CN112991009A

CN112991009A - Object recommendation method and device, electronic equipment and storage medium

Info

Publication number: CN112991009A
Application number: CN202110251130.2A
Authority: CN
Inventors: 薛淼; 叶舟; 宋冠弢
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2021-03-08
Filing date: 2021-03-08
Publication date: 2021-06-18

Abstract

The embodiment of the invention provides an object recommendation method and device, electronic equipment and a storage medium. The object recommendation method of the embodiment of the invention comprises the following steps: obtaining user data authorized by a user; determining short-term interest characteristics of a current user according to behavior information of the current user; determining a user set and an object set similar to the current user according to the user information and the historical object information; determining the long-term interest characteristics of the current user according to the user set and the object set; inputting the short-term interest features and the long-term interest features into a recommendation model to determine a recommendation object, wherein the recommendation model is obtained by pre-training according to a plurality of user data; and sending the recommended object. According to the embodiment of the invention, the accuracy of the recommended object can be improved by determining the recommended object according to the short-term interest feature and the long-term interest feature.

Description

Object recommendation method and device, electronic equipment and storage medium

Technical Field

The embodiment of the invention relates to the technical field of computers, in particular to an object recommendation method, an object recommendation device, electronic equipment and a storage medium.

Background

With the continuous improvement of the living standard of people, the automobile becomes a common tool for riding instead of walk for people when going out. However, due to the long life and high price of automobiles, people purchase automobiles less frequently, resulting in less data related to automobile transactions for users, and the number of automobile purchases is only 1-2 for most users. In the process of predicting the purchasing intention of the user, the related purchasing intention of the user cannot be predicted according to the only purchasing information of the user. The automobile which the user wants cannot be pushed to the user accurately, so that the user cannot obtain the required automobile information efficiently. Therefore, it is desirable to provide a more accurate recommendation method to improve the accuracy of vehicle recommendations.

Disclosure of Invention

The embodiment of the invention is based on the above problems, and provides a new technical scheme, which determines the short-term interest characteristics of the current user according to the behavior information of the current user, determines the long-term interest characteristics of the user according to the historical object information of a plurality of user sets similar to the current user, and determines the recommendation object according to the short-term interest characteristics, the long-term interest characteristics and the recommendation model, so that the accuracy of the recommendation object is improved.

In view of this, according to a first aspect of the embodiments of the present invention, an object recommendation method is provided, where the object recommendation method includes:

obtaining user data authorized by a user, wherein the user data comprises user information, historical object information and related object information;

determining short-term interest characteristics of a current user according to behavior information of the current user;

determining a user set and an object set similar to the current user according to user information and historical object information, wherein the user set comprises users with similar attribute information, and the object set comprises a plurality of objects similar to historical objects;

determining the long-term interest characteristics of the current user according to the user set and the object set;

inputting the short-term interest features and the long-term interest features into a recommendation model to determine a recommendation object, wherein the recommendation model is obtained by pre-training according to a plurality of user data; and

and sending the recommended object.

Preferably, the determining the short-term interest characteristics of the current user according to the behavior information of the user includes:

and determining the short-term interest characteristics of the user according to the behavior information by adopting a graph embedding algorithm.

Preferably, the determining the long-term interest characteristics of the current user according to the historical object information of the similar users in the similar user set includes:

and determining the long-term interest characteristics of the user according to the user set and the object set by adopting a graph embedding algorithm.

Preferably, the determining a user set and an object set similar to the current user according to the user information and the historical object information includes:

determining a similar user set similar to the user information by adopting a clustering algorithm; and

and determining a similar object set similar to the historical object information by adopting a clustering algorithm.

Preferably, the recommendation model is obtained by taking the short-term interest features and the long-term interest features as input, taking historical object information as output and training by adopting a logistic regression algorithm or an extreme gradient boosting algorithm.

Preferably, before the obtaining of the user data authorized by the user, the object recommendation method further includes:

preprocessing user information and historical object information of a plurality of users, and storing the user information and the historical object information in a first database; and

preprocessing the user information and behavior information of the current user and storing the user information and behavior information into a second database;

the obtaining of the user data authorized by the user comprises:

acquiring user information and historical object information of a plurality of users from a first database; and

and acquiring the user information and the behavior information of the current user from the second database.

According to a second aspect of the embodiments of the present invention, there is provided an object recommendation apparatus, the apparatus including:

the data acquisition unit is used for acquiring user data authorized by a user, wherein the user data comprises user information, historical object information and related object information;

the short-term characteristic determining unit is used for determining the short-term interest characteristics of the current user according to the behavior information of the current user;

the clustering unit is used for determining a user set and an object set similar to the current user according to user information and historical object information, wherein the user set comprises users with similar attribute information, and the object set comprises a plurality of objects similar to historical objects;

the long-term characteristic determining unit is used for determining the long-term interest characteristic of the current user according to the user set and the object set;

the prediction unit is used for inputting the short-term interest characteristics and the long-term interest characteristics into a recommendation model to determine a recommendation object, and the recommendation model is obtained by pre-training according to a plurality of user data; and

and the sending unit is used for sending the recommended object.

Preferably, the short-term feature determination unit includes:

and the short-term feature determining subunit is used for determining the short-term interest features of the user according to the behavior information by adopting a graph embedding algorithm.

Preferably, the long-term feature determination unit includes:

and the long-term characteristic determining subunit is used for determining the long-term interest characteristics of the user according to the user set and the object set by adopting a graph embedding algorithm.

Preferably, the clustering unit includes:

the first clustering subunit is used for determining a similar user set similar to the user information by adopting a clustering algorithm; and

and the second clustering subunit is used for determining a similar object set similar to the historical object information by adopting a clustering algorithm.

Preferably, the object recommending apparatus further includes:

the system comprises a first preprocessing unit, a first database and a second preprocessing unit, wherein the first preprocessing unit is used for preprocessing user information and historical object information of a plurality of users and storing the user information and the historical object information into the first database;

the second preprocessing unit is used for preprocessing the user information and the behavior information of the current user and storing the user information and the behavior information into a second database;

the data acquisition unit includes:

the first data acquisition subunit is used for acquiring the user information and the historical object information of a plurality of users from a first database;

and the second data acquisition subunit is used for acquiring the user information and the behavior information of the current user from the second database.

According to a third aspect of embodiments of the present invention, a computer-readable storage medium is presented, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the method according to any of the first aspects.

According to a fourth aspect of embodiments of the present invention, an electronic device is presented, wherein the mobile terminal comprises a processor for implementing the method according to any of the first aspect when executing a computer program stored in a memory.

The object recommendation method of the embodiment of the invention comprises the following steps: obtaining user data authorized by a user; determining short-term interest characteristics of a current user according to behavior information of the current user; determining a user set and an object set similar to the current user according to the user information and the historical object information; determining the long-term interest characteristics of the current user according to the user set and the object set; inputting the short-term interest features and the long-term interest features into a recommendation model to determine a recommendation object, wherein the recommendation model is obtained by pre-training according to a plurality of user data; and sending the recommended object. According to the embodiment of the invention, the accuracy of the recommended object can be improved by determining the recommended object according to the short-term interest feature and the long-term interest feature.

Drawings

The above and other objects, features and advantages of the present invention will become more apparent from the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

FIG. 1 is a schematic diagram of an object recommendation system according to an embodiment of the present invention;

FIG. 2 is a flowchart illustrating an object recommendation method according to an embodiment of the present invention;

FIG. 3 is a schematic structural diagram of an object recommendation apparatus according to an embodiment of the present invention;

fig. 4 is a schematic diagram of an electronic device of an embodiment of the invention.

Detailed Description

The embodiments of the present invention are described below based on examples, but the embodiments of the present invention are not limited to only these examples. In the following detailed description of embodiments of the invention, certain specific details are set forth. It will be apparent to one skilled in the art that the present invention may be practiced without these specific details. Well-known methods, procedures, components and circuits have not been described in detail so as not to obscure the embodiments of the invention.

Further, those of ordinary skill in the art will appreciate that the drawings provided herein are for illustrative purposes and are not necessarily drawn to scale.

Unless the context clearly requires otherwise, in embodiments of the invention, the words "comprise", "comprising", and the like are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is, what is meant is "including, but not limited to".

In the description of the embodiments of the present invention, it is to be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the embodiments of the present invention, "a plurality" means two or more unless otherwise specified.

For an object with low purchase frequency, it is difficult to predict the object parameters that the user wants to purchase according to the less purchase data of the user, and the object parameters may include the brand and price of the object. In view of this, the embodiment of the present invention provides a recommendation method to improve the recommendation accuracy of an object with less purchase data.

It should be understood that the recommended object according to the embodiment of the present invention may be an automobile, a house, a large or medium-sized home appliance, or the like. In the following description, the recommended object is exemplified as an automobile.

In the embodiment of the invention, the object which the user may be interested in can be determined and recommended to the user through the human-computer interaction behavior and the network access behavior data of the plurality of target users recorded by the terminal side program based on the pre-trained recommendation model.

Fig. 1 is a schematic diagram of a recommendation system according to an embodiment of the present invention. As shown in fig. 1, the recommendation system includes: a plurality of terminal devices 1 and a server 2. The terminal device 1 may be a smart phone, a tablet Computer, a Personal Computer (PC), or the like, and the server 2 may be a single server, a server cluster configured in a distributed manner, or a cloud server. Data interaction is performed between a plurality of terminal devices 1 and a server 2 through a network 3.

In the embodiment of the present invention, the terminal device 1 may be a smart phone or a PC used by a user, and when the user uses the terminal device 1, data of a human-computer interaction behavior and a network access behavior are often generated, and the consumption habit, the purchasing tendency, and the like of the user can be determined by analyzing the data through the server 2 or the terminal device 1.

In some embodiments, the server 2 may include one or more processing engines (e.g., single core processing engines or multi-core processors). By way of example only, the server 2 may include one or more combinations of central processing units (cpus), Application Specific Integrated Circuits (ASICs), application specific instruction set processors (ASIPs), image processors (GPUs), physical arithmetic processing units (PPUs), Digital Signal Processors (DSPs), Field Programmable Gate Arrays (FPGAs), Programmable Logic Devices (PLDs), controllers, microcontroller units, Reduced Instruction Set Computers (RISCs), microprocessors, and the like.

In some embodiments, the network 3 may be any form of wired or wireless network, or any combination thereof. By way of example only, network 3 may be a wireline network, a fiber optic network, a telecommunications network, an intranet, the Internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Wide Area Network (WAN), a Public Switched Telephone Network (PSTN), a Bluetooth network, a ZigBee network, a Near Field Communication (NFC) network, a Global System for Mobile communications (GSM) network, a Code Division Multiple Access (CDMA) network, a Time Division Multiple Access (TDMA) network, a General Packet Radio Service (GPRS) network, an enhanced data rates for GSM evolution (EDGE) network, a Wideband Code Division Multiple Access (WCDMA) network, a High Speed Downlink Packet Access (HSDPA) network, a Long Term Evolution (LTE) network, a User Datagram Protocol (UDP) network, a Transmission control protocol/Internet protocol (TCP/IP) network, a Short Message Service (SMS) network, a Wireless Application Protocol (WAP), One or more combinations of ultra-wideband (UWB) networks, mobile communication (1G, 2G, 3G, 4G, 5G) networks, Wi-Fi, Li-Fi, narrowband Internet of things (NB-IoT), infrared communication, and the like.

Fig. 2 is a flowchart of an object recommendation method according to an embodiment of the present invention. As shown in fig. 2, the recommendation method according to the embodiment of the present invention includes the following steps:

step S210, obtaining user data authorized by the user, where the user data includes user information, historical object information, and behavior information.

In the embodiment, the user data is the raw data which is authorized to be obtained by the user and is stored in the database by preprocessing. The raw data may include attribute information, behavior information, and historical object information of the user. The attribute information may be personal information of the user, including information of age, sex, income, and whether there is a car. The behavior information may include behavior data of the user, including click, browse, and search information. The method specifically includes page information and browsing duration of an object browsed by a user, where the page information may include multiple pages such as a commodity home page browsed, a screen page, a detail page, an evaluation page, and a parameter page, and browsing duration staying on the page. Specifically, in the present embodiment, the object information may include information such as the brand, model, and price of the automobile. The history object information is information of a car that the user has used. The order record of the user in the trading platform can be obtained, and the order record can also be obtained through information input by the user. In an optional implementation manner, the behavior information of the user may further include information of a plurality of platforms that are authorized by the user, including information of behaviors such as taxi taking, taxi renting, designated driving and the like. And accordingly, the consumption habits of the user are evaluated.

In an optional embodiment, before the obtaining of the user data authorized by the user, the method further includes:

step S200, preprocessing the user data.

Specifically, the pretreatment comprises:

and preprocessing the user information and the historical object information of the plurality of users and storing the preprocessed user information and the historical object information into a first database. The user information includes user gender, age, income level, and the like. The history object information, that is, the automobile information historically purchased by the user, may include: car guide price, displacement, gearbox type, etc. Particularly, the Hive technology is adopted to store the offline data into the first database. hive is a data warehouse tool based on Hadoop, and can be used for data extraction, conversion and loading, in practical application, hive can be used for functions of storage, preprocessing and the like of big data, and a full-link processor can be used for storing and preprocessing basic data and representing data.

And preprocessing the user information and the behavior information of the current user and storing the user information and the behavior information into a second database. The user behavior information includes a real-time click sequence: home page, business details page, video page, etc. Particularly, a Redis technology is adopted to store real-time click data into a second database. Redis is a common cache management tool, and is often used for high-concurrency performance-demanding items due to its memory-reading property.

In the implementation manner, the obtaining of the user data authorized by the user specifically includes obtaining user information and historical object information of a plurality of users from the first database; and obtaining the user information and the behavior information of the current user from the second database.

Specifically, the method is mainly divided into continuous data preprocessing, discrete data preprocessing and statistical feature generation. The main processing of continuous data preprocessing is similar: and (4) processing the abnormal value (filling or treating as a vacancy value) according to characteristics such as vehicle cost price and bargain price. The discrete data preprocessing module is mainly used for preprocessing characteristics such as time, attributes and the like, the time characteristics are subjected to box separation processing according to days, weeks and months, and attribute characteristic encoding method or one-hot mode processing and the like are performed; the statistical feature generation specifically comprises the statistics times of the user who has made a special car, a quick car, accesses a car purchasing page and the like within a period of time in the past, and the structured data obtained by processing are respectively stored in a real-time Redis device and an offline hive big data storage device.

Step S220, determining the short-term interest characteristics of the current user according to the behavior information of the current user.

The determining the short-term interest characteristics of the current user according to the behavior information of the user comprises: and determining the short-term interest characteristics of the user according to the behavior information by adopting a Graph Embedding (Graph Embedding) algorithm. Specifically, the short-term behavior characteristics of the user are obtained by performing graph embedding processing on behavior data of the user within a predetermined time. The graph embedding process is specifically to input user data into a pre-trained graph embedding model, and the graph embedding method in the embodiment of the invention comprises the following steps: deep walking (Deep Walk), Node2Vec, Large-scale Information Network Embedding (LINE), and the like.

Step S230, determining a user set and an object set similar to the current user according to the user information and the historical object information. The set of users includes users with similar attribute information, and the set of objects includes a plurality of objects similar to the historical objects.

Specifically, similar users are determined by clustering according to the main characteristics of attribute information of the users and clicked vehicle types. And clustering by using characteristics such as the current behavior information of the user and the attribute information of the user. In an alternative implementation, users similar to the current user age, income and click behavior are determined as similar users according to a clustering algorithm. The specific click behavior may be browsing or purchasing a vehicle type similar to the vehicle type recently browsed by the user. And determining an object set similar to the vehicle type clicked by the current user by adopting a clustering algorithm. And clustering by taking the brand model or the price of the vehicle purchased by the similar user as main characteristics to determine the similar object.

In the step, low-frequency transaction records and irrelevant users can be removed through aggregation, irrelevant data can be reduced, and the prediction efficiency and the prediction precision are improved.

The Clustering algorithms may include K-Means Clustering algorithms (K-Means Clustering, K-Means), Mean Shift Clustering algorithms (Mean Shift), high-Density connected region based Clustering algorithms (Density-based Spatial Clustering of Applications with Noise, DBSCAN), and Hierarchical Clustering algorithms (Hierarchical Clustering).

Step S240, determining the long-term interest characteristics of the current user according to the user set and the object set.

Specifically, the information of each user in the user set is represented as a vector through a graph embedding algorithm process. Specifically, the set of users is represented as an embedded vector by solving function (1). Wherein, book is the positive set of click behaviors, neg is the negative set of click behaviors, v_cFor a certain period of time of the user's click behavior,

clicking behavior for the user at time t.

And representing the information of the vehicles in the object set as vectors through the graph embedding algorithm processing. Specifically, the set of objects is represented as an embedded vector by solving function (2). Wherein, book is the positive set of click behaviors, neg is the negative set of click behaviors, v_cFor a certain period of time of the user's click behavior,

the car is clicked at time t.

And connecting the embedding vector determined by the similar user set and the embedding vector determined by the similar object set to determine the long-term interest characteristics of the user. To represent a vector representation of a class of users' long-term interest in the vehicle consist. The embodiment of the invention uses the clustering method to express the long-term interest characteristics of the user group and the automobile group, and can avoid the problem of inaccurate prediction caused by less data of automobile purchasing of the user. Meanwhile, the dimensionality of data is reduced, and the prediction efficiency of the model can be improved.

Step S250, inputting the short-term interest characteristics and the long-term interest characteristics into a recommendation model to determine a recommendation object, wherein the recommendation model is obtained by pre-training according to a plurality of user data.

In an optional implementation manner, the recommendation model is obtained by taking a short-term interest feature and a long-term interest feature as input, taking a historical object as output, and training by adopting a Logistic Regression (LR) algorithm or a Gradient Boosting Decision Tree (GBDT) algorithm.

The LR algorithm is a model commonly used for classification tasks in machine learning, is a generalized linear regression analysis model in essence, and has the advantages of simple model structure, high training speed and good probability explanation on output variables. The XGboost algorithm is an extensible machine learning system, the system can be used as an open-source software package, meanwhile, the influence of the system is widely recognized in a large number of machine learning and data mining challenges, and in the embodiment of the invention, the XGboost can play a good classification role along with the continuous increase of the data volume. The history object is an object which is clicked or browsed by the user history.

In an alternative implementation mode, the model is trained by continuously inputting the data of the actual vehicle purchase of the user into the model again, so that the prediction capability of the model is continuously improved.

And step S260, sending the recommendation object.

Specifically, the recommendation object is sent to the user terminal for displaying.

The embodiment of the invention expresses the short-term interest characteristics and the long-term interest characteristics of the user based on the graph _ embedding technology, and predicts the click probability of the user on the automobile. The method provided by the embodiment of the invention can be accurately used for recommending the user to buy the car, is also suitable for recommending scenes of other low-frequency services, and has universality.

The embodiment of the invention is based on the graph _ embedding technology, not only considers the short-term interest characteristics of the user, but also expresses the long-term interest characteristics of the user set and the object set by using a clustering method, and has strong generalization adaptability by repeatedly iterating and grinding the recommendation model by using actual transaction data. And from the previous data collection to the representation of the model characteristic graph _ embedding, then, combining short-term and long-term interest characteristics to use the click probability prediction of the supervised model user group and the automobile group, finally forming an accurate recommended object, feeding back whether the recommended object is clicked to the model, and repeatedly polishing. The complete link is used for accurately and effectively expressing the interest of the user in the automobile, so that the proper automobile is recommended to the user, a new idea is provided for selling the automobile in the existing automobile selling industry, and a new idea is also provided for object recommendation in the low-frequency trading industry.

The object recommendation method of the embodiment of the invention comprises the following steps: obtaining user data authorized by a user; determining short-term interest characteristics of a current user according to behavior information of the current user; determining a user set and an object set similar to the current user according to the user information and the historical object information; determining the long-term interest characteristics of the current user according to the user set and the object set; inputting the short-term interest features and the long-term interest features into a recommendation model to determine a recommendation object, wherein the recommendation model is obtained by pre-training according to a plurality of user data; and sending the recommended object. According to the embodiment of the invention, the short-term interest characteristics and the long-term interest characteristics are input into the recommendation model to determine the recommendation object, so that the accuracy of the recommendation object can be improved.

Fig. 3 is a schematic structural diagram of an object recommendation apparatus according to an embodiment of the present invention. As shown in fig. 3, in an alternative implementation manner, an object recommendation apparatus according to an embodiment of the present invention includes: a data acquisition unit 310, a short-term feature determination unit 320, a clustering unit 330, a long-term feature determination unit 340, a prediction unit 350, and a transmission unit 360.

A data obtaining unit 310, configured to obtain user data authorized by a user, where the user data includes user information, historical object information, and related object information.

The data acquisition unit 310 includes: a first data acquisition subunit and a second data acquisition subunit.

The first data acquisition subunit is used for acquiring the user information and the history object information of a plurality of users from the first database.

The second data acquisition subunit is used for acquiring the user information and the behavior information of the current user from the second database.

The short-term feature determination unit 320 is configured to determine a short-term interest feature of the current user according to the behavior information of the current user.

The short-term feature determination unit 320 includes: a short term feature determination subunit.

The short-term feature determining subunit is used for determining the short-term interest features of the user according to the behavior information by adopting a graph embedding algorithm.

A clustering unit 330, configured to determine, according to the user information and the historical object information, a user set and an object set that are similar to the current user, where the user set includes users with similar attribute information, and the object set includes multiple objects that are similar to the historical object.

The clustering unit 330 includes: a first clustering subunit and a second clustering subunit.

The first clustering subunit is used for determining a similar user set similar to the user information by adopting a clustering algorithm.

The long-term feature determination unit 340 is configured to determine a long-term interest feature of the current user according to the user set and the object set.

The long-term feature determination unit includes: a long-term feature determination subunit.

The long-term feature determination subunit is used for determining the long-term interest features of the user according to the user set and the object set by adopting a graph embedding algorithm.

The prediction unit 350 is configured to input the short-term interest features and the long-term interest features into a recommendation model to determine a recommendation object, where the recommendation model is obtained by pre-training according to a plurality of user data.

The recommendation model is obtained by taking the short-term interest features and the long-term interest features as input, taking historical object information as output and training by adopting a logistic regression algorithm or an extreme gradient supercharging algorithm.

The sending unit 360 is configured to send the recommended object.

In another optional implementation manner, the object recommending apparatus further includes: a first preprocessing unit 300a and a second preprocessing unit 300 b.

The first preprocessing unit 300a is configured to preprocess user information and history object information of a plurality of users and store the preprocessed user information and history object information in a first database.

The second preprocessing unit 300b is configured to preprocess the user information and the behavior information of the current user, and store the user information and the behavior information in the second database.

Fig. 4 is a schematic diagram of an electronic device of an embodiment of the invention. As shown in fig. 4, the electronic device shown in fig. 4 is an object recommendation apparatus, which includes a general computer hardware structure, and at least includes a processor 401 and a memory 402. The processor 401 and the memory 402 are connected by a bus 403. The memory 402 is adapted to store instructions or programs executable by the processor 401. The processor 401 may be a stand-alone microprocessor or may be a collection of one or more microprocessors. Thus, the processor 401 implements the processing of data and the control of other devices by executing instructions stored by the memory 402 to perform the method flows of embodiments of the present invention as described above. The bus 403 connects the above components together, and also connects the above components to a display controller 404 and a display device and an input/output (I/O) device 405. Input/output (I/O) device 405 may be a mouse, keyboard, modem, network interface, touch input device, motion sensing input device, printer, and other devices known in the art. Typically, the input/output devices 405 are connected to the system through input/output (I/O) controllers 406.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus (device) or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may employ a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations of methods, apparatus (devices) and computer program products according to embodiments of the invention. It will be understood that each flow in the flow diagrams can be implemented by computer program instructions.

These computer program instructions may be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows.

These computer program instructions may also be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows.

Another embodiment of the invention is directed to a non-transitory storage medium storing a computer-readable program for causing a computer to perform some or all of the above-described method embodiments.

That is, those skilled in the art can understand that all or part of the steps in the method according to the above embodiments may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps in the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. All in the invention

The embodiment of the invention provides a TS1 and an object recommendation method, wherein the object recommendation method comprises the following steps:

and sending the recommended object.

TS2, the method of TS1, the determining short-term interest characteristics of the current user from user behavior information comprising:

TS3, the method of TS1, the determining long-term interest characteristics of the current user from historical object information of similar users in a set of similar users comprising:

TS4, the method of TS1, the determining a set of users and a set of objects similar to the current user from user information and historical object information comprising:

TS5, according to the method of TS1, the recommendation model is obtained by training through a logistic regression algorithm or an extreme gradient boosting algorithm with short-term interest features and long-term interest features as input and historical object information as output.

TS6, according to the method of TS1, before the obtaining user data authorized by a user, the object recommendation method further includes:

the obtaining of the user data authorized by the user comprises:

TS7, an object recommendation apparatus, the apparatus comprising:

and the sending unit is used for sending the recommended object.

TS8, the apparatus according to TS7, the short term feature determination unit comprising:

TS9, the apparatus according to TS7, the long term feature determination unit comprising:

TS10, the apparatus according to TS7, the clustering unit comprising:

TS11, according to the device of TS7, the recommendation model is obtained by training through a logistic regression algorithm or an extreme gradient boosting algorithm with short-term interest features and long-term interest features as input and historical object information as output.

TS12, the apparatus of claim TS7, the object recommendation apparatus further comprising:

the data acquisition unit includes:

TS13, a computer readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the method according to any one of TS1 to 6.

TS14, an electronic device comprising a processor for implementing the method as claimed in any of TS1 to 6 when executing a computer program stored in a memory.

TS15, a computer program product comprising computer programs/instructions which, when executed by a processor, implement the steps of the method of any one of TS1 to 6.

Claims

1. An object recommendation method, characterized in that the object recommendation method comprises:

and sending the recommended object.

2. The method of claim 1, wherein determining the short-term interest characteristics of the current user according to the behavior information of the user comprises:

3. The method of claim 1, wherein the determining the long-term interest characteristics of the current user according to the historical object information of the similar users in the set of similar users comprises:

4. The method of claim 1, wherein determining a set of users and a set of objects similar to the current user based on user information and historical object information comprises:

5. The method of claim 1, wherein the recommendation model is obtained by training with a logistic regression algorithm or an extreme gradient boosting algorithm with short-term interest features and long-term interest features as inputs and historical object information as outputs.

6. The method of claim 1, wherein before the obtaining of the user data authorized by the user, the object recommendation method further comprises:

the obtaining of the user data authorized by the user comprises:

7. An object recommendation apparatus, characterized in that the apparatus comprises:

and the sending unit is used for sending the recommended object.

8. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1 to 6.

9. An electronic device, characterized in that the electronic device comprises a processor for implementing the method according to any of claims 1 to 6 when executing a computer program stored in a memory.

10. A computer program product comprising computer program/instructions, characterized in that the computer program/instructions, when executed by a processor, implement the steps of the method of any of claims 1 to 6.