Voice-Enabled Procurement System Query Parameterization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Business users face inefficiencies in procurement systems due to the need for familiarity with graphical user interfaces and data sources, making it cumbersome to retrieve specific information, especially in large organizations with numerous transactions and contracts across various categories and geographies.
Innovation Solution
A voice-enabled procurement system that converts voice queries to text, analyzes and parameterizes them using a command library, and matches them with knowledge models to provide quick and accurate system responses, allowing users to interact using natural language and reducing the complexity of navigating through the system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If users interact with traditional graphical user interfaces to retrieve procurement information, then the system can provide detailed and accurate information, but the operation becomes cumbersome and time-consuming due to the need for extensive knowledge of data elements and interface navigation
Solution Approach 1:
The patent replaces the mechanical interaction of clicking through graphical user interface elements with voice-based natural language processing. Users speak their information needs in natural language, and the system converts this speech to text, parses it to identify data elements and parameters, and retrieves the requested information without requiring users to navigate complex interface hierarchies.
Solution Approach 2:
The patent introduces a speech-to-text converter and natural language parser as intermediaries between the user and the procurement system database. This intermediary layer translates human speech into structured queries that the system can execute, eliminating the need for users to directly interact with complex interface elements while maintaining accurate information retrieval.
2Loss of information
If users manually filter and search through large volumes of procurement data across multiple categories and geographies, then comprehensive information can be obtained, but the process becomes lengthy and inefficient
Solution Approach 1:
The patent performs preliminary parsing and parameter identification on user speech input, extracting key data elements such as category, geography, time period, and supplier information before executing the query. This preliminary processing prepares the search parameters in advance, enabling the system to efficiently retrieve comprehensive procurement data without requiring users to manually apply multiple filters sequentially.
Solution Approach 2:
The patent transforms the user's natural language speech into structured query parameters that the procurement system can process. By converting speech to text and parsing it to identify specific data elements and parameters, the system changes the form of the input from unstructured voice to structured query parameters, enabling efficient and comprehensive data retrieval across multiple dimensions simultaneously.
3Measurement precision
If the system requires users to understand various data elements and interface structures, then accurate information can be retrieved, but the learning curve increases and user accessibility decreases
Solution Approach 1:
The patent replaces the need for users to understand complex interface mechanics and data element structures with natural language speech processing. Users can retrieve accurate procurement information by speaking their queries in everyday language, and the system's parser automatically identifies the underlying data elements and parameters, making the system accessible to users regardless of their technical knowledge.
Solution Approach 2:
The patent creates a universal interface that accepts natural language speech from any user, regardless of their familiarity with procurement system terminology or data structures. The speech-to-text converter and parser serve multiple functions: transcribing speech, identifying data elements, extracting parameters, and formulating queries, thereby making the system versatile and accessible to a broad user base while maintaining query accuracy.
Data Source
AI summary
A procurement system may include a first interface configured to receive a query from a user, a command module configured to parameterize the query, an intelligent search and match engine configured to compare the parameterized query with stored queries in a historical knowledge base and, in the event the parameterized query does not match a stored query within the historical knowledge base, search for a match in a plurality of knowledge models, and a response solution engine configured to receive a system response ID from the intelligent search and match engine, the response solution engine being configured to initiate a system action by interacting with sub-system and related databases to generate a system response.