CN112200623A - Product recommendation method, device, equipment and storage medium - Google Patents
Product recommendation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112200623A CN112200623A CN202011036837.3A CN202011036837A CN112200623A CN 112200623 A CN112200623 A CN 112200623A CN 202011036837 A CN202011036837 A CN 202011036837A CN 112200623 A CN112200623 A CN 112200623A
- Authority
- CN
- China
- Prior art keywords
- product
- recommendation
- user
- data
- comment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000007781 pre-processing Methods 0.000 claims abstract description 49
- 230000000306 recurrent effect Effects 0.000 claims abstract description 42
- 230000001537 neural effect Effects 0.000 claims abstract description 41
- 239000011159 matrix material Substances 0.000 claims description 68
- 238000012549 training Methods 0.000 claims description 35
- 239000013598 vector Substances 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 22
- 238000000605 extraction Methods 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 abstract description 11
- 238000004891 communication Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 8
- 125000004122 cyclic group Chemical group 0.000 description 7
- 210000005036 nerve Anatomy 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000013527 convolutional neural network Methods 0.000 description 4
- 230000002093 peripheral effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Finance (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Accounting & Taxation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (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, which comprises the following steps: the method comprises the steps of obtaining user information and product data to be selected of a user, wherein the product data to be selected comprises a plurality of products to be selected and historical information of each product to be selected, preprocessing the user information and the product data to be selected to obtain preprocessed data, inputting the preprocessed data into a trained recommendation model to obtain a recommendation score of each product to be selected, wherein the recommendation model comprises a recurrent neural unit, the recurrent neural unit is used for obtaining preference characteristics according to the preprocessed data, and finally outputting a recommendation result according to the recommendation score of each product to be selected. The invention discloses a product recommendation device, equipment and a storage medium, which can enable an output recommendation result to be more matched with the preference of a user, thereby improving the recommendation effect.
Description
Technical Field
The invention relates to the technical field of internet, in particular to a product recommendation method, a product recommendation device, product recommendation equipment and a storage medium.
Background
With the rapid development of mobile internet and the rapid popularization of mobile devices such as smart phones, the problem which puzzles us gradually changes from the lack of information in the early years to the information overload in the present. In the face of massive amounts of data, it is becoming increasingly difficult to find out what we really need and are interested in, and therefore recommendation systems are becoming increasingly important.
In the related art, the recommendation system directly and simply processes the historical information of the user, so that the recommendation result is obtained, the matching degree of the obtained recommendation result is insufficient, and the final recommendation effect is poor.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a product recommendation method, a product recommendation device, product recommendation equipment and a storage medium, and aims to solve the technical problems of insufficient matching degree of recommendation results and poor recommendation effect.
In order to achieve the above object, the present invention provides a product recommendation method, including the steps of:
the method comprises the steps of obtaining user information of a user and product data to be selected, wherein the product data to be selected comprises a plurality of products to be selected and historical information of each product to be selected;
preprocessing the user information and the product data to be selected to obtain preprocessed data;
inputting the preprocessing data into a trained recommendation model to obtain a recommendation score of each product to be selected, wherein the recommendation model comprises a recurrent neural unit, and the recurrent neural unit is used for obtaining preference characteristics according to the preprocessing data;
and outputting a recommendation result according to the recommendation score of each product to be selected.
Optionally, before the step of inputting the preprocessing data into a trained recommendation model to obtain a recommendation score of each of the products to be selected, the method further includes:
acquiring a user sample, a to-be-selected product sample set and a historical order sample set;
preprocessing the user sample, the to-be-selected product sample set and the historical order sample set to obtain a preprocessed data sample;
inputting the preprocessed data samples into an original recommendation model, and training the original recommendation model to obtain a trained recommendation model, wherein the original recommendation model comprises a recurrent neural unit, and the recurrent neural unit is used for obtaining preference characteristics according to the preprocessed data samples.
Optionally, the step of preprocessing the user information and the product data to be selected to obtain preprocessed data includes:
according to the user information and the data of the products to be selected, obtaining user information characteristics and a characteristic matrix of each product to be selected, wherein the characteristic matrix of each product to be selected comprises comment characteristics of each product to be selected and information characteristics of each product to be selected;
obtaining a first comment matrix of each comment of each product to be selected according to the comment characteristics of each product to be selected;
filtering the first comment matrix of each comment to obtain a second comment matrix of each comment;
and obtaining the preprocessed data based on the user information characteristics, the information characteristics of each product to be selected, the characteristic matrix of each product to be selected and the second comment matrix of each comment.
Optionally, the step of obtaining a feature matrix of each product to be selected according to the user information and the data of the product to be selected includes:
extracting the characteristics of the user information to obtain the characteristics of the user information;
performing feature extraction on the data of the products to be selected to obtain information features of each product to be selected, historical scoring features of each product to be selected and comment features of each product to be selected;
and obtaining a feature matrix of each product to be selected according to the information feature of each product to be selected, the historical grading feature of each product to be selected and the comment feature of each product to be selected.
Optionally, the recommendation model further comprises an attention network and a factorizer network; the preprocessing data also comprises a user characteristic vector and an information characteristic vector of each product to be selected;
the step of inputting the preprocessing data into a trained recommendation model to obtain a recommendation score of each product to be selected matching the user comprises:
scoring the feature matrix of each product to be selected through the recurrent neural unit to obtain the preference information of the user;
merging the user characteristic information, the preference information of the user and the second comment matrix of each comment through the attention network to obtain a preference score of each comment;
and processing the preference information, the preference score of each comment, the user characteristic vector and the information characteristic vector of each product to be selected through the factorization machine network to obtain the recommendation score of each product to be selected.
Optionally, the recommendation result includes K products to be selected with the highest recommendation score, where K is a positive integer greater than or equal to 1;
after the step of outputting a recommendation result according to the recommendation score of each product to be selected, the method further comprises:
determining M comments with the highest preference scores of the K products to be selected as recommended explanations, wherein M is a positive integer greater than or equal to 1;
and outputting the recommended explanation.
In addition, to achieve the above object, the present invention further provides a recommendation model training method, including:
acquiring a user sample, a to-be-selected product sample set and a historical order sample set;
preprocessing the user sample, the to-be-selected product sample set and the historical order sample set to obtain a preprocessed data sample;
inputting the preprocessed data samples into an original recommendation model, and training the original recommendation model to obtain a trained recommendation model, wherein the original recommendation model comprises a recurrent neural unit, and the recurrent neural unit is used for obtaining preference characteristics according to the preprocessed data samples.
In addition, to achieve the above object, the present invention also provides a product recommendation apparatus, including:
the system comprises a first obtaining module, a second obtaining module and a display module, wherein the first obtaining module is used for obtaining user information of a user and to-be-selected product data, and the to-be-selected product data comprises a plurality of to-be-selected products and historical information of each to-be-selected product;
the first preprocessing module is used for preprocessing the user information and the data of the product to be selected to obtain preprocessed data;
the scoring module is used for inputting the preprocessing data into a trained recommendation model to obtain a recommendation score of each product to be selected, wherein the recommendation model comprises a recurrent neural unit, and the recurrent neural unit is used for obtaining preference characteristics according to the preprocessing data;
and the first output module is used for outputting a recommendation result according to the recommendation score of each product to be selected.
Before the scoring module, the apparatus further comprises:
the acquisition module is used for acquiring a user sample, a to-be-selected product sample set and a historical order sample set;
the second preprocessing module is used for preprocessing the user sample, the to-be-selected product sample set and the historical order sample set to obtain a preprocessed data sample;
the first training module is used for inputting the preprocessed data samples into an original recommendation model and training the original recommendation model to obtain a trained recommendation model, wherein the original recommendation model comprises a recurrent neural unit, and the recurrent neural unit is used for obtaining preference characteristics according to the preprocessed data samples.
Optionally, the first preprocessing module includes:
the first obtaining submodule is used for obtaining user information characteristics and a characteristic matrix of each product to be selected according to the user information and the data of the product to be selected, and the characteristic matrix of each product to be selected comprises comment characteristics of each product to be selected and information characteristics of each product to be selected;
the second obtaining submodule is used for obtaining a first comment matrix of each comment of each product to be selected according to the comment characteristics of each product to be selected;
the filtering submodule is used for filtering the first comment matrix of each comment to obtain a second comment matrix of each comment;
and the third obtaining submodule is used for obtaining the preprocessed data based on the user information characteristics, the information characteristics of each product to be selected, the characteristic matrix of each product to be selected and the second comment matrix of each comment.
Optionally, the first obtaining sub-module includes:
the first feature extraction unit is used for extracting features of the user information to obtain user information features;
the second feature extraction unit is used for performing feature extraction on the data of the products to be selected to obtain the information features of each product to be selected, the historical scoring features of each product to be selected and the comment features of each product to be selected;
and the obtaining unit is used for obtaining a feature matrix of each product to be selected according to the information feature of each product to be selected, the historical scoring feature of each product to be selected and the comment feature of each product to be selected.
Optionally, the recommendation model further comprises an attention network and a factorizer network; the preprocessing data also comprises a user characteristic vector and an information characteristic vector of each product to be selected;
the scoring module comprises:
the scoring submodule is used for scoring the feature matrix of each product to be selected through the cyclic nerve unit to obtain the preference information of the user;
the merging submodule is used for merging the user characteristic information, the preference information of the user and the second comment matrix of each comment through the attention network to obtain a preference score of each comment;
and the fourth obtaining submodule is used for processing the preference information, the preference score of each comment, the user characteristic vector and the information characteristic vector of each product to be selected through the factorization machine network to obtain the recommendation score of each product to be selected.
Optionally, the recommendation result includes K products to be selected with the highest recommendation score, where K is a positive integer greater than or equal to 1;
after the first output module, the apparatus further comprises:
the determining module is used for determining the M comments with the highest preference scores of the K products to be selected as the recommended explanation, wherein M is a positive integer greater than or equal to 1;
and the second output module is used for outputting the recommended explanation.
In addition, to achieve the above object, the present invention also provides a terminal device, including: a memory, a processor and a product recommendation and recommendation model training program stored on the memory and run on the processor, which when executed by the processor implements the steps of the product recommendation method or recommendation model training method of any of the above.
In addition, to achieve the above object, the present invention further provides a storage medium having a product recommendation and recommendation model training program stored thereon, which when executed by a processor implements the steps of the product recommendation method or the recommendation model training method according to any one of the above.
According to the product recommendation method, the device, the equipment and the storage medium provided by the embodiment of the invention, the user information and the data of the products to be selected of the user are obtained, the data of the products to be selected comprise a plurality of products to be selected and the historical information of each product to be selected, then the user information and the data of the products to be selected are preprocessed to obtain preprocessed data, the preprocessed data are input into a recommendation model obtained through training to obtain the recommendation score of each product to be selected, wherein the recommendation model comprises a cyclic nerve unit, the cyclic nerve unit is used for obtaining preference characteristics according to the preprocessed data, and finally the recommendation score of each product to be selected is output. By acquiring user information and product data to be selected of a user, combining the user information and historical information of each product to be selected, preprocessing the preprocessed data, and processing the preprocessed data through a recurrent neural unit in a recommendation model, preference characteristics of the user can be obtained, so that a recommendation result can be obtained by combining the preference characteristics of the user, the output recommendation result is more matched with the preference of the user, and the recommendation effect is improved.
Drawings
Fig. 1 is a schematic structural diagram of a terminal device in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a server architecture of a hardware operating environment according to an embodiment of the present invention;
FIG. 3 is a flowchart of the steps of a first embodiment of the product recommendation method of the present invention;
FIG. 4 is a flowchart illustrating steps of a second embodiment of a product recommendation method of the present invention;
FIG. 5 is a schematic flow chart of a recommendation model training of the product recommendation method of the present invention;
FIG. 6 is a data flow diagram of a second embodiment of the product recommendation method of the present invention;
fig. 7 is a schematic structural diagram of a first embodiment of the product recommendation device of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
With the rapid development of mobile internet and the rapid popularization of mobile devices such as smart phones, the problem which puzzles us gradually changes from the lack of information in the early years to the information overload in the present. In the face of massive amounts of data, it is becoming increasingly difficult to find out what we really need and are interested in, and therefore recommendation systems are becoming increasingly important.
In the related art, the recommendation system directly and simply processes the historical information of the user, so that the recommendation result is obtained, the matching degree of the obtained recommendation result is insufficient, and the final recommendation effect is poor.
The invention provides a solution, which is characterized in that the user information and the data of products to be selected of a user are acquired, the preprocessed data are acquired through preprocessing by combining the user information and the historical information of each product to be selected, the preprocessed data are processed through a cyclic nerve unit in a recommendation model, the preference characteristics of the user can be acquired, so that the recommendation result is acquired by combining the preference characteristics of the user, the output recommendation result is more matched with the preference of the user, and the recommendation effect is improved.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a terminal device in a hardware operating environment according to an embodiment of the present invention.
The terminal device may be a User Equipment (UE) such as a smart home device, a Mobile phone, a smart phone, a laptop, a digital broadcast receiver, a Personal Digital Assistant (PDA), a tablet computer (PAD), a handheld device, a vehicle-mounted device, a wearable device, a computing device or other processing device connected to a wireless modem, a Mobile Station (MS), or the like. The device may be referred to as a user terminal, portable terminal, desktop terminal, etc.
In general, a terminal device includes: at least one processor 301, a memory 302, and a product recommendation or recommendation model training program stored on the memory and executable on the processor, the product recommendation or recommendation model training program configured to implement the steps of the product recommendation method or recommendation model training method as described in any of the following embodiments.
The processor 301 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so on. The processor 301 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 301 may also include a main processor and a coprocessor, where the main processor is a processor for processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 301 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the display screen. The processor 301 may further include an AI (Artificial Intelligence) processor for processing operations related to the product recommendation method or the recommendation model training method so that the product recommendation method or recommendation model training method model may be trained and learned autonomously, improving efficiency and accuracy.
In some embodiments, the terminal may further include: a communication interface 303 and at least one peripheral device. The processor 301, the memory 302 and the communication interface 303 may be connected by a bus or signal lines. Various peripheral devices may be connected to communication interface 303 via a bus, signal line, or circuit board. Specifically, the peripheral device includes: at least one of radio frequency circuitry 304, a display screen 305, and a power source 306.
The communication interface 303 may be used to connect at least one peripheral device related to I/O (Input/Output) to the processor 301 and the memory 302. In some embodiments, processor 301, memory 302, and communication interface 303 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 301, the memory 302 and the communication interface 303 may be implemented on a single chip or circuit board, which is not limited in this embodiment.
The Radio Frequency circuit 304 is used for receiving and transmitting RF (Radio Frequency) signals, also called electromagnetic signals. The radio frequency circuitry 304 communicates with communication networks and other communication devices via electromagnetic signals. The rf circuit 304 converts an electrical signal into an electromagnetic signal to transmit, or converts a received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 304 comprises: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and so forth. The radio frequency circuitry 304 may communicate with other terminals via at least one wireless communication protocol. The wireless communication protocols include, but are not limited to: metropolitan area networks, various generation mobile communication networks (2G, 3G, 4G, and 5G), Wireless local area networks, and/or WiFi (Wireless Fidelity) networks. In some embodiments, the rf circuit 304 may further include NFC (Near Field Communication) related circuits, which are not limited in this application.
The display screen 305 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display screen 305 is a touch display screen, the display screen 305 also has the ability to capture touch signals on or over the surface of the display screen 305. The touch signal may be input to the processor 301 as a control signal for processing. At this point, the display screen 305 may also be used to provide virtual buttons and/or a virtual keyboard, also referred to as soft buttons and/or a soft keyboard. In some embodiments, the display screen 305 may be one, the front panel of the electronic device; in other embodiments, the display screens 305 may be at least two, respectively disposed on different surfaces of the electronic device or in a folded design; in still other embodiments, the display screen 305 may be a flexible display screen disposed on a curved surface or a folded surface of the electronic device. Even further, the display screen 305 may be arranged in a non-rectangular irregular figure, i.e. a shaped screen. The Display screen 305 may be made of LCD (liquid crystal Display), OLED (Organic Light-Emitting Diode), and the like.
The power supply 306 is used to power various components in the electronic device. The power source 306 may be alternating current, direct current, disposable or rechargeable. When the power source 306 includes a rechargeable battery, the rechargeable battery may support wired or wireless charging. The rechargeable battery may also be used to support fast charge technology. Those skilled in the art will appreciate that the configuration shown in FIG. 1 does not constitute a limitation of the product recommendation or recommendation model training apparatus, and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
In addition, an embodiment of the present invention further provides a storage medium, where a product recommendation or recommendation model training program is stored on the storage medium, and when executed by a processor, the product recommendation or recommendation model training program implements the steps of the product recommendation method or recommendation model training method according to any of the following embodiments. Therefore, a detailed description thereof will be omitted. In addition, the beneficial effects of the same method are not described in detail. For technical details not disclosed in embodiments of the computer-readable storage medium referred to in the present application, reference is made to the description of embodiments of the method of the present application. It is determined that, by way of example, the program instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network.
It will be understood by those skilled in the art that all or part of the processes of the methods of any of the following embodiments may be implemented by a computer program to instruct associated hardware, and the product recommendation method or recommendation model training method program may be stored in a computer-readable storage medium, and when executed, may include processes of the embodiments of the methods as described below. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
Referring to fig. 2, fig. 2 is a schematic diagram of a server structure of a hardware operating environment according to an embodiment of the present invention.
Specifically, the server includes a Central Processing Unit (CPU)401, a system memory 404 including a Random Access Memory (RAM)402 and a Read Only Memory (ROM)403, and a system bus 405 connecting the system memory 404 and the central processing unit 401. The server also includes a basic input/output system (I/O system) 406, which facilitates the transfer of information between devices within the computer, and a mass storage device 407 for storing an operating system 413, application programs 414, and other program modules 415.
The basic input/output system 406 includes a display 408 for displaying information and an input device 409 such as a mouse, keyboard, etc. for user input of information. Wherein the display 408 and the input device 409 are connected to the central processing unit 401 through an input output controller 410 connected to the system bus 405. The basic input/output system 406 may also include an input/output controller 410 for receiving and processing input from a number of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, input/output controller 410 may also provide output to a display screen, a printer, or other type of output device.
The mass storage device 407 is connected to the central processing unit 401 through a mass storage controller connected to the system bus 405. The mass storage device 407 and its associated computer-readable media provide non-volatile storage for the server. That is, the mass storage device 407 may include a computer-readable medium such as a hard disk or CD-ROM drive.
Without loss of generality, the computer-readable media may comprise computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes RAM, ROM, EPROM, EEPROM, flash memory or other solid state memory technology, CD-ROM, DVD, or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that the computer storage media is not limited to the foregoing.
The system memory 404 and mass storage device 407 described above may be collectively referred to as memory. According to various embodiments of the present application, the server may also operate with remote computers connected to a network through a network, such as the Internet. That is, the servers may be connected to the network 412 through the network interface unit 411 attached to the system bus 405, or the network interface unit 411 may be used to connect to other types of networks or remote computer systems.
Based on the hardware structure, the embodiment of the product recommendation method or the recommendation model training method is provided.
Referring to fig. 3, fig. 3 is a flowchart of the steps of a first embodiment of the product recommendation method of the present invention, as shown in fig. 3, the recommendation method includes the following steps:
step S11: user information of a user and product data to be selected are obtained, and the product data to be selected comprises a plurality of products to be selected and historical information of each product to be selected.
In this embodiment, user information of a user and data of products to be selected are obtained first, where the data of the products to be selected includes a plurality of products to be selected and history information of each product to be selected, the user information may include age, residence address, hobbies, and the like of the user, the products to be selected are a plurality of predetermined products or all available products, and the history information of each product to be selected includes a purchasing user of each product to be selected, a purchased time of each product to be selected, comment information of each product to be selected, and rating information of each product to be selected. The comment information of each product to be selected comprises comments of a plurality of users who purchase the product to be selected on the product to be selected, and the score information of each product to be selected comprises scores of the plurality of users who purchase the product to be selected on the product to be selected.
Step S12: and preprocessing the user information and the product data to be selected to obtain preprocessed data.
In the embodiment, the user information and the product to be selected need to be preprocessed so that the recommendation model can be identified, and the data input into the recommendation model can be more concise and reasonable, so that the obtained recommendation result is more accurate.
Step S13: inputting the preprocessing data into a trained recommendation model to obtain a recommendation score of each product to be selected, wherein the recommendation model comprises a recurrent neural unit, and the recurrent neural unit is used for obtaining preference characteristics according to the preprocessing data.
In the embodiment, the pre-processing data is input into the pre-trained recommendation model, so that the recommendation score of each product to be selected can be obtained, the recommendation model comprises the recurrent neural unit, and the recurrent neural unit can obtain the preference characteristics according to the pre-processing data, so that the obtained recommendation result is more accurate, and the recommendation effect can be improved.
Step S14: and outputting a recommendation result according to the recommendation score of each product to be selected.
In this embodiment, a plurality of higher recommendation scores may be selected from the recommendation scores according to the recommendation score of each product to be selected, and the product to be recommended corresponding to the selected recommendation score is output as the recommendation result.
In the embodiment of the application, user information and to-be-selected product data of a user are obtained, the to-be-selected product data comprise a plurality of to-be-selected products and historical information of each to-be-selected product, then the user information and the to-be-selected product data are preprocessed to obtain preprocessed data, the preprocessed data are input into a trained recommendation model to obtain a recommendation score of each to-be-selected product, the recommendation model comprises a recurrent neural unit, the recurrent neural unit is used for obtaining preference characteristics according to the preprocessed data, and finally a recommendation result is output according to the recommendation score of each to-be-selected product. By acquiring user information and product data to be selected of a user, combining the user information and historical information of each product to be selected, preprocessing the preprocessed data, and processing the preprocessed data through a recurrent neural unit in a recommendation model, preference characteristics of the user can be obtained, so that a recommendation result can be obtained by combining the preference characteristics of the user, the output recommendation result is more matched with the preference of the user, and the recommendation effect is improved.
Further, referring to fig. 4 and 5, fig. 4 is a flowchart illustrating steps of a second embodiment of the product recommendation method of the present invention, and fig. 5 is a flowchart illustrating training of a recommendation model of the product recommendation method of the present invention, as shown in fig. 4 and 5, based on the above embodiment shown in fig. 3, before step S11, the product recommendation method further includes:
step S21: and acquiring a user sample, a to-be-selected product sample set and a historical order sample set.
In this embodiment, training of the recommendation model is required to obtain the trained recommendation model, and the historical data is obtained first, including obtaining a user sample, a to-be-selected product sample, and a historical order sample set, where the user sample includes user information of a plurality of users, the to-be-selected product sample set includes a plurality of to-be-selected products and historical information of each to-be-selected product, and the historical order sample set includes historical orders of the plurality of users.
Step S22: and preprocessing the user sample, the to-be-selected product sample set and the historical order sample set to obtain a preprocessed data sample.
In the embodiment, the user sample, the to-be-selected product sample set and the historical order sample set are preprocessed and converted into data which can be identified by the original recommendation model, and preprocessed data samples are obtained.
Step S23: inputting the preprocessed data samples into an original recommendation model, and training the original recommendation model to obtain a trained recommendation model, wherein the original recommendation model comprises a recurrent neural unit, and the recurrent neural unit is used for obtaining preference characteristics according to the preprocessed data samples.
In the embodiment, the preprocessed samples are input into the original recommendation model, and the original recommendation model is subjected to multiple rounds of training until the original recommendation model is converged, so that a trained recommendation model is obtained.
In this embodiment, the original recommendation model is trained by obtaining historical data including a user sample, a sample set of products to be selected, and a sample set of historical orders, so as to obtain a trained recommendation model, so that the trained recommendation model is used to recommend products to the user.
Referring to fig. 6, fig. 6 is a data flow diagram of a second embodiment of the product recommendation method of the present invention, and as shown in fig. 6, in a possible implementation, the step S12 includes the following steps S21-S24:
step S21: and obtaining user information characteristics and a characteristic matrix of each product to be selected according to the user information and the data of the product to be selected, wherein the characteristic matrix of each product to be selected comprises the comment characteristics of each product to be selected and the information characteristics of each product to be selected.
In the embodiment, the user information and the data of the products to be selected are processed to obtain the feature matrix of each product to be selected and the user information features of the user, wherein the feature matrix of each product to be selected comprises the comment features of each product to be selected and the information features of each product to be selected, so that the features of each product to be selected can be obtained from the comment features of each product to be selected, and the product features can be matched with the preference of the user.
In one possible embodiment, step S21 includes:
extracting the characteristics of the user information to obtain the characteristics of the user information;
performing feature extraction on the data of the products to be selected to obtain information features of each product to be selected, historical scoring features of each product to be selected and comment features of each product to be selected;
and obtaining a feature matrix of each product to be selected according to the information feature of each product to be selected, the historical grading feature of each product to be selected and the comment feature of each product to be selected.
In this embodiment, the user information and the data of the product to be selected are processed to obtain the user information characteristics, the information characteristics of each product to be selected, the historical score characteristics of each product to be selected, and the comment characteristics of each product to be selected, for example, if the user u has certain historical order information and scores and evaluates the orders, the historical order data set of the user u is recorded as:
wherein
luIndicating historical order number, s-th element, of user u
Indicates that user u is
Aim at article at any moment
Making a score
And evaluation of
Wherein s is a positive integer. For user u at
Data of time of day, have
I.e. xsA feature matrix for each product to be selected, wherein
And
respectively represent users u at
Item and scored one-hot representation corresponding to the order generated at the moment, EVAnd ERAre respectively provided with
And
mapping the information characteristics of the products to be selected into an embedding vector to obtain the information characteristics of the products to be selected and the historical scoring characteristics of the products to be selected, and enabling the user u to carry out article matching
Content of comments
The embedding of all the words is expressed to obtain the comment characteristics of each product to be selected, wherein the user u carries out comment on the item
Content of comments
Is the average of the embedding representations of all words of
The model can be obtained directly by using a pre-trained model, such as Bert, and will not be described herein.
Step S22: and obtaining a first comment matrix of each comment of each product to be selected according to the comment characteristics of each product to be selected.
In this embodiment, each candidate product is sortedSegmenting each comment of the product, and then performing feature extraction on each segmented comment to obtain a first comment matrix of each comment of each product to be selected, specifically, assuming that one product to be selected has n comments, and a comment set formed by all n comments is W ═ W {1,W2,…,WnW, the k-th comment WkThe embedding of all words of (a) indicates that the sequence of components is
Wherein
A pre-trained embedding representation for the ith word, where,
representing a matrix, the upper corner mark d representing the dimension thereof, i.e.
Is a d-dimensional matrix.
Step S23: and filtering the first comment matrix of each comment to obtain a second comment matrix of each comment.
In this embodiment, the first opinion matrix of each comment is filtered to obtain the second comment matrix of each comment, and specifically, each element in the first comment matrix may be extracted by using the strong extraction capability of the CNN convolutional neural network on the local feature
Adding a convolution layer with m filters, using fkiTo represent
The result obtained after the CNN convolutional neural network is the second comment matrix of each comment, and finally the kth comment WkIs denoted as fk＝[fk1,fk2,…,fkm]Compressing T words to m, i.e. extracting m key from T wordsAnd the words are shown, wherein k, T and m are all positive integers.
Step S24: and obtaining the preprocessed data based on the user information characteristics, the information characteristics of each product to be selected, the characteristic matrix of each product to be selected and the second comment matrix of each comment.
In this embodiment, the obtained user information characteristics, the information characteristics of each product to be selected, the characteristic matrix of each product to be selected, and the second comment matrix of each comment are the required preprocessed data.
In the embodiment, more accurate preprocessed data can be obtained by performing feature extraction and filtering on the user information and the data of the product to be selected, so that a more accurate recommendation result is obtained.
In one possible embodiment, the recommendation model further includes an attention network and a factoring machine network; the preprocessing data also comprises a user characteristic vector and an information characteristic vector of each product to be selected; the step S13 includes:
step S13-1: scoring the feature matrix of each product to be selected through the recurrent neural unit to obtain the preference information of the user;
in the embodiment, the feature matrix of each product to be selected is scored through a recurrent neural network, i.e. GRU, so that a preference score of the user can be obtained, specifically, x is scoredsIs obtained by GRU (recurrent neural Unit) operation
The user has different order data at different moments, so that the user has a plurality of feature matrixes of products to be selected, the feature matrixes of the products to be selected at different moments are analyzed, and the closer to the current moment, the higher the weight of the feature matrix of the products to be selected is according to the time sequence, so that the preference of the user along with the change of time can be obtained, and the preference information of the user can be obtained.
Step S13-2: and merging the user characteristic information, the preference information of the user and the second comment matrix of each comment through the attention network to obtain a preference score of each comment.
In the embodiment, the preference score of each comment is obtained by merging the attention network multi-user characteristic information, the user preference information and the second comment matrix of each comment, specifically, the user u is in
Preference of time of day is coded into
Commenting content f by attention mechanism of attention networkkAnd preference coding
Are combined to obtain
Wherein:
where ReLU denotes the Relu activation function, WhAnd WfAre respectively provided with
And
mapped into a matrix of the same dimension, [ W ]1,W2,b1,b2]Is a parameter to be learned in the attention network, tau is a parameter to be predefined, e is a natural constant, and h is a positive integer.
Step S13-3: and processing the preference information, the preference score of each comment, the user characteristic vector and the information characteristic vector of each product to be selected through the factorization machine network to obtain the recommendation score of each product to be selected.
In the embodiment, the factorization machine network processes the preference information, the preference score of each comment, the user characteristic vector and the information characteristic vector of each product to be selected, so that the recommendation score of each product to be selected can be obtained. In particular, to better describe the relationship between user u and item v, two auxiliary embedding vectors are introduced
(i.e., user feature vector) and
(namely the information characteristic vector of each product to be selected), the two K-dimensional vectors can be obtained by pre-training in advance through an FM factorization machine algorithm, so that the score of the user u on the article v is obtained:
wherein
Is a parameter to be learned [, ]]Indicating a connection operation and FM indicates a factorizer network layer.
In a possible embodiment, the recommending result includes K products to be selected with the highest recommended scores, where K is a positive integer greater than or equal to 1, and after the step S14, the method further includes:
determining M comments with the highest preference scores of the K products to be selected as recommended explanations, wherein M is a positive integer greater than or equal to 1;
and outputting the recommended explanation.
In the embodiment, considering that the recommendation effect is poor due to the fact that personalized recommendation interpretations are difficult to have in the related art, the recommendation interpretations are output when the recommendation result is output, so that the requirements of customers are met, and the recommendation effect is improved. Specifically, the recommendation scores of each product to be selected may be ranked, K highest recommendation scores may be obtained, the product to be recommended corresponding to the highest recommendation score of the K recommendation scores may be output as a final recommendation result, M comments having the highest preference score of each product to be selected may be obtained, and the M comments may be output as a recommendation explanation.
Referring to fig. 4 and 5, the present application further discloses a recommendation model training method, which includes the following steps:
acquiring a user sample, a to-be-selected product sample set and a historical order sample set;
preprocessing the user sample, the to-be-selected product sample set and the historical order sample set to obtain a preprocessed data sample;
inputting the preprocessed data samples into an original recommendation model, and training the original recommendation model to obtain a trained recommendation model, wherein the original recommendation model comprises a recurrent neural unit, and the recurrent neural unit is used for obtaining preference characteristics according to the preprocessed data samples.
The steps are the same as steps S21-S23, and the detailed explanation can refer to the above contents, which are not described herein again, wherein the original recommendation model is:
wherein
Is all user-item pairs in the training set, ruvFor the actual score of the product sample to be selected, Θ represents all the parameters that need to be trained.
The model obtained by training the objective function L is the recommended model obtained by training that we want. According to the trainingThe obtained recommendation model is trained, the scores of the items given by the user can be predicted, and sequencing is carried out according to the obtained scores, so that the items of Top-k can be taken for recommendation; for recommended items to the user, the attention score (α) is highlighted from all of their commentsuvk) The highest commenting part as a recommended explanation of the item.
Referring to fig. 7, fig. 7 is a schematic structural diagram of a first embodiment of the product recommendation device of the present invention, as shown in fig. 7, the product recommendation device includes:
the system comprises a first obtaining module 10, a second obtaining module, a third obtaining module and a fourth obtaining module, wherein the first obtaining module is used for obtaining user information of a user and data of products to be selected, and the data of the products to be selected comprises a plurality of products to be selected and historical information of each product to be selected;
the first preprocessing module 20 is configured to preprocess the user information and the data of the product to be selected to obtain preprocessed data;
the scoring module 30 is configured to input the preprocessing data into a trained recommendation model to obtain a recommendation score of each product to be selected, where the recommendation model includes a recurrent neural unit, and the recurrent neural unit is configured to obtain a preference feature according to the preprocessing data;
and the first output module 40 is used for outputting a recommendation result according to the recommendation score of each product to be selected.
Before the scoring module, the apparatus further comprises:
the acquisition module is used for acquiring a user sample, a to-be-selected product sample set and a historical order sample set;
the second preprocessing module is used for preprocessing the user sample, the to-be-selected product sample set and the historical order sample set to obtain a preprocessed data sample;
the first training module is used for inputting the preprocessed data samples into an original recommendation model and training the original recommendation model to obtain a trained recommendation model, wherein the original recommendation model comprises a recurrent neural unit, and the recurrent neural unit is used for obtaining preference characteristics according to the preprocessed data samples.
Optionally, the first preprocessing module includes:
the first obtaining submodule is used for obtaining user information characteristics and a characteristic matrix of each product to be selected according to the user information and the data of the product to be selected, and the characteristic matrix of each product to be selected comprises comment characteristics of each product to be selected and information characteristics of each product to be selected;
the second obtaining submodule is used for obtaining a first comment matrix of each comment of each product to be selected according to the comment characteristics of each product to be selected;
the filtering submodule is used for filtering the first comment matrix of each comment to obtain a second comment matrix of each comment;
and the third obtaining submodule is used for obtaining the preprocessed data based on the user information characteristics, the information characteristics of each product to be selected, the characteristic matrix of each product to be selected and the second comment matrix of each comment.
Optionally, the first obtaining sub-module includes:
the first feature extraction unit is used for extracting features of the user information to obtain user information features;
the second feature extraction unit is used for performing feature extraction on the data of the products to be selected to obtain the information features of each product to be selected, the historical scoring features of each product to be selected and the comment features of each product to be selected;
and the obtaining unit is used for obtaining a feature matrix of each product to be selected according to the information feature of each product to be selected, the historical scoring feature of each product to be selected and the comment feature of each product to be selected.
Optionally, the recommendation model further comprises an attention network and a factorizer network; the preprocessing data also comprises a user characteristic vector and an information characteristic vector of each product to be selected;
the scoring module comprises:
the scoring submodule is used for scoring the feature matrix of each product to be selected through the cyclic nerve unit to obtain the preference information of the user;
the merging submodule is used for merging the user characteristic information, the preference information of the user and the second comment matrix of each comment through the attention network to obtain a preference score of each comment;
and the fourth obtaining submodule is used for processing the preference information, the preference score of each comment, the user characteristic vector and the information characteristic vector of each product to be selected through the factorization machine network to obtain the recommendation score of each product to be selected.
Optionally, the recommendation result includes K products to be selected with the highest recommendation score, where K is a positive integer greater than or equal to 1;
after the first output module, the apparatus further comprises:
the determining module is used for determining the M comments with the highest preference scores of the K products to be selected as the recommended explanation, wherein M is a positive integer greater than or equal to 1;
and the second output module is used for outputting the recommended explanation.
According to the product recommendation device provided by the embodiment of the invention, user information and product data to be selected of a user are obtained, the product data to be selected comprise a plurality of products to be selected and historical information of each product to be selected, then the user information and the product data to be selected are preprocessed to obtain preprocessed data, the preprocessed data are input into a recommendation model obtained through training to obtain a recommendation score of each product to be selected, wherein the recommendation model comprises a cyclic nerve unit, the cyclic nerve unit is used for obtaining preference characteristics according to the preprocessed data, and finally a recommendation result is output according to the recommendation score of each product to be selected. By acquiring user information and product data to be selected of a user, combining the user information and historical information of each product to be selected, preprocessing the preprocessed data, and processing the preprocessed data through a recurrent neural unit in a recommendation model, preference characteristics of the user can be obtained, so that a recommendation result can be obtained by combining the preference characteristics of the user, the output recommendation result is more matched with the preference of the user, and the recommendation effect is improved.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A product recommendation method, characterized in that the product recommendation method comprises the steps of:
the method comprises the steps of obtaining user information of a user and product data to be selected, wherein the product data to be selected comprises a plurality of products to be selected and historical information of each product to be selected;
preprocessing the user information and the product data to be selected to obtain preprocessed data;
inputting the preprocessing data into a trained recommendation model to obtain a recommendation score of each product to be selected, wherein the recommendation model comprises a recurrent neural unit, and the recurrent neural unit is used for obtaining preference characteristics according to the preprocessing data;
and outputting a recommendation result according to the recommendation score of each product to be selected.
2. The product recommendation method of claim 1, wherein prior to said step of inputting said pre-processed data into a trained recommendation model to obtain a recommendation score for each of said products to be selected, said product recommendation method further comprises:
acquiring a user sample, a to-be-selected product sample set and a historical order sample set;
preprocessing the user sample, the to-be-selected product sample set and the historical order sample set to obtain a preprocessed data sample;
inputting the preprocessed data samples into an original recommendation model, and training the original recommendation model to obtain a trained recommendation model, wherein the original recommendation model comprises a recurrent neural unit, and the recurrent neural unit is used for obtaining preference characteristics according to the preprocessed data samples.
3. The product recommendation method of claim 1, wherein the step of preprocessing the user information and the product data to be selected to obtain preprocessed data comprises:
according to the user information and the data of the products to be selected, obtaining user information characteristics and a characteristic matrix of each product to be selected, wherein the characteristic matrix of each product to be selected comprises comment characteristics of each product to be selected and information characteristics of each product to be selected;
obtaining a first comment matrix of each comment of each product to be selected according to the comment characteristics of each product to be selected;
filtering the first comment matrix of each comment to obtain a second comment matrix of each comment;
and obtaining the preprocessed data based on the user information characteristics, the information characteristics of each product to be selected, the characteristic matrix of each product to be selected and the second comment matrix of each comment.
4. The product recommendation method of claim 3, wherein the step of obtaining a feature matrix for each product to be selected according to the user information and the data of the product to be selected comprises:
extracting the characteristics of the user information to obtain the characteristics of the user information;
performing feature extraction on the data of the products to be selected to obtain information features of each product to be selected, historical scoring features of each product to be selected and comment features of each product to be selected;
and obtaining a feature matrix of each product to be selected according to the information feature of each product to be selected, the historical grading feature of each product to be selected and the comment feature of each product to be selected.
5. The product recommendation method of claim 3, wherein the recommendation model further comprises an attention network and a factoring machine network; the preprocessing data also comprises a user characteristic vector and an information characteristic vector of each product to be selected;
the step of inputting the preprocessing data into a trained recommendation model to obtain a recommendation score of each product to be selected matching the user comprises:
scoring the feature matrix of each product to be selected through the recurrent neural unit to obtain the preference information of the user;
merging the user characteristic information, the preference information of the user and the second comment matrix of each comment through the attention network to obtain a preference score of each comment;
and processing the preference information, the preference score of each comment, the user characteristic vector and the information characteristic vector of each product to be selected through the factorization machine network to obtain the recommendation score of each product to be selected.
6. The product recommendation method of claim 5, wherein the recommendation result comprises K products to be selected with the highest recommendation score, wherein K is a positive integer greater than or equal to 1;
after the step of outputting a recommendation result according to the recommendation score of each product to be selected, the method further comprises:
determining M comments with the highest preference scores of the K products to be selected as recommended explanations, wherein M is a positive integer greater than or equal to 1;
and outputting the recommended explanation.
7. A recommendation model training method is characterized by comprising the following steps:
acquiring a user sample, a to-be-selected product sample set and a historical order sample set;
preprocessing the user sample, the to-be-selected product sample set and the historical order sample set to obtain a preprocessed data sample;
inputting the preprocessed data samples into an original recommendation model, and training the original recommendation model to obtain a trained recommendation model, wherein the original recommendation model comprises a recurrent neural unit, and the recurrent neural unit is used for obtaining preference characteristics according to the preprocessed data samples.
8. A product recommendation device, characterized in that the product recommendation device comprises:
the system comprises a first obtaining module, a second obtaining module and a display module, wherein the first obtaining module is used for obtaining user information of a user and to-be-selected product data, and the to-be-selected product data comprises a plurality of to-be-selected products and historical information of each to-be-selected product;
the first preprocessing module is used for preprocessing the user information and the data of the product to be selected to obtain preprocessed data;
the scoring module is used for inputting the preprocessing data into a trained recommendation model to obtain a recommendation score of each product to be selected, wherein the recommendation model comprises a recurrent neural unit, and the recurrent neural unit is used for obtaining preference characteristics according to the preprocessing data;
and the first output module is used for outputting a recommendation result according to the recommendation score of each product to be selected.
9. A terminal device, characterized in that the terminal device comprises: memory, a processor and a product recommendation and recommendation model training program stored on the memory and running on the processor, which when executed by the processor implement the steps of the product recommendation method or recommendation model training method of any of claims 1 to 6 or claim 7.
10. A storage medium having stored thereon a product recommendation and recommendation model training program which when executed by a processor implements the steps of the product recommendation method or recommendation model training method of any of claims 1 to 6 or claim 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011036837.3A CN112200623A (en) | 2020-09-27 | 2020-09-27 | Product recommendation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011036837.3A CN112200623A (en) | 2020-09-27 | 2020-09-27 | Product recommendation method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112200623A true CN112200623A (en) | 2021-01-08 |
Family
ID=74007492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011036837.3A Pending CN112200623A (en) | 2020-09-27 | 2020-09-27 | Product recommendation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112200623A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113689266A (en) * | 2021-08-27 | 2021-11-23 | 重庆锐云科技有限公司 | Mobile phone purchasing recommendation method and device, server and computer readable storage medium |
| CN113688314A (en) * | 2021-08-13 | 2021-11-23 | 今彩慧健康科技(苏州)有限公司 | Physiotherapy store recommendation method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109241424A (en) * | 2018-08-29 | 2019-01-18 | 陕西师范大学 | A kind of recommended method |
| WO2019223379A1 (en) * | 2018-05-22 | 2019-11-28 | 阿里巴巴集团控股有限公司 | Product recommendation method and device |
| CN111222332A (en) * | 2020-01-06 | 2020-06-02 | 华南理工大学 | Commodity recommendation method combining attention network and user emotion |
| CN111368197A (en) * | 2020-03-04 | 2020-07-03 | 哈尔滨理工大学 | Deep learning-based comment recommendation system and method |
-
2020
- 2020-09-27 CN CN202011036837.3A patent/CN112200623A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019223379A1 (en) * | 2018-05-22 | 2019-11-28 | 阿里巴巴集团控股有限公司 | Product recommendation method and device |
| CN109241424A (en) * | 2018-08-29 | 2019-01-18 | 陕西师范大学 | A kind of recommended method |
| CN111222332A (en) * | 2020-01-06 | 2020-06-02 | 华南理工大学 | Commodity recommendation method combining attention network and user emotion |
| CN111368197A (en) * | 2020-03-04 | 2020-07-03 | 哈尔滨理工大学 | Deep learning-based comment recommendation system and method |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113688314A (en) * | 2021-08-13 | 2021-11-23 | 今彩慧健康科技(苏州)有限公司 | Physiotherapy store recommendation method and device |
| CN113688314B (en) * | 2021-08-13 | 2024-03-19 | 今彩慧健康科技(苏州)有限公司 | Physical therapy store recommending method and device |
| CN113689266A (en) * | 2021-08-27 | 2021-11-23 | 重庆锐云科技有限公司 | Mobile phone purchasing recommendation method and device, server and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110363346B (en) | Click rate prediction method, training method, device and equipment of prediction model | |
| CN107943860B (en) | Model training method, text intention recognition method and text intention recognition device | |
| CN111552888A (en) | Content recommendation method, device, equipment and storage medium | |
| CN113515942A (en) | Text processing method and device, computer equipment and storage medium | |
| CN112685578B (en) | Method and device for providing multimedia information content | |
| CN111709398A (en) | Image recognition method, and training method and device of image recognition model | |
| CN112801719A (en) | User behavior prediction method, user behavior prediction device, storage medium, and apparatus | |
| CN112052297B (en) | Information generation method, apparatus, electronic device and computer readable medium | |
| CN112200623A (en) | Product recommendation method, device, equipment and storage medium | |
| CN112528164A (en) | User collaborative filtering recall method and device | |
| CN111931075B (en) | Content recommendation method and device, computer equipment and storage medium | |
| CN114765062A (en) | Gene data processing method, gene data processing device, computer equipment and storage medium | |
| CN113886688B (en) | Method, device, terminal equipment and storage medium for predicting association relation of objects | |
| CN116383478A (en) | Transaction recommendation method, device, equipment and storage medium | |
| CN111639705B (en) | Batch picture marking method, system, machine readable medium and equipment | |
| CN116205686A (en) | Method, device, equipment and storage medium for recommending multimedia resources | |
| CN113722422A (en) | Model training method, text label generation method, device, equipment and medium | |
| CN114547430A (en) | Information object label labeling method, device, equipment and storage medium | |
| CN110750715A (en) | Content recommendation method, device, equipment and readable storage medium | |
| CN117454015B (en) | Information recommendation method and device | |
| CN116911304B (en) | Text recommendation method and device | |
| CN113626683B (en) | CTR (control parameter) estimation processing method and device, electronic equipment and storage medium | |
| CN114399030B (en) | Training method of recommendation model, media information recommendation method, device and equipment | |
| CN115269949A (en) | Webpage crawling method, device, equipment and computer program | |
| CN115222432A (en) | Method, device and equipment for generating health degree index and storage medium |
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 |