linkfox-seerfar-ozon-keyword-mining
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseSeerfar 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 (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.
keywordRelevancy is the mining signal: scores how closely a mined term relates to the seed (the seed term itself returns at , related terms rank lower); reflects how densely the term appears in product titles. Both are populated on every row — sort by DESC to keep expansions on-topic.
relevancyrelevancy: 100titleDensityrelevancyPlatform coverage: each keyword record carries a field ( = Ozon, = Wildberries). The dataset is Ozon-centric; Wildberries rows appear where available. There is no input to restrict the platform — filter client-side if needed.
platform01Match mode: controls how the seed (and ) are matched — exact, fuzzy. Choose fuzzy to broaden the expansion, exact to stay tight.
matchTypekeywordincludeKeywords01No date or category selectors: this endpoint does not accept or . If you need month-over-month or category-scoped browsing, use the market keyword search skill instead.
searchDatecategories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(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。
keyword相关度为挖掘信号:分数表示挖掘出的关键词与种子词的关联紧密程度(种子词自身的为100,相关关键词的分数更低);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——按降序排序可确保拓展关键词与主题相关。
relevancyrelevancytitleDensityrelevancy平台覆盖:每个关键词记录都包含字段( = Ozon, = 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。
platform01匹配模式:控制种子词(及)的匹配方式——为精确匹配,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。
matchTypekeywordincludeKeywords01无日期或分类选择器:本接口不接受或参数。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。
searchDatecategoriesParameters
参数说明
| Parameter | Type | Required | Description |
|---|---|---|---|
| keyword | string | yes | Seed keyword; mining expands around it (maxLength 1000). |
| page | object | yes | Pagination |
| matchType | integer | no | Keyword match mode: |
| includeKeywords | array<string> | no | Terms that must appear (max 1000); narrows the expansion. |
| excludeKeywords | array<string> | no | Terms to exclude (max 1000); removes irrelevant expansions. |
| wordCount | {min,max} | no | Keyword word/char count range. |
| searchVolume | {min,max} | no | Monthly search volume range. |
| searchChange30 | {min,max} | no | 30-day search change range. |
| productViews | {min,max} | no | Product view range. |
| products | {min,max} | no | Product count range. |
| sellers | {min,max} | no | Seller count range. |
| price | {min,max} | no | Average price range. |
| marketSpace | {min,max} | no | Market space range. |
| conversionSharing | {min,max} | no | Conversion concentration range. |
| relevancy | {min,max} | no | Relevancy-to-seed range. |
| uniqQueriesWCa | {min,max} | no | Cart-add count range. |
| ca | {min,max} | no | Cart-add conversion rate range. |
| titleDensity | {min,max} | no | Title density range. |
| adRivalCount | {min,max} | no | Ad competitor count range. |
| uId | string | no | User ID. |
| memberId | string | no | Member ID (data attribution). |
All range filters are objects; supply either or both bounds. and are both required.
{min, max}keywordpage| 参数名 | 类型 | 是否必填 | 描述 |
|---|---|---|---|
| keyword | string | 是 | 种子关键词;围绕该词进行挖掘(最大长度1000)。 |
| page | object | 是 | 分页参数 |
| matchType | integer | 否 | 关键词匹配模式: |
| includeKeywords | array<string> | 否 | 必须包含的关键词(最多1000个);用于缩小拓展范围。 |
| excludeKeywords | array<string> | 否 | 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} | 否 | 关键词的词数/字符数范围。 |
| searchVolume | {min,max} | 否 | 月搜索量范围。 |
| searchChange30 | {min,max} | 否 | 30天搜索量变化率范围。 |
| productViews | {min,max} | 否 | 商品浏览量范围。 |
| products | {min,max} | 否 | 商品数量范围。 |
| sellers | {min,max} | 否 | 卖家数量范围。 |
| price | {min,max} | 否 | 均价范围。 |
| marketSpace | {min,max} | 否 | 市场空间范围。 |
| conversionSharing | {min,max} | 否 | 转化集中度范围。 |
| relevancy | {min,max} | 否 | 与种子词的相关度范围。 |
| uniqQueriesWCa | {min,max} | 否 | 加购次数范围。 |
| ca | {min,max} | 否 | 加购转化率范围。 |
| titleDensity | {min,max} | 否 | 标题密度范围。 |
| adRivalCount | {min,max} | 否 | 广告竞品数量范围。 |
| uId | string | 否 | 用户ID。 |
| memberId | string | 否 | 会员ID(数据归属标识)。 |
所有范围筛选参数均为对象;可单独传入最小值或最大值,也可同时传入两者。和为必填参数。
{min, max}keywordpage调用方式
调用方式
- API 端点:(完整参数/响应/错误码见
POST /seerfar/ozon/keywordMining)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为脚本执行时的工作目录,在 Claude Code 里即当前项目目录;<cwd>取自环境变量<session>,按用户任务自动聚合;禁止写入 /tmp,当前目录不可写则报错)SESSION_ID - 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、最大列表字段的长度 + 前 3 条样本)costToken - 加 强制全量打印到 stdout(同样落盘)
--inline
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 或 从保存的 json 文件按需抽取,避免整份 JSON 进入上下文。
jqConvertFrom-Json- API 端点:(完整参数/响应/错误码见
POST /seerfar/ozon/keywordMining)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为脚本执行时的工作目录,在Claude Code中即当前项目目录;<cwd>取自环境变量<session>,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)SESSION_ID - 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、最大列表字段的长度+前3条样本)costToken - 添加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)
--inline
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,优先使用或从保存的JSON文件中按需抽取,避免将整份JSON带入上下文。
jqConvertFrom-Json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,请参考引导用户解决:
references/onboarding.md异常情况
异常情况
- 未配置API Key:环境变量未配置 ,也未配置
LINKFOX_AGENT_API_KEY。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,也未配置
LINKFOX_AGENT_API_KEY。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
- Always lead with the seed : it is required and defines the expansion center. Pass it in Russian for Ozon.
keyword - Lead with : sort by the metric you care about (
page.ordersDESC for popularity,searchVolumeDESC for on-topic,relevancyASC for low competition).sellers - Stack range filters to find opportunities: combine a high floor with a low
searchVolumeceiling to surface blue-ocean expansions; addsellers/relevancybounds to keep them relevant to the seed.titleDensity - Use /
includeKeywordsto steer the expansion: force in must-have modifiers and strip noise without running a second query.excludeKeywords
- 始终以种子词为核心: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。
keyword - 优先设置:按您关注的指标排序(按
page.orders降序排序查看热门关键词,按searchVolume降序排序查看与主题相关的关键词,按relevancy升序排序查看低竞争关键词)。sellers - 组合范围筛选参数寻找机会:将高下限与低
searchVolume上限结合,挖掘蓝海拓展词;添加sellers/relevancy范围,确保拓展词与种子词相关。titleDensity - 使用/
includeKeywords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。excludeKeywords
Display Rules
展示规则
- Present data only: show mined-keyword metrics in a clear table without subjective advice.
- Lead with keyword columns: /
query(Chinese translation), thenqueryCn,searchVolume,count30GrowthRate,productCount,sellers; showavgPriceto convey closeness to the seed (the seed term itself isrelevancy).100 - Russian keywords: preserve the original ; the
queryfield provides a Chinese translation when available.queryCn - Platform tag: when both Ozon and Wildberries rows are present, show (0/1) so the user can distinguish them.
platform - Large result sets: when 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
total.page.page - Error handling: when is not
code(or200is noterrcode), explain the reason from200/msgand suggest adjusting the seed keyword or filters.errmsg
- 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。
- 关键词列优先:先展示/
query(中文翻译),然后展示queryCn、searchVolume、count30GrowthRate、productCount、sellers;展示avgPrice以体现与种子词的关联程度(种子词自身的relevancy为100)。relevancy - 俄文关键词:保留原始;
query字段提供中文翻译(如有)。queryCn - 平台标识:当同时存在Ozon和Wildberries数据时,展示字段(0/1),方便用户区分。
platform - 大数据集:当数值较大时,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
total参数翻页查看更多内容。page.page - 错误处理:当不为
code(或200不为errcode)时,根据200/msg解释错误原因,并建议调整种子词或筛选条件。errmsg
Important Limitations
重要限制
- +
keywordrequired: a payload missing either is rejected.page - No date selector: there is no ; you cannot pick a data month here. Use the market keyword search skill for month-scoped data.
searchDate - No category selector: is not accepted as input; each returned keyword carries a
categoriesID array you can group or filter client-side.categories - /
dimensionnot returned: both are defined in the schema and appear ascategoryInfos, but realcolumnsrows do not populate them on this endpoint. (data[*]IS populated on the sibling market-keyword-search endpoint — don't assume parity.)categoryInfos - Nested fields: (Top 商品) is structured and decision-useful — see
products[*]for sub-fields. (references/api.mdis documented there for schema completeness but is not returned on this endpoint;categoryInfos[*]/dimensionare opaque or partially populated.)columns
- +
keyword为必填项:缺少任一参数的请求会被拒绝。page - 无日期选择器:本接口不支持参数;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。
searchDate - 无分类选择器:不接受作为输入参数;返回的每个关键词都包含
categoriesID数组,您可在客户端进行分组或筛选。categories - 不返回/
dimension:这两个字段在 schema 中定义并作为categoryInfos展示,但实际columns行不会在本接口中返回这些字段。(data[*]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。)categoryInfos - 嵌套字段:(Top商品)为结构化数据,具有决策参考价值——其子字段详情见
products[*]。(references/api.md在文档中仅为schema完整性而列出,本接口不会返回;categoryInfos[*]/dimension字段为不透明或部分填充状态。)columns
User Expression & Scenario Quick Reference
用户表达与场景速查
Applicable — seed-driven Ozon keyword expansion:
| User Says | Scenario |
|---|---|
| "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参数)。categories
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:
- The functionality or purpose described in this skill does not match actual behavior
- The skill's results do not match the user's intent
- The user expresses dissatisfaction or praise about this skill
- Anything you believe could be improved
Call the feedback API as specified in . Do not interrupt the user's flow.
references/api.mdFor 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:
- 本技能描述的功能或用途与实际行为不符
- 本技能的结果不符合用户意图
- 用户表达了对本技能的不满或赞扬
- 任何您认为可以改进的内容
请按照中的说明调用反馈API,请勿中断用户的操作流程。
references/api.md如需更多高质量、专业的跨境电商技能,请访问 LinkFox Skills。