# US 10,769,386 B2 · Terminology proposal engine for determining target language equivalents > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,769,386 B2 - Document ID: US10769386B2 - Status: Granted - Kind: B2 - Application number: 15/831,395 - Filed: 2017-12-05 - Published: 2019-06-06 - Granted: 2020-09-08 - Earliest claimed: 2017-12-05 - Assignees: Sap SE - Applicants: Sap SE - Inventors: Michail Vasiltschenko; Benjamin Schork; Mark Childress; Annika Berger; Yvonne Miklosch; Thomas Alcantara Kliche; Hanne Smaadahl; Ying Zou - Web page: https://patentgrep.com/patent/US10769386B2 ## CPC - G06F 40/157: using dictionaries or tables - G06F 16/3337: {Translation of the query language, e.g. Chinese to English} - G06F 16/338: Presentation of query results - G06F 40/131: Fragmentation of text files, e.g. creating reusable text-blocks; Linking to fragments, e.g. using XInclude; Namespaces - G06F 40/237: Lexical tools - G06F 40/242: Dictionaries - G06F 40/247: Thesauruses; Synonyms - G06F 40/263: Language identification - G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) - G06F 40/44: Statistical methods, e.g. probability models - G06F 40/47: Machine-assisted translation, e.g. using translation memory - G06F 40/51: Translation evaluation - G06F 40/58: Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract An input terminology is received in a source language to determine a target language proposal. In a proposal engine when a configuration profile is available the following steps are performed. A set of target language equivalents are determined by applying a user-defined set of approaches to the input terminology. Statistics is computed corresponding to the set of target language equivalents. A target language proposal from the set of target language equivalents is determined based on the computed statistics. The target language proposal along with the computed statistics is displayed in a graphical user interface. ## Claims ### Claim 1 A non-transitory computer-readable medium to store instructions, which when executed by a computer, cause the computer to perform operations comprising: receive, from a user, an input terminology in a source language to determine a target language proposal; in a proposal engine, when a configuration profile corresponding to the user is available: determine a set of target language equivalents by applying a user-defined set of approaches to the input terminology, wherein the user-defined set of approaches are comprised in the configuration profile; compute statistics corresponding to the set of target language equivalents, wherein the statistics are computed based on a set of weights that are comprised in the configuration profile and are associated with the user-defined set of approaches, wherein the user pre-configures, in the configuration profile corresponding to the user, a corresponding weight for each one of the user-defined set of approaches; based on the computed statistics, determine the target language proposal from among the set of target language equivalents; and display the target language proposal along with at least a part of the computed statistics in a graphical user interface. ### Claim 2 (depends on 1) The non-transitory computer-readable medium of claim 1, further comprises instructions which when executed by the computer further cause the computer to: in a proposal engine, when the configuration profile is not available: determine a set of target language equivalents by applying a pre-defined set of approaches to the input terminology; compute statistics corresponding to the set of target language equivalents; based on the computed statistics, determine the target language proposal from among the set of target language equivalents; and display the target language proposal along with the computed statistics in a graphical user interface. ### Claim 3 (depends on 1) The non-transitory computer-readable medium of claim 1, further comprises instructions which when executed by the computer further cause the computer to: upon determining that a term data is available, use multi-lingual term data to verify the term data on a multi-channel approach; and upon determining that the term data is not available, use linguistic feature to determine the target language proposal. ### Claim 4 (depends on 1) The non-transitory computer-readable medium of claim 1, wherein the user-defined set of approaches to determine the target language proposal include using calque, and using a reference language as an intermediate language. ### Claim 5 (depends on 1) The non-transitory computer-readable medium of claim 1, further comprises instructions which when executed by the computer further cause the computer to: record a user action corresponding to the displayed target language proposal; recognize a pattern corresponding to the user action; and implicitly modify the configuration profile corresponding to the user based on the recognized pattern. ### Claim 6 (depends on 1) The non-transitory computer-readable medium of claim 1, further comprises instructions which when executed by the computer further cause the computer to: receive configuration parameters in a configuration user interface corresponding to the configuration profile; and save the configuration profile in a configuration and statistical database. ### Claim 7 (depends on 6) The non-transitory computer-readable medium of claim 6, further comprises instructions which when executed by the computer further cause the computer to: determine the target language proposal based on a plurality of configuration profiles, wherein a plurality of configuration parameters is defined in a configuration user interface corresponding to the configuration profiles. ### Claim 8 A computer-implemented method of determining target language equivalents, the method comprising: receiving, from a user, an input terminology in a source language to determine a target language proposal; in a proposal engine, when a configuration profile corresponding to the user available: determining a set of target language equivalents by applying a user-defined set of approaches to the input terminology, wherein the user-defined set of approaches are comprised in the configuration profile; computing statistics corresponding to the set of target language equivalents, wherein the statistics are computed based on a set of weights that are comprised in the configuration profile and are associated with the user-defined set of approaches, wherein the user pre-configures, in the configuration profile corresponding to the user, a corresponding weight for each one of the user-defined set of approaches; based on the computed statistics, determining the target language proposal from among the set of target language equivalents; and displaying the target language proposal along with at least a part of the computed statistics in a graphical user interface. ### Claim 9 (depends on 8) The method of claim 8, further comprising: in a proposal engine, when the configuration profile is not available: determining a set of target language equivalents by applying a set of pre-defined approaches to the input terminology; computing statistics corresponding to the set of target language equivalents; based on the computed statistics, determining the target language proposal from the set of target language equivalents; and displaying the target language proposal along with the computed statistics in a graphical user interface. ### Claim 10 (depends on 8) The method of claim 8, further comprising: upon determining that a term data is available, use multi-lingual term data to verifying the term data on a multi-channel approach; and upon determining that the term data is not available, using linguistic feature to determine the target language proposal. ### Claim 11 (depends on 8) The method of claim 8, wherein the user-defined set of approaches to determine the target language proposal include using calque, and using a reference language as an intermediate language. ### Claim 12 (depends on 8) The method of claim 8, further comprising: recording a user action corresponding to the displayed target language proposal; recognize a pattern corresponding to the user action; and implicitly modifying the configuration profile corresponding to the user based on the recognized pattern. ### Claim 13 (depends on 8) The method of claim 8, further comprising: receiving configuration parameters in a configuration screen corresponding to the configuration profile; and saving the configuration profile in a configuration and statistics database. ### Claim 14 (depends on 13) The method of claim 13, further comprising: determining the target language proposal based on a plurality of configuration profiles, wherein a plurality of configuration parameters is defined in a configuration user interface corresponding to the configuration profiles. ### Claim 15 A computer system for determining target language equivalents, comprising: a computer memory to store program code; and a processor to execute the program code to: receive, from a user, an input terminology in a source language to determine a target language proposal; in a proposal engine, when a configuration profile corresponding to the user is available: determine a set of target language equivalents by applying a user-defined set of approaches to the input terminology, wherein the user-defined set of approaches are comprised in the configuration profile; compute statistics corresponding to the set of target language equivalents, wherein the statistics are computed based on a set of weights that are comprised in the configuration profile and are associated with the user-defined set of approaches, wherein the user pre-configures, in the configuration profile corresponding to the user, a corresponding weight for each one of the user-defined set of approaches; based on the computed statistics, determine the target language proposal from among the set of target language equivalents; display the target language proposal along with at least a part of the computed statistics in a graphical user interface; receive an acceptance or a rejection of the target language proposal; and based on the acceptance or the rejection of the target language proposal, increase, in the configuration profile, at least a first weight of the set of weights and decrease, in the configuration profile, at least a second weight of the set of weights. ### Claim 16 (depends on 15) The system of claim 15, wherein the processor further executes the program code to: upon determining that configuration data is not available; in a proposal engine: determine a set of target language equivalents by applying a pre-defined set of approaches to the input terminology; compute statistics corresponding to the set of target language equivalents; based on the computed statistics, determine a target language proposal from among the set of target language equivalents; and display the target language proposal along with the computed statistics in a graphical user interface. ### Claim 17 (depends on 15) The system of claim 15, wherein the processor further executes the program code to: upon determining that a term data is available, use multi-lingual term data to verify the term data on a multi-channel approach; and upon determining that the term data is not available, use linguistic feature to determine the target language proposal. ### Claim 18 (depends on 15) The system of claim 15, wherein the user-defined set of approaches to determine the target language proposal include using calque, and using a reference language as an intermediate language. ### Claim 19 (depends on 15) The system of claim 15, wherein the processor further executes the program code to: record a user action corresponding to the displayed target language proposal; recognize a pattern corresponding to the user action; and implicitly modify the configuration profile corresponding to the user based on the recognized pattern. ### Claim 20 (depends on 15) The system of claim 15, wherein the processor further executes the program code to: receive configuration parameters in a configuration user interface corresponding to the configuration profile; and save the configuration profile in a configuration and statistical database.