a public training sample ID, specifically, performing intersection processing on a first training sample ID in the first equipment and a second training sample ID in the second equipment to obtain a public training sample ID.
And step B20, based on the public training sample ID, obtaining the personalized recommendation model through interacting with the second equipment for federal learning.
In this embodiment, the personalized recommendation model is obtained by interacting with the second device for federal learning based on the public training sample ID, specifically, the first sample data corresponding to the public training sample ID is extracted based on the public training sample ID, the first gradient is obtained based on the first sample data, and then the second device is assisted to obtain the second gradient by interacting with the second device, and the first gradient is sent to a preset federal server, further, a total federal model gradient fed back by the preset federal server is received, wherein the total federal model gradient is obtained by the preset federal server by federating the first gradient and the second gradient sent by the second device according to preset federal rules, wherein the preset federal rules include weighted average, summation, and the like, and then, iteratively updating the first training model in the first equipment based on the total gradient of the federal model to obtain the personalized recommendation model.
Wherein the personalized recommendation model comprises a logistic regression model,
the step of obtaining the personalized recommendation model by interacting with the second device for federal learning based on the public training sample ID includes:
step B21, based on the public training sample ID, extracting first sample data corresponding to the public training sample ID, and calculating a first weight corresponding to the first sample data;
in this embodiment, it should be noted that the first sample data is upload data of a user client, the upload data includes one or more data samples, and the first weight is a product of a first sample feature corresponding to the first sample data and a first weight in the first training model, where the first weight is a network weight of the first training model, for example, it is assumed that the first weight is WBThe first sample is characterized by XBThen the first weight is WBXB。
Step B22, receiving a second weight sent by the second device, calculating a gradient auxiliary variable corresponding to the first weight and the second weight together through a preset intermediate parameter formula, and sending the gradient auxiliary variable to the second device, wherein the second device is used for calculating a second gradient corresponding to the gradient auxiliary variable;
in this embodiment, a second weight sent by the second device is received, a gradient auxiliary variable corresponding to the first weight and the second weight together is calculated through a preset intermediate parameter formula, and the gradient auxiliary variable is sent to the second device, where the second device is configured to calculate a second gradient corresponding to the gradient auxiliary variable, specifically, the second device receives a second weight sent by encrypting the second device, and decrypts the encrypted second weight to obtain a second weight, where the second weight is a product of a second sample characteristic corresponding to the second device and a second weight in a second training model in the second device, where the second weight is a network weight of the second training model, and further, the first weight and the second weight are combined to obtain a total weight corresponding to the first device and the second device together, and then substituting the total weight variable into the preset intermediate parameter formula to obtain the gradient auxiliary variable, and sending the gradient auxiliary variable to a second device, wherein the gradient auxiliary variable is associated with the sample label, the preset intermediate parameter formula is as follows,
wherein [ [ d ]]]For the gradient auxiliary variable, wTx is the total weight, y is the sample label, and y may take a value of 1 or-1, for example, when y is 1, it may indicate that the customer is a good customer, and when y is-1, it may indicate that the customer is a bad customer.
Step B23, calculating a first gradient based on the gradient auxiliary variable, and sending the first gradient to a preset federal server, wherein the preset federal server is used for calculating a federal model total gradient based on the first gradient and a second gradient sent by the second equipment;
in this embodiment, a first gradient is calculated based on the gradient auxiliary variable, and the first gradient is sent to a preset federal server, where the preset federal server is configured to calculate a federal model total gradient based on the first gradient and a second gradient sent by the second device, and specifically, calculate a product of the gradient auxiliary variable and a first sample characteristic to obtain the first gradient, where the first gradient can be calculated by the following formula,
wherein, gBIs the first sampling gradient, wTx is the total weight variable, y is the sample label, and y may take a value of 1 or-1, for example, when y is 1, it may indicate that the customer is a good customer, when y is-1, it may indicate that the customer is a bad customer, and xBAnd further, the first gradient is sent to a preset federal server so as to calculate a federal model total gradient corresponding to the first gradient and a second gradient sent by the second equipment through the preset federal server based on preset federal rules, wherein the preset federal rules comprise weighted averaging, summation and the like, and the second gradient is the product of the gradient auxiliary variable and the second sample characteristic.
And step B24, receiving the total federal model gradient fed back by the federal server, and performing iterative updating on the local training model of the first equipment based on the total federal model gradient to obtain the logistic regression model.
In this embodiment, it should be noted that the local training model is the first training model.
Receiving the federate model total gradient fed back by the federate server, iteratively updating the local training model of the first device based on the federate model total gradient to obtain the logistic regression model, specifically, receiving the federate model total gradient fed back by the federate server, training and updating the local training model of the first device based on the federate model total gradient, and judging whether the updated local training device reaches a preset training completion condition, if the updated local training device reaches the preset training completion condition, using the updated local training device as the logistic regression model, if the updated local training device does not reach the preset training completion condition, performing next federate learning to train and update the local training device until the local training device reaches the preset training completion condition, the training completion conditions comprise that the model reaches the maximum iteration number, the model error is smaller than a preset error threshold value and is converged, and the like.
In this embodiment, a public training sample ID is obtained by performing sample matching on a second device associated with the first device, and the personalized recommendation model is obtained by interacting with the second device for federal learning based on the public training sample ID. That is, in this embodiment, first, sample matching is performed on a second device associated with the first device to obtain a public training sample ID, and then, based on the public training sample ID, federal learning is performed by performing interaction with the second device to obtain the personalized recommendation model. That is, the embodiment provides a method for obtaining an individualized recommendation model through federal learning, that is, interaction with the second device is performed, so as to combine training sample data of the second device, federate learning is performed to obtain the individualized recommendation model, further feature richness of training samples of the individualized recommendation model is improved, further the individualized recommendation model is obtained through training of training samples with higher feature richness, robustness and universality of the individualized recommendation model are improved, further prediction accuracy of the individualized recommendation model is improved, further, data to be predicted is input into the individualized recommendation model obtained based on the federal learning, a model prediction effect of predicting by combining multi-party data can be achieved under the condition of predicting by using local data only, and calculation amount during individualized recommendation is reduced, and further, the response speed during personalized recommendation is improved, and the personalized recommendation effect is enhanced, so that the implementation lays a foundation for solving the technical problem of poor personalized recommendation effect.
Referring to fig. 3, fig. 3 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present application.
As shown in fig. 3, the personalized recommendation device based on federal learning may include: a processor 1001, such as a CPU, a memory 1005, and a communication bus 1002. The communication bus 1002 is used for realizing connection communication between the processor 1001 and the memory 1005. The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a memory device separate from the processor 1001 described above.
Optionally, the personalized recommendation device based on federal learning may further include a rectangular user interface, a network interface, a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a WiFi module, and the like. The rectangular user interface may comprise a Display screen (Display), an input sub-module such as a Keyboard (Keyboard), and the optional rectangular user interface may also comprise a standard wired interface, a wireless interface. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface).
Those skilled in the art will appreciate that the structure of the personalized recommendation device based on federal learning shown in fig. 3 does not constitute a limitation of the personalized recommendation device based on federal learning, and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 3, the memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, and a personalized recommendation program based on federal learning. The operating system is a program for managing and controlling hardware and software resources of the personalized recommendation device based on the federal learning, and supports the running of the personalized recommendation program based on the federal learning and other software and/or programs. The network communication module is used for realizing communication among components in the memory 1005 and communication with other hardware and software in the personalized recommendation system based on federal learning.
In the personalized recommendation device based on federal learning shown in fig. 3, the processor 1001 is configured to execute a personalized recommendation program based on federal learning stored in the memory 1005, and implement the steps of any one of the personalized recommendation methods based on federal learning described above.
The specific implementation mode of the personalized recommendation device based on federal learning is basically the same as that of each embodiment of the personalized recommendation method based on federal learning, and details are not repeated here.
The embodiment of the present application further provides a personalized recommendation device based on federal learning, and the personalized recommendation device based on federal learning includes:
the extraction module is used for receiving the uploaded data and extracting a target recall set corresponding to the uploaded data from a preset recall set storage database;
the prediction module is used for acquiring data to be predicted which corresponds to the uploaded data and the target recall set together, inputting the data to be predicted into an individualized recommendation model acquired based on the federal learning, and acquiring a model output result;
and the screening module is used for screening the output result of the model to obtain an individualized recommendation result.
Optionally, the prediction module comprises:
the screening unit is used for screening the item data based on the item list to be recommended to obtain item data to be recommended and setting the user data, the item data to be recommended and the behavior data as the data to be predicted;
and the prediction unit is used for inputting the data to be predicted into the personalized recommendation model so as to grade and sort the articles to be recommended in the article list to be recommended and obtain a model output result.
Optionally, the prediction unit comprises:
the scoring subunit is used for inputting the data to be predicted into the personalized recommendation model so as to score the item to be recommended based on the user data and the behavior data to obtain a scoring result;
and the sorting subunit is used for sorting the articles to be recommended based on the scoring result to obtain a model output result.
Optionally, the personalized recommendation device based on federal learning further includes:
the sample matching module is used for carrying out sample matching on the second equipment associated with the first equipment to obtain a public training sample ID;
and the first federal learning module is used for obtaining the personalized recommendation model by interacting with the second equipment for federal learning based on the public training sample ID.
Optionally, the federal learning module includes:
a first calculating unit, configured to extract, based on the public training sample ID, first sample data corresponding to the public training sample ID, and calculate a first weight corresponding to the first sample data;
the second calculating unit is configured to receive a second weight sent by the second device, calculate a gradient auxiliary variable corresponding to the first weight and the second weight together through a preset intermediate parameter formula, and send the gradient auxiliary variable to the second device, where the second device is configured to calculate a second gradient corresponding to the gradient auxiliary variable;
the third calculation unit is used for calculating a first gradient based on the gradient auxiliary variable and sending the first gradient to a preset federal server, wherein the preset federal server is used for calculating a federal model total gradient based on the first gradient and a second gradient sent by the second equipment;
and the iterative updating unit is used for receiving the total federal model gradient fed back by the federal server and iteratively updating the local training model of the first device based on the total federal model gradient to obtain the logistic regression model.
Optionally, the extraction module comprises:
the extraction unit is used for receiving the uploading data and extracting the sample ID in the uploading data;
and the query unit is used for querying a corresponding target recall set in the preset recall set storage database on the basis of the sample ID.
Optionally, the personalized recommendation device based on federal learning includes:
the second federated learning module is used for the second equipment associated with the first equipment to carry out federated learning to obtain a federated recall algorithm model;
and the storage module is used for acquiring the sample uploading data, inputting the sample uploading data into the federal recall algorithm model, acquiring a target recall set and storing the target recall set in the preset recall set storage database.
The specific implementation manner of the personalized recommendation device based on federal learning in the application is basically the same as that of each embodiment of the personalized recommendation method based on federal learning, and is not described herein again.
The present application provides a medium, which is a readable storage medium and stores one or more programs, where the one or more programs are further executable by one or more processors for implementing the steps of any one of the above personalized recommendation methods based on federal learning.
The specific implementation manner of the medium of the application is basically the same as that of each embodiment of the personalized recommendation method based on federal learning, and is not described herein again.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings, or which are directly or indirectly applied to other related technical fields, are included in the scope of the present application.
Claims (10)
1. The personalized recommendation method based on the federal learning is characterized by comprising the following steps:
receiving uploaded data, and extracting a target recall set corresponding to the uploaded data from a preset recall set storage database;
acquiring data to be predicted, which corresponds to the uploaded data and the target recall set together, inputting the data to be predicted into an individualized recommendation model acquired based on the federal learning, and acquiring a model output result;
and screening the output result of the model to obtain an individualized recommendation result.
2. The personalized recommendation method based on federal learning of claim 1, wherein the target recall set includes a list of items to be recommended, the upload data includes user data, item data and behavior data,
the step of obtaining data to be predicted, which corresponds to the uploaded data and the target recall set together, and inputting the data to be predicted into an individualized recommendation model obtained based on the federal learning, and obtaining a model output result includes:
screening the item data based on the item list to be recommended to obtain item data to be recommended, and setting the user data, the item data to be recommended and the behavior data as the data to be predicted;
and inputting the data to be predicted into the personalized recommendation model to grade and sort the articles to be recommended in the article list to be recommended, and obtaining a model output result.
3. The personalized recommendation method based on federal learning as claimed in claim 2, wherein the step of inputting the data to be predicted into the personalized recommendation model to score and sort the items to be recommended in the item list to be recommended, and obtaining the output result of the model comprises:
inputting the data to be predicted into the personalized recommendation model to grade the item to be recommended based on the user data and the behavior data to obtain a grading result;
and sequencing the articles to be recommended based on the scoring result to obtain a model output result.
4. The personalized recommendation method based on federal learning of claim 1, wherein the personalized recommendation method based on federal learning is applied to a first device performing the federal learning,
the step of obtaining the data to be predicted which corresponds to the upload data and the target recall set together, inputting the data to be predicted into an individualized recommendation model which is obtained based on the federal learning, and obtaining a model output result comprises the following steps:
carrying out sample matching with second equipment associated with the first equipment to obtain a public training sample ID;
and obtaining the personalized recommendation model by interacting with the second device for federal learning based on the public training sample ID.
5. The personalized recommendation method based on federated learning of claim 4, wherein the personalized recommendation model comprises a logistic regression model,
the step of obtaining the personalized recommendation model by interacting with the second device for federal learning based on the public training sample ID includes:
based on the public training sample ID, extracting first sample data corresponding to the public training sample ID, and calculating a first weight corresponding to the first sample data;
receiving a second weight value sent by the second equipment, calculating a gradient auxiliary variable corresponding to the first weight value and the second weight value together through a preset intermediate parameter formula, and sending the gradient auxiliary variable to the second equipment, wherein the second equipment is used for calculating a second gradient corresponding to the gradient auxiliary variable;
calculating a first gradient based on the gradient auxiliary variable, and sending the first gradient to a preset federal server, wherein the preset federal server is used for calculating a federal model total gradient based on the first gradient and a second gradient sent by the second equipment;
and receiving the total federal model gradient fed back by the federal server, and iteratively updating the local training model of the first device based on the total federal model gradient to obtain the logistic regression model.
6. The personalized recommendation method based on federal learning as claimed in claim 1, wherein the step of receiving the upload data and extracting the target recalls corresponding to the upload data from a preset recall set storage database comprises:
receiving upload data and extracting a sample ID in the upload data;
and inquiring a corresponding target recall set in the preset recall set storage database based on the sample ID.
7. The personalized recommendation method based on federal learning of claim 1, wherein the personalized recommendation method based on federal learning is applied to a first device performing the federal learning,
the step of receiving the uploaded data and extracting the target recalling set corresponding to the uploaded data from the preset recalling set storage database comprises the following steps:
performing federal learning on second equipment associated with the first equipment to obtain a federal recall algorithm model;
acquiring sample uploading data, inputting the sample uploading data into the federal recall algorithm model, acquiring a target recall set, and storing the target recall set in the preset recall set storage database.
8. A personalized recommendation device based on federal learning is characterized in that the personalized recommendation device based on federal learning comprises:
the extraction module is used for receiving the uploaded data and extracting a target recall set corresponding to the uploaded data from a preset recall set storage database;
the prediction module is used for acquiring data to be predicted which corresponds to the uploaded data and the target recall set together, inputting the data to be predicted into an individualized recommendation model acquired based on the federal learning, and acquiring a model output result;
and the screening module is used for screening the output result of the model to obtain an individualized recommendation result.
9. A personalized recommendation device based on federal learning, characterized in that the personalized recommendation device based on federal learning comprises: a memory, a processor, and a program stored on the memory for implementing the federal learning based personalized recommendation method,
the memory is used for storing a program for realizing the personalized recommendation method based on the federal learning;
the processor is configured to execute a program for implementing the personalized recommendation method based on federal learning so as to implement the steps of the personalized recommendation method based on federal learning according to any one of claims 1 to 7.
10. A medium having a program for implementing the federal learning based personalized recommendation method stored thereon, the program being executed by a processor to implement the steps of the federal learning based personalized recommendation method as claimed in any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911326853.3A CN111079022B (en) | 2019-12-20 | 2019-12-20 | Personalized recommendation method, device, equipment and medium based on federal learning |
| PCT/CN2020/135030 WO2021121106A1 (en) | 2019-12-20 | 2020-12-09 | Federated learning-based personalized recommendation method, apparatus and device, and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911326853.3A CN111079022B (en) | 2019-12-20 | 2019-12-20 | Personalized recommendation method, device, equipment and medium based on federal learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111079022A true CN111079022A (en) | 2020-04-28 |
| CN111079022B CN111079022B (en) | 2023-10-03 |
Family
ID=70316309
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911326853.3A Active CN111079022B (en) | 2019-12-20 | 2019-12-20 | Personalized recommendation method, device, equipment and medium based on federal learning |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111079022B (en) |
| WO (1) | WO2021121106A1 (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111291417A (en) * | 2020-05-09 | 2020-06-16 | 支付宝(杭州)信息技术有限公司 | Method and device for protecting data privacy of multi-party combined training object recommendation model |
| CN111859136A (en) * | 2020-07-23 | 2020-10-30 | 深圳前海微众银行股份有限公司 | Personalized recommendation method, device, equipment and readable storage medium |
| CN111897800A (en) * | 2020-08-05 | 2020-11-06 | 全球能源互联网研究院有限公司 | Electric vehicle charging facility recommendation method and system based on federal learning |
| CN112287231A (en) * | 2020-11-05 | 2021-01-29 | 深圳大学 | Method and device for acquiring Federation recommendation gradient, intelligent terminal and storage medium |
| CN112449009A (en) * | 2020-11-12 | 2021-03-05 | 深圳大学 | SVD-based federated learning recommendation system communication compression method and device |
| CN112836830A (en) * | 2021-02-01 | 2021-05-25 | 广西师范大学 | Method for voting and training in parallel by using federated gradient boosting decision tree |
| CN112966182A (en) * | 2021-03-09 | 2021-06-15 | 中国民航信息网络股份有限公司 | Project recommendation method and related equipment |
| WO2021121106A1 (en) * | 2019-12-20 | 2021-06-24 | 深圳前海微众银行股份有限公司 | Federated learning-based personalized recommendation method, apparatus and device, and medium |
| CN113313268A (en) * | 2021-06-11 | 2021-08-27 | 杭州煋辰数智科技有限公司 | Federal learning-based prediction method and device, storage medium and remote sensing equipment |
| CN113656681A (en) * | 2021-07-08 | 2021-11-16 | 北京奇艺世纪科技有限公司 | Object evaluation method, device, equipment and storage medium |
| CN113704555A (en) * | 2021-07-16 | 2021-11-26 | 杭州医康慧联科技股份有限公司 | Feature management method based on medical direction federal learning |
| CN113781134A (en) * | 2020-07-28 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Item recommendation method and device and computer-readable storage medium |
| CN114969486A (en) * | 2022-08-02 | 2022-08-30 | 平安科技（深圳）有限公司 | Corpus recommendation method, apparatus, device and storage medium |
| CN115169576A (en) * | 2022-06-24 | 2022-10-11 | 上海富数科技有限公司广州分公司 | Model training method and device based on federal learning and electronic equipment |
| CN115238065A (en) * | 2022-09-22 | 2022-10-25 | 太极计算机股份有限公司 | Intelligent document recommendation method based on federal learning |
| CN117454185A (en) * | 2023-12-22 | 2024-01-26 | 深圳市移卡科技有限公司 | Federal model training method, federal model training device, federal model training computer device, and federal model training storage medium |
| CN117493662A (en) * | 2023-10-09 | 2024-02-02 | 上海及未科技有限公司 | Personalized recommendation method and system based on federal learning |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113762532B (en) * | 2021-06-28 | 2024-04-05 | 京东科技控股股份有限公司 | Training method and device of federal learning model, electronic equipment and storage medium |
| CN113627496A (en) * | 2021-07-27 | 2021-11-09 | 交控科技股份有限公司 | Method, device, electronic equipment and readable storage medium for predicting fault of turnout switch machine |
| CN113642707B (en) * | 2021-08-12 | 2023-08-18 | 深圳平安智汇企业信息管理有限公司 | Model training method, device, equipment and storage medium based on federal learning |
| CN113722738B (en) * | 2021-09-02 | 2023-08-08 | 脸萌有限公司 | Data protection method, device, medium and electronic equipment |
| CN113569151B (en) * | 2021-09-18 | 2021-12-17 | 平安科技（深圳）有限公司 | Data recommendation method, device, equipment and medium based on artificial intelligence |
| CN113902473A (en) * | 2021-09-29 | 2022-01-07 | 支付宝(杭州)信息技术有限公司 | Training method and device of business prediction system |
| CN114363176B (en) * | 2021-12-20 | 2023-08-08 | 中山大学 | Network identification method, device, terminal and medium based on federal learning |
| CN114969503B (en) * | 2022-03-30 | 2024-04-02 | 贵州大学 | Multi-data user portrait realizing method based on federal learning |
| CN114676851B (en) * | 2022-04-08 | 2024-03-29 | 中国科学技术大学 | Combined training method, equipment and storage medium for recall and sequence model |
| CN114741611B (en) * | 2022-06-08 | 2022-10-14 | 杭州金智塔科技有限公司 | Federal recommendation model training method and system |
| CN114863499B (en) * | 2022-06-30 | 2022-12-13 | 广州脉泽科技有限公司 | Finger vein and palm vein identification method based on federal learning |
| CN114996317B (en) * | 2022-07-05 | 2024-02-23 | 中国电信股份有限公司 | Asynchronous optimization method and device based on longitudinal federal learning and storage medium |
| CN116629374B (en) * | 2023-04-13 | 2023-12-26 | 南京大学 | Searching and multiplexing method for heterogeneous feature space learning piece |
| CN117076783B (en) * | 2023-10-16 | 2023-12-26 | 广东省科技基础条件平台中心 | Scientific and technological information recommendation method, device, medium and equipment based on data analysis |
| CN117421486B (en) * | 2023-12-18 | 2024-03-19 | 杭州金智塔科技有限公司 | Recommendation model updating system and method based on spherical tree algorithm and federal learning |
| CN117592042B (en) * | 2024-01-17 | 2024-04-05 | 杭州海康威视数字技术股份有限公司 | Privacy disclosure detection method and device for federal recommendation system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160379128A1 (en) * | 2015-06-26 | 2016-12-29 | Xerox Corporation | Distributed and privacy-preserving prediction method |
| WO2019090954A1 (en) * | 2017-11-07 | 2019-05-16 | 华为技术有限公司 | Prediction method, and terminal and server |
| US20190182059A1 (en) * | 2017-12-12 | 2019-06-13 | Facebook, Inc. | Utilizing machine learning from exposed and non-exposed user recall to improve digital content distribution |
| CN110134868A (en) * | 2019-05-14 | 2019-08-16 | 辽宁工程技术大学 | A kind of recommended method based on the analysis of user preference isomerism |
| CN110297848A (en) * | 2019-07-09 | 2019-10-01 | 深圳前海微众银行股份有限公司 | Recommended models training method, terminal and storage medium based on federation's study |
| CN110428058A (en) * | 2019-08-08 | 2019-11-08 | 深圳前海微众银行股份有限公司 | Federal learning model training method, device, terminal device and storage medium |
| CN110443063A (en) * | 2019-06-26 | 2019-11-12 | 电子科技大学 | The method of the federal deep learning of self adaptive protection privacy |
| CN110458663A (en) * | 2019-08-06 | 2019-11-15 | 上海新共赢信息科技有限公司 | A kind of vehicle recommended method, device, equipment and storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11093873B2 (en) * | 2018-03-30 | 2021-08-17 | Atlassian Pty Ltd. | Using a productivity index and collaboration index for validation of recommendation models in federated collaboration systems |
| CN110110229B (en) * | 2019-04-25 | 2021-06-04 | 深圳前海微众银行股份有限公司 | Information recommendation method and device |
| CN111079022B (en) * | 2019-12-20 | 2023-10-03 | 深圳前海微众银行股份有限公司 | Personalized recommendation method, device, equipment and medium based on federal learning |
-
2019
- 2019-12-20 CN CN201911326853.3A patent/CN111079022B/en active Active
-
2020
- 2020-12-09 WO PCT/CN2020/135030 patent/WO2021121106A1/en active Application Filing
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160379128A1 (en) * | 2015-06-26 | 2016-12-29 | Xerox Corporation | Distributed and privacy-preserving prediction method |
| WO2019090954A1 (en) * | 2017-11-07 | 2019-05-16 | 华为技术有限公司 | Prediction method, and terminal and server |
| US20190182059A1 (en) * | 2017-12-12 | 2019-06-13 | Facebook, Inc. | Utilizing machine learning from exposed and non-exposed user recall to improve digital content distribution |
| CN110134868A (en) * | 2019-05-14 | 2019-08-16 | 辽宁工程技术大学 | A kind of recommended method based on the analysis of user preference isomerism |
| CN110443063A (en) * | 2019-06-26 | 2019-11-12 | 电子科技大学 | The method of the federal deep learning of self adaptive protection privacy |
| CN110297848A (en) * | 2019-07-09 | 2019-10-01 | 深圳前海微众银行股份有限公司 | Recommended models training method, terminal and storage medium based on federation's study |
| CN110458663A (en) * | 2019-08-06 | 2019-11-15 | 上海新共赢信息科技有限公司 | A kind of vehicle recommended method, device, equipment and storage medium |
| CN110428058A (en) * | 2019-08-08 | 2019-11-08 | 深圳前海微众银行股份有限公司 | Federal learning model training method, device, terminal device and storage medium |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021121106A1 (en) * | 2019-12-20 | 2021-06-24 | 深圳前海微众银行股份有限公司 | Federated learning-based personalized recommendation method, apparatus and device, and medium |
| CN111291417A (en) * | 2020-05-09 | 2020-06-16 | 支付宝(杭州)信息技术有限公司 | Method and device for protecting data privacy of multi-party combined training object recommendation model |
| CN111859136A (en) * | 2020-07-23 | 2020-10-30 | 深圳前海微众银行股份有限公司 | Personalized recommendation method, device, equipment and readable storage medium |
| CN111859136B (en) * | 2020-07-23 | 2024-03-15 | 深圳前海微众银行股份有限公司 | Personalized recommendation method, device, equipment and readable storage medium |
| CN113781134A (en) * | 2020-07-28 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Item recommendation method and device and computer-readable storage medium |
| CN111897800A (en) * | 2020-08-05 | 2020-11-06 | 全球能源互联网研究院有限公司 | Electric vehicle charging facility recommendation method and system based on federal learning |
| CN111897800B (en) * | 2020-08-05 | 2021-06-22 | 全球能源互联网研究院有限公司 | Electric vehicle charging facility recommendation method and system based on federal learning |
| CN112287231A (en) * | 2020-11-05 | 2021-01-29 | 深圳大学 | Method and device for acquiring Federation recommendation gradient, intelligent terminal and storage medium |
| CN112287231B (en) * | 2020-11-05 | 2024-04-05 | 深圳大学 | Federal recommendation gradient acquisition method and device, intelligent terminal and storage medium |
| CN112449009A (en) * | 2020-11-12 | 2021-03-05 | 深圳大学 | SVD-based federated learning recommendation system communication compression method and device |
| CN112836830A (en) * | 2021-02-01 | 2021-05-25 | 广西师范大学 | Method for voting and training in parallel by using federated gradient boosting decision tree |
| CN112836830B (en) * | 2021-02-01 | 2022-05-06 | 广西师范大学 | Method for voting and training in parallel by using federated gradient boosting decision tree |
| CN112966182A (en) * | 2021-03-09 | 2021-06-15 | 中国民航信息网络股份有限公司 | Project recommendation method and related equipment |
| CN112966182B (en) * | 2021-03-09 | 2024-02-09 | 中国民航信息网络股份有限公司 | Project recommendation method and related equipment |
| CN113313268A (en) * | 2021-06-11 | 2021-08-27 | 杭州煋辰数智科技有限公司 | Federal learning-based prediction method and device, storage medium and remote sensing equipment |
| CN113656681B (en) * | 2021-07-08 | 2023-08-11 | 北京奇艺世纪科技有限公司 | Object evaluation method, device, equipment and storage medium |
| CN113656681A (en) * | 2021-07-08 | 2021-11-16 | 北京奇艺世纪科技有限公司 | Object evaluation method, device, equipment and storage medium |
| CN113704555A (en) * | 2021-07-16 | 2021-11-26 | 杭州医康慧联科技股份有限公司 | Feature management method based on medical direction federal learning |
| CN113704555B (en) * | 2021-07-16 | 2023-11-07 | 杭州医康慧联科技股份有限公司 | Feature management method based on medical direction federal learning |
| CN115169576A (en) * | 2022-06-24 | 2022-10-11 | 上海富数科技有限公司广州分公司 | Model training method and device based on federal learning and electronic equipment |
| CN115169576B (en) * | 2022-06-24 | 2024-02-09 | 上海富数科技有限公司 | Model training method and device based on federal learning and electronic equipment |
| CN114969486A (en) * | 2022-08-02 | 2022-08-30 | 平安科技（深圳）有限公司 | Corpus recommendation method, apparatus, device and storage medium |
| CN115238065A (en) * | 2022-09-22 | 2022-10-25 | 太极计算机股份有限公司 | Intelligent document recommendation method based on federal learning |
| CN117493662A (en) * | 2023-10-09 | 2024-02-02 | 上海及未科技有限公司 | Personalized recommendation method and system based on federal learning |
| CN117454185B (en) * | 2023-12-22 | 2024-03-12 | 深圳市移卡科技有限公司 | Federal model training method, federal model training device, federal model training computer device, and federal model training storage medium |
| CN117454185A (en) * | 2023-12-22 | 2024-01-26 | 深圳市移卡科技有限公司 | Federal model training method, federal model training device, federal model training computer device, and federal model training storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111079022B (en) | 2023-10-03 |
| WO2021121106A1 (en) | 2021-06-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111079022B (en) | Personalized recommendation method, device, equipment and medium based on federal learning | |
| CN109819284B (en) | Short video recommendation method and device, computer equipment and storage medium | |
| CN106296059B (en) | Method and equipment for determining delivery network points | |
| US10878044B2 (en) | System and method for providing content recommendation service | |
| WO2017071251A1 (en) | Information pushing method and device | |
| JP2020509449A (en) | Method and device for warning | |
| CN107105031A (en) | Information-pushing method and device | |
| US20200356572A1 (en) | Search ranking method and apparatus, electronic device and storage medium | |
| US20140095308A1 (en) | Advertisement distribution apparatus and advertisement distribution method | |
| CN105306495B (en) | user identification method and device | |
| CN110020162B (en) | User identification method and device | |
| US10606910B2 (en) | Ranking search results using machine learning based models | |
| CN103368992A (en) | Message push method and device | |
| US20210248198A1 (en) | Content Recommendation Method and Apparatus, Mobile Terminal, and Server | |
| CN107885783B (en) | Method and device for obtaining high-correlation classification of search terms | |
| CN102541853A (en) | Method and device which are capable of obtaining application information by utilizing browser address bar | |
| CN108776692A (en) | Method and apparatus for handling information | |
| CN108600329B (en) | Method and equipment for pushing information and displaying information | |
| CN107977678A (en) | Method and apparatus for output information | |
| CN105095253A (en) | Webpage display method and webpage display device | |
| CN112330382A (en) | Item recommendation method and device, computing equipment and medium | |
| CN113378067B (en) | Message recommendation method, device and medium based on user mining | |
| CN112825089A (en) | Article recommendation method, article recommendation device, article recommendation equipment and storage medium | |
| JP6680663B2 (en) | Information processing apparatus, information processing method, prediction model generation apparatus, prediction model generation method, and program | |
| CN112381236A (en) | Data processing method, device, equipment and storage medium for federal transfer learning |
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 |