TWM573855U - Product image intelligent system - Google Patents

Abstract

A product image intelligent system is disclosed, which comprises a database, a product feature extraction module, a product image analysis module, a recommended label module and a synthesis module. The product feature extraction module extracts relevant features of a product from the database. The product image analysis module analyzes relevant information of a product image based on the relevant features of the product. The recommended label module provides at least one recommended label based on the relevant information of the product image. The synthesis module synthesizes the recommended label on the product image based on the relevant information of the product image.

Description

Product picture smart system

This creation is about a product picture smart technology, especially a product picture smart system.

In the past, retailers' product images usually only had a simple product appearance, which led consumers to understand the product's characteristics through online price comparison, reading product features, and even viewing numerous out-of-box evaluations in addition to intuitive appearance choices. In particular, when the product is exposed to advertisements and the layout size is limited, in order to make the consumer (viewer) interested in a very short time and a very small range, the current practice is mainly to conduct a single image for one person. Judgment and processing to provide labels for product images, but this practice is very labor intensive and labor intensive.

Therefore, how to solve the above-mentioned shortcomings of the prior art has become one of the major problems of those skilled in the art.

This creation provides a product image intelligence system that intelligently synthesizes at least one recommended label on the product image to save staff time and labor costs.

The product picture smart system in this creation is used in an electronic device having a processor and a memory, and includes: a database; a product feature extraction mode The group is the relevant feature extracted from the database; a product image analysis module is based on the relevant characteristics of the product extracted by the product feature extraction module to analyze the product image information; a recommended label module Providing at least one recommended label according to the information of the product image analyzed by the product image analysis module; and a synthesis module, which is based on the information of the product image analyzed by the product image analysis module, and will recommend the label module At least one recommended label is provided on the product image.

In order to make the above features and advantages of the present invention more comprehensible, the embodiments are described below in detail with reference to the accompanying drawings. Additional features and advantages of the present invention will be set forth in part in the description which follows. The features and advantages of the present invention are recognized and attained by means of the elements and combinations particularly pointed out in the appended claims. It is to be understood that both the foregoing general description

1‧‧‧Product Picture Smart System

10‧‧‧Database

20‧‧‧Product Feature Extraction Module

30‧‧‧Product Image Analysis Module

40‧‧‧Product Data Comparison Module

50‧‧‧Sales Analysis Module

60‧‧‧Shopping Behavior Analysis Module

70‧‧‧foot scale group

80‧‧‧Recommended label module

90‧‧‧Synthesis module

100‧‧‧ Performance Analysis Module

A, A'‧‧‧ product picture

B‧‧‧Recommended label

C‧‧‧ label border

S1 to S5‧‧‧ steps

The first picture is a schematic diagram of the architecture of the product picture smart system of the creation; the 2A to 2C pictures are schematic diagrams for adjusting the size of the product picture by the rule size group in the creation; the 3A to 3C are The schematic diagram of synthesizing the recommended label on the product image by the synthesizing module in the creation; the 4A to 4C are schematic diagrams of placing the label frame on the product image by the synthesizing module in the creation; 5A to 5B 'Figure is the recommended label by the synthesis module in the creation A schematic diagram of an embodiment synthesized with a label frame or placed on a product image; and FIG. 6 is a schematic flow chart of a smart method for creating a product image.

The embodiments of the present invention are described in the following specific embodiments, and those skilled in the art can easily understand other advantages and functions of the present invention by the contents disclosed in the present specification, and can also be implemented by other different embodiments. Or application.

This creation can collect related features (such as product images, sales information, shopping behaviors, etc.) of various products through methods such as network burying, API (Application Programming Interface), media delivery, and web crawling. The product data is stored in the database, and the recommended label (or recommended frame) is provided by the recommended label module to be synthesized on the product image, and the finished product image is stored in a new link to provide the customer to use on the product page or dynamic Product advertising and interaction with consumers.

The first picture is a schematic diagram of the structure of the product picture smart system 1 of the present creation, and the second picture to the second picture CC are the dimensions of the product picture A adjusted by the ruler size group 70 of the first picture in the creation (see product picture A). FIG. 3A to FIG. 3C are diagrams showing the synthesis of the recommended label B on the product image A′ by the synthesis module 90 of FIG. 1 , and FIGS. 4A to 4C are the creations of the present drawing. A schematic diagram of the label frame C placed on the product image A' by the synthesizing module 90 of FIG. 1 , and FIGS. 5A to 5B′ are the recommended labels B of the synthesizing module 90 of FIG. 1 in the present creation. A schematic diagram of an embodiment in which the label frame C is composited or placed on the product image A'.

As shown in Fig. 1, the product picture smart system 1 of the present invention is used in an electronic device (not shown) having a processor and a memory. The processor can be, for example, a central processing unit or the like, and the memory can be, for example, a hard disk, a floppy disk, a compact disk, a flash drive, or a memory card. The electronic device can be, for example, a computer (such as a personal computer, a notebook computer, or a tablet computer). But not limited to devices (such as data servers, cloud servers or web servers), smart phones or personal digital assistants.

The product image smart system 1 may include a database 10, and includes a product feature extraction module 20 composed of a hardware, a firmware or a software, a product image analysis module 30, and a product data comparison module 40. A sales analysis module 50, a shopping behavior analysis module 60, a one-foot scale group 70, a recommendation label module 80, a synthesis module 90, and a performance analysis module 100.

For example, the product image analysis module 30, the sales analysis module 50, the shopping behavior analysis module 60, or the performance analysis module 100 can be a hardware analyzer or a software analysis program, and the product data comparison module 40 can be hard. The comparison module or the software comparison program, the synthesis module 90 can be a hardware synthesizer or a software synthesis program. However, this creation is not limited to this.

As shown in FIG. 1 and FIG. 2A to FIG. 2C, the product feature extraction module 20 can be connected or communicated with the database 10 for obtaining or receiving, for example, a customer's product or product image A in the product image smart system 1. At the time, the product feature extraction module 20 extracts relevant features of the product from the database 10.

For example, related features of the product may include product image A, product image A link, product name, product description, product availability, product page link, product currency, product classification, product brand, Sales information of the product, and/or related shopping behavior of the product, wherein the sales information of the product may include the selling price of the product, the quantity of the product sold, and/or the profit of the product, and the related shopping behavior of the product may include the product. The number of times viewed, the number of times a product was clicked on by an ad, the number of times a product was added to a shopping cart, the number of times a product was checked out, and/or the number of times a product was purchased.

The product image analysis module 30 of FIG. 1 can be connected or communicated with the product feature extraction module 20 for automatically analyzing the product image A of the product according to the relevant features of the product extracted by the product feature extraction module 20 (see 2A). Figure to Figure 2C). For example, the information about product image A includes the color, composition, feature object, brand logo, text, style, and/or field of product image A.

The product data comparison module 40 of FIG. 1 can be connected or communicated with the product feature extraction module 20 for automatically comparing the data of the product according to the relevant features of the product extracted by the product feature extraction module 20. For example, product changes include product additions, product price changes, product price changes, product fold changes, product inventory changes, and/or product availability changes.

The sales analysis module 50 of FIG. 1 can be connected or communicated with the product feature extraction module 20 to automatically analyze the sales quantity of the product and the profit of the product according to the relevant features of the product extracted by the product feature extraction module 20.

The shopping behavior analysis module 60 of FIG. 1 can be connected or communicated with the product feature extraction module 20 to automatically analyze the relevant shopping behavior of the product according to the relevant features of the product extracted by the product feature extraction module 20. For example, the relevant shopping behavior of the product includes the number of times the product was viewed, and the product was advertised. The number of clicks, the number of times the product was added to the shopping cart, the number of times the product was checked out, and/or the number of purchases of the product.

The scale group 70 of FIG. 1 can be linked or communicated with the product image analysis module 30 to determine whether to cut the size of the product image A or the scaled product image A to adjust the consistency of the size of the product image A. For example, in FIGS. 2A-2C, the scale group 70 can adjust three different size product images A into three product images A' of the same size (eg, 600x600, unlimited units).

As shown in FIG. 1 and FIG. 2A to FIG. 2C, the recommended label module 80 can be connected to the product image analysis module 30, the product data comparison module 40, the sales analysis module 50, or the shopping behavior analysis module 60. Or communication, based on the information related to the product image A analyzed by the product image analysis module 30 (or the sales quantity and revenue of the product analyzed by the sales analysis module 50, and the product analyzed by the shopping behavior analysis module 60) Shopping behavior), providing at least one recommended label B (or label border C).

In addition, the recommended label module 80 can automatically generate a weighted order of multiple recommended labels B (or label borders C) according to the related information of the product image A (or A') analyzed by the product image analysis module 30, and according to Weight Sorting and Conspicuous Color Select at least one recommended label B (or label border C) from a plurality of recommended labels B (or label borders C).

The above recommended label B may include a hot sale label, a price label (such as a special price label), a discount label, a new product label, a hot search label, an evaluation label (such as a positive/negative evaluation label), a qualified label (such as a seasonally qualified label), and / or during the event, etc., and the content of the recommended label B can be, for example, the best for sale, The cheapest price, the most discount, the new product, the most popular search, the highest rating, limited products, summer limited, and / or only one left. The label frame C may have a variety of conspicuous color patterns, shapes, lines, patterns, or any combination thereof, and the like.

The composite module 90 of FIG. 1 can process the product image A' processed by the rule size group 70 (see FIG. 2A to FIG. 2C or FIG. 5A), according to the product image A analyzed by the product image analysis module 30. Relevant information, and the location and color of the composition picture of product image A, automatically synthesize at least one recommended label B into product image A' (see pictures 3A to 3C or 5B to 5B'), or A label frame C is placed on the product picture A' (see Figures 4A to 4C or 5B to 5B').

For example, in Figures 3A to 3C, the recommended label B may include a hot sale label "hot sale", a discount label "30% off", and a price label " $899", the new listing label "new product". In FIGS. 4A to 4C, the label frame C may include a pattern, a shape, a line, a pattern, or a combination thereof. In FIGS. 5B to 5B', the synthesizing module 90 can synthesize both the recommended label B and the label frame C and place it on the product picture A'.

As shown in FIG. 1 to FIG. 5B′, the performance analysis module 100 can automatically compare the information of the product image A′, the recommendation label B, and the placement of the label frame C through the website or the advertisement to automatically compare or The results of the performance analysis are provided, and the results of the performance analysis are sequentially passed through the database 10, the product feature extraction module 20, and the product image analysis module 30 (or the product data comparison module 40, the sales analysis module 50, and the shopping behavior analysis module). The group 60) is fed back to the recommended label module 80 and the synthesis module 90 to provide a correction result of the loop.

Figure 6 is a schematic flow chart of the product image wisdom method of the creation. Please refer to the above figures 1 to 5B'. The main technical contents of the product picture smart method in this creation are as follows, and the rest of the technical contents are as detailed in the above-mentioned FIGS. 1 to 5B', and will not be repeated here.

In step S1 of FIG. 6, a product feature extraction module 20 automatically extracts relevant features of the product from a database 10.

In step S2 of FIG. 6, a product image analysis module 30 automatically analyzes the related information of the product image A of the product according to the relevant features of the product extracted by the product feature extraction module 20.

In this step, a product data comparison module 40 can automatically compare the data of the product according to the relevant features of the product extracted by the product feature extraction module 20; or, by a sales analysis module 50, based on product characteristics. The relevant features of the product extracted by the extraction module 20 automatically analyze the sales quantity of the product and the profit of the product; or, by a shopping behavior analysis module 60, automatically analyze the relevant features of the product extracted by the product feature extraction module 20. Product related shopping behavior.

In step S3 of Fig. 6, the size of the product picture A or the scaled product picture A is automatically cropped by the one-foot scale group 70 to adjust the consistency of the size of the product picture A (see product picture A'). At the same time, at least one recommended label B (or label border C) is provided by a recommended label module 80 according to the related information of the product picture A analyzed by the product picture analysis module 30. Moreover, the recommended label module 80 can automatically generate the weighted order of the plurality of recommended labels B (or the label border C) according to the related information of the product image A analyzed by the product image analysis module 30, according to the weight sorting and the conspicuous color self. Multiple recommendations At least one recommended label B (or label border C) is selected in the sign B (or label border C).

In step S4 of FIG. 6, a synthesis module 90 synthesizes at least one recommended label B provided by the recommended label module 80 into the product image A according to the product image A related information analyzed by the product image analysis module 30. 'on.

In this step, the synthesis module 90 may also place a label frame C in the product image according to the information about the product image A analyzed by the product image analysis module 30 and the position and color of the composition recommendation of the product image A. A.

In step S5 of FIG. 6 , information such as the product image A, at least one recommended label B, and the label frame C are placed by a performance analysis module 100 to compare or analyze the results of the performance through the disclosure of the website or the advertisement. .

In summary, the product image smart system of this creation can have the following characteristics, advantages or technical effects: the creation can automatically extract relevant features of the product from the database, and analyze the relevant information of the product image and provide at least one recommended label ( Or label borders, to intelligently synthesize recommended labels (or label borders) on product images, thereby saving staff time and labor costs.

In addition, this creation can collect related features (such as product images, sales information, shopping behaviors, etc.) of various products through methods such as network burying, API (application interface) cascading, media delivery, and web crawling. The product data is stored in the database, and the recommended label (or recommended frame) is provided by the recommended label module to be synthesized on the product image, and the finished product image is stored. A new link that provides customers with the ability to interact with consumers on product pages or dynamic product ads.

The above-described embodiments are merely illustrative of the principles, features, and effects of the present invention, and are not intended to limit the scope of the present invention. Anyone skilled in the art can do so without departing from the spirit and scope of the present invention. The embodiment is modified and changed. Any equivalent changes and modifications made using the content disclosed in this work should be covered by the scope of the patent application. Therefore, the scope of protection of this creation should be as listed in the scope of patent application.

Claims (10)

A product picture smart system is used in an electronic device having a processor and a memory, and includes: a database for storing product data; and a product feature extraction module for extracting products from the database Corresponding characteristics; a product image analysis module is based on the relevant features of the product extracted by the product feature extraction module to analyze the product image of the product; a recommended label module is based on the product image analysis The information about the product image analyzed by the module provides at least one recommended label; and a composite module is provided according to the information of the product image analyzed by the product image analysis module, and the recommended label module provides The at least one recommended label is synthesized on the product image. For example, the product picture smart system described in claim 1 of the patent scope, wherein the relevant features of the product include the product picture, the link of the product picture, the name of the product, the description of the product, the supply of the product, the page link of the product, At least one of the currency of the product, the classification of the product, the brand of the product, the sales information of the product, and the related shopping behavior of the product. For example, the product picture smart system described in claim 1 of the patent scope, wherein the information about the product picture includes the color, composition, feature object, brand logo, text, style, and field of the product image. At least one of them. For example, the product picture intelligent system described in claim 1 further includes a product data comparison module, which is based on the data of the product extracted by the product feature extraction module. For example, the product picture smart system described in claim 1 further includes a sales analysis module, which analyzes the sales quantity of the product and the product according to the relevant characteristics of the product extracted by the product feature extraction module. income. For example, the product picture intelligent system described in claim 1 further includes a shopping behavior analysis module, which analyzes the related shopping behavior of the product according to the relevant characteristics of the product extracted by the product feature extraction module. For example, the product picture intelligent system described in claim 1 of the patent scope further includes a one-foot scale group for cutting the product picture or scaling the size of the product picture to adjust the consistency of the size of the product picture. The product picture smart system of claim 1, wherein the recommended label module generates a weighting order of the plurality of recommended labels according to the related information in the product image analyzed by the product image analysis module, The at least one recommended label is selected from the plurality of recommended labels according to the weight sorting and the conspicuous color. The product picture smart system according to claim 1, wherein the synthesis module is further recommended according to the product image analyzed by the product image analysis module and the composition of the product image. Position and color, a label border is placed on the product image. For example, the product image intelligent system described in claim 1 further includes a performance analysis module, which compares the product image with the at least one recommended label through a website or an advertisement to compare or provide a performance analysis. result.