I am having a hard time understading why the scoring of record #1 is higher than #2.
The one on #2 has more matches (see Highlight entry). Both terms are found on fields with higher boosting criteria ss_categories_full vs ss_name_full and it has matches without the need of fuzziness, yet the score is much lower (48 vs 70).
I tried the multi_match w/ best_fields and most_fields but the answer is the same. I am puzzled!
Highlight for Max Score record:
"highlight": {
"ss_name_full": [
"Lundhs <em>EmeraldÂ</em>®"
]
}
Highlight for 2nd Position Record:
"highlight": {
"ss_searchable_1": [
"<em>emerald</em> palace",
"wide width <em>textiles</em>"
],
"ss_name_full": [
"Standard <em>Textile</em>"
],
"ss_categories_full": [
"<em>Textile</em>",
"<em>Textile</em>>Vertically Hanging <em>Textile</em>",
"<em>Textile</em>"
]
}
Important part of the Query:
"minimum_should_match": 1,
"should": [
{
"match_phrase": {
"ss_name_full": {
"query": "emerald textile"
}
}
},
{
"multi_match": {
"boost": 1,
"fields": [
"sku^10",
"rfid^10",
"ss_categories_full^8",
"ss_name_full^5",
"manufacturer_sku.txt^3.2",
"ss_searchable_1^3",
"ss_searchable_2^2",
"ss_searchable_3"
],
"fuzziness": "1",
"query": "emerald textile",
"slop": 2,
"tie_breaker": 0.3,
"type": "most_fields"
}
}
]
Results w/ Explain = true
{
"took": 21,
"timed_out": false,
"_shards": {
"total": 9,
"successful": 9,
"skipped": 0,
"failed": 0
},
"hits": {
"total": {
"value": 10000,
"relation": "gte"
},
"max_score": 70.357056,
"hits": [
{
"_shard": "[materialbank_product_en_v4][7]",
"_node": "Q2Mj0tZETx6ZeFHu9t-hLA",
"_index": "materialbank_product_en_v4",
"_id": "821937",
"_score": 70.357056,
"_ignored": [
"install_07",
"install_06",
"install_05",
"install_04",
"install_09",
"install_08",
"install_10",
"install_03",
"install_02",
"install_01"
],
"_source": {
"ss_searchable_1": [
"low emitting",
"low emitting/low vocs",
"fireplace",
"fireplace/fireplace surround",
"flooring",
"kitchen",
"furniture",
"stair & elevator",
"bath",
"countertop",
"wall/backsplash",
"pool & fountain",
"wall",
"the lundhs real stone collection",
"astm c-170 - 38850 psi",
"stone",
"norway",
"fireplace surround",
"backsplash",
"slab",
"modular",
"natural",
"leed compliant",
"large format tile",
"field tile"
],
"ss_searchable_2": [
"atsm c-1352 - 171.1 wear index value; en 14157",
"typically stocked",
"stocked in north america",
"made to order / special order",
"medium",
"light",
"monochromatic",
"polished silk/leather honed",
"rectangle",
"square",
"indoor",
"outdoor",
"may contribute toward leed credits.",
"natural",
"residential use",
"commercial use",
"freeze/thaw resistant"
],
"ss_searchable_3": [
"material",
"bs en 12720:2009 - resistant",
"astm c-99 modulus of rupture - 1846 psi",
"atsm c-97 - 0.26% resistant"
],
"rfid": null,
"sku": "100511650",
"manufacturer_sku": [
"Emerald-Polished",
"Emerald-Silk-Leather",
"Emerald-Honed"
]
},
"highlight": {
"ss_name_full": [
"Lundhs <em>EmeraldÂ</em>®"
]
},
"_explanation": {
"value": 70.357056,
"description": "sum of:",
"details": [
{
"value": 70.357056,
"description": "weight(FunctionScoreQuery((ss_name_full:\"emerald textile\" ((ss_name_full:emerald (ss_name_full:emeralda)^0.85714287 (ss_name_full:emeraldâ)^0.85714287 ss_name_full:textile (ss_name_full:textiles)^0.85714287)^5.0 | MatchNoDocsQuery(\"empty BooleanQuery\") | MatchNoDocsQuery(\"empty BooleanQuery\") | (Synonym(ss_searchable_2:textil ss_searchable_2:textile))^2.0 | (manufacturer_sku.txt:emerald)^3.2 | (Synonym(ss_categories_full:textil ss_categories_full:textile))^8.0 | Synonym(ss_searchable_3:textil ss_searchable_3:textile) | (ss_searchable_1:emerald Synonym(ss_searchable_1:textil ss_searchable_1:textile))^3.0)~0.3 #visibility:Catalog| Search)~1, scored by boost(queryboost(score(qty:[-2147483648 TO 3]))^1.0))), result of:",
"details": [
{
"value": 70.357056,
"description": "sum of:",
"details": [
{
"value": 70.357056,
"description": "max plus 0.3 times others of:",
"details": [
{
"value": 70.357056,
"description": "sum of:",
"details": [
{
"value": 35.178528,
"description": "weight(ss_name_full:emeralda in 14860) [PerFieldSimilarity], result of:",
"details": [
{
"value": 35.178528,
"description": "score(freq=1.0), computed as boost * idf * tf from:",
"details": [
{
"value": 9.428572,
"description": "boost",
"details": []
},
{
"value": 8.087933,
"description": "idf, computed as log(1 + (N - n + 0.5) / (n + 0.5)) from:",
"details": [
{
"value": 10,
"description": "n, number of documents containing term",
"details": []
},
{
"value": 34176,
"description": "N, total number of documents with field",
"details": []
}
]
},
{
"value": 0.46131146,
"description": "tf, computed as freq / (freq + k1 * (1 - b + b * dl / avgdl)) from:",
"details": [
{
"value": 1,
"description": "freq, occurrences of term within document",
"details": []
},
{
"value": 1.2,
"description": "k1, term saturation parameter",
"details": []
},
{
"value": 0.75,
"description": "b, length normalization parameter",
"details": []
},
{
"value": 7,
"description": "dl, length of field",
"details": []
},
{
"value": 7.2602997,
"description": "avgdl, average length of field",
"details": []
}
]
}
]
}
]
},
{
"value": 35.178528,
"description": "weight(ss_name_full:emeraldâ in 14860) [PerFieldSimilarity], result of:",
"details": [
{
"value": 35.178528,
"description": "score(freq=1.0), computed as boost * idf * tf from:",
"details": [
{
"value": 9.428572,
"description": "boost",
"details": []
},
{
"value": 8.087933,
"description": "idf, computed as log(1 + (N - n + 0.5) / (n + 0.5)) from:",
"details": [
{
"value": 10,
"description": "n, number of documents containing term",
"details": []
},
{
"value": 34176,
"description": "N, total number of documents with field",
"details": []
}
]
},
{
"value": 0.46131146,
"description": "tf, computed as freq / (freq + k1 * (1 - b + b * dl / avgdl)) from:",
"details": [
{
"value": 1,
"description": "freq, occurrences of term within document",
"details": []
},
{
"value": 1.2,
"description": "k1, term saturation parameter",
"details": []
},
{
"value": 0.75,
"description": "b, length normalization parameter",
"details": []
},
{
"value": 7,
"description": "dl, length of field",
"details": []
},
{
"value": 7.2602997,
"description": "avgdl, average length of field",
"details": []
}
]
}
]
}
]
}
]
}
]
},
{
"value": 0,
"description": "match on required clause, product of:",
"details": [
{
"value": 0,
"description": "# clause",
"details": []
},
{
"value": 1,
"description": "visibility:Catalog| Search",
"details": []
}
]
}
]
}
]
},
{
"value": 0,
"description": "match on required clause, product of:",
"details": [
{
"value": 0,
"description": "# clause",
"details": []
},
{
"value": 1,
"description": "FieldExistsQuery [field=_primary_term]",
"details": []
}
]
}
]
}
},
{
"_shard": "[materialbank_product_en_v4][5]",
"_node": "pA3QwgxUT4W8IOSDkb2QWQ",
"_index": "materialbank_product_en_v4",
"_id": "502774",
"_score": 48.005,
"_source": {
"ss_searchable_1": [
"window",
"haze",
"twilight",
"emerald palace",
"city scape",
"volcano",
"static",
"woven",
"polyester",
"roll",
"wide width textiles",
"abstract",
"texture"
],
"ss_searchable_2": [
"flammability",
"typically stocked",
"none",
"trevira cs",
"light",
"medium",
"polychromatic",
"nfpa 701",
"indoor",
"translucent / sheer",
"abstract / organic",
"texture",
"commercial use",
"contemporary"
],
"ss_searchable_3": [
"material",
"railroaded",
"small"
],
"rfid": null,
"sku": "100156051",
"manufacturer_sku": [
"SD013807",
"SD013806",
"SD013801",
"SD013803",
"SD013804",
"SD013805"
]
},
"highlight": {
"ss_searchable_1": [
"<em>emerald</em> palace",
"wide width <em>textiles</em>"
],
"ss_name_full": [
"Standard <em>Textile</em>"
],
"ss_categories_full": [
"<em>Textile</em>",
"<em>Textile</em>>Vertically Hanging <em>Textile</em>",
"<em>Textile</em>"
]
},
"_explanation": {
"value": 48.005,
"description": "sum of:",
"details": [
{
"value": 48.005,
"description": "weight(FunctionScoreQuery((ss_name_full:\"emerald textile\" ((ss_name_full:emerald ss_name_full:textile (ss_name_full:textiles)^0.85714287)^5.0 | (Synonym(ss_searchable_2:textil ss_searchable_2:textile))^2.0 | MatchNoDocsQuery(\"empty BooleanQuery\") | MatchNoDocsQuery(\"empty BooleanQuery\") | (manufacturer_sku.txt:emerald)^3.2 | (Synonym(ss_categories_full:textil ss_categories_full:textile))^8.0 | (ss_searchable_1:emerald (ss_searchable_1:esmerald)^0.85714287 Synonym(ss_searchable_1:textil ss_searchable_1:textile))^3.0 | Synonym(ss_searchable_3:textil ss_searchable_3:textile))~0.3 #visibility:Catalog| Search)~1, scored by boost(queryboost(score(qty:[-2147483648 TO 3]))^1.0))), result of:",
"details": [
{
"value": 48.005,
"description": "sum of:",
"details": [
{
"value": 48.005,
"description": "max plus 0.3 times others of:",
"details": [
{
"value": 10.20312,
"description": "sum of:",
"details": [
{
"value": 10.20312,
"description": "weight(ss_name_full:textile in 1857) [PerFieldSimilarity], result of:",
"details": [
{
"value": 10.20312,
"description": "score(freq=1.0), computed as boost * idf * tf from:",
"details": [
{
"value": 11,
"description": "boost",
"details": []
},
{
"value": 2.1248493,
"description": "idf, computed as log(1 + (N - n + 0.5) / (n + 0.5)) from:",
"details": [
{
"value": 4068,
"description": "n, number of documents containing term",
"details": []
},
{
"value": 34059,
"description": "N, total number of documents with field",
"details": []
}
]
},
{
"value": 0.4365281,
"description": "tf, computed as freq / (freq + k1 * (1 - b + b * dl / avgdl)) from:",
"details": [
{
"value": 1,
"description": "freq, occurrences of term within document",
"details": []
},
{
"value": 1.2,
"description": "k1, term saturation parameter",
"details": []
},
{
"value": 0.75,
"description": "b, length normalization parameter",
"details": []
},
{
"value": 8,
"description": "dl, length of field",
"details": []
},
{
"value": 7.266831,
"description": "avgdl, average length of field",
"details": []
}
]
}
]
}
]
}
]
},
{
"value": 21.658363,
"description": "weight(Synonym(ss_categories_full:textil ss_categories_full:textile) in 1857) [PerFieldSimilarity], result of:",
"details": [
{
"value": 21.658363,
"description": "score(freq=8.0), computed as boost * idf * tf from:",
"details": [
{
"value": 17.6,
"description": "boost",
"details": []
},
{
"value": 1.3459563,
"description": "idf, computed as log(1 + (N - n + 0.5) / (n + 0.5)) from:",
"details": [
{
"value": 8865,
"description": "n, number of documents containing term",
"details": []
},
{
"value": 34059,
"description": "N, total number of documents with field",
"details": []
}
]
},
{
"value": 0.91428584,
"description": "tf, computed as freq / (freq + k1 * (1 - b + b * dl / avgdl)) from:",
"details": [
{
"value": 8,
"description": "termFreq=8.0",
"details": []
},
{
"value": 1.2,
"description": "k1, term saturation parameter",
"details": []
},
{
"value": 0.75,
"description": "b, length normalization parameter",
"details": []
},
{
"value": 6,
"description": "dl, length of field",
"details": []
},
{
"value": 12.00003,
"description": "avgdl, average length of field",
"details": []
}
]
}
]
}
]
},
{
"value": 38.446556,
"description": "sum of:",
"details": [
{
"value": 25.229454,
"description": "weight(ss_searchable_1:emerald in 1857) [PerFieldSimilarity], result of:",
"details": [
{
"value": 25.229454,
"description": "score(freq=1.0), computed as boost * idf * tf from:",
"details": [
{
"value": 6.6000004,
"description": "boost",
"details": []
},
{
"value": 6.0805163,
"description": "idf, computed as log(1 + (N - n + 0.5) / (n + 0.5)) from:",
"details": [
{
"value": 76,
"description": "n, number of documents containing term",
"details": []
},
{
"value": 33449,
"description": "N, total number of documents with field",
"details": []
}
]
},
{
"value": 0.62867105,
"description": "tf, computed as freq / (freq + k1 * (1 - b + b * dl / avgdl)) from:",
"details": [
{
"value": 1,
"description": "freq, occurrences of term within document",
"details": []
},
{
"value": 1.2,
"description": "k1, term saturation parameter",
"details": []
},
{
"value": 0.75,
"description": "b, length normalization parameter",
"details": []
},
{
"value": 17,
"description": "dl, length of field",
"details": []
},
{
"value": 52.639362,
"description": "avgdl, average length of field",
"details": []
}
]
}
]
}
]
},
{
"value": 13.2171,
"description": "weight(Synonym(ss_searchable_1:textil ss_searchable_1:textile) in 1857) [PerFieldSimilarity], result of:",
"details": [
{
"value": 13.2171,
"description": "score(freq=1.0), computed as boost * idf * tf from:",
"details": [
{
"value": 6.6000004,
"description": "boost",
"details": []
},
{
"value": 3.1854353,
"description": "idf, computed as log(1 + (N - n + 0.5) / (n + 0.5)) from:",
"details": [
{
"value": 1383,
"description": "n, number of documents containing term",
"details": []
},
{
"value": 33449,
"description": "N, total number of documents with field",
"details": []
}
]
},
{
"value": 0.62867105,
"description": "tf, computed as freq / (freq + k1 * (1 - b + b * dl / avgdl)) from:",
"details": [
{
"value": 1,
"description": "termFreq=1.0",
"details": []
},
{
"value": 1.2,
"description": "k1, term saturation parameter",
"details": []
},
{
"value": 0.75,
"description": "b, length normalization parameter",
"details": []
},
{
"value": 17,
"description": "dl, length of field",
"details": []
},
{
"value": 52.639362,
"description": "avgdl, average length of field",
"details": []
}
]
}
]
}
]
}
]
}
]
},
{
"value": 0,
"description": "match on required clause, product of:",
"details": [
{
"value": 0,
"description": "# clause",
"details": []
},
{
"value": 1,
"description": "visibility:Catalog| Search",
"details": []
}
]
}
]
}
]
},
{
"value": 0,
"description": "match on required clause, product of:",
"details": [
{
"value": 0,
"description": "# clause",
"details": []
},
{
"value": 1,
"description": "FieldExistsQuery [field=_primary_term]",
"details": []
}
]
}
]
}
}
]
}
}