CN117453988A - Product recommendation method and device - Google Patents

Product recommendation method and device Download PDF

Info

Publication number
CN117453988A
CN117453988A CN202210846271.3A CN202210846271A CN117453988A CN 117453988 A CN117453988 A CN 117453988A CN 202210846271 A CN202210846271 A CN 202210846271A CN 117453988 A CN117453988 A CN 117453988A
Authority
CN
China
Prior art keywords
product
user
model
behavior data
acquiring
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210846271.3A
Other languages
Chinese (zh)
Inventor
金均生
齐浩
王昆垚
李健
戴移胜
陈广朋
王宝
陈航
王名茗
黄茂仰
高嵩
张国威
王珮
许瀚
赵夕炜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Wodong Tianjun Information Technology Co Ltd
Original Assignee
Beijing Wodong Tianjun Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Wodong Tianjun Information Technology Co Ltd filed Critical Beijing Wodong Tianjun Information Technology Co Ltd
Priority to CN202210846271.3A priority Critical patent/CN117453988A/en
Publication of CN117453988A publication Critical patent/CN117453988A/en
Pending legal-status Critical Current

Links

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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses a product recommendation method and device, and relates to the technical field of search recommendation. One embodiment of the method comprises the following steps: responding to a product recommendation request of a user, acquiring a product set to be ordered and user behavior data according to a user identifier, and processing the user behavior data through a user feature model to generate user features; acquiring the product characteristics of each product to be sequenced according to the product set to be sequenced; generating a product sorting result through a product sorting model according to the user characteristics and the product characteristics of each product to be sorted; and determining at least one product to be recommended from the product set to be sequenced according to the product sequencing result, and recommending the product to be recommended to the user. According to the method and the device for recommending the product, hysteresis of user data can be avoided, calculation time of product recommendation is reduced, efficiency of product recommendation is improved, compression of the user data is not needed, a pre-estimated model can be updated, and accuracy of user characteristics and effect of product recommendation are improved.

Description

Product recommendation method and device
Technical Field
The invention relates to the technical field of search recommendation, in particular to a product recommendation method and device.
Background
The product recommendation is to recommend the product related to the user through the user data, so that personalized product recommendation requirements can be met. The current recommended product proposal is to recall and coarse-rank products according to the pre-generated user characteristics and product characteristics, and select products with higher matching degree with the user characteristics from the coarse-rank products to recommend to the user.
In the process of implementing the present invention, the inventor finds that at least the following problems exist in the prior art:
pre-generated user characteristics can cause the system to have difficulty in responding to rapid changes in data distribution, so that hysteresis exists in recommendation; user characteristics generated based on compressed user data cannot completely represent the user characteristics, and accuracy is poor, so that the effect of product recommendation is affected.
Disclosure of Invention
In view of the above, the embodiment of the invention provides a product recommendation method and device, which can calculate user characteristics by using real-time user data through a front-end calculation module while recalling and roughly arranging products, can avoid the hysteresis of the user data, reduce the calculation time of product recommendation, improve the efficiency of product recommendation, and can update a prediction model without compressing the user data, thereby improving the accuracy of the user characteristics and the effect of product recommendation.
In order to achieve the above object, according to an aspect of the embodiments of the present invention, there is provided a product recommendation method.
A product recommendation method comprising: responding to a product recommendation request of a user, acquiring a product set to be ordered and user behavior data according to a user identifier, and processing the user behavior data through a user feature model to generate user features; acquiring the product characteristics of each product to be sequenced according to the product set to be sequenced; generating a product sorting result through a product sorting model according to the user characteristics and the product characteristics of each product to be sorted; and determining at least one product to be recommended from the product set to be sequenced according to the product sequencing result, and recommending the product to be recommended to the user.
Optionally, the obtaining the product set to be ranked and the user behavior data according to the user identifier, and processing the user behavior data through a user feature model to generate user features includes: constructing a product acquisition request and a user characteristic modeling request according to the user identifier; acquiring a product set to be ordered corresponding to the user identifier according to the product acquisition request; and acquiring user behavior data according to the user feature modeling request, and processing the user behavior data through a user feature model to generate user features.
Optionally, the obtaining the user behavior data according to the user feature modeling request and processing the user behavior data through a user feature model to generate the user feature includes: acquiring user behavior data corresponding to the user identification according to the user characteristic modeling request; extracting feature data required by modeling from the user behavior data; and inputting the characteristic data into a user characteristic model for calculation to obtain the user characteristics.
Optionally, before the obtaining the product features of each product to be sorted according to the set of products to be sorted, the method further includes: acquiring user session data triggering the product recommendation request according to the user identifier; and screening the to-be-sequenced product set according to the user session data to delete to-be-sequenced products with the association degree with the user session data smaller than a set threshold value.
Optionally, the user feature model and the product ordering model are obtained by logically splitting an estimated model, and are merged and deployed together.
Optionally, after recommending the product to be recommended to the user, the method further includes: respectively acquiring a calculation log of the user characteristic model, a sequencing log of the product sequencing model and an operation log of the user on the product to be recommended; and retraining the pre-estimated model according to the calculation log, the sequencing log and the operation log so as to update the pre-estimated model.
According to another aspect of the embodiment of the invention, a product recommendation device is provided.
A product recommendation device, comprising: the user characteristic generating module is used for responding to a product recommendation request of a user, acquiring a product set to be ordered and user behavior data according to a user identifier, and processing the user behavior data through a user characteristic model to generate user characteristics; the product characteristic acquisition module is used for acquiring the product characteristics of each product to be sequenced according to the product set to be sequenced; the product sorting module is used for generating a product sorting result through a product sorting model according to the user characteristics and the product characteristics of each product to be sorted; and the product recommending module is used for determining at least one product to be recommended from the product to be sequenced set according to the product sequencing result, and recommending the product to be recommended to the user.
Optionally, the user feature generation module is further configured to: constructing a product acquisition request and a user characteristic modeling request according to the user identifier; acquiring a product set to be ordered corresponding to the user identifier according to the product acquisition request; and acquiring user behavior data according to the user feature modeling request, and processing the user behavior data through a user feature model to generate user features.
Optionally, the user feature generation module is further configured to: acquiring user behavior data corresponding to the user identification according to the user characteristic modeling request; extracting feature data required by modeling from the user behavior data; and inputting the characteristic data into a user characteristic model for calculation to obtain the user characteristics.
Optionally, the product screening module is further included for: acquiring user session data triggering the product recommendation request according to the user identifier; and screening the to-be-sequenced product set according to the user session data to delete to-be-sequenced products with the association degree with the user session data smaller than a set threshold value.
Optionally, the user feature model and the product ordering model are obtained by logically splitting an estimated model, and are merged and deployed together.
Optionally, the method further comprises a model training module for: respectively acquiring a calculation log of the user characteristic model, a sequencing log of the product sequencing model and an operation log of the user on the product to be recommended; and retraining the pre-estimated model according to the calculation log, the sequencing log and the operation log so as to update the pre-estimated model.
According to yet another aspect of an embodiment of the present invention, an electronic device is provided.
An electronic device, comprising: one or more processors; and the memory is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are enabled to realize the product recommendation method provided by the embodiment of the invention.
According to yet another aspect of an embodiment of the present invention, a computer-readable medium is provided.
A computer readable medium having stored thereon a computer program which, when executed by a processor, implements a product recommendation method provided by an embodiment of the present invention.
One embodiment of the above invention has the following advantages or benefits: acquiring a product set to be ordered and user behavior data according to a user identifier by responding to a product recommendation request of a user, and processing the user behavior data through a user feature model to generate user features; acquiring the product characteristics of each product to be sequenced according to the product set to be sequenced; generating a product sorting result through a product sorting model according to the user characteristics and the product characteristics of each product to be sorted; according to the technical scheme, the user characteristics can be calculated by using real-time user data through the user characteristic model of the front-end calculation module while recalling and roughly arranging the products, so that the hysteresis of the user data can be avoided, the calculation time of product recommendation is reduced, the efficiency of product recommendation is improved, the user data is not required to be compressed, the estimated model can be updated, and the accuracy of the user characteristics and the effect of product recommendation are improved.
Further effects of the above-described non-conventional alternatives are described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a schematic diagram of the main steps of a product recommendation method according to one embodiment of the invention;
FIG. 2 is a schematic flow diagram of generating user features and recall products in parallel, according to one embodiment of the invention;
FIG. 3 is a flow diagram of product ordering according to one embodiment of the invention;
FIG. 4 is a flow diagram of updating a predictive model in accordance with one embodiment of the invention;
FIG. 5 is a flow chart of a product recommendation method according to one embodiment of the invention;
FIG. 6 is a schematic diagram of the main modules of a product recommendation device according to one embodiment of the present invention;
FIG. 7 is an exemplary system architecture diagram in which embodiments of the present invention may be applied;
fig. 8 is a schematic diagram of a computer system suitable for use in implementing an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present invention are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic diagram of main steps of a product recommendation method according to an embodiment of the present invention.
As shown in fig. 1, the product recommendation method according to an embodiment of the present invention mainly includes the following steps S101 to S104.
Step S101: and responding to a product recommendation request of a user, acquiring a product set to be ordered and user behavior data according to a user identifier, and processing the user behavior data through a user feature model to generate user features.
In one embodiment, the user feature model and the product ordering model may be obtained by logically splitting the pre-estimated model and are merged and deployed together. Specifically, the embodiment of the invention designs a front-end computing module (namely a module of a user characteristic model) and a module of a product ordering model by splitting and secondarily developing a CTR estimation model (click rate estimation model), and can deploy a long-sequence user history behavior modeling service in the front-end computing module and parallelize the computing process and the recall process. The traditional offline and near-line two-stage calculation solution is difficult to guarantee due to the consistency of data, and the advantage of deep learning end-to-end real-time training is difficult to play, but the embodiment of the invention realizes the two-stage calculation while guaranteeing the unification of the data by logically splitting and merging and deploying the pre-estimated model, and can support the end-to-end solution.
FIG. 2 is a schematic flow diagram of generating user features and recall products in parallel, according to one embodiment of the invention.
As shown in fig. 2, in one embodiment, obtaining a product set to be ranked and user behavior data according to a user identifier, and processing the user behavior data through a user feature model to generate a user feature may include: constructing a product acquisition request and a user characteristic modeling request according to the user identifier; acquiring a product set to be ordered corresponding to the user identifier according to the product acquisition request; and acquiring user behavior data according to the user feature modeling request, and processing the user behavior data through a user feature model to generate user features. Specifically, the product recommendation request includes a user identifier, and after receiving the product recommendation request (i.e., a model estimation request), a pre-calculation request (i.e., a user feature modeling request) and a recall request (i.e., a product acquisition request) are respectively constructed according to the product recommendation request, wherein the pre-calculation request includes the user feature modeling request identifier and the user identifier, and the recall request includes the user identifier.
In one embodiment, obtaining user behavior data according to a user feature modeling request and processing the user behavior data through a user feature model to generate user features may include: acquiring user behavior data corresponding to a user identifier according to a user feature modeling request; extracting feature data required by modeling from user behavior data; and inputting the feature data into a user feature model for calculation to obtain the user features. Specifically, user behavior data corresponding to the user identifier is obtained through the user identifier in the pre-calculation request, feature data (such as user behavior data within one year) required by behavior modeling is extracted from the user behavior data, then the feature data is input to a pre-calculation module, the pre-calculation module deploys a user historical behavior modeling service, and a user behavior modeling result (namely user feature) is generated through calculation by the pre-calculation module. The user identification is user identification information, and the user behavior data comprises multidimensional behavior data such as browsing, purchasing and collecting of the user.
Step S102: and obtaining the product characteristics of each product to be sequenced according to the product set to be sequenced.
The product characteristics of each product to be ranked can be generated according to the product set to be ranked through a user ranking model or a pre-estimation model.
In one embodiment, before obtaining the product characteristics of each product to be ordered according to the set of products to be ordered, the method may further include: acquiring user session data triggering a product recommendation request according to a user identifier; screening the product to be sorted set according to the user session data to delete the products to be sorted, the association degree of which with the user session data is smaller than a set threshold value. Specifically, the corresponding user session data is obtained through the user identifier in the recall request, the product is recalled through the user session data, the product set to be ordered is obtained, and the user session data can be browsing information of the user and the like. And then roughly ranking the products in the product set to be ranked through the user session data, namely matching each product in the product set to be ranked according to the user session data, generating the association degree of each product and the user session data, deleting the product to be ranked, of which the association degree with the user session data is smaller than a set threshold value, and reserving the product to be ranked, of which the association degree with the user session data is greater than or equal to the set threshold value, wherein the set threshold value can be set according to experience.
Step S103: and generating a product sorting result through a product sorting model according to the user characteristics and the product characteristics of each product to be sorted.
FIG. 3 is a flow chart of product ordering according to one embodiment of the invention.
As shown in FIG. 3, in one embodiment, the user behavior modeling results (i.e., user features) and recall coarse ranking results (i.e., product features of the products to be ranked) are combined, a product ranking request (i.e., fine ranking request) is generated, and fine ranking scheduling is performed. Inputting the user features and the product features into a product sorting model, generating a matching score of each product to be sorted, sorting the products to be sorted according to the sequence of the matching score from high to low, taking the preset number of the products to be sorted which are arranged in front as the products to be recommended, or taking the products to be sorted with the matching score larger than a preset score threshold as the products to be recommended.
Step S104: and determining at least one product to be recommended from the product set to be sequenced according to the product sequencing result, and recommending the product to be recommended to the user.
After recommending the product to be recommended to the user, the method can further comprise: respectively acquiring a calculation log of a user characteristic model and a sequencing log of a product sequencing model, and an operation log of a user to-be-recommended product; and retraining the estimated model according to the calculation log, the sequencing log and the operation log to update the estimated model.
FIG. 4 is a flow chart of updating a predictive model in accordance with one embodiment of the invention.
As shown in fig. 4, in one embodiment, after recommending the product to be recommended to the user, a calculation log of the user feature model and a sorting log of the product sorting model are respectively obtained, and an operation log of the product to be recommended by the user includes operation information such as browsing information, clicking information and the like of the user for each product to be recommended. Training the pre-estimated model through the calculation log, the sequencing log and the operation log to update the pre-estimated model, thereby improving the calculation accuracy of the pre-estimated model.
Fig. 5 is a flow chart of a product recommendation method according to an embodiment of the present invention.
As shown in FIG. 5, in one embodiment, a user request (i.e., a product recommendation request) including a user identifier is received, a pre-calculation module calculates user characteristics according to the user identifier, and a product to be ordered collection is obtained according to recall and coarse-ranking of the user identifier, so as to generate product characteristics of each product to be ordered. And combining the user characteristics with the product characteristics of each product to be sequenced to obtain a product sequencing request, and sequencing the product by using a product sequencing model to obtain each product to be recommended.
The embodiment of the invention provides a front-end computing scheme based on distributed machine learning, which can complete a long-user historical behavior modeling process under the condition of strict time-consuming constraint, improves the accuracy of model estimation, can be used for deploying long-time user behavior modeling service, can be used for other modeling processes without related characteristics of a product to be estimated, greatly reduces the time consumption required for completing the model estimation process, and reserves sufficient time-consuming space for a model with more complex time-consuming constraint service deployment computing process and better effect.
Fig. 6 is a schematic diagram of main modules of a product recommendation device according to an embodiment of the present invention.
As shown in fig. 6, a product recommendation device 600 according to an embodiment of the present invention mainly includes: a user feature generation module 601, a product feature acquisition module 602, a product ordering module 603, and a product recommendation module 604.
The user feature generation module 601 is configured to obtain a product set to be ranked and user behavior data according to a user identifier in response to a product recommendation request of a user, and process the user behavior data through a user feature model to generate user features.
The product feature acquiring module 602 is configured to acquire a product feature of each product to be ordered according to the set of products to be ordered.
The product sorting module 603 is configured to generate a product sorting result according to the user characteristics and the product characteristics of each product to be sorted through the product sorting model.
The product recommending module 604 is configured to determine at least one product to be recommended from the set of products to be sequenced according to the product sequencing result, and recommend the product to be recommended to the user.
In one embodiment, the user feature generation module 601 is further configured to: constructing a product acquisition request and a user characteristic modeling request according to the user identifier; acquiring a product set to be ordered corresponding to the user identifier according to the product acquisition request; and acquiring user behavior data according to the user feature modeling request, and processing the user behavior data through a user feature model to generate user features.
In one embodiment, the user feature generation module 601 is further configured to: acquiring user behavior data corresponding to a user identifier according to a user feature modeling request; extracting feature data required by modeling from user behavior data; and inputting the feature data into a user feature model for calculation to obtain the user features.
In one embodiment, the system further comprises a product screening module (not shown) for: acquiring user session data triggering a product recommendation request according to a user identifier; screening the product to be sorted set according to the user session data to delete the products to be sorted, the association degree of which with the user session data is smaller than a set threshold value.
In one embodiment, the user feature model and the product ordering model are obtained by logically splitting the pre-estimated model and are merged and deployed together.
In one embodiment, the system further comprises a model training module (not shown in the figure) for: respectively acquiring a calculation log of a user characteristic model and a sequencing log of a product sequencing model, and an operation log of a user to-be-recommended product; and retraining the estimated model according to the calculation log, the sequencing log and the operation log to update the estimated model.
In addition, the specific implementation of the product recommendation device in the embodiment of the present invention has been described in detail in the above product recommendation method, so the description thereof will not be repeated here.
FIG. 7 illustrates an exemplary system architecture 700 to which a product recommendation method or device of embodiments of the present invention may be applied.
As shown in fig. 7, a system architecture 700 may include terminal devices 701, 702, 703, a network 704, and a server 705. The network 704 is the medium used to provide communication links between the terminal devices 701, 702, 703 and the server 705. The network 704 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
A user may interact with the server 705 via the network 704 using the terminal devices 701, 702, 703 to receive or send messages or the like. Various communication client applications such as shopping class applications, web browser applications, search class applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only) may be installed on the terminal devices 701, 702, 703.
The terminal devices 701, 702, 703 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.
The server 705 may be a server providing various services, such as a background management server (by way of example only) providing support for shopping-type websites browsed by users using the terminal devices 701, 702, 703. The background management server can respond to the received data such as the product recommendation request and the like to obtain a product set to be ordered and user behavior data according to the user identification, and process the user behavior data through a user feature model to generate user features; acquiring the product characteristics of each product to be sequenced according to the product set to be sequenced; generating a product sorting result through a product sorting model according to the user characteristics and the product characteristics of each product to be sorted; according to the product sorting result, determining at least one product to be recommended from the product set to be sorted, recommending the product to be recommended to a user and the like, and feeding back the processing result (such as a product recommending result-only an example) to the terminal device.
It should be noted that, the product recommending method provided in the embodiment of the present invention is generally executed by the server 705, and accordingly, the product recommending apparatus is generally disposed in the server 705.
It should be understood that the number of terminal devices, networks and servers in fig. 7 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 8, there is illustrated a schematic diagram of a computer system 800 suitable for use in implementing a terminal device or server in accordance with an embodiment of the present invention. The terminal device or server shown in fig. 8 is only an example, and should not impose any limitation on the functions and scope of use of the embodiments of the present invention.
As shown in fig. 8, the computer system 800 includes a Central Processing Unit (CPU) 801 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 802 or a program loaded from a storage section 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the system 800 are also stored. The CPU 801, ROM 802, and RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to the bus 804.
The following components are connected to the I/O interface 805: an input portion 806 including a keyboard, mouse, etc.; an output portion 807 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and a speaker; a storage section 808 including a hard disk or the like; and a communication section 809 including a network interface card such as a LAN card, a modem, or the like. The communication section 809 performs communication processing via a network such as the internet. The drive 810 is also connected to the I/O interface 805 as needed. A removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 810 as needed so that a computer program read out therefrom is mounted into the storage section 808 as needed.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 809, and/or installed from the removable media 811. The above-described functions defined in the system of the present invention are performed when the computer program is executed by a Central Processing Unit (CPU) 801.
The computer readable medium shown in the present invention may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules involved in the embodiments of the present invention may be implemented in software or in hardware. The described modules may also be provided in a processor, for example, as: a processor comprises a user feature generation module, a product feature acquisition module, a product ordering module and a product recommendation module. The names of these modules do not limit the module itself in some cases, for example, the user feature generation module may also be described as "a module for acquiring a set of products to be ranked and user behavior data according to a user identifier in response to a product recommendation request of a user, and processing the user behavior data to generate a user feature through a user feature model".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be present alone without being fitted into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to include: responding to a product recommendation request of a user, acquiring a product set to be ordered and user behavior data according to a user identifier, and processing the user behavior data through a user feature model to generate user features; acquiring the product characteristics of each product to be sequenced according to the product set to be sequenced; generating a product sorting result through a product sorting model according to the user characteristics and the product characteristics of each product to be sorted; and determining at least one product to be recommended from the product set to be sequenced according to the product sequencing result, and recommending the product to be recommended to the user.
According to the technical scheme of the embodiment of the invention, in response to a product recommendation request of a user, a product set to be ordered and user behavior data are obtained according to a user identifier, and the user behavior data are processed through a user feature model to generate user features; acquiring the product characteristics of each product to be sequenced according to the product set to be sequenced; generating a product sorting result through a product sorting model according to the user characteristics and the product characteristics of each product to be sorted; and determining at least one product to be recommended from the product set to be sequenced according to the product sequencing result, and recommending the product to be recommended to the user. The method and the device have the advantages that the user characteristics can be calculated by using real-time user data through the front-end calculation module while the products are recalled and roughly arranged, the hysteresis of the user data can be avoided, the calculation time of product recommendation is reduced, the efficiency of product recommendation is improved, the user data is not required to be compressed, the estimated model can be updated, and the accuracy of the user characteristics and the effect of product recommendation are improved.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives can occur depending upon design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims (10)

1. A method of product recommendation, comprising:
responding to a product recommendation request of a user, acquiring a product set to be ordered and user behavior data according to a user identifier, and processing the user behavior data through a user feature model to generate user features;
acquiring the product characteristics of each product to be sequenced according to the product set to be sequenced;
generating a product sorting result through a product sorting model according to the user characteristics and the product characteristics of each product to be sorted;
and determining at least one product to be recommended from the product set to be sequenced according to the product sequencing result, and recommending the product to be recommended to the user.
2. The method according to claim 1, wherein the obtaining the set of products to be ranked and the user behavior data according to the user identification, and processing the user behavior data through the user feature model to generate the user feature, includes:
constructing a product acquisition request and a user characteristic modeling request according to the user identifier;
acquiring a product set to be ordered corresponding to the user identifier according to the product acquisition request;
and acquiring user behavior data according to the user feature modeling request, and processing the user behavior data through a user feature model to generate user features.
3. The method of claim 2, wherein the obtaining user behavior data according to the user feature modeling request and processing the user behavior data through a user feature model to generate user features comprises:
acquiring user behavior data corresponding to the user identification according to the user characteristic modeling request;
extracting feature data required by modeling from the user behavior data;
and inputting the characteristic data into a user characteristic model for calculation to obtain the user characteristics.
4. The method of claim 1, wherein prior to obtaining the product characteristics for each product to be ordered from the set of products to be ordered, further comprising:
acquiring user session data triggering the product recommendation request according to the user identifier;
and screening the to-be-sequenced product set according to the user session data to delete to-be-sequenced products with the association degree with the user session data smaller than a set threshold value.
5. The method of claim 1, wherein the user feature model and the product ordering model are obtained by logically splitting a predictive model and are merged and deployed together.
6. The method of claim 5, wherein after recommending the product to be recommended to the user, further comprising:
respectively acquiring a calculation log of the user characteristic model, a sequencing log of the product sequencing model and an operation log of the user on the product to be recommended;
and retraining the pre-estimated model according to the calculation log, the sequencing log and the operation log so as to update the pre-estimated model.
7. A product recommendation device, comprising:
the user characteristic generating module is used for responding to a product recommendation request of a user, acquiring a product set to be ordered and user behavior data according to a user identifier, and processing the user behavior data through a user characteristic model to generate user characteristics;
the product characteristic acquisition module is used for acquiring the product characteristics of each product to be sequenced according to the product set to be sequenced;
the product sorting module is used for generating a product sorting result through a product sorting model according to the user characteristics and the product characteristics of each product to be sorted;
and the product recommending module is used for determining at least one product to be recommended from the product to be sequenced set according to the product sequencing result, and recommending the product to be recommended to the user.
8. The method of claim 5, further comprising a model training module for:
respectively acquiring a calculation log of the user characteristic model, a sequencing log of the product sequencing model and an operation log of the user on the product to be recommended;
and retraining the pre-estimated model according to the calculation log, the sequencing log and the operation log so as to update the pre-estimated model.
9. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs,
when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-6.
10. A computer readable medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method according to any of claims 1-6.
CN202210846271.3A 2022-07-19 2022-07-19 Product recommendation method and device Pending CN117453988A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210846271.3A CN117453988A (en) 2022-07-19 2022-07-19 Product recommendation method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210846271.3A CN117453988A (en) 2022-07-19 2022-07-19 Product recommendation method and device

Publications (1)

Publication Number Publication Date
CN117453988A true CN117453988A (en) 2024-01-26

Family

ID=89586147

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210846271.3A Pending CN117453988A (en) 2022-07-19 2022-07-19 Product recommendation method and device

Country Status (1)

Country Link
CN (1) CN117453988A (en)

Similar Documents

Publication Publication Date Title
CN109460514B (en) Method and device for pushing information
CN108536650B (en) Method and device for generating gradient lifting tree model
CN108804450B (en) Information pushing method and device
CN108989397B (en) Data recommendation method and device and storage medium
CN114329201B (en) Training method of deep learning model, content recommendation method and device
CN112527649A (en) Test case generation method and device
CN110020162B (en) User identification method and device
CN107908662B (en) Method and device for realizing search system
CN112257868A (en) Method and device for constructing and training integrated prediction model for predicting passenger flow
CN110866040A (en) User portrait generation method, device and system
CN112116426A (en) Method and device for pushing article information
CN110992127A (en) Article recommendation method and device
CN114119123A (en) Information pushing method and device
CN113365090B (en) Object recommendation method, object recommendation device, electronic equipment and readable storage medium
CN112801053B (en) Video data processing method and device
CN114428907A (en) Information searching method and device, electronic equipment and storage medium
CN108509442B (en) Search method and apparatus, server, and computer-readable storage medium
CN112231299B (en) Method and device for dynamically adjusting feature library
CN112395490B (en) Method and device for generating information
CN115619142A (en) Method, device, equipment and computer readable medium for matching data
CN113743973B (en) Method and device for analyzing market hotspot trend
CN110852078A (en) Method and device for generating title
CN112308016B (en) Expression image acquisition method and device, electronic equipment and storage medium
CN117453988A (en) Product recommendation method and device
CN109669779B (en) Method and device for determining cleaning path of data and cleaning data

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