Abstract: After finishing the content review, I connected the crawling tool, content review API, and text summary generation API together. From capturing to reviewing to editing, I established an automated content production line. The editing team only needs to be high-quality The content recommendation is enough.
Last week, the operation department operated the information section of the official website as a content product independently. I used the "text abstract generation API" to quickly generate abstracts for automatically obtained articles, instead of the work of a 10-person content team. After the content products are introduced to the market, the feedback is very good, and the user growth curve is getting higher and higher.
(For details, please see: "Break the circle, use an API instead of a 10-person content team")
Two days ago, the boss of the operations department came to me for help again. The reason is that the number of users is growing rapidly, the demand for content is also increasing, and many new content sections have been expanded, and a large number of articles need to be filled every day. Although the content of the article can be automatically obtained and the abstract can be automatically generated, the workload of content recommendation and review is also very large, and the existing three editors are simply too busy. Ask the boss for someone, and the boss asks him to come to me for help!
Emmm... The boss used me directly as HR... However, the operation department had to recruit people at the beginning, and it was indeed because I proposed a plan to not recruit. Now, how can I solve the problem with insufficient staff?
Specific issues need to be analyzed in detail. The current editorial team is mainly responsible for content review and recommendation. If the editorial team is only responsible for recommending high-quality content, it can save 40% of manpower. Is there any way to replace content review with tools?
I think of a "Content Moderation API" that I have learned before , which can automatically detect images, texts, and videos. Information related to pornography, advertisements, politics, violence, and sensitive people can all be audited and filtered to reduce content The risk of non-compliance.
There is a pillow when you doze off! Quickly use handwriting technology to realize the document.
The content audit API can be debugged in the HUAWEI CLOUD API Explorer. The calling example is as follows:
Step 1: Activate the service
First , enable text content review and image content review services in the HUAWEI CLOUD console .
Step 2: Debug service
Quick debugging is possible through API Explorer .
Click "Content Review" in API Explorer.
Next, take "text content detection" as an example for debugging.
On the TextModeration interface interface, enter the categories, items-text, and items-type required by the interface. Precautions such as request parameters can be viewed in the document on the right side of the above figure.
Click the "Debug" button above to start debugging, and you can view the results on the "Debug Results" page on the right.
Similarly, debug the "image content detection":
When sending a request, select one of the parameters image and url. The parameter information can also be viewed on the "Documents" page on the right.
After finishing the content review, I connected the crawling tool, content review API, and text summary generation API together. From capturing to reviewing to editing, I established an automated content production line. The editing team only needs to do high-quality content. Recommend it.
Another business problem has been solved. Can content recommendations be replaced next time?
Learn more about HUAWEI CLOUD API: " Free download of the innovation acceleration tool "Huawei CLOUD API Selection Manual"
Click to follow and learn about Huawei Cloud's fresh technology for the first time~