Solr Meilleur résultat de recherche avec requête adjacente mot-clé

Question

J'ai configuré solr pour mon application de commerce électronique (qui contient principalement des données de livres). Le résultat de la recherche ne semble pas retourner ce que j'attends.

Voici la configuration.

schema.xml `

<field name="namespace" type="string" indexed="true" stored="false" /> 
    <field name="id" type="string" indexed="true" stored="true" /> 
    <field name="productId" type="long" indexed="true" stored="true" /> 
    <field name="skuId" type="long" indexed="true" stored="true" /> 
    <field name="category" type="long" indexed="true" stored="false" multiValued="true" /> 
    <field name="explicitCategory" type="long" indexed="true" stored="false" multiValued="true" /> 
    <field name="searchable" type="text_general" indexed="true" stored="false" /> 

    <dynamicField name="*_searchable" type="text_general" indexed="true" stored="false" /> 
    <dynamicField name="*_i" type="int" indexed="true" stored="false" /> 
    <dynamicField name="*_is" type="int" indexed="true" stored="false" multiValued="true" /> 
    <dynamicField name="*_s" type="string" indexed="true" stored="false" /> 
    <dynamicField name="*_ss" type="string" indexed="true" stored="false" multiValued="true" /> 
    <dynamicField name="*_l" type="long" indexed="true" stored="false" /> 
    <dynamicField name="*_ls" type="long" indexed="true" stored="false" multiValued="true" /> 
    <dynamicField name="*_t" type="text_general" indexed="true" stored="false" /> 
    <dynamicField name="*_txt" type="text_general" indexed="true" stored="false" multiValued="true" /> 
    <dynamicField name="*_b" type="boolean" indexed="true" stored="false" /> 
    <dynamicField name="*_bs" type="boolean" indexed="true" stored="false" multiValued="true" /> 
    <dynamicField name="*_d" type="double" indexed="true" stored="false" /> 
    <dynamicField name="*_ds" type="double" indexed="true" stored="false" multiValued="true" /> 
    <dynamicField name="*_p" type="double" indexed="true" stored="false" /> 

    <dynamicField name="*_dt" type="date" indexed="true" stored="false" /> 
    <dynamicField name="*_dts" type="date" indexed="true" stored="false" multiValued="true" /> 

    <!-- some trie-coded dynamic fields for faster range queries --> 
    <dynamicField name="*_ti" type="tint" indexed="true" stored="false" /> 
    <dynamicField name="*_tl" type="tlong" indexed="true" stored="false" /> 
    <dynamicField name="*_td" type="tdouble" indexed="true" stored="false" /> 
    <dynamicField name="*_tdt" type="tdate" indexed="true" stored="false" /> 

    <!-- Both field types required for geolocation searches. First stores the 
     lat and lon components for the "coordinate" FieldType. Second stores 
     the coordinate. --> 
    <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/> 
    <dynamicField name="*_c" type="coordinate" indexed="true" stored="false"/> 
</fields> 

<uniqueKey>id</uniqueKey> 

<types> 
    <!-- The StrField type is not analyzed, but indexed/stored verbatim. --> 
    <fieldType name="string" class="solr.StrField" sortMissingLast="true" /> 

    <!-- boolean type: "true" or "false" --> 
    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" /> 

    <!-- Default numeric field types. For faster range queries, consider the 
     tint/tlong/tdouble types. --> 
    <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0" /> 
    <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0" /> 
    <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0" /> 

    <!-- Numeric field types that index each value at various levels of precision 
     to accelerate range queries when the number of values between the range endpoints 
     is large. See the javadoc for NumericRangeQuery for internal implementation 
     details. Smaller precisionStep values (specified in bits) will lead to more 
     tokens indexed per value, slightly larger index size, and faster range queries. 
     A precisionStep of 0 disables indexing at different precision levels. --> 
    <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0" /> 
    <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0" /> 
    <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0" /> 

    <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, 
     and is a more restricted form of the canonical representation of dateTime 
     http://www.w3.org/TR/xmlschema-2/#dateTime The trailing "Z" designates UTC 
     time and is mandatory. Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z 
     All other components are mandatory. Expressions can also be used to denote 
     calculations that should be performed relative to "NOW" to determine the 
     value, ie... NOW/HOUR ... Round to the start of the current hour NOW-1DAY 
     ... Exactly 1 day prior to now NOW/DAY+6MONTHS+3DAYS ... 6 months and 3 days 
     in the future from the start of the current day Consult the DateField javadocs 
     for more information. Note: For faster range queries, consider the tdate 
     type --> 
    <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0" /> 

    <!-- A Trie based date field for faster date range queries and date faceting. --> 
    <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0" /> 

    <!-- A general text field that has reasonable, generic cross-language defaults: 
     it tokenizes with StandardTokenizer and down cases. --> 
    <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100"> 
     <analyzer type="index"> 
      <tokenizer class="solr.StandardTokenizerFactory" /> 
      <filter class="solr.LowerCaseFilterFactory" /> 
     </analyzer> 
     <analyzer type="query"> 
      <tokenizer class="solr.StandardTokenizerFactory" /> 
      <filter class="solr.LowerCaseFilterFactory" /> 
     </analyzer> 
    </fieldType> 

    <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. --> 
    <fieldType name="coordinate" class="solr.LatLonType" subFieldSuffix="_coordinate"/> 

</types> 

`

solrconfig.xml

<?xml version="1.0" encoding="UTF-8" ?> 
<config> 
<luceneMatchVersion>4.10.3</luceneMatchVersion> 
<directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.StandardDirectoryFactory}" /> 
<updateHandler class="solr.DirectUpdateHandler2" /> 

<query> 
    <maxBooleanClauses>1024</maxBooleanClauses> 

    <filterCache class="solr.FastLRUCache" size="512" initialSize="512" autowarmCount="0" /> 
    <queryResultCache class="solr.LRUCache" size="512" initialSize="512" autowarmCount="0" /> 
    <documentCache class="solr.LRUCache" size="512" initialSize="512" autowarmCount="0" /> 
    <cache name="perSegFilter" class="solr.search.LRUCache" size="10" initialSize="0" autowarmCount="10" 
      regenerator="solr.NoOpRegenerator" /> 

    <enableLazyFieldLoading>true</enableLazyFieldLoading> 

    <queryResultWindowSize>20</queryResultWindowSize> 
    <queryResultMaxDocsCached>200</queryResultMaxDocsCached> 

    <listener event="newSearcher" class="solr.QuerySenderListener" /> 
    <listener event="firstSearcher" class="solr.QuerySenderListener"> 
     <arr name="queries"> 
      <lst> 
       <str name="q">static firstSearcher warming in solrconfig.xml</str> 
      </lst> 
     </arr> 
    </listener> 

    <useColdSearcher>false</useColdSearcher> 
    <maxWarmingSearchers>2</maxWarmingSearchers> 
</query> 

<requestDispatcher handleSelect="false"> 
    <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048000" formdataUploadLimitInKB="2048" 
       addHttpRequestToContext="false"/> 
    <httpCaching never304="true" /> 
</requestDispatcher> 

<requestHandler name="/select" class="solr.SearchHandler"> 
    <lst name="defaults"> 
     <str name="echoParams">explicit</str> 
     <int name="rowsa">10</int> 
     <str name="df">name_t</str> 
    </lst> 
</requestHandler> 

<queryResponseWriter name="json" class="solr.JSONResponseWriter"> 
    <str name="content-type">text/plain; charset=UTF-8</str> 
</queryResponseWriter> 

Pour Par exemple, lorsque je recherche 2 états, cela me donne beaucoup de résultats aléatoires, qui ne contiennent même pas 2 états dans le titre.

Cependant, lorsque je recherche 2 états dans la phrase « 2 États », je reçois les résultats pertinents »

Je ne veux pas restreindre chaque recherche dans les citations, depuis l'utilisateur peut rechercher une combinaison comme "livre par auteur" qui donne certainement 0 résultats si recherché dans la phrase car il ne correspondra pas à la phrase exacte

Comment puis-je améliorer ma recherche de sorte que Je peux énumérer les résultats les plus pertinents sur le dessus.

Answer 1

Vous pouvez utiliser les pf2 et pf3 paramètres dans le gestionnaire edismax pour donner boosts aux documents où se trouvent deux (pf2) ou trois (pf3) de termes après l'autre sur le terrain.

defType=edismax&pf2=title^4 

Vous avez aussi l'argument pf pour le gestionnaire dismax régulier, mais qui est construit sur l'hypothèse que tous les termes sont proches. Cela peut aider, mais pf2 ou pf3 sonne mieux adapté à ce dont vous avez besoin.