127 lines
3.5 KiB
JSON
127 lines
3.5 KiB
JSON
{
|
|
"source_dataset": "基础使用场景测试集.xlsx",
|
|
"source_version": "1.0",
|
|
"summary": {
|
|
"query_total": 72,
|
|
"primary_scene_total": 12,
|
|
"secondary_scene_total": 55,
|
|
"atomic_capability_total": 139,
|
|
"difficulty_distribution": {
|
|
"l1": 22,
|
|
"l2": 39,
|
|
"l3": 11
|
|
},
|
|
"design_principles": [
|
|
"mece_atomic_capabilities",
|
|
"parameterized_case_expansion",
|
|
"clear_and_ambiguous_query_variants",
|
|
"dual_channel_delivery_judging"
|
|
]
|
|
},
|
|
"scenario_catalog": [
|
|
{
|
|
"scenario": "file_system_ops",
|
|
"source_label_zh": "文件与系统操作",
|
|
"query_count": 8,
|
|
"weight": 0.13,
|
|
"difficulty_distribution": {"l1": 4, "l2": 4, "l3": 0}
|
|
},
|
|
{
|
|
"scenario": "web_info_ops",
|
|
"source_label_zh": "信息查询与网页操作",
|
|
"query_count": 6,
|
|
"weight": 0.1,
|
|
"difficulty_distribution": {"l1": 2, "l2": 3, "l3": 1}
|
|
},
|
|
{
|
|
"scenario": "calendar_reminders",
|
|
"source_label_zh": "日程与提醒",
|
|
"query_count": 5,
|
|
"weight": 0.08,
|
|
"difficulty_distribution": {"l1": 3, "l2": 2, "l3": 0}
|
|
},
|
|
{
|
|
"scenario": "communication_messaging",
|
|
"source_label_zh": "通讯与消息",
|
|
"query_count": 5,
|
|
"weight": 0.09,
|
|
"difficulty_distribution": {"l1": 0, "l2": 5, "l3": 0}
|
|
},
|
|
{
|
|
"scenario": "data_processing_analysis",
|
|
"source_label_zh": "数据处理与分析",
|
|
"query_count": 8,
|
|
"weight": 0.11,
|
|
"difficulty_distribution": {"l1": 2, "l2": 6, "l3": 0}
|
|
},
|
|
{
|
|
"scenario": "coding_dev_assist",
|
|
"source_label_zh": "编程与开发辅助",
|
|
"query_count": 7,
|
|
"weight": 0.09,
|
|
"difficulty_distribution": {"l1": 3, "l2": 4, "l3": 0}
|
|
},
|
|
{
|
|
"scenario": "personal_life_assistant",
|
|
"source_label_zh": "个人生活助理",
|
|
"query_count": 5,
|
|
"weight": 0.06,
|
|
"difficulty_distribution": {"l1": 4, "l2": 1, "l3": 0}
|
|
},
|
|
{
|
|
"scenario": "multi_step_compound",
|
|
"source_label_zh": "多步骤复合任务",
|
|
"query_count": 7,
|
|
"weight": 0.12,
|
|
"difficulty_distribution": {"l1": 0, "l2": 0, "l3": 7}
|
|
},
|
|
{
|
|
"scenario": "context_continuation",
|
|
"source_label_zh": "上下文理解与连续对话",
|
|
"query_count": 7,
|
|
"weight": 0.05,
|
|
"difficulty_distribution": {"l1": 0, "l2": 5, "l3": 2}
|
|
},
|
|
{
|
|
"scenario": "error_boundary_cases",
|
|
"source_label_zh": "错误处理与边界情况",
|
|
"query_count": 6,
|
|
"weight": 0.05,
|
|
"difficulty_distribution": {"l1": 3, "l2": 2, "l3": 1}
|
|
},
|
|
{
|
|
"scenario": "skill_calling",
|
|
"source_label_zh": "Skill调用",
|
|
"query_count": 4,
|
|
"weight": 0.07,
|
|
"difficulty_distribution": {"l1": 0, "l2": 4, "l3": 0}
|
|
},
|
|
{
|
|
"scenario": "system_capabilities",
|
|
"source_label_zh": "系统能力",
|
|
"query_count": 4,
|
|
"weight": 0.05,
|
|
"difficulty_distribution": {"l1": 1, "l2": 3, "l3": 0}
|
|
}
|
|
],
|
|
"current_corpus_alignment": {
|
|
"mapped_task_total": 20,
|
|
"covered_scenarios": {
|
|
"coding_dev_assist": 9,
|
|
"data_processing_analysis": 2,
|
|
"web_info_ops": 2,
|
|
"multi_step_compound": 3,
|
|
"context_continuation": 1,
|
|
"error_boundary_cases": 2,
|
|
"system_capabilities": 1
|
|
},
|
|
"missing_scenarios": [
|
|
"file_system_ops",
|
|
"calendar_reminders",
|
|
"communication_messaging",
|
|
"personal_life_assistant",
|
|
"skill_calling"
|
|
]
|
|
}
|
|
}
|