CN112581227A - Product recommendation method and device, electronic equipment and storage medium - Google Patents

Product recommendation method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN112581227A
CN112581227A CN202011528718.XA CN202011528718A CN112581227A CN 112581227 A CN112581227 A CN 112581227A CN 202011528718 A CN202011528718 A CN 202011528718A CN 112581227 A CN112581227 A CN 112581227A
Authority
CN
China
Prior art keywords
user
image
information
portrait
face image
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
CN202011528718.XA
Other languages
Chinese (zh)
Inventor
陈伟滨
高洪喜
许云辉
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.)
Ping An Bank Co Ltd
Original Assignee
Ping An Bank 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 Ping An Bank Co Ltd filed Critical Ping An Bank Co Ltd
Priority to CN202011528718.XA priority Critical patent/CN112581227A/en
Publication of CN112581227A publication Critical patent/CN112581227A/en
Pending legal-status Critical Current

Links

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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24323—Tree-organised classifiers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/02—Banking, e.g. interest calculation or account maintenance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Health & Medical Sciences (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • General Health & Medical Sciences (AREA)
  • Technology Law (AREA)
  • Image Analysis (AREA)

Abstract

The invention relates to the field of artificial intelligence, and discloses a product recommendation method which comprises the steps of obtaining a user image, carrying out face feature recognition on the user image by using a face feature recognition model which is trained in advance to obtain a face feature image, and preprocessing the face feature image to obtain a standard face image; performing portrait matching on the standard face image and user portraits in a pre-established user portrait library, and taking the user portraits successfully matched with the portraits as target user portraits of the standard face image; inquiring user information of the standard face image from the target user portrait, and performing feature extraction on the user information to obtain user feature information; and selecting products with the association degree with the user characteristic information exceeding a preset threshold value from the products to be recommended, and pushing the selected products to the corresponding users. In addition, the invention also relates to a block chain technology, and the user characteristic information can be stored in the block chain. The invention can improve the accuracy of product recommendation.

Description

Product recommendation method and device, electronic equipment and storage medium
Technical Field
The present invention relates to the field of artificial intelligence, and in particular, to a method and an apparatus for recommending a product, an electronic device, and a computer-readable storage medium.
Background
Product recommendation refers to a process of pushing a product to a user, and is applied to different business scenarios, and product brand promotion can be realized based on product recommendation, for example, in order to enable the user to know the business product as much as possible and improve sales volume of the business product in business product operation of a bank, pushing of the business product is extremely important.
At present, a product recommendation method generally pushes a corresponding product to a user based on user group portrait analysis, and the product recommendation method cannot accurately position the interval range of the user, so that specific user preference information cannot be accurately depicted, and the accuracy of product recommendation is affected.
Disclosure of Invention
The invention provides a product recommendation method, a product recommendation device, electronic equipment and a computer-readable storage medium, and mainly aims to improve the accuracy of product recommendation.
In order to achieve the above object, the present invention provides a product recommendation method, including:
acquiring a user image, performing face feature recognition on the user image by using a face feature recognition model which is trained in advance to obtain a face feature image, and preprocessing the face feature image to obtain a standard face image;
performing portrait matching on the standard face image and user portraits in a user portrait library established in advance, and taking the user portraits successfully matched with the portrait as target user portraits of the standard face image;
inquiring user information of the standard face image from the target user portrait, and performing feature extraction on the user information to obtain user feature information;
and selecting products with the association degree with the user characteristic information exceeding a preset threshold value from the products to be recommended, and pushing the selected products to corresponding users.
Optionally, the performing feature extraction on the face image by using the pre-trained face feature recognition model to obtain a face feature image includes:
calculating the state value of the face image by using an input gate in the face feature recognition model, and calculating the activation value of the face image by using a forgetting gate in the face feature recognition model;
calculating a state updating value of the face image according to the state value and the activation value;
calculating a characteristic information sequence of the state updating value by using an output gate in the human face characteristic recognition model;
and calculating the loss values of the characteristic information sequences and the corresponding face image labels by using the loss function in the face feature recognition model, and selecting the characteristic information sequences with the loss values smaller than the preset loss values to obtain the face feature images.
Optionally, before portrait matching the standard face image with a user portrait in a pre-created user portrait library, the method further includes:
acquiring a user data set, and constructing a decision tree of the user data set by using a decision tree algorithm;
calculating a negative gradient of the user data set in the decision tree;
updating the decision tree according to the negative gradient until the decision tree tends to be stable to obtain a user portrait, and generating a user portrait library according to the user portrait
Optionally, the calculating a negative gradient of the user data set in the decision tree includes:
calculating a negative gradient of the user data set in the decision tree using:
Figure BDA0002851464630000021
wherein r isimA negative gradient is indicated and the gradient is,
Figure BDA0002851464630000022
denotes the learning rate, L (y)i,f(xi) Represents the loss function, yiPredicted value of sample data representing ith user data of user data set, f (x)i) The true value of sample data representing the ith user data of the user data set, f (x) the region function in the decision tree, fm-1(x)Representing the region fit function in the decision tree.
Optionally, the performing feature extraction on the user to obtain user feature information includes:
calculating an information weighted value of each user data in the user information, screening the user data with the information weighted value larger than a preset weighted value from the user information, and generating user characteristic information according to the screened user data.
Optionally, the calculating an information weight value of each piece of user data in the user information includes:
calculating an information weight value of each user data in the user information by using the following method:
Figure BDA0002851464630000023
wherein, CiInformation weight values representing user data, EiRepresents the ith user data in the user information,
Figure BDA0002851464630000024
represents the eigenvector covariance of the ith user data in the user information, and trace () represents the spatial filter function.
Optionally, the selecting a product from the products to be recommended, the association degree of which with the user characteristic information exceeds a preset threshold, includes:
identifying the product type of the product to be recommended, calculating the association degree of the product type and the user characteristic information, and selecting the corresponding product of the product type with the association degree larger than a preset threshold value.
In order to solve the above problems, the present invention also provides a product recommendation apparatus, comprising:
the recognition module is used for acquiring a user image, performing face feature recognition on the user image by using a pre-trained face feature recognition model to obtain a face feature image, and preprocessing the face feature image to obtain a standard face image;
the matching module is used for carrying out portrait matching on the standard face image and the user portrait in a user portrait library established in advance, and using the user portrait successfully matched with the portrait as a target user portrait of the standard face image;
the extraction module is used for inquiring the user information of the standard face image from the target user portrait and extracting the characteristics of the user information to obtain user characteristic information;
and the pushing module is used for selecting a product with the correlation degree with the user characteristic information exceeding a preset threshold value from products to be recommended and pushing the selected product to a corresponding user.
In order to solve the above problem, the present invention also provides an electronic device, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to implement the product recommendation method described above.
In order to solve the above problem, the present invention also provides a computer-readable storage medium having at least one computer program stored therein, the at least one computer program being executed by a processor in an electronic device to implement the product recommendation method described above.
The embodiment of the invention firstly obtains a user image, carries out face feature recognition on the user image by utilizing a face feature recognition model which is trained in advance to obtain a face feature image, and carries out preprocessing on the face feature image to obtain a standard face image, so that the quality of the face image can be improved, noise can be eliminated, the gray value and the size of the image can be unified, the standard face image is subjected to portrait matching with user portraits in a user portrait library which is created in advance, the user portraits which are successfully matched with the portraits are used as target user portraits of the standard face image, the comprehensiveness of user information acquisition is ensured, and the range of a user can be accurately positioned; secondly, the embodiment of the invention inquires the user information of the standard face image from the target user portrait, and performs feature extraction on the user information to obtain the user feature information, so that specific user preference information can be accurately described, and the accuracy of product recommendation can be improved; further, the embodiment of the invention selects products with the association degree with the user characteristic information exceeding a preset threshold value from the products to be recommended, and pushes the selected products to the corresponding users. Therefore, the product recommendation method, the product recommendation device, the electronic equipment and the storage medium can improve the product recommendation accuracy.
Drawings
Fig. 1 is a schematic flowchart of a product recommendation method according to an embodiment of the present invention;
FIG. 2 is a detailed flowchart illustrating a step of the product recommendation method provided in FIG. 1 according to a first embodiment of the present invention;
FIG. 3 is a block diagram of a product recommendation device according to an embodiment of the present invention;
fig. 4 is a schematic internal structural diagram of an electronic device implementing a product recommendation method according to an embodiment 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.
The embodiment of the application provides a product recommendation method. The execution subject of the product recommendation method includes, but is not limited to, at least one of electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiments of the present application. In other words, the product recommendation method may be performed by software or hardware installed in the terminal device or the server device, and the software may be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Referring to fig. 1, a flowchart of a product recommendation method according to an embodiment of the present invention is shown. In an embodiment of the present invention, the product recommendation method includes:
s1, obtaining a user image, carrying out face feature recognition on the user image by using the face feature recognition model which is trained in advance to obtain a face feature image, and carrying out preprocessing on the face feature image to obtain a standard face image.
In the embodiment of the invention, the user image is captured and shot through the camera, it should be understood that the image shot through the camera may include all body parts of a human body, and in order to more accurately analyze and compare the user image, the embodiment of the invention uses the pre-trained face feature recognition model to perform face recognition on the user image to obtain the face feature image. The face feature recognition model is composed of a Long Short-Term Memory network (LSTM) model, and is a time-cycle neural network and comprises the following components: an input gate, a forgetting gate and an output gate.
In the invention, the face feature recognition model is used for recognizing the face feature sequence of the user image so as to recognize face feature information and generate a face feature image, thereby helping a user to better judge the distribution condition of the face feature information in the user image.
In detail, the extracting the features of the face image by using the pre-trained face feature recognition model to obtain the face feature image includes: calculating a state value of the face image by using the input gate; calculating an activation value of the face image by using the forgetting gate; calculating a state updating value of the face image according to the state value and the activation value; calculating a sequence of signature information for the state update value using the output gate; and calculating the loss values of the characteristic information sequences and the corresponding face image labels by using the loss function in the face feature recognition model, and selecting the characteristic information sequences with the loss values smaller than the preset loss values to obtain the face feature images.
In an optional embodiment, the method for calculating the state value includes:
Figure BDA0002851464630000051
wherein itThe value of the state is represented by,
Figure BDA0002851464630000052
indicates the offset of the cell unit in the input gate, wiDenotes the activation factor of the input gate, ht-1Representing the peak, x, of the face image at time t-1 of the input gatetRepresenting the face image at time t, biRepresenting the weight of the cell units in the input gate.
In an optional embodiment, the method for calculating the activation value includes:
Figure BDA0002851464630000053
wherein f istThe value of the activation is represented by,
Figure BDA0002851464630000054
indicating the bias of the cell unit in the forgetting gate, wfAn activation factor that indicates that the door was forgotten,
Figure BDA0002851464630000055
the peak value x of the face image at the moment of the forgetting gate t-1 is showntIs shown at tFace image input at all times, bfRepresenting the weight of the cell unit in the forgetting gate.
In an optional embodiment, the method for calculating the state update value includes:
Figure BDA0002851464630000056
wherein, ctRepresents the state update value, ht-1Represents the peak value of the face image at the time of the input gate t-1,
Figure BDA0002851464630000057
and the peak value of the face image at the moment of forgetting the gate t-1 is shown.
In an optional embodiment, the method for calculating the characteristic information sequence includes:
ot＝tanh(ct)
wherein o istRepresenting a sequence of characteristic information, tanh representing an activation function of the output gate, ctRepresenting the state update value.
In an optional embodiment, the loss function is a softmax function, where the facial image tag refers to a facial feature information sequence that is previously indicated in a facial image by a user, and further, in the present invention, a feature information sequence with a loss value smaller than a preset loss value is selected as the feature information sequence to screen out feature information in the facial image, so as to generate a facial feature image. Optionally, the preset loss value is 0.1.
Further, the embodiment of the invention performs preprocessing operation on the face feature image to improve the quality of the face image, eliminate noise and unify the gray value and the size of the image. In detail, the pre-processing the face feature image to obtain a standard face image includes: executing gray level conversion operation on the face feature image through each proportion method to obtain a gray level face feature image; reducing noise of the gray level human face characteristic image by Gaussian filtering; eliminating isolated noise points of the gray-scale face characteristic image after noise reduction by adopting median filtering, and enhancing the contrast of the gray-scale face characteristic image after the isolated noise points are eliminated by utilizing contrast enhancement; and carrying out thresholding operation on the gray-level face feature image after the contrast enhancement according to an OTSU algorithm to obtain the standard face image.
S2, matching the standard face image with the user portrait in the user portrait base created in advance, and using the user portrait successfully matched as the target user portrait of the standard face image.
In the embodiment of the invention, the user image library is a set constructed by a plurality of user images, and the user images comprise user basic information (such as name, age, address and the like) and user behavior data (such as behavior tracks, preference items, interests and the like).
Further, before portrait matching the standard face image with a user portrait in a pre-created user portrait library, the embodiment of the present invention further includes: acquiring a user data set, and constructing a decision tree of the user data set by using a decision tree algorithm; calculating a negative gradient of the user data set in the decision tree; and updating the decision tree according to the negative gradient until the decision tree tends to be stable to obtain a user portrait, and generating a user portrait library according to the user portrait.
In an optional embodiment of the present invention, the principle of constructing the decision tree for constructing the user data set by using the decision tree algorithm is as follows: based on the input space where the user data set is located, recursively dividing each region in the input space into two sub-regions, determining an output value on each sub-region, and constructing a decision tree of the user data set according to the output values. Wherein the decision tree algorithm comprises an XGboost algorithm.
Further, the negative gradient refers to a residual of the user data set, and by fitting the residual of the user data set, robustness and reliability of the entire decision tree can be enhanced.
In a preferred embodiment, the negative gradient of the user data set in the decision tree is calculated using the following method:
Figure BDA0002851464630000061
wherein r isimA negative gradient is indicated and the gradient is,
Figure BDA0002851464630000062
denotes the learning rate, L (y)i,f(xi) Represents the loss function, yiPredicted value of sample data representing ith user data of user data set, f (x)i) The true value of sample data representing the ith user data of the user data set, f (x) the region function in the decision tree, fm-1(x)Representing the region fit function in the decision tree.
Furthermore, the embodiment of the invention carries out portrait matching on the standard face image and the user portrait in the pre-established user portrait library, and uses the user portrait successfully matched with the portrait as the target user portrait of the standard face image so as to inquire the user information of the standard face image.
In an alternative embodiment, the standard face image is portrait matched to a user portrait in a pre-created user portrait library using the following method:
Figure BDA0002851464630000063
wherein, R represents the portrait matching degree, Ai represents the ith standard face image, and Bi represents the ith user portrait in the user portrait library.
Further, the embodiment of the invention takes the user portrait with the portrait matching degree exceeding the preset portrait matching degree as the target user portrait of the standard face image. Optionally, the preset portrait matching degree is 0.95.
S3, inquiring the user information of the standard face image from the target user portrait, and carrying out feature extraction on the user information to obtain user feature information.
It should be understood that the user information corresponding to the standard face image exists in the target user portrait, and therefore, the embodiment of the invention better realizes product matching for the user by querying the user information of the standard face image from the target user portrait, and improves the accuracy of product recommendation. And querying the user information from the decision tree corresponding to the target user image through an sql query statement.
Further, since the user information includes the user basic information and the user behavior information, which may include a lot of useless user data, in order to increase the speed of recommending user products, the embodiment of the present invention performs feature extraction on the user to obtain user feature information.
In detail, the extracting the features of the user to obtain the user feature information includes: calculating an information weighted value of each user data in the user information, screening the user data with the information weighted value larger than a preset weighted value from the user information, and generating user characteristic information according to the screened user data. Optionally, the preset weight value is 0.88.
In an optional embodiment, the information weight value of each user data in the user information is calculated by using the following method:
Figure BDA0002851464630000071
wherein, CiInformation weight values representing user data, EiRepresents the ith user data in the user information,
Figure BDA0002851464630000072
represents the eigenvector covariance of the ith user data in the user information, and trace () represents the spatial filter function.
Further, to ensure the privacy and security of the user feature information, the user feature information may also be stored in a blockchain node.
S4, selecting products with the correlation degree exceeding a preset threshold value with the user characteristic information from the products to be recommended, and pushing the selected products to corresponding users.
In the embodiment of the invention, the product to be recommended is set based on user requirements, such as an advertisement product, and it should be understood that the product to be recommended contains many product types, and if product recommendation is directly performed on the product to be recommended to a user, some products which are not interesting to the user or are not interesting to the user are easily recommended, so that the accuracy of product recommendation is reduced.
In detail, referring to fig. 2, the selecting a product from the products to be recommended, the association degree of which with the user characteristic information exceeds a preset threshold, includes:
s20, identifying the product type of the product to be recommended, and calculating the association degree of the product type and the user characteristic information;
and S21, selecting the corresponding product of the product type with the relevance degree larger than the preset threshold value.
In an alternative embodiment, the predetermined threshold is 0.8.
In an optional embodiment, the product type is identified by a field of the product to be recommended, for example, if the field of the product to be recommended is ad, the corresponding product type is an advertisement product.
In an optional embodiment, the association degree between the product type and the user characteristic information is calculated by the following method:
Figure BDA0002851464630000081
wherein T (x, y) represents a degree of association, xiIndicates the ith product type, y, in the products to be recommendediIndicating the ith user characteristic information.
The embodiment of the invention firstly obtains a user image, carries out face feature recognition on the user image by utilizing a face feature recognition model which is trained in advance to obtain a face feature image, and carries out preprocessing on the face feature image to obtain a standard face image, so that the quality of the face image can be improved, noise can be eliminated, the gray value and the size of the image can be unified, the standard face image is subjected to portrait matching with user portraits in a user portrait library which is created in advance, the user portraits which are successfully matched with the portraits are used as target user portraits of the standard face image, the comprehensiveness of user information acquisition is ensured, and the range of a user can be accurately positioned; secondly, the embodiment of the invention inquires the user information of the standard face image from the target user portrait, and performs feature extraction on the user information to obtain the user feature information, so that specific user preference information can be accurately described, and the accuracy of product recommendation can be improved; further, the embodiment of the invention selects products with the association degree with the user characteristic information exceeding a preset threshold value from the products to be recommended, and pushes the selected products to the corresponding users. Therefore, the method and the device can improve the accuracy of product recommendation.
Fig. 3 is a functional block diagram of the product recommendation device of the present invention.
The product recommendation device 100 of the present invention may be installed in an electronic device. According to the implemented functions, the product recommendation device may include an identification module 101, a matching module 102, an extraction module 103, and a push module 104. A module according to the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the recognition module 101 is configured to acquire a user image, perform face feature recognition on the user image by using a pre-trained face feature recognition model to obtain a face feature image, and perform preprocessing on the face feature image to obtain a standard face image;
the matching module 102 is configured to perform portrait matching on the standard face image and a user portrait in a pre-created user portrait library, and use a user portrait with a portrait matching success as a target user portrait of the standard face image;
the extraction module 103 is configured to query user information of the standard face image from the target user portrait, and perform feature extraction on the user information to obtain user feature information;
the pushing module 104 is configured to select a product from the products to be recommended, where the association degree with the user feature information exceeds a preset threshold, and push the selected product to a corresponding user.
In detail, when the modules in the product recommendation device 100 in the embodiment of the present invention are used, the same technical means as the product recommendation method described in fig. 1 and fig. 2 are used, and the same technical effects can be produced, which is not described herein again.
Fig. 4 is a schematic structural diagram of an electronic device implementing the product recommendation method according to the present invention.
The electronic device 1 may comprise a processor 10, a memory 11 and a bus, and may further comprise a computer program, such as a product recommendation program 12, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only to store application software installed in the electronic device 1 and various types of data, such as codes for product recommendations, etc., but also to temporarily store data that has been output or is to be output.
The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device 1 by running or executing programs or modules (e.g., performing product recommendation, etc.) stored in the memory 11 and calling data stored in the memory 11.
The bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
Fig. 4 only shows an electronic device with components, and it will be understood by those skilled in the art that the structure shown in fig. 4 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than those shown, or some components may be combined, or a different arrangement of components.
For example, although not shown, the electronic device 1 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so as to implement functions of charge management, discharge management, power consumption management, and the like through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 1 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
Further, the electronic device 1 may further include a network interface, and optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a bluetooth interface, etc.), which are generally used for establishing a communication connection between the electronic device 1 and other electronic devices.
Optionally, the electronic device 1 may further comprise a user interface, which may be a Display (Display), an input unit (such as a Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the electronic device 1 and for displaying a visualized user interface, among other things.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The memory 11 in the electronic device 1 stores product recommendations 12 that are a combination of computer programs that, when executed in the processor 10, enable:
acquiring a user image, performing face feature recognition on the user image by using a face feature recognition model which is trained in advance to obtain a face feature image, and preprocessing the face feature image to obtain a standard face image;
performing portrait matching on the standard face image and user portraits in a user portrait library established in advance, and taking the user portraits successfully matched with the portrait as target user portraits of the standard face image;
inquiring user information of the standard face image from the target user portrait, and performing feature extraction on the user information to obtain user feature information;
and selecting products with the association degree with the user characteristic information exceeding a preset threshold value from the products to be recommended, and pushing the selected products to corresponding users.
Specifically, the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1 for a specific implementation method of the computer program, which is not described herein again.
Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a non-volatile computer-readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device, may implement:
acquiring a user image, performing face feature recognition on the user image by using a face feature recognition model which is trained in advance to obtain a face feature image, and preprocessing the face feature image to obtain a standard face image;
performing portrait matching on the standard face image and user portraits in a user portrait library established in advance, and taking the user portraits successfully matched with the portrait as target user portraits of the standard face image;
inquiring user information of the standard face image from the target user portrait, and performing feature extraction on the user information to obtain user feature information;
and selecting products with the association degree with the user characteristic information exceeding a preset threshold value from the products to be recommended, and pushing the selected products to corresponding users.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (10)

1. A method for recommending products, the method comprising:
acquiring a user image, performing face feature recognition on the user image by using a face feature recognition model which is trained in advance to obtain a face feature image, and preprocessing the face feature image to obtain a standard face image;
performing portrait matching on the standard face image and user portraits in a user portrait library established in advance, and taking the user portraits successfully matched with the portrait as target user portraits of the standard face image;
inquiring user information of the standard face image from the target user portrait, and performing feature extraction on the user information to obtain user feature information;
and selecting products with the association degree with the user characteristic information exceeding a preset threshold value from the products to be recommended, and pushing the selected products to corresponding users.
2. The product recommendation method of claim 1, wherein the extracting the features of the face image by using the pre-trained face feature recognition model to obtain the face feature image comprises:
calculating the state value of the face image by using an input gate in the face feature recognition model, and calculating the activation value of the face image by using a forgetting gate in the face feature recognition model;
calculating a state updating value of the face image according to the state value and the activation value;
calculating a characteristic information sequence of the state updating value by using an output gate in the human face characteristic recognition model;
and calculating the loss values of the characteristic information sequences and the corresponding face image labels by using the loss function in the face feature recognition model, and selecting the characteristic information sequences with the loss values smaller than the preset loss values to obtain the face feature images.
3. The product recommendation method of claim 1, wherein prior to portrait matching said standard face image with a user portrait in a pre-created user portrait library, further comprising:
acquiring a user data set, and constructing a decision tree of the user data set by using a decision tree algorithm;
calculating a negative gradient of the user data set in the decision tree;
and updating the decision tree according to the negative gradient until the decision tree tends to be stable to obtain a user portrait, and generating a user portrait library according to the user portrait.
4. The product recommendation method of claim 3, wherein said calculating a negative gradient of a user data set in said decision tree comprises:
calculating a negative gradient of the user data set in the decision tree using:
Figure FDA0002851464620000011
wherein r isimA negative gradient is indicated and the gradient is,
Figure FDA0002851464620000012
denotes the learning rate, L (y)i,f(xi) Represents the loss function, yiPredicted value of sample data representing ith user data of user data set, f (x)i) The true value of sample data representing the ith user data of the user data set, f (x) the region function in the decision tree, fm-1(x)Representing the region fit function in the decision tree.
5. The product recommendation method of claim 1, wherein said extracting features of said user to obtain user feature information comprises:
calculating an information weighted value of each user data in the user information, screening the user data with the information weighted value larger than a preset weighted value from the user information, and generating user characteristic information according to the screened user data.
6. The product recommendation method of claim 5, wherein said calculating an information weight value for each user data in said user information comprises:
calculating an information weight value of each user data in the user information by using the following method:
Figure FDA0002851464620000021
wherein, CiInformation weight values representing user data, EiRepresents the ith user data in the user information,
Figure FDA0002851464620000022
represents the eigenvector covariance of the ith user data in the user information, and trace () represents the spatial filter function.
7. The product recommendation method according to any one of claims 1 to 6, wherein selecting a product from the products to be recommended whose degree of association with the user feature information exceeds a preset threshold includes:
identifying the product type of the product to be recommended, calculating the association degree of the product type and the user characteristic information, and selecting the corresponding product of the product type with the association degree larger than a preset threshold value.
8. A product recommendation device, the device comprising:
the recognition module is used for acquiring a user image, performing face feature recognition on the user image by using a pre-trained face feature recognition model to obtain a face feature image, and preprocessing the face feature image to obtain a standard face image;
the matching module is used for carrying out portrait matching on the standard face image and the user portrait in a user portrait library established in advance, and using the user portrait successfully matched with the portrait as a target user portrait of the standard face image;
the extraction module is used for inquiring the user information of the standard face image from the target user portrait and extracting the characteristics of the user information to obtain user characteristic information;
and the pushing module is used for selecting a product with the correlation degree with the user characteristic information exceeding a preset threshold value from products to be recommended and pushing the selected product to a corresponding user.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the product recommendation method of any one of claims 1-7.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the product recommendation method of any one of claims 1 to 7.
CN202011528718.XA 2020-12-22 2020-12-22 Product recommendation method and device, electronic equipment and storage medium Pending CN112581227A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011528718.XA CN112581227A (en) 2020-12-22 2020-12-22 Product recommendation method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011528718.XA CN112581227A (en) 2020-12-22 2020-12-22 Product recommendation method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN112581227A true CN112581227A (en) 2021-03-30

Family

ID=75138839

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011528718.XA Pending CN112581227A (en) 2020-12-22 2020-12-22 Product recommendation method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112581227A (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113077317A (en) * 2021-04-19 2021-07-06 北京京东拓先科技有限公司 Item recommendation method, device and equipment based on user data and storage medium
CN113344673A (en) * 2021-06-28 2021-09-03 平安信托有限责任公司 Product pushing method and device, electronic equipment and storage medium
CN113362039A (en) * 2021-06-30 2021-09-07 深圳壹账通智能科技有限公司 Business approval method and device, electronic equipment and storage medium
CN113379581A (en) * 2021-08-16 2021-09-10 迅管(深圳)科技有限公司 Special service pushing method and system based on user portrait
CN113449002A (en) * 2021-06-28 2021-09-28 平安银行股份有限公司 Vehicle recommendation method and device, electronic equipment and storage medium
CN113486238A (en) * 2021-06-29 2021-10-08 平安信托有限责任公司 Information pushing method, device and equipment based on user portrait and storage medium
CN113554508A (en) * 2021-07-27 2021-10-26 未鲲(上海)科技服务有限公司 Virtual resource object matching method and device, electronic equipment and storage medium
CN114612194A (en) * 2022-03-23 2022-06-10 平安普惠企业管理有限公司 Product recommendation method and device, electronic equipment and storage medium

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113077317A (en) * 2021-04-19 2021-07-06 北京京东拓先科技有限公司 Item recommendation method, device and equipment based on user data and storage medium
CN113344673A (en) * 2021-06-28 2021-09-03 平安信托有限责任公司 Product pushing method and device, electronic equipment and storage medium
CN113449002A (en) * 2021-06-28 2021-09-28 平安银行股份有限公司 Vehicle recommendation method and device, electronic equipment and storage medium
CN113486238A (en) * 2021-06-29 2021-10-08 平安信托有限责任公司 Information pushing method, device and equipment based on user portrait and storage medium
CN113362039A (en) * 2021-06-30 2021-09-07 深圳壹账通智能科技有限公司 Business approval method and device, electronic equipment and storage medium
CN113554508A (en) * 2021-07-27 2021-10-26 未鲲(上海)科技服务有限公司 Virtual resource object matching method and device, electronic equipment and storage medium
CN113379581A (en) * 2021-08-16 2021-09-10 迅管(深圳)科技有限公司 Special service pushing method and system based on user portrait
CN114612194A (en) * 2022-03-23 2022-06-10 平安普惠企业管理有限公司 Product recommendation method and device, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
CN112581227A (en) Product recommendation method and device, electronic equipment and storage medium
CN112100425B (en) Label labeling method and device based on artificial intelligence, electronic equipment and medium
CN112231586A (en) Course recommendation method, device, equipment and medium based on transfer learning
CN112396005A (en) Biological characteristic image recognition method and device, electronic equipment and readable storage medium
CN114663198A (en) Product recommendation method, device and equipment based on user portrait and storage medium
CN113705462A (en) Face recognition method and device, electronic equipment and computer readable storage medium
CN113298159A (en) Target detection method and device, electronic equipment and storage medium
CN113886691A (en) Intelligent recommendation method and device based on historical data, electronic equipment and medium
CN114781832A (en) Course recommendation method and device, electronic equipment and storage medium
CN113592605A (en) Product recommendation method, device, equipment and storage medium based on similar products
CN114756669A (en) Intelligent analysis method and device for problem intention, electronic equipment and storage medium
CN114220536A (en) Disease analysis method, device, equipment and storage medium based on machine learning
CN114494800A (en) Prediction model training method and device, electronic equipment and storage medium
CN114022841A (en) Personnel monitoring and identifying method and device, electronic equipment and readable storage medium
CN113656690A (en) Product recommendation method and device, electronic equipment and readable storage medium
CN112269875A (en) Text classification method and device, electronic equipment and storage medium
CN112329666A (en) Face recognition method and device, electronic equipment and storage medium
CN112052310A (en) Information acquisition method, device, equipment and storage medium based on big data
CN111950707A (en) Behavior prediction method, apparatus, device and medium based on behavior co-occurrence network
CN114996386A (en) Business role identification method, device, equipment and storage medium
CN115203364A (en) Software fault feedback processing method, device, equipment and readable storage medium
CN114219367A (en) User scoring method, device, equipment and storage medium
CN114187476A (en) Vehicle insurance information checking method, device, equipment and medium based on image analysis
CN114610854A (en) Intelligent question and answer method, device, equipment and storage medium
CN113486238A (en) Information pushing method, device and equipment based on user portrait 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