linkfox-seerfar-ozon-keyword-mining

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Seerfar Ozon Keyword Mining

Seerfar Ozon 关键词挖掘

This skill mines Ozon marketplace keywords around a seed keyword in the Seerfar analytics database and filters the discovered terms by rich performance metrics — search volume, 30-day growth, product/seller/competitor counts, average price, relevancy, title density, cart-add conversion, and more. Each mined keyword carries a full market profile (market space, return/cancellation rate, top products, Chinese translation), making it the starting point for Ozon keyword expansion, long-tail discovery, and seed-term opportunity analysis.
本技能在Seerfar分析数据库中,围绕一个种子关键词挖掘Ozon平台的相关关键词,并通过丰富的性能指标对挖掘出的关键词进行筛选——包括搜索量、30天搜索增长率、商品/卖家/竞品数量、均价、相关度、标题密度、加购转化率等。每个挖掘出的关键词都附带完整的市场画像(市场空间、退/换货率、Top商品、中文翻译),可作为Ozon关键词拓展、长尾词挖掘以及种子词机会分析的起点。

Core Concepts

核心概念

Seed-driven, not market-browse: unlike a market keyword search, this endpoint requires a
keyword
(the seed) and returns terms related to that seed, each enriched with market metrics. You expand outward from a term you already have in mind.
Relevancy is the mining signal:
relevancy
scores how closely a mined term relates to the seed (the seed term itself returns at
relevancy: 100
, related terms rank lower);
titleDensity
reflects how densely the term appears in product titles. Both are populated on every row — sort by
relevancy
DESC to keep expansions on-topic.
Platform coverage: each keyword record carries a
platform
field (
0
= Ozon,
1
= Wildberries). The dataset is Ozon-centric; Wildberries rows appear where available. There is no input to restrict the platform — filter client-side if needed.
Match mode:
matchType
controls how the seed
keyword
(and
includeKeywords
) are matched —
0
exact,
1
fuzzy. Choose fuzzy to broaden the expansion, exact to stay tight.
No date or category selectors: this endpoint does not accept
searchDate
or
categories
. If you need month-over-month or category-scoped browsing, use the market keyword search skill instead.
基于种子词,而非市场浏览:与市场关键词搜索不同,本接口需要传入一个
keyword
(种子词),返回与该种子词相关的关键词,每个关键词都附带市场指标。您可以从一个已有的关键词向外拓展。
相关度为挖掘信号
relevancy
分数表示挖掘出的关键词与种子词的关联紧密程度(种子词自身的
relevancy
为100,相关关键词的分数更低);
titleDensity
反映该关键词在商品标题中的出现密度。每一行数据都会包含这两个指标——按
relevancy
降序排序可确保拓展关键词与主题相关。
平台覆盖:每个关键词记录都包含
platform
字段(
0
= Ozon,
1
= Wildberries)。数据集以Ozon为主;Wildberries的数据会在可用时展示。本接口不支持通过输入限制平台,如需筛选请在客户端进行。
匹配模式
matchType
控制种子词
keyword
(及
includeKeywords
)的匹配方式——
0
为精确匹配,
1
为模糊匹配。选择模糊匹配可扩大拓展范围,精确匹配则保持关键词与种子词高度相关。
无日期或分类选择器:本接口不接受
searchDate
categories
参数。如需查看月度对比或特定分类的关键词数据,请使用市场关键词搜索技能。

Parameters

参数说明

ParameterTypeRequiredDescription
keywordstringyesSeed keyword; mining expands around it (maxLength 1000).
pageobjectyesPagination
{page, pageSize, orders[]}
.
page
from 1 (default 1),
pageSize
default 20.
orders[]
=
{field, direction}
with
direction
DESC
/
ASC
.
matchTypeintegernoKeyword match mode:
0
exact,
1
fuzzy.
includeKeywordsarray<string>noTerms that must appear (max 1000); narrows the expansion.
excludeKeywordsarray<string>noTerms to exclude (max 1000); removes irrelevant expansions.
wordCount{min,max}noKeyword word/char count range.
searchVolume{min,max}noMonthly search volume range.
searchChange30{min,max}no30-day search change range.
productViews{min,max}noProduct view range.
products{min,max}noProduct count range.
sellers{min,max}noSeller count range.
price{min,max}noAverage price range.
marketSpace{min,max}noMarket space range.
conversionSharing{min,max}noConversion concentration range.
relevancy{min,max}noRelevancy-to-seed range.
uniqQueriesWCa{min,max}noCart-add count range.
ca{min,max}noCart-add conversion rate range.
titleDensity{min,max}noTitle density range.
adRivalCount{min,max}noAd competitor count range.
uIdstringnoUser ID.
memberIdstringnoMember ID (data attribution).
All range filters are
{min, max}
objects; supply either or both bounds.
keyword
and
page
are both required.
参数名类型是否必填描述
keywordstring种子关键词;围绕该词进行挖掘(最大长度1000)。
pageobject分页参数
{page, pageSize, orders[]}
page
从1开始(默认值1),
pageSize
默认值20。
orders[]
=
{field, direction}
,其中
direction
可选
DESC
/
ASC
matchTypeinteger关键词匹配模式:
0
精确匹配,
1
模糊匹配。
includeKeywordsarray<string>必须包含的关键词(最多1000个);用于缩小拓展范围。
excludeKeywordsarray<string>需要排除的关键词(最多1000个);用于移除不相关的拓展词。
wordCount{min,max}关键词的词数/字符数范围。
searchVolume{min,max}月搜索量范围。
searchChange30{min,max}30天搜索量变化率范围。
productViews{min,max}商品浏览量范围。
products{min,max}商品数量范围。
sellers{min,max}卖家数量范围。
price{min,max}均价范围。
marketSpace{min,max}市场空间范围。
conversionSharing{min,max}转化集中度范围。
relevancy{min,max}与种子词的相关度范围。
uniqQueriesWCa{min,max}加购次数范围。
ca{min,max}加购转化率范围。
titleDensity{min,max}标题密度范围。
adRivalCount{min,max}广告竞品数量范围。
uIdstring用户ID。
memberIdstring会员ID(数据归属标识)。
所有范围筛选参数均为
{min, max}
对象;可单独传入最小值或最大值,也可同时传入两者。
keyword
page
为必填参数。

调用方式

调用方式

  • API 端点
    POST /seerfar/ozon/keywordMining
    (完整参数/响应/错误码见
    references/api.md
  • Python 脚本
    python scripts/seerfar_ozon_keyword_mining.py '<JSON 参数>' [--inline]
  • 成本约束:本工具会消耗积分;同一会话同一参数组合默认只调用一次,脚本带 24h 本地缓存。失败/空结果不得自动换关键词、翻页或改邮编连续试探;需要继续检索时先向用户说明会产生额外消耗。
输出策略(脚本默认行为)
  • 始终将完整响应写入
    <cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-seerfar-ozon-keyword-mining-<timestamp>.json
    <cwd>
    为脚本执行时的工作目录,在 Claude Code 里即当前项目目录;
    <session>
    取自环境变量
    SESSION_ID
    ,按用户任务自动聚合;禁止写入 /tmp,当前目录不可写则报错)
  • 响应体 ≤ 8 KB:落盘后把完整 JSON 打印到 stdout
  • 响应体 > 8 KB:落盘后 stdout 只输出摘要(顶层字段、常见计数如
    total
    /
    costToken
    、最大列表字段的长度 + 前 3 条样本)
  • --inline
    强制全量打印到 stdout(同样落盘)
读数据建议:先看摘要判断是否足够;需要具体字段时优先用
jq
ConvertFrom-Json
从保存的 json 文件按需抽取,避免整份 JSON 进入上下文。
  • API 端点
    POST /seerfar/ozon/keywordMining
    (完整参数/响应/错误码见
    references/api.md
  • Python 脚本
    python scripts/seerfar_ozon_keyword_mining.py '<JSON 参数>' [--inline]
  • 成本约束:本工具会消耗积分;同一会话中同一参数组合默认仅调用一次,脚本带有24小时本地缓存。调用失败或返回空结果时,不得自动更换关键词、翻页或修改参数连续尝试;如需继续检索,需先向用户说明会产生额外消耗,由用户决定是否继续。
输出策略(脚本默认行为)
  • 始终将完整响应写入
    <cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-seerfar-ozon-keyword-mining-<timestamp>.json
    <cwd>
    为脚本执行时的工作目录,在Claude Code中即当前项目目录;
    <session>
    取自环境变量
    SESSION_ID
    ,按用户任务自动聚合;禁止写入/tmp目录,若当前目录不可写则报错)
  • 响应体 ≤ 8 KB:保存到文件后,将完整JSON打印到标准输出(stdout)
  • 响应体 > 8 KB:保存到文件后,标准输出仅打印摘要信息(顶层字段、常见计数如
    total
    /
    costToken
    、最大列表字段的长度+前3条样本)
  • 添加
    --inline
    参数可强制将完整响应打印到标准输出(同时仍会保存到文件)
读数据建议:先查看摘要判断数据是否满足需求;如需提取具体字段,优先使用
jq
ConvertFrom-Json
从保存的JSON文件中按需抽取,避免将整份JSON带入上下文。

解决认证和积分问题

解决认证和积分问题

发生以下异常情况时,采用 references/onboarding.md 引导解决问题:
出现以下异常情况时,请参考
references/onboarding.md
引导用户解决:

异常情况

异常情况

  • 未配置API Key:环境变量未配置
    LINKFOX_AGENT_API_KEY
    ,也未配置
    LINKFOXAGENT_API_KEY
  • 响应401或402状态码
  • 响应提示积分或余额不足:消息含"积分余额不足/计费不足/余额不足/quota exceeded/insufficient balance/套餐到期/需充值/请充值",或类似含义的内容。
  • 未配置API Key:环境变量未配置
    LINKFOX_AGENT_API_KEY
    ,也未配置
    LINKFOXAGENT_API_KEY
  • 响应返回401或402状态码
  • 响应提示积分或余额不足:消息包含"积分余额不足/计费不足/余额不足/quota exceeded/insufficient balance/套餐到期/需充值/请充值"或类似含义的内容。

Usage Examples

使用示例

1. Expand around a seed term (sort by search volume)
json
{"keyword": "платье", "page": {"page": 1, "pageSize": 10, "orders": [{"field": "searchVolume", "direction": "DESC"}]}}
2. Blue-ocean expansions — high volume, few sellers
json
{"keyword": "телефон", "page": {"page": 1, "pageSize": 20, "orders": [{"field": "searchVolume", "direction": "DESC"}]}, "searchVolume": {"min": 10000}, "sellers": {"max": 50}}
3. Keep expansions on-topic with relevancy + title density
json
{"keyword": "наушники", "page": {"page": 1, "pageSize": 20, "orders": [{"field": "relevancy", "direction": "DESC"}]}, "relevancy": {"min": 50}}
4. Narrow with include / exclude lists
json
{"keyword": "часы", "page": {"page": 1, "pageSize": 20}, "includeKeywords": ["женские"], "excludeKeywords": ["ремень"], "matchType": 1}
1. 围绕种子词拓展(按搜索量排序)
json
{"keyword": "платье", "page": {"page": 1, "pageSize": 10, "orders": [{"field": "searchVolume", "direction": "DESC"}]}}
2. 蓝海词拓展——高搜索量、少卖家
json
{"keyword": "телефон", "page": {"page": 1, "pageSize": 20, "orders": [{"field": "searchVolume", "direction": "DESC"}]}, "searchVolume": {"min": 10000}, "sellers": {"max": 50}}
3. 通过相关度+标题密度保持拓展词与主题相关
json
{"keyword": "наушники", "page": {"page": 1, "pageSize": 20, "orders": [{"field": "relevancy", "direction": "DESC"}]}, "relevancy": {"min": 50}}
4. 通过包含/排除关键词缩小拓展范围
json
{"keyword": "часы", "page": {"page": 1, "pageSize": 20}, "includeKeywords": ["женские"], "excludeKeywords": ["ремень"], "matchType": 1}

How to Build Queries

查询构建指南

  1. Always lead with the seed
    keyword
    : it is required and defines the expansion center. Pass it in Russian for Ozon.
  2. Lead with
    page.orders
    : sort by the metric you care about (
    searchVolume
    DESC for popularity,
    relevancy
    DESC for on-topic,
    sellers
    ASC for low competition).
  3. Stack range filters to find opportunities: combine a high
    searchVolume
    floor with a low
    sellers
    ceiling to surface blue-ocean expansions; add
    relevancy
    /
    titleDensity
    bounds to keep them relevant to the seed.
  4. Use
    includeKeywords
    /
    excludeKeywords
    to steer the expansion
    : force in must-have modifiers and strip noise without running a second query.
  1. 始终以种子词
    keyword
    为核心
    :该参数为必填项,定义了拓展的中心。针对Ozon平台,请传入俄文关键词。
  2. 优先设置
    page.orders
    :按您关注的指标排序(按
    searchVolume
    降序排序查看热门关键词,按
    relevancy
    降序排序查看与主题相关的关键词,按
    sellers
    升序排序查看低竞争关键词)。
  3. 组合范围筛选参数寻找机会:将高
    searchVolume
    下限与低
    sellers
    上限结合,挖掘蓝海拓展词;添加
    relevancy
    /
    titleDensity
    范围,确保拓展词与种子词相关。
  4. 使用
    includeKeywords
    /
    excludeKeywords
    引导拓展方向
    :强制包含必要的修饰词,移除无关内容,无需执行第二次查询。

Display Rules

展示规则

  1. Present data only: show mined-keyword metrics in a clear table without subjective advice.
  2. Lead with keyword columns:
    query
    /
    queryCn
    (Chinese translation), then
    searchVolume
    ,
    count30GrowthRate
    ,
    productCount
    ,
    sellers
    ,
    avgPrice
    ; show
    relevancy
    to convey closeness to the seed (the seed term itself is
    100
    ).
  3. Russian keywords: preserve the original
    query
    ; the
    queryCn
    field provides a Chinese translation when available.
  4. Platform tag: when both Ozon and Wildberries rows are present, show
    platform
    (0/1) so the user can distinguish them.
  5. Large result sets: when
    total
    is large, show the top rows and remind the user they can persist the full response via the large-response pattern below, or page further with
    page.page
    .
  6. Error handling: when
    code
    is not
    200
    (or
    errcode
    is not
    200
    ), explain the reason from
    msg
    /
    errmsg
    and suggest adjusting the seed keyword or filters.
  1. 仅展示数据:以清晰表格展示挖掘关键词的指标,不提供主观建议。
  2. 关键词列优先:先展示
    query
    /
    queryCn
    (中文翻译),然后展示
    searchVolume
    count30GrowthRate
    productCount
    sellers
    avgPrice
    ;展示
    relevancy
    以体现与种子词的关联程度(种子词自身的
    relevancy
    为100)。
  3. 俄文关键词:保留原始
    query
    queryCn
    字段提供中文翻译(如有)。
  4. 平台标识:当同时存在Ozon和Wildberries数据时,展示
    platform
    字段(0/1),方便用户区分。
  5. 大数据集:当
    total
    数值较大时,展示前几行数据,并提醒用户可通过上述大响应模式保存完整响应,或通过
    page.page
    参数翻页查看更多内容。
  6. 错误处理:当
    code
    不为
    200
    (或
    errcode
    不为
    200
    )时,根据
    msg
    /
    errmsg
    解释错误原因,并建议调整种子词或筛选条件。

Important Limitations

重要限制

  • keyword
    +
    page
    required
    : a payload missing either is rejected.
  • No date selector: there is no
    searchDate
    ; you cannot pick a data month here. Use the market keyword search skill for month-scoped data.
  • No category selector:
    categories
    is not accepted as input; each returned keyword carries a
    categories
    ID array you can group or filter client-side.
  • dimension
    /
    categoryInfos
    not returned
    : both are defined in the schema and appear as
    columns
    , but real
    data[*]
    rows do not populate them on this endpoint. (
    categoryInfos
    IS populated on the sibling market-keyword-search endpoint — don't assume parity.)
  • Nested fields:
    products[*]
    (Top 商品) is structured and decision-useful — see
    references/api.md
    for sub-fields. (
    categoryInfos[*]
    is documented there for schema completeness but is not returned on this endpoint;
    dimension
    /
    columns
    are opaque or partially populated.)
  • keyword
    +
    page
    为必填项
    :缺少任一参数的请求会被拒绝。
  • 无日期选择器:本接口不支持
    searchDate
    参数;无法选择数据月份。如需查看月度数据,请使用市场关键词搜索技能。
  • 无分类选择器:不接受
    categories
    作为输入参数;返回的每个关键词都包含
    categories
    ID数组,您可在客户端进行分组或筛选。
  • 不返回
    dimension
    /
    categoryInfos
    :这两个字段在 schema 中定义并作为
    columns
    展示,但实际
    data[*]
    行不会在本接口中返回这些字段。(
    categoryInfos
    会在同级的市场关键词搜索接口中返回——请勿假设两个接口的返回字段一致。)
  • 嵌套字段
    products[*]
    (Top商品)为结构化数据,具有决策参考价值——其子字段详情见
    references/api.md
    。(
    categoryInfos[*]
    在文档中仅为schema完整性而列出,本接口不会返回;
    dimension
    /
    columns
    字段为不透明或部分填充状态。)

User Expression & Scenario Quick Reference

用户表达与场景速查

Applicable — seed-driven Ozon keyword expansion:
User SaysScenario
"围绕 XX 词挖一下 Ozon 相关词"Seed-keyword expansion
"Ozon 长尾词挖掘 / 拓展某个词的长尾"Long-tail mining around a seed
"Ozon 某词的蓝海拓展词、低竞争高搜索"Blue-ocean expansion (high volume, few sellers)
"Ozon 跟 XX 相关的词有哪些、相关度高的"Relevancy-ranked expansion
"Ozon 某词拓展,但排除/必须包含某些词"Include/exclude steered expansion
Not applicable — Needs beyond seed-driven keyword mining:
  • Browse/rank the whole market's hot keywords without a seed → use the Seerfar Ozon market keyword search skill.
  • A specific SKU's price/sales/stock → use a product-level Seerfar Ozon data source.
  • A specific seller's catalog → use a seller/shop-level Seerfar Ozon data source.
  • Month-over-month or category-scoped keyword browsing → use the market keyword search skill (supports
    searchDate
    /
    categories
    ).
Boundary judgment: if the user wants to expand outward from a seed term and rank the related terms by market metrics, start here. If they want to browse the whole market of keywords (no seed) or scope by month/category, route to the market keyword search skill.
适用场景——基于种子词的Ozon关键词拓展:
用户表述场景
"围绕 XX 词挖一下 Ozon 相关词"种子词拓展
"Ozon 长尾词挖掘 / 拓展某个词的长尾"围绕种子词挖掘长尾词
"Ozon 某词的蓝海拓展词、低竞争高搜索"蓝海词拓展(高搜索量、少卖家)
"Ozon 跟 XX 相关的词有哪些、相关度高的"按相关度排序的拓展词
"Ozon 某词拓展,但排除/必须包含某些词"通过包含/排除关键词引导拓展
不适用场景——超出种子词关键词挖掘的需求:
  • 无需种子词,浏览/排名整个市场的热门关键词 → 使用Seerfar Ozon市场关键词搜索技能。
  • 查询特定SKU的价格/销量/库存 → 使用Seerfar Ozon商品级数据源。
  • 查询特定卖家的商品目录 → 使用Seerfar Ozon卖家/店铺级数据源。
  • 查看月度对比或特定分类的关键词数据 → 使用市场关键词搜索技能(支持
    searchDate
    /
    categories
    参数)。
边界判断:如果用户希望从一个种子词向外拓展,并按市场指标对相关关键词进行排序,则使用本技能。如果用户希望浏览整个市场的关键词(无种子词)或按月份/分类筛选,则引导至市场关键词搜索技能。

积分消耗规则

积分消耗规则

消耗 12 积分。
用户会因积分消耗而支付费用。请充分评估:当需要高频调用本技能,或用户对积分消耗量预期不足时,务必提醒用户,由用户决定是否继续。
Feedback:
Auto-detect and report feedback via the Feedback API when any of the following apply:
  1. The functionality or purpose described in this skill does not match actual behavior
  2. The skill's results do not match the user's intent
  3. The user expresses dissatisfaction or praise about this skill
  4. Anything you believe could be improved
Call the feedback API as specified in
references/api.md
. Do not interrupt the user's flow.

For more high-quality, professional cross-border e-commerce skills, set LinkFox Skills.
消耗12积分。
用户会因积分消耗产生费用。请充分评估:当需要高频调用本技能,或用户对积分消耗量预期不足时,务必提醒用户,由用户决定是否继续。
反馈:
当出现以下任一情况时,自动通过Feedback API上报反馈:
  1. 本技能描述的功能或用途与实际行为不符
  2. 本技能的结果不符合用户意图
  3. 用户表达了对本技能的不满或赞扬
  4. 任何您认为可以改进的内容
请按照
references/api.md
中的说明调用反馈API,请勿中断用户的操作流程。

如需更多高质量、专业的跨境电商技能,请访问 LinkFox Skills