SYSTEM AND METHOD FOR INCREASING ACCURACY OF APPROXIMATING QUERY RESULTS USING NEURAL NETWORKS
A system and method for increasing the accuracy of generated approximations of query results. The method includes sending a received query to a first neural network and a second neural network; receiving from the first neural network a first predicted result to the received query; providing the firs...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Patent |
| Sprache: | eng ; fre |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | REGEV, Nir LEVY YURISTA, Guy ORAD, Amir AZARIA, Adi |
| description | A system and method for increasing the accuracy of generated approximations of query results. The method includes sending a received query to a first neural network and a second neural network; receiving from the first neural network a first predicted result to the received query; providing the first predicted result as a first output to a device having initiated the received query; receiving from the second neural network a second predicted result to the received query; and providing the second predicted result as a second output to the device having initiated the received query, wherein the first neural network requires less computational resources than the second neural network, and whereby the first output is provided before the second output.
L'invention concerne un système et un procédé pour augmenter la précision d'approximations de résultats d'interrogation générées. Le procédé comprend l'envoi d'une interrogation reçue à un premier réseau neuronal et à un second réseau neuronal ; la réception, en provenance du premier réseau neuronal, d'un premier résultat prédit à l'interrogation reçue ; la fourniture du premier résultat prédit en tant que première sortie à un dispositif ayant initié l'interrogation reçue ; la réception, en provenance du second réseau neuronal, d'un second résultat prédit à l'interrogation reçue ; et la fourniture du second résultat prédit en tant que seconde sortie au dispositif ayant initié l'interrogation reçue, le premier réseau neuronal nécessitant moins de ressources de calcul que le second réseau neuronal, et la première sortie étant fournie avant la seconde sortie. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_WO2019035862A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>WO2019035862A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_WO2019035862A13</originalsourceid><addsrcrecordid>eNrjZIgLjgwOcfVVcPRzUfB1DfHwd1Fw8w9S8PRzDnJ1DPb0c1dwdHYODXJ0jlTwd1NwDAgI8o_w9HUMAckEhroGRSoEuQaH-oQEK4SCVfu5AhX7AKmQcP8g72AeBta0xJziVF4ozc2g7OYa4uyhm1qQH59aXJCYnJqXWhIf7m9kYGhpYGxqYWbkaGhMnCoAHWg0VQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>SYSTEM AND METHOD FOR INCREASING ACCURACY OF APPROXIMATING QUERY RESULTS USING NEURAL NETWORKS</title><source>esp@cenet</source><creator>REGEV, Nir ; LEVY YURISTA, Guy ; ORAD, Amir ; AZARIA, Adi</creator><creatorcontrib>REGEV, Nir ; LEVY YURISTA, Guy ; ORAD, Amir ; AZARIA, Adi</creatorcontrib><description>A system and method for increasing the accuracy of generated approximations of query results. The method includes sending a received query to a first neural network and a second neural network; receiving from the first neural network a first predicted result to the received query; providing the first predicted result as a first output to a device having initiated the received query; receiving from the second neural network a second predicted result to the received query; and providing the second predicted result as a second output to the device having initiated the received query, wherein the first neural network requires less computational resources than the second neural network, and whereby the first output is provided before the second output.
L'invention concerne un système et un procédé pour augmenter la précision d'approximations de résultats d'interrogation générées. Le procédé comprend l'envoi d'une interrogation reçue à un premier réseau neuronal et à un second réseau neuronal ; la réception, en provenance du premier réseau neuronal, d'un premier résultat prédit à l'interrogation reçue ; la fourniture du premier résultat prédit en tant que première sortie à un dispositif ayant initié l'interrogation reçue ; la réception, en provenance du second réseau neuronal, d'un second résultat prédit à l'interrogation reçue ; et la fourniture du second résultat prédit en tant que seconde sortie au dispositif ayant initié l'interrogation reçue, le premier réseau neuronal nécessitant moins de ressources de calcul que le second réseau neuronal, et la première sortie étant fournie avant la seconde sortie.</description><language>eng ; fre</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2019</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20190221&DB=EPODOC&CC=WO&NR=2019035862A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20190221&DB=EPODOC&CC=WO&NR=2019035862A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>REGEV, Nir</creatorcontrib><creatorcontrib>LEVY YURISTA, Guy</creatorcontrib><creatorcontrib>ORAD, Amir</creatorcontrib><creatorcontrib>AZARIA, Adi</creatorcontrib><title>SYSTEM AND METHOD FOR INCREASING ACCURACY OF APPROXIMATING QUERY RESULTS USING NEURAL NETWORKS</title><description>A system and method for increasing the accuracy of generated approximations of query results. The method includes sending a received query to a first neural network and a second neural network; receiving from the first neural network a first predicted result to the received query; providing the first predicted result as a first output to a device having initiated the received query; receiving from the second neural network a second predicted result to the received query; and providing the second predicted result as a second output to the device having initiated the received query, wherein the first neural network requires less computational resources than the second neural network, and whereby the first output is provided before the second output.
L'invention concerne un système et un procédé pour augmenter la précision d'approximations de résultats d'interrogation générées. Le procédé comprend l'envoi d'une interrogation reçue à un premier réseau neuronal et à un second réseau neuronal ; la réception, en provenance du premier réseau neuronal, d'un premier résultat prédit à l'interrogation reçue ; la fourniture du premier résultat prédit en tant que première sortie à un dispositif ayant initié l'interrogation reçue ; la réception, en provenance du second réseau neuronal, d'un second résultat prédit à l'interrogation reçue ; et la fourniture du second résultat prédit en tant que seconde sortie au dispositif ayant initié l'interrogation reçue, le premier réseau neuronal nécessitant moins de ressources de calcul que le second réseau neuronal, et la première sortie étant fournie avant la seconde sortie.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2019</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZIgLjgwOcfVVcPRzUfB1DfHwd1Fw8w9S8PRzDnJ1DPb0c1dwdHYODXJ0jlTwd1NwDAgI8o_w9HUMAckEhroGRSoEuQaH-oQEK4SCVfu5AhX7AKmQcP8g72AeBta0xJziVF4ozc2g7OYa4uyhm1qQH59aXJCYnJqXWhIf7m9kYGhpYGxqYWbkaGhMnCoAHWg0VQ</recordid><startdate>20190221</startdate><enddate>20190221</enddate><creator>REGEV, Nir</creator><creator>LEVY YURISTA, Guy</creator><creator>ORAD, Amir</creator><creator>AZARIA, Adi</creator><scope>EVB</scope></search><sort><creationdate>20190221</creationdate><title>SYSTEM AND METHOD FOR INCREASING ACCURACY OF APPROXIMATING QUERY RESULTS USING NEURAL NETWORKS</title><author>REGEV, Nir ; LEVY YURISTA, Guy ; ORAD, Amir ; AZARIA, Adi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_WO2019035862A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre</language><creationdate>2019</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>REGEV, Nir</creatorcontrib><creatorcontrib>LEVY YURISTA, Guy</creatorcontrib><creatorcontrib>ORAD, Amir</creatorcontrib><creatorcontrib>AZARIA, Adi</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>REGEV, Nir</au><au>LEVY YURISTA, Guy</au><au>ORAD, Amir</au><au>AZARIA, Adi</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>SYSTEM AND METHOD FOR INCREASING ACCURACY OF APPROXIMATING QUERY RESULTS USING NEURAL NETWORKS</title><date>2019-02-21</date><risdate>2019</risdate><abstract>A system and method for increasing the accuracy of generated approximations of query results. The method includes sending a received query to a first neural network and a second neural network; receiving from the first neural network a first predicted result to the received query; providing the first predicted result as a first output to a device having initiated the received query; receiving from the second neural network a second predicted result to the received query; and providing the second predicted result as a second output to the device having initiated the received query, wherein the first neural network requires less computational resources than the second neural network, and whereby the first output is provided before the second output.
L'invention concerne un système et un procédé pour augmenter la précision d'approximations de résultats d'interrogation générées. Le procédé comprend l'envoi d'une interrogation reçue à un premier réseau neuronal et à un second réseau neuronal ; la réception, en provenance du premier réseau neuronal, d'un premier résultat prédit à l'interrogation reçue ; la fourniture du premier résultat prédit en tant que première sortie à un dispositif ayant initié l'interrogation reçue ; la réception, en provenance du second réseau neuronal, d'un second résultat prédit à l'interrogation reçue ; et la fourniture du second résultat prédit en tant que seconde sortie au dispositif ayant initié l'interrogation reçue, le premier réseau neuronal nécessitant moins de ressources de calcul que le second réseau neuronal, et la première sortie étant fournie avant la seconde sortie.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng ; fre |
| recordid | cdi_epo_espacenet_WO2019035862A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | SYSTEM AND METHOD FOR INCREASING ACCURACY OF APPROXIMATING QUERY RESULTS USING NEURAL NETWORKS |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T00%3A47%3A50IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=REGEV,%20Nir&rft.date=2019-02-21&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EWO2019035862A1%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |