# US 12,762,144 B2 · Multi-dimensional hierarchical data structures for analysis and comprehension using large language models > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,762,144 B2 - Document ID: US12762144B2 - Status: Granted - Kind: B2 - Application number: 19/015,894 - Filed: 2025-01-10 - Published: 2026-07-16 - Granted: 2026-10-13 - Earliest claimed: 2025-01-10 - Assignees: Sap SE - Applicants: Sap SE - Inventors: Harsh Rao Dhanyamraju; Wei Ming Neo; Rajesh Vellore Arumugam - Web page: https://patentgrep.com/patent/US12762144B2 ## CPC - G06F 16/258: {Data format conversion from or to a database} - G06F 16/2246: {Trees, e.g. B+trees} - G06F 16/2264: {Multidimensional index structures} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Methods, systems, and computer-readable storage media for retrieving data from a data store, the data being in a storage format and including multiple dimensions in a hierarchy, at least one dimension having a sub-hierarchy, converting the data from the storage format to an analytics format including a set of nodes, each node representing a dimension of the multiple dimensions, a set of hierarchy characters, one or more hierarchy characters separating two or more nodes to represent a hierarchical relationship between nodes, and an attribute delimiter to separate attribute values of a node, generating a prompt that references the data in the analytics format, transmitting the prompt to a LLM system, and receiving a response to the prompt from the LLM system. ## Claims ### Claim 1 A computer-implemented method for providing analytics over multi-dimensional, hierarchical data using large language models (LLMs), the method being executed by one or more processors and comprising: retrieving data from a data store, the data being in a storage format comprising multiple rows, the data comprising multiple dimensions in a hierarchy, at least one dimension having a sub-hierarchy, each dimension recorded in a row of the multiple rows; converting the data from the storage format to an analytics format by processing the data through preprocessing to convert the storage format to an intermediate data structure, a forward pass to traverse the intermediate data structure row-by-row and provide an intermediate text dataset, and a backwards pass to provide the analytics format from the intermediate text dataset, the analytics format comprising a set of nodes, each node representing a row of a dimension of the multiple dimensions, a set of hierarchy characters, one or more hierarchy characters separating two or more nodes to represent a hierarchical relationship between nodes as a parent node and child node relationship, and an attribute delimiter to separate attribute values of a node; generating a prompt that references the data in the analytics format; transmitting the prompt to a LLM system; and receiving a response to the prompt from the LLM system. ### Claim 2 (depends on 1) The method of claim 1, wherein the data is retrieved from the data store in response to determining that a review booklet is open concurrent with receiving a query from a user. ### Claim 3 (depends on 1) The method of claim 1, wherein at least one dimension of the multiple dimensions comprises a sub-hierarchy represented using a sub-set of hierarchy characters of the set of hierarchy characters. ### Claim 4 (depends on 1) The method of claim 1, wherein the prompt comprises a query submitted by a user. ### Claim 5 (depends on 1) The method of claim 1, wherein the prompt comprises a chain-of-thought (CoT) prompt. ### Claim 6 (depends on 1) The method of claim 1, wherein the set of hierarchy characters comprises —, ├, ∈, and |. ### Claim 7 (depends on 1) The method of claim 1, wherein the attribute delimiter comprises a semi-colon. ### Claim 8 A non-transitory computer-readable storage medium coupled to one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations for providing analytics over multi-dimensional, hierarchical data using large language models (LLMs), the operations comprising: retrieving data from a data store, the data being in a storage format comprising multiple rows, the data comprising multiple dimensions in a hierarchy, at least one dimension having a sub-hierarchy, each dimension recorded in a row of the multiple rows; converting the data from the storage format to an analytics format by processing the data through preprocessing to convert the storage format to an intermediate data structure, a forward pass to traverse the intermediate data structure row-by-row and provide an intermediate text dataset, and a backwards pass to provide the analytics format from the intermediate text dataset, the analytics format comprising a set of nodes, each node representing a row of a dimension of the multiple dimensions, a set of hierarchy characters, one or more hierarchy characters separating two or more nodes to represent a hierarchical relationship between nodes as a parent node and child node relationship, and an attribute delimiter to separate attribute values of a node; generating a prompt that references the data in the analytics format; transmitting the prompt to a LLM system; and receiving a response to the prompt from the LLM system. ### Claim 9 (depends on 8) The non-transitory computer-readable storage medium of claim 8, wherein the data is retrieved from the data store in response to determining that a review booklet is open concurrent with receiving a query from a user. ### Claim 10 (depends on 8) The non-transitory computer-readable storage medium of claim 8, wherein at least one dimension of the multiple dimensions comprises a sub-hierarchy represented using a sub-set of hierarchy characters of the set of hierarchy characters. ### Claim 11 (depends on 8) The non-transitory computer-readable storage medium of claim 8, wherein the prompt comprises a query submitted by a user. ### Claim 12 (depends on 8) The non-transitory computer-readable storage medium of claim 8, wherein the prompt comprises a chain-of-thought (CoT) prompt. ### Claim 13 (depends on 8) The non-transitory computer-readable storage medium of claim 8, wherein the set of hierarchy characters comprises —, ├, ∈, and |. ### Claim 14 (depends on 8) The non-transitory computer-readable storage medium of claim 8, wherein the attribute delimiter comprises a semi-colon. ### Claim 15 A system, comprising: a computing device; and a computer-readable storage device coupled to the computing device and having instructions stored thereon which, when executed by the computing device, cause the computing device to perform operations for providing analytics over multi-dimensional, hierarchical data using large language models (LLMs), the operations comprising: retrieving data from a data store, the data being in a storage format comprising multiple rows, the data comprising multiple dimensions in a hierarchy, at least one dimension having a sub-hierarchy, each dimension recorded in a row of the multiple rows; converting the data from the storage format to an analytics format by processing the data through preprocessing to convert the storage format to an intermediate data structure, a forward pass to traverse the intermediate data structure row-by-row and provide an intermediate text dataset, and a backwards pass to provide the analytics format from the intermediate text dataset, the analytics format comprising a set of nodes, each node representing a row of a dimension of the multiple dimensions, a set of hierarchy characters, one or more hierarchy characters separating two or more nodes to represent a hierarchical relationship between nodes as a parent node and child node relationship, and an attribute delimiter to separate attribute values of a node; generating a prompt that references the data in the analytics format; transmitting the prompt to a LLM system; and receiving a response to the prompt from the LLM system. ### Claim 16 (depends on 15) The system of claim 15, wherein the data is retrieved from the data store in response to determining that a review booklet is open concurrent with receiving a query from a user. ### Claim 17 (depends on 15) The system of claim 15, wherein at least one dimension of the multiple dimensions comprises a sub-hierarchy represented using a sub-set of hierarchy characters of the set of hierarchy characters. ### Claim 18 (depends on 15) The system of claim 15, wherein the prompt comprises a query submitted by a user. ### Claim 19 (depends on 15) The system of claim 15, wherein the prompt comprises a chain-of-thought (CoT) prompt. ### Claim 20 (depends on 15) The system of claim 15, wherein the set of hierarchy characters comprises —, ├, ∈, and |.