CN115187331A - Product recommendation method, device, equipment and storage medium based on multi-modal data - Google Patents
Product recommendation method, device, equipment and storage medium based on multi-modal data Download PDFInfo
- Publication number
- CN115187331A CN115187331A CN202210730854.XA CN202210730854A CN115187331A CN 115187331 A CN115187331 A CN 115187331A CN 202210730854 A CN202210730854 A CN 202210730854A CN 115187331 A CN115187331 A CN 115187331A
- Authority
- CN
- China
- Prior art keywords
- product
- user
- recommended
- target
- products
- 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
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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9035—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9038—Presentation of query results
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (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 application provides a product recommendation method, a device, equipment and a storage medium based on multi-modal data, and the product recommendation method based on the multi-modal data comprises the following steps: acquiring a user browsing page of a target user and user behavior data associated with the user browsing page; generating product preference characteristics of the target user according to the user browsing page and user behavior data associated with the user browsing page; determining similarity according to the product preference characteristics and product basic characteristics of products to be recommended in a product database to be recommended, determining and recommending target products from the products to be recommended according to the similarity, and extracting the product basic characteristics from at least two of product image information, product text information and product audio information of the products to be recommended. By analyzing the user behavior data of the target user, the target product is determined according to the real-time product preference characteristics of the target user, and the recommendation precision of the target product is ensured.
Description
Technical Field
The application relates to the technical field of intelligent recommendation, in particular to a product recommendation method, device, equipment and storage medium based on multi-mode data.
Background
In the prior art, target product recommendation is generally performed through a preset target user interest identifier, however, interest products of a target user change with time, and if the update is not adjusted, the recommended products of the target user are not matched with the user requirements or preferences.
Disclosure of Invention
The application provides a product recommendation method, a product recommendation device and a storage medium based on multi-modal data.
In a first aspect, the present application provides a method for product recommendation based on multimodal data, comprising:
acquiring a user browsing page of a target user and user behavior data associated with the user browsing page;
generating product preference characteristics of the target user according to the user browsing page and user behavior data associated with the user browsing page;
determining similarity according to the product preference characteristics and product basic characteristics of products to be recommended in a product database to be recommended, and determining and recommending target products from the products to be recommended according to the similarity, wherein the product basic characteristics of the products to be recommended are extracted from at least two of product image information, product text information and product audio information of the products to be recommended in the recommended product database.
In one embodiment of the present application, the generating a product preference feature of the target user according to the user browsing page and the user behavior data associated with the user browsing page includes:
respectively extracting product basic characteristics of various products in each user browsing page;
according to the basic characteristics of the products, counting the browsing frequency and the browsing duration of the user behavior data corresponding to the same type of products;
and fusing the product basic characteristics corresponding to the similar products, the browsing frequency and the browsing duration to obtain the product preference characteristics of the target user.
In one embodiment of the present application, the counting browsing frequency and browsing duration in user behavior data corresponding to a similar product according to the product basic features includes:
when a target user is detected to browse a user browsing page, acquiring browsing duration of a basic product detail page corresponding to each product in the user browsing page;
if the browsing duration exceeds a preset threshold, acquiring product basic characteristics corresponding to the basic product detail page, and accumulating to obtain an accumulated value;
accumulating the browsing duration to obtain the accumulated browsing duration;
and calculating the browsing frequency in a preset period according to the accumulated value.
In one embodiment of the present application, the fusing the product basic features, the browsing frequency, and the browsing duration corresponding to the similar products to obtain the product preference features of the target user includes:
mapping based on a preset browsing duration mapping rule to obtain a first adjustment parameter corresponding to the browsing duration of the basic features of the product;
mapping based on a preset browsing frequency mapping rule to obtain a second adjustment parameter corresponding to the browsing frequency of the product basic feature;
and weighting the product basic characteristics based on the first adjustment parameters and the second adjustment parameters to obtain the product preference characteristics of the target user.
In one embodiment of the present application, the determining a similarity according to the product preference characteristics and the product basic characteristics of the product to be recommended in the product database to be recommended, and determining and recommending a target product from the product to be recommended according to the similarity includes:
the method comprises the steps of obtaining a product to be recommended and at least two of product image information, product character information and product audio information of the product to be recommended;
semantic alignment and fusion are carried out on the product image information, the product character information and the product audio information, and product basic characteristics of the product to be recommended are obtained;
and calculating the similarity between the product preference characteristics and the product basic characteristics of each product to be recommended, and setting the product to be recommended with the similarity higher than a preset similarity threshold as a target product for recommendation.
In one embodiment of the present application, the setting, as a target product, a product to be recommended whose similarity is higher than a preset similarity threshold for recommendation includes:
determining product preference characteristics with similarity higher than a preset similarity threshold value and preference degree values corresponding to the product preference characteristics with the similarity higher than the preset similarity threshold value;
setting a target product to be recommended, which is similar to the target product preference characteristics and corresponds to the target product preference characteristics;
the target products are sorted according to the corresponding preference degree values;
and recommending the sorted target products.
In one embodiment of the application, after determining similarity according to the product preference characteristics and product basic characteristics of a product to be recommended in a product database to be recommended, and determining and recommending a target product from the product to be recommended according to the similarity, the method includes:
collecting user behavior data of the target user on a product recommendation page corresponding to the target product;
updating the product preference characteristics of the target user according to the user behavior data of the product recommendation page;
and adjusting the target product according to the updated product preference characteristic and the product basic characteristic of the target product.
In a second aspect, the present application provides a product recommendation device based on multimodal data, the device comprising:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a user browsing page of a target user and user behavior data associated with the user browsing page;
the data processing module is used for generating product preference characteristics of the target user according to the user browsing page and user behavior data associated with the user browsing page;
and the recommending module is used for determining similarity according to the product preference characteristics and the product basic characteristics of the products to be recommended in the product database to be recommended, and determining and recommending target products from the products to be recommended according to the similarity, wherein the product basic characteristics of the products to be recommended are extracted from at least two of product image information, product text information and product audio information of the products to be recommended in the recommended product database.
In a third aspect, the present application provides a product recommendation device based on multi-modal data, including:
one or more processors;
a memory; and
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement any of the multimodal data based product recommendation methods.
In a fourth aspect, the present application provides a computer readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to perform any of the steps of the method for multi-modal data based product recommendation.
The application provides a product recommendation method, a product recommendation device, product recommendation equipment and a storage medium based on multi-mode data, wherein a user browsing page of a target user and user behavior data related to the user browsing page are obtained; then generating product preference characteristics of the target user according to the user browsing page and user behavior data associated with the user browsing page; and finally, determining similarity according to the product preference characteristics and the product basic characteristics of the products to be recommended in the product database to be recommended, and determining and recommending target products from the products to be recommended according to the similarity, wherein the product basic characteristics of the products to be recommended are extracted from at least two of product image information, product text information and product audio information of the products to be recommended in the recommended product database. The method comprises the steps of determining product preference characteristics of a target user through a user browsing page and user behavior data, automatically updating and identifying the product preference of the target user in real time, matching the product preference characteristics of the target user with product basic characteristics of a product to be recommended according to the product preference characteristics automatically updated in real time, confirming the corresponding target product and recommending the target product to the target user, avoiding limitation of recommending the target product based on preset preference information of the target user, and further ensuring recommendation accuracy of the target product.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of a scenario of a method for recommending a product based on multimodal data provided in an embodiment of the present application;
FIG. 2 is a schematic flow diagram illustrating one embodiment of a method for product recommendation of multimodal data as provided in an embodiment of the present application;
FIG. 3 is a schematic flow chart diagram illustrating one embodiment of the product preference feature capture in the product recommendation method for multimodal data as provided in the examples herein;
FIG. 4 is a flowchart illustrating an embodiment of statistics of browsing frequency and browsing duration in the method for recommending multi-modal data for a product provided in the embodiment of the present application;
FIG. 5 is a schematic flow diagram of one embodiment of the determination and recommendation of a target product in the product recommendation method for multimodal data provided in the embodiments of the present application;
FIG. 6 is a schematic flow diagram of another embodiment of a method for product recommendation of multimodal data provided in an embodiment of the present application;
FIG. 7 is a schematic structural diagram of an embodiment of a multi-modal data based product recommendation device provided in an embodiment of the present application;
FIG. 8 is a structural diagram of an embodiment of a multi-modal data based product recommendation device provided in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be considered as limiting the present invention. Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
In this application, the word "exemplary" is used to mean "serving as an example, instance, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the invention. In the following description, details are set forth for the purpose of explanation. It will be apparent to one of ordinary skill in the art that the present invention may be practiced without these specific details. In other instances, well-known structures and processes are not shown in detail to avoid obscuring the description of the invention with unnecessary detail. Thus, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.
The embodiments of the present application provide a method, an apparatus, a device, a storage medium, and a computer-readable storage medium for recommending a product based on multimodal data, which are described in detail below.
The product recommendation method of the multi-modal data is applied to a product recommendation device of the multi-modal data, the product recommendation device of the multi-modal data is arranged in a product recommendation device of the multi-modal data, one or more processors, a memory and one or more application programs are arranged in the product recommendation device of the multi-modal data, and the one or more application programs are stored in the memory and configured to be executed by the processor to realize the product recommendation method of the multi-modal data; the product recommendation device for multi-modal data can be a terminal, such as a mobile phone or a tablet computer, and the product recommendation device for multi-modal data can also be a server or a service cluster formed by a plurality of servers.
As shown in fig. 1, fig. 1 is a schematic view of a scene of a multi-modal data product recommendation method according to an embodiment of the present application, where the scene of multi-modal data product recommendation includes a multi-modal data product recommendation device 100 (a multi-modal data product recommendation apparatus is integrated in the multi-modal data product recommendation device 100), and the multi-modal data product recommendation device 100 runs a computer-readable storage medium corresponding to product recommendation of multi-modal data to perform a step of multi-modal data product recommendation.
It should be understood that the product recommendation device for multi-modal data in the scenario of the product recommendation method for multi-modal data shown in fig. 1, or the apparatuses included in the product recommendation device for multi-modal data, do not limit the embodiments of the present invention, that is, the number of apparatuses and the types of apparatuses included in the scenario of the product recommendation method for multi-modal data, or the number of apparatuses and the types of apparatuses included in each apparatus do not affect the overall implementation of the technical solution in the embodiments of the present invention, and can be calculated as equivalent replacements or derivatives of the technical solution claimed in the embodiments of the present invention.
The product recommendation device 100 for multi-modal data in the embodiment of the present invention is mainly used for: acquiring a user browsing page of a target user and user behavior data associated with the user browsing page; generating product preference characteristics of a target user according to a user browsing page and user behavior data associated with the user browsing page; determining similarity according to the product preference characteristics and the product basic characteristics of the products to be recommended in the product database to be recommended, and determining and recommending target products from the products to be recommended according to the similarity, wherein the product basic characteristics of the products to be recommended are extracted from at least two of product image information, product text information and product audio information of the products to be recommended in the recommended product database.
The product recommendation device 100 for multi-modal data in the embodiment of the present invention may be an independent product recommendation device for multi-modal data, or may be a product recommendation device network for multi-modal data or a product recommendation device cluster for multi-modal data, for example, the product recommendation device 100 for multi-modal data described in the embodiment of the present invention includes, but is not limited to, a computer, a network host, a product recommendation device for single network multi-modal data, a product recommendation device set for multiple network multi-modal data, or a product recommendation device for cloud multi-modal data formed by multiple product recommendation devices for multi-modal data. The product recommendation device for cloud multi-modal data is composed of a large number of computers based on cloud computing (cloud computing) or a product recommendation device for network multi-modal data.
Those skilled in the art can understand that the application environment shown in fig. 1 is only one application scenario related to the present application scheme, and does not constitute a limitation on the application scenario of the present application scheme, and that other application environments may further include more or less product recommendation devices of multi-modal data than those shown in fig. 1, or a network connection relationship of the product recommendation devices of multi-modal data, for example, only 1 product recommendation device of multi-modal data is shown in fig. 1, and it can be understood that the scenario of the product recommendation method of multi-modal data may further include one or more product recommendation devices of other multi-modal data, and is not limited herein; the multi-modal data product recommendation device 100 may further include a memory for storing data, for example, user information of a target user, product information of a product to be recommended, and the like.
In addition, in the scene of the product recommendation method for multimodal data, the product recommendation device 100 for multimodal data may be provided with a display device, or the product recommendation device 100 for multimodal data is not provided with a display device which is in communication connection with an external display device 200, and the display device 200 is used for outputting a result of the product recommendation method for multimodal data in the product recommendation device for multimodal data. The product recommendation device 100 for multi-modal data may access the background database 300 (the background database may be a local memory of the product recommendation device for multi-modal data, and may also be set in the cloud), and the background database 300 stores information related to product recommendation for multi-modal data, for example, user information of a target user in the background database 300, or product information of a product to be recommended.
It should be noted that the scene schematic diagram of the product recommendation method for multimodal data shown in fig. 1 is only an example, and the scene of the product recommendation method for multimodal data described in the embodiment of the present invention is for more clearly explaining the technical solution of the embodiment of the present invention, and does not form a limitation on the technical solution provided in the embodiment of the present invention.
Based on the scene of the product recommendation method of the multi-modal data, the embodiment of the product recommendation method of the multi-modal data is provided.
As shown in fig. 2, a flowchart of an embodiment of a multi-modal data based product recommendation method in the embodiment of the present application is shown, where the multi-modal data based product recommendation method includes steps S201 to S203:
s201, acquiring a user browsing page of a target user and user behavior data associated with the user browsing page.
The target users are recommended audience users, it can be understood that the recommended audience users can include a plurality of recommended audience users, the target users do not limit a certain user and include any recommended audience user, for example, when the product recommendation method based on the multi-mode data is applied to product business in a mobile phone bank APP, the target users are any user of the audience users stored in a mobile phone bank APP background database, and it can be understood that user information of the target users can be obtained when the users log in the mobile phone bank APP for the first time, and the user information of the target users is stored in the bank APP background database.
The user browses a page, that is, a product page browsed by a target user, the user browses the page and may include product information of a plurality of products, and the user behavior data is operations such as a detail viewing page, product shielding and the like, which are performed on the browsed page by the user.
It can be understood that, in the embodiment of the present application, the product recommendation device based on the multimodal data may be a mobile phone, that is, it can be understood that the user information of the target user may be obtained according to the mobile phone, and when the target user logs in the bank APP, the browsing information of the target user and the user behavior data associated with the user browsing page may be associated with the target user, that is, it can be understood that the user browsing page corresponding to the target user and the user behavior data associated with the user browsing page may be obtained according to the user identification information of the target user.
S202, generating product preference characteristics of the target user according to the user browsing page and user behavior data associated with the user browsing page.
The product preference characteristics, namely the product basic characteristics liked by the target user, can be obtained by analyzing the user behavior data of the target user.
Specifically, referring to fig. 3, an embodiment of obtaining the product preference feature in one embodiment of the present application includes steps S301 to S303:
s301, product basic features of various products in the browsing page of each user are respectively extracted.
Wherein, various products, that is, each basic product in the user browsed page browsed by the target user, and product basic features, that is, product features of each basic product in the user browsed page browsed by the target user, for example, the user browsed page includes basic products: extracting basic product features corresponding to the mobile phone, wherein the basic product features can be designed according to application scenarios, and the basic product features include: specifically, for example, when a target user browses a user browsing page through a mobile banking APP, the product types, the product prices, and the product colors of all basic products in the user browsing page are extracted, the product types are used as main features, and the product prices and the product colors corresponding to the product types are used as auxiliary features to be associated with the product types to form product basic features.
It can be understood that the extraction of the basic features of the product can be obtained by extracting keywords from the product name field, the image of the basic product, or the audio introduction of the basic product of each basic product in the user browsing page, and by using a trained preset product basic feature extraction model.
S302, according to the basic characteristics of the products, the browsing frequency and the browsing duration of the user behavior data corresponding to the similar products are counted.
The browsing duration may be accumulated browsing duration for the target user to browse the products corresponding to the same product basic feature, or may be total browsing duration for the target user to browse the products accumulated corresponding to the same product basic feature, which is not specifically limited in the present application.
The browsing frequency is the frequency of a product corresponding to the same product basic feature browsed by the target user, and may be calculated according to the browsing frequency in a preset time period and the preset time period by counting the browsing times in the preset time period, or may be calculated according to the number of the same product basic features of a page browsed by the user and the browsing times of a product corresponding to the same product basic feature browsed by the target user, and the specific application is not particularly limited.
Specifically, referring to fig. 4, a statistical implementation of browsing frequency and browsing duration in one embodiment of the present application specifically includes steps S401 to S404:
s401, when it is detected that a target user browses a page by the user, browsing duration of a basic product detail page corresponding to each product in the user browsing page is collected.
S402, if the browsing time exceeds a preset threshold, obtaining the product basic characteristics corresponding to the basic product detail page, and accumulating to obtain an accumulated value.
And S403, accumulating the browsing duration to obtain the accumulated browsing duration.
S404, calculating the browsing frequency in a preset period according to the accumulated value.
The basic product detail pages, namely the detail pages corresponding to each basic product in the user browsing pages, can be understood that the user browses the basic products displayed on the pages and does not display the detail pages of each basic product, and the basic product detail pages corresponding to the basic products can be displayed to the target user only after detecting the detail page viewing request of the user basic products.
The preset threshold is used for comparing with the browsing duration, and then whether the detail page checking request is misoperation of the target user is judged.
Specifically, when it is detected that a target user browses a page by the user, acquiring browsing duration of a basic product detail page corresponding to each product in the browsing page of the user, for example, when it is detected that the target user initiates a detail page viewing request, starting a timing task corresponding to the detail page viewing request, when it is detected that the target user starts a detail page viewing instruction to close, stopping the timing task, and further acquiring browsing duration corresponding to the detail page viewing request, in an embodiment of the present application, the timing task is accumulated from zero, after the browsing duration corresponding to the detail page viewing request is acquired, screening and determining the browsing duration, and when it is detected that the browsing duration exceeds a preset threshold, acquiring product basic features corresponding to the basic product detail page.
It can be understood that the product basic features corresponding to the basic product detail page can be searched and acquired according to the product name or the product identification information, and it can be understood that when it is detected that the browsing duration does not exceed the preset threshold, the browsing duration is ignored, and the browsing frequency is not calculated, that is, when it is detected that the browsing duration does not exceed the preset threshold, it indicates that the browsing time of the target user is too short, and it is possible that the detail page viewing request is a misoperation of the target user, that is, the viewing behavior of the basic product detail page of the target user is filtered through the browsing duration, so that the influence of the misoperation of the target user on the browsing time of the detail page of the target user and further the calculation of the browsing frequency is avoided, and further the influence on the precision of the product preference features of the target user is avoided.
Specifically, when the product basic feature is obtained, whether a corresponding accumulated value exists in the product basic feature is determined, if yes, an accumulation operation is added on the basis of the accumulated value to update the accumulated value to obtain a corresponding accumulated value, and if no corresponding accumulated value exists in the product basic feature, the accumulated value corresponding to the product basic feature is recorded as 1.
Specifically, when the product basic features are obtained, whether corresponding historical browsing time exists in the product basic features or not is determined, if yes, the historical browsing time and the browsing time are added and accumulated to obtain accumulated browsing duration, and if not, the browsing time and the product basic features are associated and correspond to each other.
Specifically, in the embodiment of the present application, the browsing frequency in the preset period is calculated according to the obtained accumulated value, and it can be understood that the preset period is a preset time period, and the preset period may be specifically designed according to actual requirements.
S303, fusing basic characteristics, browsing frequency and browsing duration of products corresponding to the same type of products to obtain product preference characteristics of the target user.
Specifically, in the embodiment of the present application, the obtaining of the product preference characteristics of the target user specifically includes:
(1) Mapping to obtain a first adjusting parameter corresponding to the browsing time of the basic characteristics of the product based on a preset browsing time mapping rule;
(2) Mapping based on a preset browsing frequency mapping rule to obtain a second adjusting parameter corresponding to the browsing frequency of the basic features of the product;
(3) And weighting the basic characteristics of the product based on the first adjusting parameter and the second adjusting parameter to obtain the product preference characteristics of the target user.
The product basic characteristics are more in line with the preference of the target user to the basic product corresponding to the browsing time and the browsing frequency, that is, the browsing time and the browsing frequency are converted into the first adjustment parameter and the second adjustment parameter for weighting the product basic characteristics.
S203, determining the similarity according to the product preference characteristics and the product basic characteristics of the products to be recommended in the product database to be recommended, and determining and recommending the target products from the products to be recommended according to the similarity.
The product basic features are products to be recommended in a product database to be recommended, and it can be understood that the product basic features are extracted from at least two of product image information, product text information and product audio information of the products to be recommended after detecting that the basic products to be recommended are added into the product database.
Specifically, referring to fig. 5, the embodiment of determining and recommending a target product in one embodiment of the present application specifically includes the steps of: S501-S503:
s501, obtaining a product to be recommended and at least two of product image information, product character information and product audio information of the product to be recommended;
s502, semantically aligning and fusing product image information, product character information and product audio information to obtain product basic characteristics of a product to be recommended;
s503, calculating the similarity between the product preference characteristics and the product basic characteristics of the products to be recommended, and setting the products to be recommended with the similarity higher than a preset similarity threshold as target products for recommendation.
Specifically, after a basic product to be recommended is added into a detected product database, a product to be recommended and at least two of product image information, product text information and product audio information of the product to be recommended are obtained, the product image information, the product text information and the product audio information are input into a preset comparison learning neural network for semantic alignment, semantic alignment and fusion are performed through a preset single tower model, product basic characteristics of the product to be recommended are obtained, then the similarity between the product preference characteristics and the product basic characteristics of each product to be recommended is calculated, and the product to be recommended with the similarity higher than a preset similarity threshold is set as a target product for recommendation.
The method includes the steps that a product to be recommended with similarity higher than a preset similarity threshold is set as a target product to be recommended, and recommendation is carried out, and the method specifically includes the following steps:
(1) Determining product preference characteristics with the similarity higher than a preset similarity threshold value and preference degree values corresponding to the product preference characteristics with the similarity higher than the preset similarity threshold value;
(2) Setting a target product to be recommended, which is similar to the preference characteristics of the target product and corresponds to the preference characteristics of the target product;
(3) Sequencing the target products according to the corresponding preference degree values;
(4) And recommending the sorted target products.
The preference degree value is associated with each product preference feature, specifically, the product preference feature value is used to indicate a preference degree of a target user to each product preference feature, and it can be understood that the preference degree value can be obtained according to statistical data of a product basic feature corresponding to the product preference feature, for example, referring to the above embodiment, a first adjustment parameter corresponding to a browsing duration is obtained based on mapping of a preset browsing duration mapping rule; mapping based on a preset browsing frequency mapping rule to obtain a second adjustment parameter corresponding to the browsing frequency; and performing weighting adjustment on the preset initial preference degree value based on the first adjustment parameter and the second adjustment parameter to obtain a preference degree value, and storing the preference degree value and the corresponding product preference characteristics in an associated manner.
Referring to fig. 6, on the basis of any of the above embodiments, step S203 is followed by steps S601-S602:
s601, collecting user behavior data of a target user on a product recommendation page corresponding to a target product;
s602, updating product preference characteristics of a target user according to user behavior data of a product recommendation page;
and S603, adjusting the target product according to the updated product preference characteristic and the product basic characteristic of the target product.
The target product corresponds to a product recommendation page, that is, the product recommendation page including the target product, it can be understood that after the target product is determined, the target product may include a plurality of target products, the product recommendation page including the plurality of target products is generated based on a preset product recommendation page template, and the product recommendation page corresponds to the target user for display.
Specifically, the user behavior data of the product recommendation page corresponding to the target product is collected, that is, after the user behavior data is displayed, it can be understood that the collection of the user behavior data can be collected in a click instruction, a slide instruction and other manners of the target user, and specifically, when it is detected that the target user browses the product recommendation page, the browsing duration of the target product detail page corresponding to the product recommendation page is collected; if the browsing duration exceeds a preset threshold, acquiring product basic characteristics corresponding to the basic product detail pages, and accumulating to obtain an accumulated value; accumulating the browsing time to obtain the accumulated browsing time; the browsing frequency in the preset period is calculated according to the accumulated value, and the specific embodiment can be described with reference to the above embodiment.
Further, according to the updated product preference characteristics and the product basic characteristics of the target product, adjusting the target product, wherein the step of obtaining a first adjustment parameter corresponding to the browsing time of the product basic characteristics based on the mapping of a preset browsing time mapping rule is included; mapping based on a preset browsing frequency mapping rule to obtain a second adjusting parameter corresponding to the browsing frequency of the basic features of the product; and weighting the target product characteristics based on the first adjustment parameter and the second adjustment parameter, further determining a new target product based on the weighted target product characteristics, and adding the new target product into a product recommendation page to realize the adjustment of the target product.
The application provides a product recommendation method based on multi-modal data, which comprises the steps of obtaining a user browsing page of a target user and user behavior data related to the user browsing page; then, generating product preference characteristics of a target user according to the user browsing page and user behavior data associated with the user browsing page; and finally, determining similarity according to the product preference characteristics and the product basic characteristics of the product to be recommended in the product database to be recommended, and determining and recommending a target product from the product to be recommended according to the similarity, wherein the product basic characteristics of the product to be recommended are extracted from at least two of product image information, product text information and product audio information of the product to be recommended in the recommended product database. The product preference characteristics of the target user are determined through the user browsing page and the user behavior data, the product preference of the target user is automatically updated and identified in real time, the user matches the product preference characteristics automatically updated in real time with the product basic characteristics of the product to be recommended, confirms the corresponding target product and recommends the target product to the target user, limitation of recommending the target product based on preset preference information of the target user is avoided, and recommendation accuracy of the target product is further guaranteed.
In order to better implement the multi-modal data based product recommendation method in the embodiment of the present application, on the basis of the multi-modal data based product recommendation method, a multi-modal data based product recommendation device is further provided in the embodiment of the present application, as shown in fig. 7, the multi-modal data based product recommendation device includes 701-703:
an obtaining module 701, configured to obtain a user browsing page of a target user and user behavior data associated with the user browsing page;
the data processing module 702 is configured to generate a product preference feature of a target user according to a user browsing page and user behavior data associated with the user browsing page;
the recommending module 703 is configured to determine similarity according to the product preference feature and a product basic feature of a product to be recommended in a product database to be recommended, and determine and recommend a target product from the product to be recommended according to the similarity, where the product basic feature of the product to be recommended is extracted from at least two of product image information, product text information, and product audio information of the product to be recommended in the recommended product database.
In some embodiments of the present application, the data processing module 702 is configured to generate the product preference feature of the target user according to the user browsing page and the user behavior data associated with the user browsing page, and specifically includes:
respectively extracting product basic characteristics of various products in each user browsing page;
according to the basic characteristics of the products, counting the browsing frequency and the browsing duration of the user behavior data corresponding to the same type of products;
and fusing the basic product characteristics, the browsing frequency and the browsing duration corresponding to the similar products to obtain the product preference characteristics of the target user.
In some embodiments of the present application, the data processing module 702 is configured to count browsing frequency and browsing duration in user behavior data corresponding to a similar product according to product basic features, and specifically includes:
when a target user is detected to browse a user browsing page, acquiring browsing duration of a basic product detail page corresponding to each product in the user browsing page;
if the browsing time exceeds a preset threshold, acquiring product basic characteristics corresponding to the basic product detail page, and accumulating to obtain an accumulated value;
accumulating the browsing time to obtain the accumulated browsing time;
and calculating the browsing frequency in a preset period according to the accumulated value.
In some embodiments of the present application, the data processing module 702 is configured to fuse product basic features, browsing frequency, and browsing duration corresponding to similar products to obtain a product preference feature of a target user, and specifically includes:
mapping based on a preset browsing duration mapping rule to obtain a first adjustment parameter corresponding to the browsing duration of the basic features of the product;
mapping based on a preset browsing frequency mapping rule to obtain a second adjustment parameter corresponding to the browsing frequency of the basic characteristics of the product;
and weighting the basic characteristics of the product based on the first adjusting parameter and the second adjusting parameter to obtain the product preference characteristics of the target user.
In some embodiments of the present application, the recommending module 703 is configured to determine a similarity according to the product preference feature and a product basic feature of a product to be recommended in a product database to be recommended, and determine and recommend a target product from the product to be recommended according to the similarity, specifically including:
acquiring a product to be recommended and at least two of product image information, product character information and product audio information of the product to be recommended;
semantic alignment and fusion are carried out on the product image information, the product character information and the product audio information, and product basic characteristics of a product to be recommended are obtained;
and calculating the similarity between the preference characteristics of the product and the basic characteristics of the products to be recommended, and setting the products to be recommended with the similarity higher than a preset similarity threshold as target products for recommendation.
In some embodiments of the present application, the recommending module 703 is configured to set a product to be recommended, whose similarity is higher than a preset similarity threshold, as a target product for recommendation, and specifically includes:
determining product preference characteristics with the similarity higher than a preset similarity threshold value and preference degree values corresponding to the product preference characteristics with the similarity higher than the preset similarity threshold value;
setting a target product to be recommended, which is similar to the preference characteristics of the target product and corresponds to the preference characteristics of the target product;
sequencing the target products according to the corresponding preference degree values;
and recommending the sorted target products.
In some embodiments of the present application, the multi-modal data based product recommendation apparatus further comprises an adjustment module configured to:
collecting user behavior data of a target user on a product recommendation page corresponding to a target product;
updating the product preference characteristics of the target user according to the user behavior data of the product recommendation page;
and adjusting the target product according to the updated product preference characteristic and the product basic characteristic of the target product.
The application provides a product recommendation device based on multi-modal data, which is characterized in that a user browsing page of a target user and user behavior data associated with the user browsing page are obtained; then, generating product preference characteristics of a target user according to the user browsing page and user behavior data associated with the user browsing page; and finally, determining similarity according to the product preference characteristics and the product basic characteristics of the products to be recommended in the product database to be recommended, and determining and recommending target products from the products to be recommended according to the similarity, wherein the product basic characteristics of the products to be recommended are extracted from at least two of product image information, product text information and product audio information of the products to be recommended in the recommended product database. The product preference characteristics of the target user are determined through the user browsing page and the user behavior data, the product preference of the target user is automatically updated and identified in real time, the user matches the product preference characteristics automatically updated in real time with the product basic characteristics of the product to be recommended, confirms the corresponding target product and recommends the target product to the target user, limitation of recommending the target product based on preset preference information of the target user is avoided, and recommendation accuracy of the target product is further guaranteed.
An embodiment of the present invention further provides a product recommendation device based on multi-modal data, as shown in fig. 8, fig. 8 is a schematic structural diagram of an embodiment of the product recommendation device based on multi-modal data provided in the embodiment of the present application.
The product recommendation device based on multi-modal data integrates any one of the product recommendation devices based on multi-modal data provided by the embodiment of the invention, and comprises:
one or more processors;
a memory; and
one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the processor for performing the steps of the multi-modal data based product recommendation method in any of the above embodiments of the multi-modal data based product recommendation method.
Specifically, the method comprises the following steps: the multimodal data based product recommendation device may include components such as a processor 801 of one or more processing cores, memory 802 of one or more computer-readable storage media, a power supply 803, and an input unit 804. Those skilled in the art will appreciate that the multi-modal data based product recommendation device structure illustrated in FIG. 8 does not constitute a limitation of multi-modal data based product recommendation devices, and may include more or fewer components than illustrated, or some components in combination, or a different arrangement of components. Wherein:
the processor 801 is a control center of the multi-modal data based product recommendation device, connects various parts of the entire multi-modal data based product recommendation device by using various interfaces and lines, and executes various functions and processes data of the multi-modal data based product recommendation device by running or executing software programs and/or modules stored in the memory 802 and calling the data stored in the memory 802, thereby performing overall monitoring of the multi-modal data based product recommendation device. Alternatively, processor 801 may include one or more processing cores; preferably, the processor 801 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 801.
The memory 802 may be used to store software programs and modules, and the processor 801 executes various functional applications and data processing by operating the software programs and modules stored in the memory 802. The memory 802 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created from use of the multi-modal data based product recommendation device, and the like. Further, the memory 802 may include high speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 802 may also include a memory controller to provide the processor 801 access to the memory 802.
The multi-modal data based product recommendation device further comprises a power supply 803 for supplying power to each component, and preferably, the power supply 803 can be logically connected with the processor 801 through a power management system, so that functions of charging, discharging, power consumption management and the like can be managed through the power management system. The power supply 803 may also include any component of one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.
The multi-modal data based product recommendation device may further include an input unit 804, the input unit 804 operable to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.
Although not shown, the multi-modal data based product recommendation device may further include a display unit or the like, which will not be described herein. Specifically, in this embodiment, the processor 801 in the product recommendation device based on multimodal data loads the executable file corresponding to the process of one or more application programs into the memory 802 according to the following instructions, and the processor 801 runs the application programs stored in the memory 802, thereby implementing various functions as follows:
acquiring a user browsing page of a target user and user behavior data associated with the user browsing page;
generating product preference characteristics of a target user according to a user browsing page and user behavior data associated with the user browsing page;
determining similarity according to the product preference characteristics and product basic characteristics of products to be recommended in a product database to be recommended, and determining and recommending target products from the products to be recommended according to the similarity, wherein the product basic characteristics of the products to be recommended are extracted from at least two of product image information, product text information and product audio information of the products to be recommended in the recommended product database.
It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions, or by instructions controlling associated hardware, which may be stored in a computer-readable storage medium and loaded and executed by a processor.
To this end, an embodiment of the present invention provides a computer-readable storage medium, which may include: a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and the like. Stored thereon, is a computer program that is loaded by a processor to perform the steps of any of the methods for multimodal data based product recommendation provided by embodiments of the present invention. For example, the computer program may be loaded by a processor to perform the steps of:
acquiring a user browsing page of a target user and user behavior data associated with the user browsing page;
generating product preference characteristics of a target user according to a user browsing page and user behavior data associated with the user browsing page;
determining similarity according to the product preference characteristics and product basic characteristics of products to be recommended in a product database to be recommended, and determining and recommending target products from the products to be recommended according to the similarity, wherein the product basic characteristics of the products to be recommended are extracted from at least two of product image information, product text information and product audio information of the products to be recommended in the recommended product database.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and parts that are not described in detail in a certain embodiment may refer to the above detailed descriptions of other embodiments, and are not described herein again.
In a specific implementation, each unit or structure may be implemented as an independent entity, or may be combined arbitrarily to be implemented as one or several entities, and the specific implementation of each unit or structure may refer to the foregoing method embodiment, which is not described herein again.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
The method, the apparatus, the device and the storage medium for recommending a product based on multimodal data provided in the embodiments of the present application are described in detail above, and a specific example is applied in the present application to explain the principle and the implementation of the present invention, and the description of the above embodiments is only used to help understanding the method and the core idea of the present invention; meanwhile, for those skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A method for product recommendation based on multimodal data, comprising:
acquiring a user browsing page of a target user and user behavior data associated with the user browsing page;
generating product preference characteristics of the target user according to the user browsing page and user behavior data associated with the user browsing page;
determining similarity according to the product preference characteristics and product basic characteristics of products to be recommended in a product database to be recommended, and determining and recommending target products from the products to be recommended according to the similarity, wherein the product basic characteristics of the products to be recommended are extracted from at least two of product image information, product text information and product audio information of the products to be recommended in the recommended product database.
2. The multi-modal data based product recommendation method of claim 1, wherein generating product preference characteristics of the target user based on the user browsed pages and user behavior data associated with the user browsed pages comprises:
respectively extracting product basic characteristics of various products in each user browsing page;
according to the basic characteristics of the products, counting browsing frequency and browsing duration in user behavior data corresponding to the same type of products;
and fusing the product basic characteristics corresponding to the similar products, the browsing frequency and the browsing duration to obtain the product preference characteristics of the target user.
3. The multi-modal data-based product recommendation method of claim 2, wherein the step of counting browsing frequency and browsing duration in user behavior data corresponding to the same type of product according to the product basic features comprises:
when a target user is detected to browse a user browsing page, acquiring browsing duration of a basic product detail page corresponding to each product in the user browsing page;
if the browsing duration exceeds a preset threshold, acquiring product basic characteristics corresponding to the basic product detail page, and accumulating to obtain an accumulated value;
accumulating the browsing duration to obtain the accumulated browsing duration;
and calculating the browsing frequency in a preset period according to the accumulated value.
4. The multi-modal data-based product recommendation method according to claim 2, wherein the fusing the product basic features, the browsing frequency and the browsing duration corresponding to the same kind of products to obtain the product preference features of the target user comprises:
mapping based on a preset browsing duration mapping rule to obtain a first adjustment parameter corresponding to the browsing duration of the product basic feature;
mapping based on a preset browsing frequency mapping rule to obtain a second adjusting parameter corresponding to the browsing frequency of the basic features of the product;
and weighting the product basic characteristics based on the first adjustment parameters and the second adjustment parameters to obtain the product preference characteristics of the target user.
5. The method for recommending products based on multimodal data as claimed in claim 1, wherein said determining similarity according to the product preference characteristics and the product base characteristics of the products to be recommended in the product database to be recommended, and determining and recommending the target product from the products to be recommended according to the similarity comprises:
acquiring a product to be recommended and at least two of product image information, product character information and product audio information of the product to be recommended;
semantic alignment and fusion are carried out on the product image information, the product text information and the product audio information to obtain product basic characteristics of the product to be recommended;
and calculating the similarity between the product preference characteristics and the product basic characteristics of the products to be recommended, and setting the products to be recommended with the similarity higher than a preset similarity threshold as target products for recommendation.
6. The multi-modal data based product recommendation method according to claim 5, wherein the recommending the product to be recommended with similarity higher than a preset similarity threshold by setting the product to be recommended as the target product comprises:
determining product preference characteristics with similarity higher than a preset similarity threshold value and preference degree values corresponding to the product preference characteristics with the similarity higher than the preset similarity threshold value;
setting a target product to be recommended, which is similar to the target product preference characteristics and corresponds to the target product preference characteristics;
the target products are sorted according to the corresponding preference degree values;
and recommending the sorted target products.
7. The multi-modal data based product recommendation method of claim 1, wherein after determining the similarity according to the product preference characteristics and the product base characteristics of the products to be recommended in the product database to be recommended, and determining and recommending the target products from the products to be recommended according to the similarity, the method comprises:
collecting user behavior data of the target user on a product recommendation page corresponding to the target product;
updating the product preference characteristics of the target user according to the user behavior data of the product recommendation page;
and adjusting the target product according to the updated product preference characteristic and the product basic characteristic of the target product.
8. A product recommendation device based on multimodal data, the device comprising:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a user browsing page of a target user and user behavior data associated with the user browsing page;
the data processing module is used for generating product preference characteristics of the target user according to the user browsing page and user behavior data associated with the user browsing page;
and the recommending module is used for determining similarity according to the product preference characteristics and the product basic characteristics of the products to be recommended in the product database to be recommended, and determining and recommending target products from the products to be recommended according to the similarity, wherein the product basic characteristics of the products to be recommended are extracted from at least two of product image information, product text information and product audio information of the products to be recommended in the recommended product database.
9. A multi-modal data-based product recommendation device, the multi-modal data-based product recommendation device comprising:
one or more processors;
a memory; and
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the multimodal data based product recommendation method of any of claims 1-7.
10. A computer-readable storage medium, having stored thereon a computer program which is loaded by a processor to perform the steps of the method for multi-modal data based recommendation of a product according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210730854.XA CN115187331A (en) | 2022-06-24 | 2022-06-24 | Product recommendation method, device, equipment and storage medium based on multi-modal data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210730854.XA CN115187331A (en) | 2022-06-24 | 2022-06-24 | Product recommendation method, device, equipment and storage medium based on multi-modal data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115187331A true CN115187331A (en) | 2022-10-14 |
Family
ID=83515879
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210730854.XA Pending CN115187331A (en) | 2022-06-24 | 2022-06-24 | Product recommendation method, device, equipment and storage medium based on multi-modal data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115187331A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116975396A (en) * | 2023-09-25 | 2023-10-31 | 北京市大数据中心 | Intelligent recommendation method, system, equipment and storage medium for government service |
| CN117474636A (en) * | 2023-12-27 | 2024-01-30 | 广州宇中网络科技有限公司 | Platform user recommendation method and system based on big data |
| CN117611245A (en) * | 2023-12-14 | 2024-02-27 | 浙江博观瑞思科技有限公司 | Data analysis management system and method for planning E-business operation activities |
| CN117835170A (en) * | 2023-10-16 | 2024-04-05 | 深圳市天一泓科技有限公司 | Intelligent short message sending method and system based on short message template |
-
2022
- 2022-06-24 CN CN202210730854.XA patent/CN115187331A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116975396A (en) * | 2023-09-25 | 2023-10-31 | 北京市大数据中心 | Intelligent recommendation method, system, equipment and storage medium for government service |
| CN117835170A (en) * | 2023-10-16 | 2024-04-05 | 深圳市天一泓科技有限公司 | Intelligent short message sending method and system based on short message template |
| CN117611245A (en) * | 2023-12-14 | 2024-02-27 | 浙江博观瑞思科技有限公司 | Data analysis management system and method for planning E-business operation activities |
| CN117611245B (en) * | 2023-12-14 | 2024-05-31 | 浙江博观瑞思科技有限公司 | Data analysis management system and method for planning E-business operation activities |
| CN117474636A (en) * | 2023-12-27 | 2024-01-30 | 广州宇中网络科技有限公司 | Platform user recommendation method and system based on big data |
| CN117474636B (en) * | 2023-12-27 | 2024-04-12 | 广州宇中网络科技有限公司 | Platform user recommendation method and system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115187331A (en) | Product recommendation method, device, equipment and storage medium based on multi-modal data | |
| CN101990668B (en) | Recommendation information generation apparatus and recommendation information generation method | |
| WO2020233360A1 (en) | Method and device for generating product evaluation model | |
| CN113051362B (en) | Data query method, device and server | |
| CN111611284A (en) | Material list generation method and electronic equipment | |
| CN112699295A (en) | Webpage content recommendation method and device and computer readable storage medium | |
| JP7150228B2 (en) | Recommendation method, device, storage medium, terminal equipment, and program | |
| CN107547646B (en) | Application program pushing method and device, terminal and computer readable storage medium | |
| CN114332931A (en) | Pet relation map updating method, device, equipment and computer-readable storage medium | |
| WO2024179519A1 (en) | Semantic recognition method and apparatus | |
| CN108021713B (en) | Document clustering method and device | |
| CN115204889A (en) | Text processing method and device, computer equipment and storage medium | |
| CN111625737A (en) | Label display method, device, equipment and storage medium | |
| EP3828712A1 (en) | Data parsing method and device | |
| CN115118774A (en) | Equipment updating method and device, electronic equipment and storage medium | |
| CN112200602B (en) | Neural network model training method and device for advertisement recommendation | |
| CN114357293A (en) | Object recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN114428894A (en) | Page search analysis method, device, equipment and medium | |
| CN113434585A (en) | Resource saving method and equipment | |
| CN115774797A (en) | Video content retrieval method, device, equipment and computer readable storage medium | |
| US9753901B1 (en) | Identifying important document content using geometries of page elements | |
| CN113821596A (en) | Information recommendation method and device, computer equipment and storage medium | |
| CN113407859B (en) | Resource recommendation method and device, electronic equipment and storage medium | |
| CN117725303B (en) | Content query method, device and computer readable storage medium | |
| CN113052632B (en) | Advertisement traffic data identification method, device, equipment 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 |