# US 12,008,559 B1 · Decentralized blockchain for artificial intelligence-enabled multi-party skills exchanges over a network > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,008,559 B1 - Document ID: US12008559B1 - Status: Granted - Kind: B1 - Application number: 17/843,927 - Filed: 2022-06-17 - Granted: 2024-06-11 - Earliest claimed: 2017-12-29 - Assignees: Entefy Inc. - Applicants: Entefy Inc. - Inventors: Alston Ghafourifar; Mehdi Ghafourifar - Web page: https://patentgrep.com/patent/US12008559B1 ## CPC - G06Q 20/3829: {involving key management} - G06N 5/043: Distributed expert systems; Blackboards - G06Q 20/223: {based on the use of peer-to-peer networks} - G06Q 20/3827: {Use of message hashing} - G06Q 30/0206: {Price or cost determination based on market factors} - G06Q 40/04: Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange - H04L 9/0637: {Modes of operation, e.g. cipher block chaining [CBC], electronic codebook [ECB] or Galois/counter mode [GCM]} - H04L 9/3239: {involving non-keyed hash functions, e.g. modification detection codes [MDCs], MD5, SHA or RIPEMD} - H04L 9/50: {using hash chains, e.g. blockchains or hash trees} - H04L 67/1042: using topology management mechanisms - H04W 4/70: Services for machine-to-machine communication [M2M] or machine type communication [MTC] - G06Q 2220/10: Usage protection of distributed data files - H04L 2209/56: Financial cryptography, e.g. electronic payment or e-cash - H04L 2463/102: applying security measure for e-commerce - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) - H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72) ## Abstract An improved decentralized, blockchain-driven network for artificial intelligence (AI)-enabled skills exchange between Intelligent Personal Assistants (IPAs) in a network is disclosed that is configured to perform computational tasks or services (also referred to herein as “skills”) in an optimally-efficient fashion. In some embodiments, this may comprise a first IPA paying an agreed cost to a second IPA to perform a particular skill in a more optimally-efficient fashion. In some embodiments, a skills registry is published, comprising benchmark analyses and costs for the skills offered by the various nodes on the skills exchange network. In other embodiments, a transaction ledger is maintained that provides a record of all transactions performed across the network in a tamper-proof and auditable fashion, e.g., via the use of blockchain technology. Over time, the AI-enabled nodes in the system may learn to scale, replicate, and transact with each other in an optimized—and fully autonomous—fashion. ## Claims ### Claim 1 A computer-implemented method for Intelligent Personal Assistant (IPA) applications, comprising: receiving a request for a performance of a first computational skill using a network comprising a plurality of IPA nodes, wherein each of the plurality of IPA nodes are configured to execute at least one IPA application for at least a portion of computational skills available on the network, and wherein the network further comprises an artificial intelligence (AI) computational environment that autonomously selects one or more of the plurality of IPA nodes when performing each of the computational skills based on a efficiency processing benchmark; determining benchmark scores and node availability for each of the plurality of IPA nodes; determining a computational efficiency of each of the plurality of IPA nodes in performing the first computational skill using the at least one IPA application executing on the one of more of the plurality of IPA nodes; performing a benchmarking analysis of the first computational skill on each of the plurality of IPA nodes based at least on the computational efficiency, wherein the benchmarking analysis comprises at least one computational rating required for a performance of the first computational skill using the network; selecting, by the AI computational environment, a first IPA application and a second IPA application based on the benchmark scores, the node availability, and the benchmarking analysis; establishing a smart contract between the first IPA application and the second IPA application for performing the first computational skill at a set processing rate; and performing, by the first IPA application and the second IPA application, the first computational skill using at least one of the plurality of IPA nodes based on the smart contract. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein the selecting the first IPA application and the second IPA application comprises: selecting, by the AI computational environment, a first node of the plurality of IPA nodes for the first IPA application and a second node of the plurality of IPA nodes for the second IPA application based on the benchmark scores, the node availability, and the benchmarking analysis, wherein the selecting the first node and the second nodes is based on a efficiency type of processing of the first computational skill selected by the AI computational environment for the efficiency processing benchmark. ### Claim 3 (depends on 2) The computer-implemented method of claim 2, further comprising: learning, by the AI computational environment, at least one IPA task improvement for at least one of the first node or the second node based on performing the first computational skill; updating the at least one of the first node or the second node based on the learning; and updating a skills registry based on the updated at least one of the first node or the second node. ### Claim 4 (depends on 3) The computer-implemented method of claim 3, wherein the learning the at least one IPA task improvement comprises determining to outsource at least a portion of the first computational skill between the first node and the second node based on one of a lowest cost provider, a fastest service provider, a most reliable provider or a highest quality provider. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, further comprising: recording the performing of the first computational skill, by at least one of the first IPA application or the second IPA application, at a determined price in a transaction ledger accessible by the plurality of IPA nodes in the network. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein the selecting the first IPA application and the second IPA application comprises: determining, by the AI computational environment, that the second IPA application provides the efficiency processing benchmark for a portion of the first computational skill; selecting, by the AI computational environment, the first IPA application for another portion of the first computational skill; and selecting, by the AI computational environment, the second IPA application to outsource the portion of the first computational skill at a determined price for the network. ### Claim 7 (depends on 6) The computer-implemented method of claim 6, wherein the determined price comprises one of an agreed price between a first node corresponding to the first IPA application and a second node corresponding to the second IPA application, a set price by the second node, or a historically determined price associated with the portion of the first computational skill performed by at least one of the second node or one or more other nodes of the plurality of IPA nodes. ### Claim 8 (depends on 1) The computer-implemented method of claim 1, wherein the benchmark scores for each of the plurality of IPA nodes comprises at least one of a hardware rating, a user rating, a throughput speed, a percentage success rate, a compression ratio, or a network transaction queue. ### Claim 9 A system for Intelligent Personal Assistant (IPA) applications, comprising: one or more non-transitory memory devices; and one or more hardware processors configured to execute instructions from the one or more non-transitory memory devices to cause the system to perform operations comprising: receiving a request for a performance of a first computational skill using a network comprising a plurality of IPA nodes, wherein each of the plurality of IPA nodes are configured to execute at least one IPA application for at least a portion of computational skills available on the network, and wherein the network further comprises an artificial intelligence (AI) computational environment that autonomously selects one or more of the plurality of IPA nodes when performing each of the computational skills based on a efficiency processing benchmark; determining benchmark scores and node availability for each of the plurality of IPA nodes; determining a computational efficiency of each of the plurality of IPA nodes in performing the first computational skill using the at least one IPA application executing on the one of more of the plurality of IPA nodes; performing a benchmarking analysis of the first computational skill on each of the plurality of IPA nodes based at least one the computational efficiency, wherein the benchmarking analysis comprises at least one computational rating required for a performance of the first computational skill using the network; selecting a first IPA application and a second IPA application based on the benchmark scores, the node availability, and the benchmarking analysis; establishing a smart contract between the first IPA application and the second IPA application for performing the first computational skill at a set processing rate; and performing, by the first IPA application and the second IPA application, the first computational skill using at least one of the plurality of IPA nodes based on the smart contract. ### Claim 10 (depends on 9) The system of claim 9, wherein the selecting the first IPA application and the second IPA application comprises: selecting, by the AI computational environment, a first node of the plurality of IPA nodes for the first IPA application and a second node of the plurality of IPA nodes for the second IPA application based on the benchmark scores, the node availability, and the benchmarking analysis, wherein the selecting the first node and the second nodes is based on a efficiency type of processing of the first computational skill selected by the AI computational environment for the efficiency processing benchmark. ### Claim 11 (depends on 10) The system of claim 10, wherein the operations further comprise: learning, by the AI computational environment, at least one IPA task improvement for at least one of the first node or the second node based performing the first computational skill; updating the at least one of the first node or the second node based on the learning; and updating a skills registry based on the updated at least one of the first node or the second node. ### Claim 12 (depends on 11) The system of claim 11, wherein the learning the at least one IPA task improvement comprises determining to outsource at least a portion of the first computational skill between the first node and the second node based on one of a lowest cost provider, a fastest service provider, a most reliable provider or a highest quality provider. ### Claim 13 (depends on 9) The system of claim 9, wherein the operations further comprise: recording the performing of the first computational skill, by at least one of the first IPA application or the second IPA application, at a determined price in a transaction ledger accessible by the plurality of IPA nodes in the network. ### Claim 14 (depends on 9) The system of claim 9, wherein the selecting the first IPA application and the second IPA application comprises: determining, by the AI computational environment, that the second IPA application provides the efficiency processing benchmark for a portion of the first computational skill; selecting, by the AI computational environment, the first IPA application for another portion of the first computational skill; and selecting, by the AI computational environment, the second IPA application to outsource the portion of the first computational skill at a determined price for the network. ### Claim 15 (depends on 14) The system of claim 14, wherein the determined price comprises one of an agreed price between a first node corresponding to the first IPA application and a second node corresponding to the second IPA application, a set price by the second node, or a historically determined price associated with the portion of the first computational skill performed by at least one of the second node or one or more other nodes of the plurality of IPA nodes. ### Claim 16 (depends on 9) The system of claim 9, wherein the benchmark scores for each of the plurality of IPA nodes comprises at least one of a hardware rating, a user rating, a throughput speed, a percentage success rate, a compression ratio, or a network transaction queue. ### Claim 17 A non-transitory machine-readable medium, on which are stored instructions for Intelligent Personal Assistant (IPA) applications, comprising instructions that when executed cause a machine to perform operations comprising: receiving a request for a performance of a first computational skill using a skills exchange network comprising a plurality of IPA nodes, wherein each of the plurality of IPA nodes are configured to execute at least one IPA application for at least a portion of computational skills available on the skills exchange network, and wherein the skills exchange network comprises an artificial intelligence (AI) computational environment that autonomously selects one or more of the plurality of IPA nodes when performing each of the computational skills based on a efficiency processing benchmark; determining benchmark scores and node availability for each of the plurality of IPA nodes; determining a computational efficiency of each of the plurality of IPA nodes in performing the first computational skill using the at least one IPA application executing on the one of more of the plurality of IPA nodes; performing a benchmarking analysis of the first computational skill on each of the plurality of IPA nodes based at least one the computational efficiency, wherein the benchmarking analysis comprises at least one computational rating required for a performance of the first computational skill using the skills exchange network; selecting a first IPA application and a second IPA application based on the benchmark scores, the node availability, and the benchmarking analysis; establishing a smart contract between the first IPA application and the second IPA application for performing the first computational skill at a set processing rate; and performing, by the first IPA application and the second IPA application, the first computational skill using at least one of the plurality of IPA nodes based on the smart contract. ### Claim 18 (depends on 17) The non-transitory machine-readable medium of claim 17, wherein the selecting the first IPA application and the second IPA application comprises: selecting, by the AI computational environment, a first node of the plurality of IPA nodes for the first IPA application and a second node of the plurality of IPA nodes for the second IPA application based on the benchmark scores, the node availability, and the benchmarking analysis, wherein the selecting the first node and the second nodes is based on a efficiency type of processing of the first computational skill selected by the AI computational environment for the efficiency processing benchmark. ### Claim 19 (depends on 18) The non-transitory machine-readable medium of claim 18, wherein the operations further comprise: learning, by the AI computational environment, at least one IPA task improvement for at least one of the first node or the second node based performing the first computational skill; updating the at least one of the first node or the second node based on the learning; and updating a skills registry based on the updated at least one of the first node or the second node. ### Claim 20 (depends on 17) The non-transitory machine-readable medium of claim 17, wherein the selecting the first IPA application and the second IPA application comprises: determining, by the AI computational environment, that the second IPA application provides the efficiency processing benchmark for a portion of the first computational skill; selecting, by the AI computational environment, the first IPA application for another portion of the first computational skill; and selecting, by the AI computational environment, the second IPA application to outsource the portion of the first computational skill at a determined price for the skills exchange network.