# US 10,642,835 B2 · System and method for increasing accuracy of approximating query results using neural networks > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,642,835 B2 - Document ID: US10642835B2 - Status: Granted - Kind: B2 - Application number: 15/858,967 - Filed: 2017-12-29 - Published: 2019-02-14 - Granted: 2020-05-05 - Earliest claimed: 2017-08-14 - Assignees: Sisense Ltd. - Applicants: Sisense Ltd. - Inventors: Amir Orad; Nir Regev; Guy Levy Yurista; Adi Azaria - Web page: https://patentgrep.com/patent/US10642835B2 ## CPC - G06N 3/084: Backpropagation, e.g. using gradient descent - G06N 3/098: Distributed learning, e.g. federated learning - G06F 16/24549: {Run-time optimisation} - G06F 16/2455: Query execution - G06F 16/2462: {Approximate or statistical queries} - G06F 16/248: Presentation of query results - G06F 16/903: Querying (for retrieval from the web G06F16/953) - G06F 16/90335: {Query processing} - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/045: Combinations of networks - G06N 3/0499: Feedforward networks - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - G05B 2219/33025: Recurrent artificial neural network - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G) ## 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. ## Claims ### Claim 1 A method for improving accuracy of generated approximations of query results, comprising: 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; determining a confidence level for the first predicted result, wherein the received query is sent to the second neural network only when the confidence level is below a first predefined threshold; 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. ### Claim 2 (depends on 1) The method of claim 1, further comprising: querying the database with the received query to retrieve a real result. ### Claim 3 (depends on 2) The method of claim 2, wherein the second predicted result has a margin of error lower than a margin of error of the first predicted result. ### Claim 4 (depends on 2) The method of claim 2, further comprising: determining if the second predicted result exceeds a predetermined threshold of the real result. ### Claim 5 (depends on 4) The method of claim 4, further comprising: providing the real result as a third output, when the second predicted result exceeds the predetermined threshold of the real result. ### Claim 6 (depends on 4) The method of claim 4, further comprising: providing the second output when the second output exceeds the predetermined threshold. ### Claim 7 (depends on 1) The method of claim 1, wherein the first neural network and the second neural network each include a plurality of neurons configured to generate the first predicted result and the second predicted result respectively, and wherein each neuron is assigned a weight value. ### Claim 8 (depends on 7) The method of claim 7, wherein the second neural network includes more neurons than the first neural network. ### Claim 9 (depends on 1) The method of claim 1, wherein the first predicted result and the second predicted result are provided without querying the database with the received query. ### Claim 10 (depends on 1) The method of claim 1, wherein the confidence level is determined using a loss function. ### Claim 11 (depends on 1) The method of claim 1, further comprising: receiving the query and providing any of the first output, the second output, and the third output to any one of: a user node and an approximation server. ### Claim 12 (depends on 11) The method of claim 11, wherein the approximation server is connected to a plurality of user devices and a plurality of neural networks. ### Claim 13 A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to perform a process, the process comprising: 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; determining a confidence level for the first predicted result, wherein the received query is sent to the second neural network only when the confidence level is below a first predefined threshold; 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. ### Claim 14 A system for increasing the accuracy of generated approximations of query results, comprising: a processing circuitry; and a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to: send a received query to a first neural network and a second neural network; receive from the first neural network a first predicted result to the received query; determine a confidence level for the first predicted result, wherein the received query is sent to the second neural network only when the confidence level is below a first predefined threshold; provide the first predicted result as a first output to a device having initiated the received query; receive from the second neural network a second predicted result to the received query; and provide 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. ### Claim 15 (depends on 14) The system of claim 14, wherein the system is further configured to: query the database with the received query to retrieve a real result. ### Claim 16 (depends on 15) The system of claim 15, wherein the second predicted result has a margin of error lower than a margin of error of the first predicted result. ### Claim 17 (depends on 15) The system of claim 15, wherein the system is further configured to: determine if the second predicted result exceeds a predetermined threshold of the real result. ### Claim 18 (depends on 17) The system of claim 17, wherein the system is further configured to: provide the real result as a third output, when the second predicted result exceeds the predetermined threshold of the real result. ### Claim 19 (depends on 17) The system of claim 17, wherein the system is further configured to: provide the second output when the second output exceeds the predetermined threshold. ### Claim 20 (depends on 14) The system of claim 14, wherein the first neural network and the second neural network each include a plurality of neurons configured to generate the first predicted result and the second predicted result respectively, and wherein each neuron is assigned a weight value. ### Claim 21 (depends on 20) The system of claim 20, wherein the second neural network includes more neurons than the first neural network. ### Claim 22 (depends on 14) The system of claim 14, wherein the first predicted result and the second predicted result are provided without querying the database with the received query. ### Claim 23 (depends on 14) The system of claim 14, wherein the confidence level is determined using a loss function. ### Claim 24 (depends on 14) The system of claim 14, wherein the system is further configured to: receive the query and providing any of the first output, the second output, and the third output to any one of: a user node and an approximation server. ### Claim 25 (depends on 24) The system of claim 24, wherein the approximation server is connected to a plurality of user devices and a plurality of neural networks.