CN115587873A - Artificial intelligence based commodity recommendation system and method - Google Patents
Artificial intelligence based commodity recommendation system and method Download PDFInfo
- Publication number
- CN115587873A CN115587873A CN202211357918.2A CN202211357918A CN115587873A CN 115587873 A CN115587873 A CN 115587873A CN 202211357918 A CN202211357918 A CN 202211357918A CN 115587873 A CN115587873 A CN 115587873A
- Authority
- CN
- China
- Prior art keywords
- commodity
- user
- data
- module
- mall
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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]
- G06Q30/0641—Shopping interfaces
- G06Q30/0643—Graphical representation of items or shoppers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a commodity recommendation system and method based on artificial intelligence, wherein the commodity recommendation system based on artificial intelligence comprises a virtual market construction module, a commodity data acquisition module, a commodity classification module, a user data acquisition module, a data processing module, a user model construction module, a commodity recommendation module and a display module. The virtual mall building module is used for building a three-dimensional model of the virtual mall, the commodity data obtaining module and the commodity classifying module are used for realizing classification of similar commodities, the user data obtaining module and the user model building module are used for carrying out feature extraction and portrait drawing on a user, and the commodity recommending module selects commodities matched with the user and displays the commodities on a user terminal through the display module.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a commodity recommendation system and method based on artificial intelligence.
Background
With the advancement of science and technology, the development of market economy and the improvement of living standard of people, a large number of commodities appear, not only are the commodities of various types, but also the commodities with the same performance or similar performance under different types are particularly numerous, and customers can spend a large amount of time to find the commodities which the customers want to buy. This process of viewing large amounts of unrelated information and products will undoubtedly result in constant loss of consumers who are overwhelmed by the problem of information overload.
In order to solve the problems, a personalized recommendation system is developed, which recommends information, products and the like interested by a user to the user according to the information demand, interest and the like of the user. Compared with a search engine, the recommendation system carries out personalized calculation by researching the interest preference of the user, and the system finds the interest points of the user, so that the user is guided to find the own information requirement. A good recommendation system not only can provide personalized services for users, but also can establish close relations with the users, and the users can generate dependence on the recommendation. The personalized recommendation system is a high-level business intelligent platform established on the basis of mass data mining to help an e-commerce website to provide completely personalized decision support and information service for shopping of customers.
However, in the existing commodity recommendation method, the relevant commodities are usually recommended only by tracking the commodity browsing records, consumption records and the like of the user on line, and other influencing factors are ignored; meanwhile, the recommendation form of the existing system is not intelligent enough, and the user can not experience the interest of shopping.
Disclosure of Invention
The invention is based on the problems, and provides a commodity recommendation system and a method based on artificial intelligence.
In view of the above, one aspect of the present invention provides a commodity recommendation system based on artificial intelligence, including a virtual mall building module, a commodity data acquisition module, a commodity classification module, a user data acquisition module, a data processing module, a user model building module, a commodity recommendation module, and a display module;
the virtual mall building module is used for building a mall three-dimensional model of the virtual mall according to the acquired mall building data of the entity mall and the mall preference data of the user to the entity mall; the shopping mall three-dimensional model comprises a shop three-dimensional model of each shop;
the commodity data acquisition module is used for acquiring commodity data, wherein the commodity data comprises a commodity number, a commodity attribute, a commodity image and a commodity brand category;
the commodity classification module is used for inputting the commodity data into a first convolution neural network to classify the commodity to obtain commodity classification data;
the data processing module is used for processing the commodity data and the commodity classification data to obtain commodity display data, and associating the commodity display data with the corresponding shop three-dimensional model;
the user data acquisition module is used for acquiring user data, wherein the user data comprises a user number, a user shopping place, user shopping time, an interactive commodity number and an interactive behavior;
the user model building module is used for building a user model according to the user data and the second convolutional neural network;
the commodity recommendation module is used for establishing a user preference commodity library and recommending commodities to the user;
the display module is used for displaying the shopping entrance on an interface of a user terminal for the user to select;
the display module is further used for displaying the three-dimensional model of the shopping mall in a first visual angle form of the user after the user selects a shopping entrance;
the display module is further used for displaying the three-dimensional model of the shop and the three-dimensional images of the commodities in the shop in a first visual angle mode of the user after receiving a shop selection instruction of the user.
Optionally, the user model building module is configured to build a user model according to the user data and a second convolutional neural network, specifically:
inputting the user data into the second convolutional neural network, and acquiring user shopping feature data of the user based on different shopping places and/or different shopping times according to the interactive commodity numbers and the interactive behaviors;
and constructing the user model according to the user shopping characteristic data and the user data.
Optionally, the commodity classifying module is configured to input the commodity data into a first convolutional neural network to classify a commodity to obtain commodity classification data, and includes:
determining any commodity as a current commodity from a pre-acquired commodity library, wherein other commodities in the commodity library are reference commodities;
constructing a current commodity vector based on the commodity data of the current commodity, and respectively constructing each reference commodity vector based on the commodity data of the reference commodity;
respectively calculating the similarity between the current commodity vector and each reference commodity vector, and determining the commodity corresponding to the reference commodity vector with the similarity larger than a similarity threshold value as a similar commodity;
the commodity recommendation module is used for establishing a user preference commodity library and recommending commodities to the user, and specifically comprises the following steps:
acquiring a user characteristic vector from the user model, calculating a correlation value of the user characteristic vector and the current commodity vector, and determining commodities and similar commodities corresponding to the current commodity vector as the user preference commodity library when the correlation value is greater than a correlation value threshold;
and generating a three-dimensional image of each commodity in the user preference commodity library and synchronizing the three-dimensional image to the corresponding shop three-dimensional model.
Optionally, the system further comprises a mall building data acquisition module; the mall building data acquisition module is used for identifying an entity mall building drawing and a real-time photo and extracting the mall building data;
the virtual mall building module is used for building a mall three-dimensional model of the virtual mall according to the acquired mall building data of the entity mall and the mall preference data of the entity mall of the user, and specifically comprises the following steps:
establishing the BIM model of the virtual mall according to the acquired mall building data of the entity mall and the mall favorite data of the user on the entity mall;
and (3) after analyzing, converting, rendering and lightening the BIM model of the virtual market, importing the BIM model into three-dimensional modeling software to generate the three-dimensional model of the market.
Optionally, a personalized customization module is further included;
the personalized customization module is used for generating a commodity model to be customized according to the user preference commodity library and the user model;
constructing a three-dimensional image of the product to be customized according to the commodity model to be customized;
and synchronizing the three-dimensional image of the product to be customized to the corresponding shop three-dimensional model.
The invention provides a commodity recommendation method based on artificial intelligence, which is applied to a commodity recommendation system based on artificial intelligence, wherein the commodity recommendation system based on artificial intelligence comprises a virtual market building module, a commodity data acquisition module, a commodity classification module, a user data acquisition module, a data processing module, a user model building module, a commodity recommendation module and a display module; the method comprises the following steps:
establishing a market three-dimensional model of a virtual market according to the acquired market building data of the entity market and the market preference data of the user to the entity market; the shopping mall three-dimensional model comprises a shop three-dimensional model of each shop;
acquiring commodity data, wherein the commodity data comprises a commodity number, commodity attributes, a commodity image and a commodity brand category;
inputting the commodity data into a first convolutional neural network to classify the commodity to obtain commodity classification data;
obtaining commodity display data according to the commodity data and the commodity classification data, and associating the commodity display data with the corresponding shop three-dimensional model;
acquiring user data, wherein the user data comprises a user number, a user shopping place, user shopping time, an interactive commodity number and interactive behaviors;
constructing a user model according to the user data and a second convolutional neural network;
establishing a user preference commodity library and recommending commodities to the user;
displaying a shopping entry on an interface of a user terminal for selection by the user;
after the user selects a shopping entrance, displaying the three-dimensional model of the shopping mall in a first visual angle form of the user;
after receiving a shop selection instruction of a user, displaying the three-dimensional shop model and the three-dimensional images of the commodities in the shop in a first visual angle form of the user.
Optionally, in the step of constructing a user model according to the user data and the second convolutional neural network, specifically:
inputting the user data into the second convolutional neural network, and acquiring user shopping feature data of the user based on different shopping places and/or different shopping times according to the interactive commodity numbers and the interactive behaviors;
and constructing the user model according to the user shopping characteristic data and the user data.
Optionally, the step of inputting the commodity data into a first convolutional neural network to classify the commodity to obtain commodity classification data includes:
determining any commodity as a current commodity from a pre-acquired commodity library, wherein other commodities in the commodity library are reference commodities;
constructing a current commodity vector based on the commodity data of the current commodity, and respectively constructing each reference commodity vector based on the commodity data of the reference commodity;
respectively calculating the similarity between the current commodity vector and each reference commodity vector, and determining that the commodity corresponding to the reference commodity vector with the similarity larger than a similarity threshold value is a similar commodity;
the steps of establishing a user preference commodity library and recommending commodities to the user are specifically as follows:
acquiring a user characteristic vector from the user model, calculating a correlation value of the user characteristic vector and the current commodity vector, and determining commodities and similar commodities corresponding to the current commodity vector as the user preference commodity library when the correlation value is greater than a correlation value threshold;
and generating a three-dimensional image of each commodity in the user preference commodity library and synchronizing the three-dimensional image to the corresponding shop three-dimensional model.
Optionally, the method further comprises the step of: identifying an entity market building drawing and a real-area photo, and extracting the market building data;
the step of establishing a three-dimensional market model of the virtual market according to the acquired market building data of the entity market and the market preference data of the entity market by the user is specifically as follows:
establishing a BIM (building information model) of the virtual mall according to the acquired mall building data of the entity mall and the mall preference data of the user to the entity mall;
and (3) after analyzing, converting, rendering and lightening the BIM model of the virtual market, importing the BIM model into three-dimensional modeling software to generate the three-dimensional model of the market.
Optionally, the method further comprises the step of:
generating a commodity model to be customized according to the user preference commodity library and the user model;
constructing a three-dimensional image of the product to be customized according to the commodity model to be customized;
and synchronizing the three-dimensional graph of the product to be manufactured to the corresponding three-dimensional model of the shop.
By adopting the technical scheme of the invention, the artificial intelligence-based commodity recommendation system is provided with a virtual market construction module, a commodity data acquisition module, a commodity classification module, a user data acquisition module, a data processing module, a user model construction module, a commodity recommendation module and a display module. The virtual mall building module is used for building a three-dimensional model of the virtual mall, the commodity data obtaining module and the commodity classifying module are used for realizing classification of similar commodities, the user data obtaining module and the user model building module are used for carrying out feature extraction and portrait drawing on a user, and the commodity recommending module selects commodities matched with the user and displays the commodities on a user terminal through the display module.
Drawings
FIG. 1 is a schematic block diagram of an artificial intelligence based merchandise recommendation system provided in accordance with an embodiment of the present invention;
fig. 2 is a flowchart of a method for recommending commodities based on artificial intelligence according to another embodiment of the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention, taken in conjunction with the accompanying drawings and detailed description, is set forth below. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced otherwise than as specifically described herein and, therefore, the scope of the present invention is not limited by the specific embodiments disclosed below.
In the description of the present invention, the terms "plurality" or "a plurality" refer to two or more, and unless otherwise specifically limited, the terms "upper", "lower", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are merely for convenience in describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus should not be construed as limiting the present invention. The terms "connected," "mounted," "secured," and the like are to be construed broadly and include, for example, fixed connections, removable connections, or integral connections; may be directly connected or indirectly connected through an intermediate. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations. Furthermore, the terms "first", "second", etc. 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, a feature defined as "first," "second," etc. may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the description of the specification, reference to "one embodiment," "some embodiments," "a specific embodiment," or the like, means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
An artificial intelligence based goods recommendation system and method provided according to some embodiments of the present invention will be described below with reference to fig. 1 to 2.
As shown in fig. 1, an embodiment of the present invention provides an artificial intelligence based product recommendation system, including: the system comprises a virtual mall building module, a commodity data acquisition module, a commodity classification module, a user data acquisition module, a data processing module, a user model building module, a commodity recommendation module and a display module;
the virtual mall building module is used for building a mall three-dimensional model of the virtual mall according to the acquired mall building data of the entity mall and the mall preference data of the user to the entity mall; the shopping mall three-dimensional model comprises a shop three-dimensional model of each shop;
the commodity data acquisition module is used for acquiring commodity data, wherein the commodity data comprises a commodity number, a commodity attribute, a commodity image and a commodity brand category;
the commodity classification module is used for inputting the commodity data into a first convolutional neural network trained in advance to classify commodities to obtain commodity classification data;
the data processing module is used for processing the commodity data and the commodity classification data to obtain commodity display data, and associating the commodity display data with the corresponding shop three-dimensional model;
the system comprises a user data acquisition module, a user data acquisition module and a display module, wherein the user data acquisition module is used for acquiring user data, and the user data comprises a user number, a user shopping place, user shopping time, an interactive commodity number and interactive behaviors, and the interactive behaviors comprise product clicking, browsing, access frequency, collection, addition to a shopping cart, removal from the shopping cart, collection, purchase, sharing, member registration, shopping coupon picking, goods returning, goods changing, complaint, refund, comment, card swiping and recharging;
the user model building module is used for building a user model according to the user data and a pre-trained second convolutional neural network;
the commodity recommendation module is used for establishing a user preference commodity library and recommending commodities to the user;
the display module is used for displaying the shopping entrance on an interface of a user terminal for the user to select;
the display module is further used for displaying the three-dimensional model of the mall in a first visual angle form of the user after the user selects a shopping entrance;
the display module is further used for displaying the three-dimensional model of the shop and the three-dimensional images of the commodities in the shop in a first visual angle mode of the user after receiving a shop selection instruction of the user.
By adopting the technical scheme of the embodiment, the artificial intelligence-based commodity recommendation system is provided with a virtual market building module, a commodity data acquisition module, a commodity classification module, a user data acquisition module, a data processing module, a user model building module, a commodity recommendation module and a display module. The virtual mall building module is used for building a three-dimensional model of the virtual mall, the commodity data obtaining module and the commodity classifying module are used for realizing classification of similar commodities, the user data obtaining module and the user model building module are used for carrying out feature extraction and portrait drawing on a user, and the commodity recommending module selects commodities matched with the user and displays the commodities on a user terminal through the display module.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Artificial intelligence is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. Based on big data and a deep learning model, a user portrait can be constructed according to information such as basic features, browsing behaviors, access frequency and purchasing behaviors of a user, the interests, purchasing abilities, consumption habits and the like of the user can be known in a multi-dimensional mode, the user can be known more clearly and comprehensively, and the user is not divided simply according to demographic features such as regional distribution, age and gender.
It should be understood that the block diagram of the artificial intelligence based merchandise recommendation system shown in fig. 1 is merely illustrative, and the number of the illustrated modules does not limit the scope of the present invention.
In some possible embodiments of the present invention, the user model building module is configured to build a user model according to the user data and a second convolutional neural network, specifically:
inputting the user data into the second convolutional neural network, and obtaining user shopping characteristic data of the user based on different shopping places and/or different shopping times according to the interactive commodity numbers and the interactive behaviors;
and constructing the user model according to the user shopping characteristic data and the user data.
It can be understood that, in order to recommend a commodity more suitable for the user's needs to the user, in an embodiment of the present invention, the user data is input into a trained second convolutional neural network, and user shopping feature data of the user based on different shopping places and/or different shopping times is obtained according to the interactive commodity numbers and the interactive behaviors, it should be noted that the interactive behaviors of the user at different shopping places and different shopping times may have a larger difference, and if the difference is not obtained, the precision of recommending the commodity to the user may be affected, for example, a browsing object of the user at a work place may be an office product or a commodity recommended by a colleague, and an object browsed at home may have more household products; the time difference is more reflected in the aspects of seasons, festivals and the like. Therefore, in the embodiment of the invention, a plurality of user models are constructed by using the user shopping characteristic data and the user data based on different shopping places and/or different shopping times.
In some possible embodiments of the present invention, the commodity classification module is configured to input the commodity data into a first convolutional neural network to classify a commodity to obtain commodity classification data, and includes:
determining any commodity as a current commodity from a pre-acquired commodity library, wherein other commodities in the commodity library are reference commodities;
constructing a current commodity vector based on the commodity data of the current commodity, and respectively constructing each reference commodity vector based on the commodity data of the reference commodity;
respectively calculating the similarity between the current commodity vector and each reference commodity vector, and determining the commodity corresponding to the reference commodity vector with the similarity larger than a similarity threshold value as a similar commodity;
the commodity recommendation module is used for establishing a user preference commodity library and recommending commodities to the user, and specifically comprises the following steps:
obtaining a user characteristic vector from the user model, calculating a correlation value of the user characteristic vector and the current commodity vector, and determining commodities and similar commodities corresponding to the current commodity vector as the user preference commodity library when the correlation value is greater than a correlation value threshold;
and generating a three-dimensional image of each commodity in the user preference commodity library and synchronizing the three-dimensional image to the corresponding shop three-dimensional model.
It can be understood that the user feature vector obtained from the user model includes preference information of the user for the commodity, the user feature vector and the current commodity vector are subjected to vector calculation, the obtained association value is the matching condition of the commodity corresponding to the current commodity vector and the user, the higher the association value is, the higher the matching degree is, the commodity corresponding to the current commodity vector is closer to the real demand commodity of the user, and thus the commodity corresponding to the current commodity vector and the similar commodity can be recommended to the user as the preference commodity of the user. The similarity between the current commodity vector and each reference commodity vector is calculated, so that similar commodities can be determined for each commodity in a commodity library acquired in advance, accurate classification of the commodities is achieved, and conditions are provided for calculating the association degree by using the user feature vector and the current commodity vector to accurately and quickly select a preference commodity library of a user.
It is understood that, in some possible embodiments, similarity calculation is performed on the user model and the user models of other users, when the similarity is within a preset similarity threshold, the two users may be considered as being similar to each other, and the goods matching the user models of the other users may be recommended to the user corresponding to the user model.
In some possible embodiments of the present invention, the system further comprises a mall building data acquisition module; the mall building data acquisition module is used for identifying an entity mall building drawing and a real-time photo and extracting mall building data;
the virtual mall construction module is used for establishing a mall three-dimensional model of the virtual mall according to the acquired mall construction data of the entity mall and the mall preference data of the entity mall by the user, and specifically comprises the following steps:
establishing a BIM (building information model) of the virtual mall according to the acquired mall building data of the entity mall and the mall preference data of the user to the entity mall;
and (3) leading the BIM model of the virtual market into three-dimensional modeling software after analysis, conversion, rendering and weight reduction, and generating the three-dimensional model of the market.
It is understood that the BIM model is a Building Information Model (BIM). Furthermore, in order to enable the three-dimensional model of the market to be more real and vivid, the physical market construction drawing can be called from the existing database, and the field photo can also be shot on site by an unmanned aerial vehicle with a camera and a robot. The construction drawing mainly comprises a construction drawing, a structure construction drawing, an equipment construction drawing, a completion drawing, engineering change data and the like, wherein the construction drawing is used for representing the planning position, the external shape and the arrangement condition of each internal room of a building and mainly comprises a general plane drawing, a plane drawing, an elevation drawing, a section drawing, a construction detail drawing and the like; the structure construction drawing is used for representing the structure type, the structure arrangement, the component type, the quantity and the like of the load-bearing structure of the building, and mainly comprises a structure plane arrangement drawing, a structure detailed drawing of each component and the like; the equipment construction drawing is used for representing the arrangement and construction requirements of equipment for water supply and drainage, heating and ventilation, power supply and illumination and the like of a building, and mainly comprises a plane arrangement drawing, a system drawing and an installation detailed drawing of the equipment for water supply and drainage, heating and ventilation, electricity and the like; the completion drawing is a drawing drawn according to the actual construction situation and comprises the actual trend of pipelines and the actual installation situation of other equipment in civil engineering, building construction engineering, electrical installation engineering and water supply and drainage engineering; the type of the required drawing can be determined according to different requirements for building the three-dimensional model, after the construction drawing of the entity market is selected, the drawing can be led into a BIM modeling platform (such as Revit), parameters are modified according to preference data of a user to the entity market, and the BIM model of the virtual market is built.
Of course, the point cloud data of the existing building can be collected by the unmanned aerial vehicle or the robot equipped with the three-dimensional laser scanner to obtain the actual geometric information of the entity market, and the BIM model established based on the point cloud data can express the actual geometric information and the attribute information of the existing building. After point cloud data and drawing data of an entity market are obtained, the drawing data and the point cloud data are imported to the same BIM modeling platform (such as Revit) and combined with favorite data of a user to the entity market to complete BIM modeling.
And (3) after analyzing, converting, rendering and lightening the virtual market BIM model, importing the virtual market BIM model into three-dimensional modeling software (such as Smart 3D) to generate the market three-dimensional model.
In some possible embodiments of the invention, the system further comprises a personalization customization module;
the personalized customization module is used for generating a commodity model to be customized according to the user preference commodity library and the user model;
constructing a three-dimensional image of the product to be customized according to the commodity model to be customized;
and synchronizing the three-dimensional image of the product to be customized to the corresponding shop three-dimensional model.
It will be appreciated that in order to provide the user with merchandise that better fits his or her needs, the system also includes a personalized customization module to provide customized merchandise. According to the user preference commodity library, data of commodities closest to user requirements can be obtained; and then obtaining demand data and interest data of the user from the user model, correcting the commodity which is closest to the demand of the user according to the demand data and the interest data, generating a to-be-customized commodity model, further constructing a three-dimensional image of the to-be-customized product, and synchronizing the three-dimensional image of the to-be-customized product to the corresponding shop three-dimensional model so as to display the three-dimensional image of the to-be-customized product on the shop three-dimensional model for the user to browse and select.
In order to further acquire the real requirements of the user, in another possible embodiment of the invention, the system further comprises an intelligent head-mounted device configured with a brain wave acquisition module; the user terminal is an intelligent device with a communication function and a display function;
the intelligent head-mounted equipment can be connected with the intelligent equipment through a wired or wireless network, the intelligent equipment comprises a computer, a mobile phone, a palm computer and the like, and the intelligent head-mounted equipment acquires electroencephalogram signals induced by visual stimulation to obtain data required by analysis;
the intelligent equipment is provided with a brain wave compiling module which can receive the brain wave signals collected and sent by the brain wave collecting module, analyze the brain wave signals and compile the analyzed signals into a marking instruction for marking the user interaction behaviors and transmit the marking instruction to the intelligent equipment; the marking instruction is mainly used for marking the user interaction behavior, and information of degrees of 'like', 'generally like', 'not like a lot' and the like can be obtained according to the strength of the electroencephalogram signal representing 'like', and the intelligent device can mark the user interaction behavior in the above-mentioned way.
And the intelligent equipment receives the compiled marking instruction, executes the marking instruction, and stores the received marking instruction after arranging.
The intelligent equipment feeds back the execution result to the user, and the user can evaluate the execution result so as to adjust the working accuracy of the brain wave compiling module.
Referring to fig. 2, another embodiment of the present invention provides an artificial intelligence based product recommendation method, which is applied to an artificial intelligence based product recommendation system, where the artificial intelligence based product recommendation system includes a virtual mall construction module, a product data acquisition module, a product classification module, a user data acquisition module, a data processing module, a user model construction module, a product recommendation module, and a display module; the method comprises the following steps:
establishing a market three-dimensional model of a virtual market according to the acquired market building data of the entity market and the market preference data of the entity market by the user; the shopping mall three-dimensional model comprises a shop three-dimensional model of each shop;
acquiring commodity data, wherein the commodity data comprises a commodity number, a commodity attribute, a commodity image and a commodity brand category;
inputting the commodity data into a first convolutional neural network to classify the commodity to obtain commodity classification data;
obtaining commodity display data according to the commodity data and the commodity classification data, and associating the commodity display data with the corresponding shop three-dimensional model;
acquiring user data, wherein the user data comprises a user number, a user shopping place, user shopping time, an interactive commodity number and interactive behaviors, and the interactive behaviors comprise product clicking, browsing, access frequency, collection, addition to a shopping cart, removal from the shopping cart, collection, purchase, sharing, member registration, shopping coupon pickup, goods return, goods exchange, complaint, refund, comment, card swiping and recharging;
constructing a user model according to the user data and a second convolutional neural network;
establishing a user preference commodity library and recommending commodities to the user;
displaying a shopping entrance on an interface of a user terminal for selection by the user;
after the user selects a shopping entrance, displaying the three-dimensional model of the shopping mall in a first visual angle form of the user;
after receiving a shop selection instruction of a user, displaying the three-dimensional shop model and the three-dimensional images of the commodities in the shop in a first visual angle form of the user.
By adopting the technical scheme of the embodiment, the artificial intelligence-based commodity recommendation system is provided with a virtual market building module, a commodity data acquisition module, a commodity classification module, a user data acquisition module, a data processing module, a user model building module, a commodity recommendation module and a display module. The virtual mall building module is used for building a three-dimensional model of the virtual mall, the commodity data obtaining module and the commodity classifying module are used for realizing classification of similar commodities, the user data obtaining module and the user model building module are used for carrying out feature extraction and portrait drawing on a user, and the commodity recommending module selects commodities matched with the user and displays the commodities on a user terminal through the display module.
In some possible embodiments of the present invention, in the step of constructing the user model according to the user data and the second convolutional neural network, specifically:
inputting the user data into the second convolutional neural network, and obtaining user shopping characteristic data of the user based on different shopping places and/or different shopping times according to the interactive commodity numbers and the interactive behaviors;
and constructing the user model according to the user shopping characteristic data and the user data.
It can be understood that, in order to recommend a commodity more suitable for the user's needs to the user, in an embodiment of the present invention, the user data is input into a trained second convolutional neural network, and user shopping feature data of the user based on different shopping places and/or different shopping times is obtained according to the interactive commodity numbers and the interactive behaviors, it should be noted that the interactive behaviors of the user at different shopping places and different shopping times may have a larger difference, and if the difference is not obtained, the precision of recommending the commodity to the user may be affected, for example, a browsing object of the user at a work place may be an office product or a commodity recommended by a colleague, and an object browsed at home may have more household products; the difference in time is more reflected in the aspects of seasons, festivals and the like. Therefore, in the embodiment of the invention, a plurality of user models are constructed by using the user shopping characteristic data and the user data based on different shopping places and/or different shopping times.
In some possible embodiments of the present invention, the step of inputting the commodity data into a first convolutional neural network to classify the commodity to obtain commodity classification data includes:
determining any commodity as a current commodity from a pre-acquired commodity library, wherein other commodities in the commodity library are reference commodities;
constructing a current commodity vector based on the commodity data of the current commodity, and respectively constructing each reference commodity vector based on the commodity data of the reference commodity;
respectively calculating the similarity between the current commodity vector and each reference commodity vector, and determining that the commodity corresponding to the reference commodity vector with the similarity larger than a similarity threshold value is a similar commodity;
the steps of establishing a user preference commodity library and recommending commodities to the user are specifically as follows:
acquiring a user characteristic vector from the user model, calculating a correlation value of the user characteristic vector and the current commodity vector, and determining commodities and similar commodities corresponding to the current commodity vector as the user preference commodity library when the correlation value is greater than a correlation value threshold;
and generating a three-dimensional image of each commodity in the user preference commodity library and synchronizing the three-dimensional image to the corresponding shop three-dimensional model.
It can be understood that the user feature vector obtained from the user model includes preference information of the user for a commodity, vector calculation is performed on the user feature vector and the current commodity vector, and the obtained association value is the matching condition between the commodity corresponding to the current commodity vector and the user, and the higher the association value is, the higher the matching degree is, the closer the commodity corresponding to the current commodity vector is to the real demand commodity of the user, so that the commodity corresponding to the current commodity vector and the similar commodity can be recommended to the user as the preference commodity of the user. The similarity between the current commodity vector and each reference commodity vector is calculated, so that similar commodities can be determined for each commodity in a commodity library acquired in advance, accurate classification of the commodities is achieved, and conditions are provided for calculating the association degree by using the user feature vector and the current commodity vector to accurately and quickly select a preference commodity library of a user.
It is understood that, in some possible embodiments, similarity calculation is performed on the user model and the user models of other users, when the similarity is within a preset similarity threshold, the two users may be considered as being similar to each other, and the goods matching the user models of the other users may be recommended to the user corresponding to the user model.
In some possible embodiments of the invention, the method further comprises the step of: identifying an entity market building drawing and a real-time photo, and extracting the market building data;
the step of establishing a three-dimensional market model of the virtual market according to the acquired market building data of the entity market and the market preference data of the entity market by the user is specifically as follows:
establishing a BIM (building information model) of the virtual mall according to the acquired mall building data of the entity mall and the mall preference data of the user to the entity mall;
and (3) leading the BIM model of the virtual market into three-dimensional modeling software after analysis, conversion, rendering and weight reduction, and generating the three-dimensional model of the market.
Further, in order to enable the three-dimensional model of the mall to be more real and lifelike, the entity mall construction drawing can be called from the existing database, and the on-site photo can also be shot on site through an unmanned aerial vehicle and a robot with cameras. The construction drawing mainly comprises a construction drawing, a structure construction drawing, an equipment construction drawing, a completion drawing, engineering change data and the like, wherein the construction drawing is used for representing the planning position, the external shape and the arrangement condition of each internal room of a building and mainly comprises a general plane drawing, a plane drawing, an elevation drawing, a section drawing, a construction detail drawing and the like; the structure construction drawing is used for representing the structure type, the structure arrangement, the component type, the quantity and the like of the load-bearing structure of the building, and mainly comprises a structure plane arrangement drawing, a structure detailed drawing of each component and the like; the equipment construction drawing is used for representing the arrangement and construction requirements of equipment for water supply and drainage, heating and ventilation, power supply and illumination and the like of a building, and mainly comprises a plane arrangement drawing, a system drawing and an installation detailed drawing of the equipment for water supply and drainage, heating and ventilation, electricity and the like; the completion drawing is a drawing drawn according to the actual construction situation and comprises the actual trend of pipelines and the actual installation situation of other equipment in civil engineering, building construction engineering, electrical installation engineering and water supply and drainage engineering; the type of the required drawing can be determined according to different requirements for establishing the three-dimensional model, after the construction drawing of the entity market is selected, the drawing can be led into a BIM modeling platform (such as Revit), parameters are modified according to favorite data of the entity market by a user, and the BIM model of the virtual market is established.
Certainly, the point cloud data of the existing building can be collected by an unmanned aerial vehicle or a robot equipped with a three-dimensional laser scanner to obtain the actual geometric information of the entity mall, and the BIM model established based on the point cloud data can express the actual geometric information and attribute information of the existing building. After point cloud data and drawing data of an entity market are obtained, the drawing data and the point cloud data are imported to the same BIM modeling platform (such as Revit) and combined with favorite data of a user to the entity market to complete BIM modeling.
And (3) after analyzing, converting, rendering and lightening the virtual market BIM model, importing the virtual market BIM model into three-dimensional modeling software (such as Smart 3D) to generate the market three-dimensional model.
In some possible embodiments of the invention, the method further comprises the step of:
generating a to-be-customized commodity model according to the user preference commodity library and the user model;
constructing a three-dimensional image of the product to be customized according to the commodity model to be customized;
and synchronizing the three-dimensional graph of the product to be customized to the corresponding shop three-dimensional model.
It will be appreciated that in order to provide the user with merchandise more tailored to their needs, the system also includes a customisation module to provide customised merchandise. According to the user preference commodity library, data of commodities closest to user requirements can be obtained; and then obtaining demand data and interest data of the user from the user model, correcting the commodity which is closest to the demand of the user according to the demand data and the interest data, generating a to-be-customized commodity model, further constructing a three-dimensional image of the to-be-customized product, and synchronizing the three-dimensional image of the to-be-customized product to the corresponding shop three-dimensional model so as to display the three-dimensional image of the to-be-customized product on the shop three-dimensional model for the user to browse and select.
In order to further acquire the real requirements of the user, in another possible embodiment of the invention, the system further comprises an intelligent head-mounted device configured with a brain wave acquisition module; the user terminal is an intelligent device with a communication function and a display function;
the intelligent head-mounted equipment can be connected with the intelligent equipment through a wired or wireless network, the intelligent equipment comprises a computer, a mobile phone, a palm computer and the like, and the intelligent head-mounted equipment acquires electroencephalogram signals induced by visual stimulation to obtain data required by analysis;
the intelligent equipment is provided with a brain wave compiling module which can receive the brain wave signals collected and sent by the brain wave collecting module, analyze the brain wave signals and compile the analyzed signals into a marking instruction for marking the user interaction behaviors and transmit the marking instruction to the intelligent equipment; the marking instruction is mainly used for marking the user interaction behaviors, for example, information of degrees of 'favorite', 'general favorite', 'not favorite' and the like can be obtained according to the strength of electroencephalogram signals representing 'favorite', and the intelligent device can mark the user interaction behaviors in an alignment manner.
And the intelligent equipment receives the compiled marking instruction, executes the marking instruction, and stores the received marking instruction after arranging.
The intelligent equipment feeds back the execution result to the user, and the user can evaluate the execution result so as to adjust the working accuracy of the brain wave compiling module.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
While embodiments in accordance with the invention have been described above, these embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments described. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention and various embodiments with various modifications as are suited to the particular use contemplated. The invention is limited only by the claims and their full scope and equivalents.
Claims (10)
1. A commodity recommendation system based on artificial intelligence is characterized by comprising a virtual mall construction module, a commodity data acquisition module, a commodity classification module, a user data acquisition module, a data processing module, a user model construction module, a commodity recommendation module and a display module;
the virtual mall building module is used for building a mall three-dimensional model of the virtual mall according to the acquired mall building data of the entity mall and the mall preference data of the user to the entity mall; the shopping mall three-dimensional model comprises a shop three-dimensional model of each shop;
the commodity data acquisition module is used for acquiring commodity data, wherein the commodity data comprises a commodity number, a commodity attribute, a commodity image and a commodity brand category;
the commodity classification module is used for inputting the commodity data into a first convolution neural network to classify the commodity to obtain commodity classification data;
the data processing module is used for processing the commodity data and the commodity classification data to obtain commodity display data, and associating the commodity display data with the corresponding shop three-dimensional model;
the user data acquisition module is used for acquiring user data, wherein the user data comprises a user number, a user shopping place, user shopping time, an interactive commodity number and an interactive behavior;
the user model building module is used for building a user model according to the user data and the second convolutional neural network;
the commodity recommendation module is used for establishing a user preference commodity library and recommending commodities to the user;
the display module is used for displaying the shopping entrance on an interface of a user terminal for the user to select;
the display module is further used for displaying the three-dimensional model of the shopping mall in a first visual angle form of the user after the user selects a shopping entrance;
the display module is further used for displaying the three-dimensional model of the shop and the three-dimensional images of the commodities in the shop in a first visual angle mode of the user after receiving a shop selection instruction of the user.
2. The artificial intelligence based commodity recommendation system of claim 1, wherein the user model construction module is configured to construct a user model according to the user data and a second convolutional neural network, and specifically:
and inputting the user data into the second convolutional neural network, and acquiring user shopping characteristic data of the user based on different shopping places and/or different shopping times according to the interactive commodity number and the interactive behavior.
3. The artificial intelligence based commodity recommendation system according to claim 2, wherein the commodity classification module is configured to input the commodity data into a first convolutional neural network to classify commodities to obtain commodity classification data, and the commodity classification data includes:
determining any commodity as a current commodity from a pre-acquired commodity library, wherein other commodities in the commodity library are reference commodities;
constructing a current commodity vector based on the commodity data of the current commodity, and respectively constructing each reference commodity vector based on the commodity data of the reference commodity;
respectively calculating the similarity between the current commodity vector and each reference commodity vector, and determining the commodity corresponding to the reference commodity vector with the similarity larger than a similarity threshold value as a similar commodity;
the commodity recommendation module is used for establishing a user preference commodity library and recommending commodities to the user, and specifically comprises the following steps:
acquiring a user characteristic vector from the user model, calculating a correlation value of the user characteristic vector and the current commodity vector, and determining commodities and similar commodities corresponding to the current commodity vector as the user preference commodity library when the correlation value is greater than a correlation value threshold;
and generating a three-dimensional image of each commodity in the user preference commodity library and synchronizing the three-dimensional image to the corresponding shop three-dimensional model.
4. The artificial intelligence based commodity recommendation system according to claim 3, further comprising a mall building data acquisition module; the mall building data acquisition module is used for identifying an entity mall building drawing and a real-time photo and extracting mall building data;
the virtual mall building module is used for building a mall three-dimensional model of the virtual mall according to the acquired mall building data of the entity mall and the mall preference data of the entity mall of the user, and specifically comprises the following steps:
establishing the BIM model of the virtual mall according to the acquired mall building data of the entity mall and the mall favorite data of the user on the entity mall;
and (3) leading the BIM model of the virtual market into three-dimensional modeling software after analysis, conversion, rendering and weight reduction, and generating the three-dimensional model of the market.
5. The artificial intelligence based merchandise recommendation system of claim 4, further comprising a personalization customization module;
the personalized customization module is used for generating a commodity model to be customized according to the user preference commodity library and the user model;
constructing a three-dimensional image of the product to be determined according to the commodity model to be determined;
and synchronizing the three-dimensional image of the product to be manufactured to the corresponding three-dimensional model of the shop.
6. A commodity recommendation method based on artificial intelligence is applied to a commodity recommendation system based on artificial intelligence, and is characterized in that the commodity recommendation system based on artificial intelligence comprises a virtual market construction module, a commodity data acquisition module, a commodity classification module, a user data acquisition module, a data processing module, a user model construction module, a commodity recommendation module and a display module, and the method comprises the following steps:
establishing a market three-dimensional model of a virtual market according to the acquired market building data of the entity market and the market preference data of the user to the entity market; the shopping mall three-dimensional model comprises a shop three-dimensional model of each shop;
acquiring commodity data, wherein the commodity data comprises a commodity number, a commodity attribute, a commodity image and a commodity brand category;
inputting the commodity data into a first convolution neural network to classify the commodity to obtain commodity classification data;
obtaining commodity display data according to the commodity data and the commodity classification data, and associating the commodity display data with the corresponding shop three-dimensional model;
acquiring user data, wherein the user data comprises a user number, a user shopping place, user shopping time, an interactive commodity number and interactive behaviors;
constructing a user model according to the user data and a second convolutional neural network;
establishing a user preference commodity library and recommending commodities to the user;
displaying a shopping entrance on an interface of a user terminal for selection by the user;
after the user selects a shopping entrance, displaying the three-dimensional model of the shopping mall in a first visual angle form of the user;
after receiving a shop selection instruction of a user, displaying the three-dimensional shop model and the three-dimensional images of the commodities in the shop in a first visual angle form of the user.
7. The artificial intelligence based commodity recommendation method according to claim 6, wherein in the step of constructing a user model according to the user data and a second convolutional neural network, specifically:
and inputting the user data into the second convolutional neural network, and acquiring user shopping characteristic data of the user based on different shopping places and/or different shopping times according to the interactive commodity numbers and the interactive behaviors.
8. The artificial intelligence based commodity recommendation method of claim 7, wherein the step of inputting the commodity data into a first convolutional neural network for classifying the commodity to obtain commodity classification data comprises:
determining any commodity as a current commodity from a pre-acquired commodity library, wherein other commodities in the commodity library are reference commodities;
constructing a current commodity vector based on the commodity data of the current commodity, and respectively constructing each reference commodity vector based on the commodity data of the reference commodity;
respectively calculating the similarity between the current commodity vector and each reference commodity vector, and determining the commodity corresponding to the reference commodity vector with the similarity larger than a similarity threshold value as a similar commodity;
the steps of establishing a user preference commodity library and recommending commodities to the user are specifically as follows:
acquiring a user characteristic vector from the user model, calculating a correlation value of the user characteristic vector and the current commodity vector, and determining commodities and similar commodities corresponding to the current commodity vector as the user preference commodity library when the correlation value is greater than a correlation value threshold;
and generating a three-dimensional image of each commodity in the user preference commodity library and synchronizing the three-dimensional image to the corresponding shop three-dimensional model.
9. The artificial intelligence based commodity recommendation method according to claim 8, further comprising the steps of: identifying an entity market building drawing and a real-area photo, and extracting the market building data;
the step of establishing a three-dimensional market model of the virtual market according to the acquired market building data of the entity market and the market preference data of the entity market by the user is specifically as follows:
establishing a BIM (building information model) of the virtual mall according to the acquired mall building data of the entity mall and the mall preference data of the user to the entity mall;
and (3) after analyzing, converting, rendering and lightening the BIM model of the virtual market, importing the BIM model into three-dimensional modeling software to generate the three-dimensional model of the market.
10. The artificial intelligence based merchandise recommendation method of claim 9, further comprising the steps of:
generating a to-be-customized commodity model according to the user preference commodity library and the user model;
constructing a three-dimensional image of the product to be customized according to the commodity model to be customized;
and synchronizing the three-dimensional graph of the product to be customized to the corresponding shop three-dimensional model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211357918.2A CN115587873A (en) | 2022-11-01 | 2022-11-01 | Artificial intelligence based commodity recommendation system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211357918.2A CN115587873A (en) | 2022-11-01 | 2022-11-01 | Artificial intelligence based commodity recommendation system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115587873A true CN115587873A (en) | 2023-01-10 |
Family
ID=84781432
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211357918.2A Pending CN115587873A (en) | 2022-11-01 | 2022-11-01 | Artificial intelligence based commodity recommendation system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115587873A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117952650A (en) * | 2024-01-30 | 2024-04-30 | 和源顺(湖州)工艺品有限公司 | Handicraft e-commerce sales management system based on big data |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739633A (en) * | 2008-11-18 | 2010-06-16 | 上海旺城网络科技有限公司 | Method for realizing interactive three-dimensional virtual city e-commerce platform |
| CN103761667A (en) * | 2014-01-09 | 2014-04-30 | 贵州宝森科技有限公司 | Virtual reality e-commerce platform system and application method thereof |
| CN108932511A (en) * | 2018-10-09 | 2018-12-04 | 南京邮电大学 | A kind of shopping decision-making technique based on brain-machine interaction |
| US20200090411A1 (en) * | 2017-07-07 | 2020-03-19 | Alibaba Group Holding Limited | Offline shopping guide method and apparatus |
| CN111612559A (en) * | 2019-02-26 | 2020-09-01 | 浙江开奇科技有限公司 | Implementation method of virtual intelligent interactive cloud shelf |
| CN112418995A (en) * | 2020-11-26 | 2021-02-26 | 珠海格力电器股份有限公司 | Online shopping virtual interaction method based on MR virtual reality technology and storage medium |
| CN113554763A (en) * | 2021-07-30 | 2021-10-26 | 北京创程科技有限公司 | Construction method of indoor navigation system |
| CN114758106A (en) * | 2022-03-04 | 2022-07-15 | 雷帮英 | Online simulation shopping system |
| CN114820121A (en) * | 2022-04-22 | 2022-07-29 | 北京优全智汇信息技术有限公司 | Insurance business pushing system and method |
-
2022
- 2022-11-01 CN CN202211357918.2A patent/CN115587873A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739633A (en) * | 2008-11-18 | 2010-06-16 | 上海旺城网络科技有限公司 | Method for realizing interactive three-dimensional virtual city e-commerce platform |
| CN103761667A (en) * | 2014-01-09 | 2014-04-30 | 贵州宝森科技有限公司 | Virtual reality e-commerce platform system and application method thereof |
| US20200090411A1 (en) * | 2017-07-07 | 2020-03-19 | Alibaba Group Holding Limited | Offline shopping guide method and apparatus |
| CN108932511A (en) * | 2018-10-09 | 2018-12-04 | 南京邮电大学 | A kind of shopping decision-making technique based on brain-machine interaction |
| CN111612559A (en) * | 2019-02-26 | 2020-09-01 | 浙江开奇科技有限公司 | Implementation method of virtual intelligent interactive cloud shelf |
| CN112418995A (en) * | 2020-11-26 | 2021-02-26 | 珠海格力电器股份有限公司 | Online shopping virtual interaction method based on MR virtual reality technology and storage medium |
| CN113554763A (en) * | 2021-07-30 | 2021-10-26 | 北京创程科技有限公司 | Construction method of indoor navigation system |
| CN114758106A (en) * | 2022-03-04 | 2022-07-15 | 雷帮英 | Online simulation shopping system |
| CN114820121A (en) * | 2022-04-22 | 2022-07-29 | 北京优全智汇信息技术有限公司 | Insurance business pushing system and method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117952650A (en) * | 2024-01-30 | 2024-04-30 | 和源顺(湖州)工艺品有限公司 | Handicraft e-commerce sales management system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11216861B2 (en) | Color based social networking recommendations | |
| CN108009871B (en) | Product recommendation based on augmented reality viewpoints | |
| CN108876526B (en) | Commodity recommendation method and device and computer-readable storage medium | |
| Ringel et al. | Visualizing asymmetric competition among more than 1,000 products using big search data | |
| US10402917B2 (en) | Color-related social networking recommendations using affiliated colors | |
| Stangl et al. | Browsewithme: An online clothes shopping assistant for people with visual impairments | |
| US10467507B1 (en) | Image quality scoring | |
| CN108022152A (en) | The automatic commending system of user's commodity and recommendation method based on image recognition | |
| CN106991576A (en) | A kind of heating power of geographic area shows method and apparatus | |
| CN110008397B (en) | Recommendation model training method and device | |
| CN111784845B (en) | Virtual try-on method and device based on artificial intelligence, server and storage medium | |
| CN108335317A (en) | Shopping guide method and device under a kind of line | |
| KR102132714B1 (en) | System and method for providing related services of immersive virtual fitting | |
| CN115392947A (en) | Demand prediction method and device | |
| CN115587873A (en) | Artificial intelligence based commodity recommendation system and method | |
| KR20240016176A (en) | System for providing online advertising content platform | |
| KR101345119B1 (en) | System and method for generating and diagonizing image concept identity code, and system for providing information and method for providing services thereof | |
| KR20170091402A (en) | System for searching fashion item | |
| EP3176743A1 (en) | Statistical-data-generating server device, statistical-data generation system, and statistical-data generation method | |
| CN115358807A (en) | Article recommendation method and device, storage medium and electronic equipment | |
| KR20220121003A (en) | Program for providing product recommendation service | |
| CN110781399A (en) | Cross-platform information pushing method and device | |
| KR20150076407A (en) | System, apparatus and method for providing cosmetic sample based on user's skin condition | |
| CN108416611B (en) | Supermarket path recommendation system and method thereof | |
| KR20130112613A (en) | Magazine type product advertisement service providing method using smart device |
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 |