WO2020010572A1 - Video propagation system in reviewing products and method thereof - Google Patents

Abstract

Provided by the present invention is a video propagation system in reviewing products, comprising a verification system and an automatic examination system; the verification system is used for verifying identity information and purchased product information of an uploading user; the verification system comprises an account inspection module, a purchased product checking module, a payment checking module, and a shipping time checking module; the automatic examination system is used for automatically examining whether a product in a video uploaded by an account is a reviewed product. Further provided by the present invention is a method used for the described video propagation system in reviewing products. In the present invention, a product review video uploaded by a user may be compared to an image of the reviewed product, the comparison efficiency and accuracy thereof both being high, thus ensuring that the video uploaded by the user is a product video of the reviewed product, and guaranteeing the correctness of the review.

Description

Video communication system and method in commodity evaluation Technical field

The present invention relates to a video transmission system, and more particularly, to a video transmission system and method for consumers to evaluate and order products in an electronic commerce.

Background technique

In the prior art, e-commerce shoppers often evaluate products after shopping, and current e-commerce systems often use text evaluation or upload pictures to set such evaluations, and video formats The evaluation is more convincing. In the current product evaluation, after uploading the e-commerce account after the login of the e-commerce account, there is not yet a better verification and verification system, which has become a technical problem urgently solved by those skilled in the art.

Summary of the invention

The technical purpose of the present invention is to overcome the lack of technical problems of automatic proofreading and automatic approval of uploading of video content in the evaluation of products after the completion of e-commerce in the prior art; and to provide a highly efficient check of video content and product content Video dissemination system and method in product evaluation for automatically checking and completing video upload review.

To achieve the above technical objectives, the technical solution of the present invention is:

A video dissemination system in product evaluation, including a verification system and an automatic review system;

The verification system is used to verify the identity information of the uploaded user and the purchased product information; the verification system includes an account verification module, a purchased product verification module, a payment verification module, and a logistics time verification module;

Wherein, the account verification module is used to verify the user ’s account identity and account cumulative credit; if the logged-in user ’s account identity is correct and the account ’s cumulative credit is greater than or equal to a certain value, it is directly transferred to the automatic review system. If the user ’s account If the accumulated credit is less than a certain value, it will be transferred to the purchased commodity verification module;

The purchased commodity checking module is used to check whether the user's account has purchased the evaluated product, and if the evaluated product has been purchased, it is transferred to the payment checking module;

The payment verification module is used to check whether the account has completed payment for the product, and if the payment is completed, it is transferred to the logistics time verification module;

The logistics time verification module is used to make a normal judgment on the delivery time and the video upload time of the product evaluation, and to determine that the product evaluation time is after the time required for normal logistics transportation, then directly transfer to the automatic review system;

The automatic review system is used for automatically reviewing whether a product in a video uploaded by the account is an evaluated product, and the automatic review system includes a video screen capture module and a product image proofreading module;

The video screenshot module is used to pick up video interface pictures at certain or dozens of random time points of uploading videos to the account to obtain multiple video interface pictures;

The product picture proofreading module is used to compare each video interface picture obtained with the product picture of the evaluated product. If the comparison is successful, the uploaded video is the product video of the evaluated product, and the uploaded video is posted to Product evaluation display module;

The product evaluation display module is configured to display evaluation information of a product.

Further, the account verification module first checks the user's account identity. Only when the user's account identity is correct, the account's accumulated credit is checked. When the user's account identity is incorrect, a prompt for re-entry is prompted.

Further, the logistics time verification module first calculates the time required for normal logistics transportation of the purchase order according to the purchase order of the product, and then determines the delivery time and calculates the receipt time. When the video upload time is in the receipt After the time, it will be directly transferred to the automatic review system. When the video upload time is before the delivery time, it will be prompted.

Further, the logistics time verification module first obtains the logistics information of the purchase order of the product, and then judges based on the inbound information. If the logistics information does not have a delivery time, it prompts if the logistics information has a delivery. Time, and the video upload time is after the receiving time, it will be directly transferred to the automatic review system.

Further, the video screenshot module randomly selects a few or dozens of random time points to take a screenshot of the uploaded video, and then screens all the screenshots of the video interface pictures, filters out the images without products in the video interface pictures, and then Filter out blurry and distorted video interface pictures according to the image blur and distortion model.

Further, the specific steps of the product picture proofreading module for comparing each obtained video interface picture with the product picture of the evaluated product are:

First, obtain the original comparative pictures taken in all directions of the evaluated product, then extract the features and shapes of each original comparative picture, and then build the shape feature models belonging to each original comparison picture according to the extracted shape features. The extracted color features are used to build a color feature model belonging to each original contrast map;

Then each video interface picture is compared with the shape feature model and color feature model of each original comparison picture, if and only if the video interface picture is compared with the shape feature model and color feature model of a certain original comparison picture , The comparison success number is increased by one;

Then, after the comparison of all video interface pictures is completed, a comparison rate is obtained. When the comparison rate is greater than or equal to a certain value, the uploaded video is judged to be a product video of the evaluated product; when the comparison rate is less than a certain value, then It is determined that the uploaded video is not a product video of the evaluated product.

The present invention also provides a method for a video propagation system applied to the above-mentioned product evaluation, including the following steps:

Step S1: verify the account identity of the user;

When the user's account identity is correct, check the user's account cumulative credit;

When the account ID of the user is incorrect, the user is prompted to enter again;

Step S2, verifying the accumulated credit of the account;

When the accumulated credit of the user's account is greater than or equal to a certain value, directly jump to step S6;

When the accumulated credit of the user's account is less than a certain value, go to step S3;

Step S3, it is checked whether to purchase the evaluated product;

If the evaluated product has been purchased, go to step S4;

If the evaluated product is not purchased, it indicates that the evaluated product is not purchased;

Step S4: Check whether the account has completed payment for the product;

If payment is completed, skip to step S5;

If the payment is not completed, it will prompt that the payment is not made;

Step S5, verifying the logistics time;

If the evaluation time of the product is after the time required for normal logistics transportation, go to step S6;

If the evaluation time of the product is before the time required for normal logistics transportation, then prompt;

Step S6, picking up multiple video interface pictures;

Use the video screen capture module to pick up the video interface pictures at certain random time points for uploading videos to the account to get multiple video interface pictures;

Step S7, comparing with the product picture;

The product picture proofreading module compares each video interface picture obtained with the product picture of the evaluated product. If the comparison is successful, the uploaded video is the product video of the evaluated product, and skips to step S8;

Step S8, publishing a product evaluation;

The product evaluation display module publishes the uploaded video into the evaluation of the evaluation product.

Further, in step S5, the logistics time verification module first obtains the logistics information of the purchase order of the product, and then judges based on the inflow information. If the logistics information does not have a delivery time, a prompt is provided. If the logistics information If there is a receipt time, and the video upload time is after the receipt time, then go to step S6.

Further, in step S6, after picking up a plurality of video interface pictures, the video interface pictures of all screen shots are filtered to filter out the images without products in the video interface pictures, and then the blurry and distorted images are filtered according to the image blurring distortion model. Video interface picture.

Further, the specific steps of comparing each video interface picture with the product picture of the evaluated product are:

First, obtain the original comparative pictures taken in all directions of the evaluated product, then extract the features and shapes of each original comparative picture, and then build the shape feature models belonging to each original comparison picture according to the extracted shape features. The extracted color features are used to build a color feature model belonging to each original contrast map;

Then each video interface picture is compared with the shape feature model and color feature model of each original comparison picture, if and only if the video interface picture is compared with the shape feature model and color feature model of a certain original comparison picture , The comparison success number is increased by one;

Then, after the comparison of all video interface pictures is completed, a comparison rate is obtained. When the comparison rate is greater than or equal to a certain value, the uploaded video is judged to be a product video of the evaluated product; when the comparison rate is less than a certain value, then It is determined that the uploaded video is not a product video of the evaluated product.

The video propagation system and method in the product evaluation of the present invention have the following beneficial effects:

1. The video dissemination system of the present invention can compare the image of the product evaluation video uploaded by the user with the evaluated product. The comparison efficiency and accuracy are very high. This ensures that the video uploaded by the user belongs to the product video of the evaluated product, ensuring the evaluation Correctness.

2. The present invention can directly jump to an automatic review system for user accounts with high accumulated account credit, thereby shortening the review time and improving the user experience.

3. The video screen capture module of the present invention picks up video interface pictures at certain random time points for uploading videos to the account, first filters out images without products in the video interface pictures, and then performs blurring and distortion processing, which can greatly reduce Improve contrast accuracy.

4. In the present invention, the shape of the color feature model and the color feature model are used to compare the video interface pictures, which can further improve the contrast efficiency and accuracy, and ensure the correctness of the evaluation.

Additional aspects and advantages of the present invention will be given in part in the following description, part of which will become apparent from the following description, or be learned through the practice of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a functional block diagram of a software module according to an embodiment of the present invention;

FIG. 2 is a software flowchart of an embodiment of the present invention.

In the figure, 1. a verification system; 2. an automatic review system; 3. a product evaluation display module; 11. an account verification module; 12. a purchased product verification module; 13. a payment verification module; 14. a logistics time verification module; 21. Video screenshot module; 22. Commodity picture proofreading module;

detailed description

Hereinafter, embodiments of the present invention will be described in detail. Examples of the embodiments are shown in the drawings, wherein the same or similar reference numerals indicate the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present invention, but should not be construed as limiting the present invention.

In an embodiment of the present invention, as shown in FIG. 1, a video dissemination system in product evaluation includes a verification system 1 and an automatic review system 2.

The verification system 1 is used to verify the identity information of the uploaded user and the purchased product information; the verification system 1 includes an account verification module 11, a purchased product verification module 12, a payment verification module 13, and a logistics time verification module 14.

The account verification module 11 is used to verify the user's account identity and the account's accumulated credit; the account verification module 11 first checks the user's account identity. Only when the user's account identity is correct, the account's accumulated credit is checked. When the user's account identity is wrong , You are prompted to re-enter.

If the logged-in user's account identity is correct and the account's accumulated credit is greater than or equal to a certain value (for a high-credit user), it is directly transferred to the automatic review system 2.

If the accumulated credit of the user's account is less than a certain value (for a low-credit user), it is transferred to the purchased product verification module 12. Among them, the accumulated credit of the user's account is also related to the number of orders returned and the number of bad reviews.

The purchased product verification module 12 is used to check whether the user's account has purchased the evaluated product. If the evaluated product has been purchased, it is transferred to the payment check module 13. If the evaluated product is not purchased, a prompt is given.

The payment verification module 13 is used to check whether the account has completed payment for the product, and if the payment is completed, it is transferred to the logistics time verification module 14. If payment is not completed, a prompt is issued.

The logistics time verification module 14 is used to make a normal judgment on the delivery time and the video upload time of the product evaluation. After determining that the product evaluation time is after the time required for normal logistics transportation, it is directly transferred to the automatic review system 2.

Among them, there are two methods for determining whether the evaluation time of a product is within the time required for normal logistics transportation;

One is the logistic time check module 14 that first calculates the time required for normal logistics transportation of the purchase order based on the purchase order of the product, and then determines the delivery time and calculates the receipt time. When the video upload time is at the receipt time After that, it is directly transferred to the automatic review system 2, and when the video upload time is before the delivery time, it is prompted.

The other is that the logistics time verification module 14 first obtains the logistics information of the purchase order of the product, and then judges based on the inbound information. If the logistics information does not have a delivery time, it prompts if the logistics information is received. Delivery time, and the video upload time is after the delivery time, it will be directly transferred to the automatic review system2.

The automatic review system 2 is used to automatically check whether the products in the video uploaded by the account are the evaluated products. The automatic review system 2 includes a video screen capture module 21 and a product picture proofreading module 22.

The video screenshot module 21 is used to pick up video interface pictures at certain or dozens of random time points of uploading videos to the account to obtain multiple video interface pictures.

The video screen capture module 21 can also filter all screen capture video interface pictures, use significant color feature value comparison to filter out images without products in the video interface picture; first, extract multiple significant color feature values of the product, and then take all screenshots The video interface picture is compared with the significant color feature value. If there is a significant color feature value in the video interface picture, it is judged that the video interface picture has a product. If there is no significant color feature value in the video interface picture, it is judged that the video interface picture is not. Commodities should be rejected.

Then, according to the image blur and distortion model, the blurry and distorted video interface picture is filtered out.

The product picture proofreading module 22 is used to compare each video interface picture obtained with the product picture of the evaluated product. If the comparison is successful, the uploaded video is the product video of the evaluated product, and the uploaded video is posted to the product. Evaluation display module 3.

The specific steps of the product picture proofreading module 22 for comparing each obtained video interface picture with the product picture of the evaluated product are:

First, obtain the original comparative pictures taken in all directions of the evaluated product, then extract the features and shapes of each original comparative picture, and then build the shape feature models belonging to each original comparison picture according to the extracted shape features. The extracted color features are used to build a color feature model belonging to each original contrast map;

Then each video interface picture is compared with the shape feature model and color feature model of each original comparison picture, if and only if the video interface picture is compared with the shape feature model and color feature model of a certain original comparison picture , The comparison success number is increased by one;

Then, after the comparison of all video interface pictures is completed, a comparison rate is obtained. When the comparison rate is greater than or equal to a certain value, the uploaded video is judged as a product video of the evaluated product; It is determined that the uploaded video is not a product video of the evaluated product.

The product evaluation display module 3 is configured to display evaluation information of a product.

The video screen capture module of the present invention picks up video interface pictures at certain random points in time for uploading videos to the account, first filters out images without products in the video interface pictures, and then performs blurring and distortion filtering, which can greatly improve the The accuracy of the ratio.

The present invention also provides a method for a video dissemination system applied to the above-mentioned product evaluation. As shown in FIG. 2, the method includes the following steps:

Step S1: verify the account identity of the user;

When the user's account identity is correct, check the user's account cumulative credit;

When the account ID of the user is incorrect, the user is prompted to enter again;

Step S2, verifying the accumulated credit of the account;

When the accumulated credit of the user's account is greater than or equal to a certain value, directly jump to step S6;

When the accumulated credit of the user's account is less than a certain value, go to step S3;

Step S3, it is checked whether to purchase the evaluated product;

If the evaluated product has been purchased, go to step S4;

If the evaluated product is not purchased, it indicates that the evaluated product is not purchased;

Step S4: Check whether the account has completed payment for the product;

If payment is completed, skip to step S5;

If the payment is not completed, it will prompt that the payment is not made;

Step S5, verifying the logistics time;

If the evaluation time of the product is after the time required for normal logistics transportation, go to step S6;

If the evaluation time of the product is before the time required for normal logistics transportation, then prompt;

The logistics time verification module first obtains the logistics information of the purchase order of the product, and then judges based on the inbound information. If the logistics information does not have a receiving time, it prompts if the logistics information has a receiving time, and After the video upload time is after the delivery time, the process jumps to step S6.

You can also first calculate the time required for normal logistics transportation of the purchase order based on the purchase order of the product, and then determine the delivery time and calculate the receipt time. When the video upload time is after the receipt time, it will be directly transferred to the automatic Review system 2, when the video upload time is before the receiving time, it will prompt.

Step S6, picking up multiple video interface pictures;

Use the video screen capture module to pick up the video interface pictures at certain random time points for uploading videos to the account to get multiple video interface pictures;

After picking up multiple video interface pictures, filter all screen shot video interface pictures, filter out images without products in the video interface pictures, and then filter out blurry and distorted video interface pictures based on the image blur and distortion model.

Step S7, comparing with the product picture;

The product picture proofreading module compares each video interface picture obtained with the product picture of the evaluated product. If the comparison is successful, the uploaded video is the product video of the evaluated product, and skips to step S8;

The specific steps for comparing each video interface picture with the product picture of the evaluated product are:

First, obtain the original comparative pictures taken in all directions of the evaluated product, then extract the features and shapes of each original comparative picture, and then build the shape feature models belonging to each original comparison picture according to the extracted shape features. The extracted color features are used to build a color feature model belonging to each original contrast map;

Then each video interface picture is compared with the shape feature model and color feature model of each original comparison picture, if and only if the video interface picture is compared with the shape feature model and color feature model of a certain original comparison picture , The comparison success number is increased by one;

Then, after the comparison of all video interface pictures is completed, a comparison rate is obtained. When the comparison rate is greater than or equal to a certain value, the uploaded video is judged as a product video of the evaluated product; when the comparison rate is less than a certain value, then It is determined that the uploaded video is not a product video of the evaluated product.

Step S8, publishing a product evaluation;

The product evaluation display module publishes the uploaded video into the evaluation of the evaluation product.

The video dissemination system and method of the present invention can compare the image of the product evaluation video uploaded by the user with the evaluated product, and its comparison efficiency and accuracy are very high. Correctness.

Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limitations on the present invention. Those skilled in the art will not depart from the principles and purposes of the present invention. In the case of the present invention, changes, modifications, replacements, and variations can be made to the above embodiments within the scope of the present invention. The scope of the invention is defined extremely equally by the appended claims.

Claims (10)

A video dissemination system in product evaluation, which is characterized by including a verification system and an automatic review system; The verification system is used to verify the identity information of the uploaded user and the purchased product information; the verification system includes an account verification module, a purchased product verification module, a payment verification module, and a logistics time verification module; Wherein, the account verification module is used to verify the user ’s account identity and account cumulative credit; if the logged-in user ’s account identity is correct and the account ’s cumulative credit is greater than or equal to a certain value, it is directly transferred to the automatic review system. If the accumulated credit is less than a certain value, it will be transferred to the purchased commodity verification module; The purchased commodity checking module is used to check whether the user's account has purchased the evaluated product, and if the evaluated product has been purchased, it is transferred to the payment checking module; The payment verification module is used to check whether the account has completed payment for the product, and if the payment is completed, it is transferred to the logistics time verification module; The logistics time verification module is used to make a normal judgment on the delivery time and the video upload time of the product evaluation, and to determine that the product evaluation time is after the time required for normal logistics transportation, then directly transfer to the automatic review system; The automatic review system is used for automatically reviewing whether a product in a video uploaded by the account is an evaluated product, and the automatic review system includes a video screen capture module and a product image proofreading module; The video screenshot module is used to pick up video interface pictures at certain or dozens of random time points of uploading videos to the account to obtain multiple video interface pictures; The product picture proofreading module is used to compare each video interface picture obtained with the product picture of the evaluated product. If the comparison is successful, the uploaded video is the product video of the evaluated product, and the uploaded video is posted to Product evaluation display module; The product evaluation display module is configured to display evaluation information of a product. The video dissemination system in product evaluation according to claim 1, wherein the account verification module first checks a user's account identity, and only checks the account's accumulated credit if the user's account identity is correct, and when the user's If the account ID is incorrect, you will be prompted to enter again. The video dissemination system in product evaluation according to claim 1, wherein the logistics time verification module first calculates the time required for normal logistics transportation of the purchase order according to the purchase order of the product, and then determines The receiving time is calculated to obtain the receiving time. When the video upload time is after the receiving time, it will be directly transferred to the automatic review system. When the video upload time is before the receiving time, it will be prompted. The video dissemination system in product evaluation according to claim 1, wherein the logistics time verification module first obtains the logistics information of the purchase order of the product, and then judges based on the inbound information, if the logistics information is not If there is a delivery time, a prompt will be given. If the logistics information has a delivery time and the video upload time is after the delivery time, it will be directly transferred to the automatic review system. The video dissemination system in product evaluation according to claim 1, wherein the video screen capture module randomly selects a few or dozens of random time points to take a screenshot of the uploaded video, and then takes a picture of the video interface of all the screenshots Perform filtering to filter out the images without products in the video interface pictures, and then filter out the blurry and distorted video interface pictures according to the image blur and distortion model. The video dissemination system in product evaluation according to claim 1, characterized in that the specific steps of the product picture proofreading module for comparing each obtained video interface picture with the product picture of the evaluated product are: First, obtain the original comparative pictures taken in all directions of the evaluated product, then extract the features and shapes of each original comparative picture, and then build the shape feature models belonging to each original comparison picture according to the extracted shape features. The extracted color features are used to build a color feature model belonging to each original contrast map; Then each video interface picture is compared with the shape feature model and color feature model of each original comparison picture, if and only if the video interface picture is compared with the shape feature model and color feature model of a certain original comparison picture , The comparison success number is increased by one; Then, after the comparison of all video interface pictures is completed, a comparison rate is obtained. When the comparison rate is greater than or equal to a certain value, the uploaded video is judged to be a product video of the evaluated product; when the comparison rate is less than a certain value, then It is determined that the uploaded video is not a product video of the evaluated product. A method applied to a video dissemination system in product evaluation according to any one of claims 1-6, comprising the following steps: Step S1: verify the account identity of the user; When the user's account identity is correct, check the user's account cumulative credit; When the account ID of the user is incorrect, the user is prompted to enter again; Step S2, verifying the accumulated credit of the account; When the accumulated credit of the user's account is greater than or equal to a certain value, directly jump to step S6; When the accumulated credit of the user's account is less than a certain value, go to step S3; Step S3, it is checked whether to purchase the evaluated product; If the evaluated product has been purchased, go to step S4; If the evaluated product is not purchased, it indicates that the evaluated product is not purchased; Step S4: Check whether the account has completed payment for the product; If payment is completed, skip to step S5; If the payment is not completed, it will prompt that the payment is not made; Step S5, verifying the logistics time; If the evaluation time of the product is after the time required for normal logistics transportation, go to step S6; If the evaluation time of the product is before the time required for normal logistics transportation, then prompt; Step S6, picking up multiple video interface pictures; Use the video screen capture module to pick up the video interface pictures at certain random time points for uploading videos to the account to get multiple video interface pictures; Step S7, comparing with the product picture; The product picture proofreading module compares each video interface picture obtained with the product picture of the evaluated product. If the comparison is successful, the uploaded video is the product video of the evaluated product, and skips to step S8; Step S8, publishing a product evaluation; The product evaluation display module publishes the uploaded video into the evaluation of the evaluation product. The method according to claim 7, characterized in that, in step S5, the logistics time check module first obtains the logistics information of the purchase order of the product, and then judges based on the inflow information, if the logistics information has not been received. Time, a prompt is provided. If the logistics information has a delivery time, and the video upload time is after the delivery time, the process jumps to step S6. The method according to claim 7, characterized in that, in step S6, after picking up a plurality of video interface pictures, the video interface pictures of all screen shots are filtered, images without products in the video interface pictures are filtered out, and then according to Image blur and distortion model, filter out blurry and distorted video interface pictures. The method according to claim 7, wherein the specific steps of comparing each video interface picture with the product picture of the evaluated product are: First, obtain the original comparative pictures taken in all directions of the evaluated product, then extract the features and shapes of each original comparative picture, and then build the shape feature models belonging to each original comparison picture according to the extracted shape features. The extracted color features are used to build a color feature model belonging to each original contrast map; Then each video interface picture is compared with the shape feature model and color feature model of each original comparison picture, if and only if the video interface picture is compared with the shape feature model and color feature model of a certain original comparison picture , The comparison success number is increased by one; Then, after the comparison of all video interface pictures is completed, a comparison rate is obtained. When the comparison rate is greater than or equal to a certain value, the uploaded video is judged to be a product video of the evaluated product; when the comparison rate is less than a certain value, then It is determined that the uploaded video is not a product video of the evaluated product.

Images