Перейти к навигации

How do I find brand-related problems on Xiaohongshu and hand them off for follow-up?

To find brand problems on Xiaohongshu, search data:xiaohongshu.app_v2.search_notes for the brand or model together with a specific experience, read the comments of the relevant notes, and hand off each excerpt with its source and next action. For a coffee-machine brand, search the model plus leaking, cleaning or customer support instead of the brand name alone.

The deliverable is a reviewed feedback queue. For each item, the queue records whether the item concerns the brand, whether the item is a product or service issue, what information is missing and who checks next. Finish one round of discovery and handoff before you arrange recurring updates.

1. Search experiences and confirm brand relevance

Call data:xiaohongshu.app_v2.search_notes with sort_type:time_descending for the latest notes. Save the results with the note-search workflow and check each note’s model, context and source. When several search terms find the same note, reuse the existing note record.

Give an assistant that has the BeatAPI tools configured a task like this one:

Search recent feedback for this brand and model using three specific problem terms. Select notes actually concerning the brand, keeping sources and selection reasons. Read selected comments and organize product, logistics and service feedback with excerpts and next actions.

Build the first search terms from real usage stages, and refine the terms after reviewing the returned material. Use search excerpts to select candidate notes; retrieve note details or thread context when an interpretation depends on more than the excerpt.

2. Preserve comments worth checking

Save the selected comments with the comment and reply guide, then extract the saved comments locally:

python3 comment_research.py extract comment-pages.json comment-review

Read each note together with the note’s discussion. A damaged delivery, a cleaning question and a reply saying an issue was handled each need a separate record. A negative label alone does not establish an incident.

Keep the complete comment-review directory. To revise categories, re-export the saved responses locally instead of retrieving the comments again.

3. Review relevance, type and next action

Save the Python script below as complaint_queue.py, then run complaint_queue.py prepare to create the review template complaint-review.json:

python3 complaint_queue.py prepare comment-review "ExampleBrand / model" complaint-review.json

Review the original material and complete one decision for each item in complaint-review.json:

DecisionRequired review
relevantActual excerpt, brand-context evidence, product/logistics/service/other category, work priority, reason and next action
unrelatedWhy the item is outside this brand or task, preserving the exclusion reason
needs_contextExcerpt, missing context and a way to check it

For example, a report that an accessory box arrived damaged becomes a logistics lead for delivery verification, not a product-design conclusion. The accessory-box report only illustrates the category; quote wording actually present in your saved material.

After the review, run complaint_queue.py finalize to create the queue in the complaint-queue directory:

python3 complaint_queue.py finalize comment-review complaint-review.json complaint-queue
import csv, hashlib, json, pathlib, sys
mode, directory, argument, output = sys.argv[1:]
root = pathlib.Path(directory)
raw_comments = (root/'comments.json').read_bytes()
integrity_bytes = (root/'integrity.json').read_bytes()
integrity = json.loads(integrity_bytes)
if hashlib.sha256(raw_comments).hexdigest() != integrity['comments_sha256']: raise ValueError('Comment evidence changed')
for filename,key in [('pagination.json','pagination_sha256'),('input-manifest.json','manifest_sha256')]:
if hashlib.sha256((root/filename).read_bytes()).hexdigest()!=integrity[key]: raise ValueError('Export provenance changed')
for source in integrity['sources']:
if pathlib.Path(source['file']).name!=source['file']: raise ValueError('Invalid source path')
if hashlib.sha256((root/source['file']).read_bytes()).hexdigest()!=source['sha256']: raise ValueError('Raw source changed')
records=json.loads(raw_comments);by_id={r['evidence_id']:r for r in records}
if len(by_id)!=len(records): raise ValueError('Duplicate evidence ID')
def write_new(path,value):
with pathlib.Path(path).open('x',encoding='utf-8') as f:json.dump(value,f,ensure_ascii=False,indent=2)
if mode=='prepare':
if not argument.strip(): raise ValueError('Name the brand/product in scope')
items=[{k:r[k] for k in ['evidence_id','note_id','comment_id','source_sha256']} for r in records]
for item in items:item.update(decision='unreviewed',category='',priority='',quote='',brand_context='',next_step='',reason='')
write_new(output,{'brand_scope':argument,'comments_sha256':integrity['comments_sha256'],'items':items})
print(json.dumps({'review_items':len(items),'executed_calls':0}))
elif mode=='finalize':
review_bytes=pathlib.Path(argument).read_bytes();review=json.loads(review_bytes)
brand=review.get('brand_scope');items=review.get('items')
if not isinstance(brand,str) or not brand.strip() or review.get('comments_sha256')!=integrity['comments_sha256']: raise ValueError('Wrong brand scope or evidence export')
if not isinstance(items,list) or len(items)!=len(records) or {x['evidence_id'] for x in items}!=set(by_id): raise ValueError('Review every evidence row exactly once')
queue,unrelated,context=[],[],[]
for item in items:
r=by_id[item['evidence_id']]
if any(item.get(k)!=r[k] for k in ['note_id','comment_id','source_sha256']): raise ValueError('Review belongs to another source')
decision=item.get('decision');reason=item.get('reason')
if decision not in ('relevant','unrelated','needs_context') or not isinstance(reason,str) or not reason.strip(): raise ValueError('Every decision needs a review reason')
if decision=='unrelated':
unrelated.append({'evidence_id':r['evidence_id'],'reason':reason});continue
quote=item.get('quote');next_step=item.get('next_step')
if not isinstance(quote,str) or not quote.strip() or len(quote)>500 or quote not in r['text']: raise ValueError('Use an exact short source excerpt')
if not isinstance(next_step,str) or not next_step.strip(): raise ValueError('Record the next internal verification step')
if decision=='needs_context':
context.append({'evidence_id':r['evidence_id'],'note_id':r['note_id'],'comment_id':r['comment_id'],'quote':quote,'reason':reason,'next_step':next_step});continue
if item.get('category') not in ('product','logistics','service','other') or item.get('priority') not in ('routine','priority'): raise ValueError('Choose category and human-assigned review priority')
if not isinstance(item.get('brand_context'),str) or not item['brand_context'].strip(): raise ValueError('Explain how you verified brand/product relevance from the source context')
queue.append({'evidence_id':r['evidence_id'],'note_id':r['note_id'],'comment_id':r['comment_id'],
'brand_scope':brand,'category':item['category'],'review_priority':item['priority'],
'quote':quote,'brand_context':item['brand_context'],'review_reason':reason,'next_step':next_step,
'source_file':r['source_file'],'source_sha256':r['source_sha256'],'request_id':r['request_id'],
'claim_verified':False,'contacted_anyone':False})
target=pathlib.Path(output);target.mkdir()
(target/'review-input.json').write_bytes(review_bytes)
(target/'integrity.json').write_bytes(integrity_bytes)
write_new(target/'issue-queue.json',{'brand_scope':brand,'items':queue,'needs_context':context,'unrelated':unrelated,
'coverage':{'reviewed_comments':len(records),'relevant_signals':len(queue),'unrelated':len(unrelated),'needs_context':len(context),'distinct_notes_with_signals':len({r['note_id'] for r in queue})},
'review_sha256':hashlib.sha256(review_bytes).hexdigest(),'scope':'Human-reviewed signals in the saved sample, not verified incidents, unique customers or population prevalence','executed_calls':0})
fields=['evidence_id','note_id','comment_id','brand_scope','category','review_priority','quote','brand_context','review_reason','next_step','source_file','source_sha256','request_id']
with (target/'issue-queue.csv').open('w',encoding='utf-8-sig',newline='') as f:
w=csv.DictWriter(f,fieldnames=fields);w.writeheader()
for row in queue:
cells={k:str(row[k]) for k in fields};w.writerow({k:"'"+v if v.lstrip().startswith(('=','+','-','@')) else v for k,v in cells.items()})
print(json.dumps({'signals':len(queue),'needs_context':len(context),'unrelated':len(unrelated),'executed_calls':0}))
else: raise ValueError('Use prepare EXPORT_DIR BRAND OUTPUT_JSON or finalize EXPORT_DIR REVIEW_JSON OUTPUT_DIR')

4. Hand off the queue

issue-queue.csv holds the relevant leads and their next actions. issue-queue.json holds the same leads plus the exclusions and the context-needed items. Keep the original responses and the review records so each lead can be checked against its source.

The review priority sets work order, and claim_verified:false marks facts that still require verification. Repeated observations in one note are not additional incidents. Group similar questions under one theme, and keep each question’s own source note and excerpt.

If someone writes “The adapter gets hot as soon as I plug it in,” send the excerpt and the source to product support as an open case, and ask for the adapter model, how long the adapter was used and where the adapter heated up. Send “The outer box arrived crushed” to logistics to check the shipment. The brief can say “Two reports routed for follow-up” and update the outcome once product support and logistics respond.

5. Plan costs and later checks

Count search pages, root-comment pages, selected reply pages and extra detail requests separately, and price each with current pricing. A first round of three keyword pages, two selected comment pages and one reply page is at most six planned page requests. Retrieve less in later rounds when the results are irrelevant.

For recurring checks, keep the reviewed note IDs and the unresolved leads. New notes go through discovery; older issues follow their review status. Record the scope and times of each round. Scheduling and notifications are configured separately, in your own tools.

Note search · Comment research