9 Integration with Oracle Digital Assistant
LPO is integrated with a voice assistant such as Oracle Digital Assistant to handle complex workflow and business process questions. The functionality integrates voice assistants, machine learning techniques such as NLP, and a pricing solution such as LPO. This reduces the workflow for a typical user of such software and helps in handling complex business process use cases. For example, buyers or managers who manage price recommendations for retail apparel might be interested in use cases such as:
-
Chain/country-level view. For example, a user can ask to see the performance of a department or all departments at the country level.
Exception management. For example, a user can ask to see the locations for a department where the margin improvements are lower than 5%.
-
Approval process. A few use cases are possible. A user can approve all batch runs or select specific runs for approval. For example, a user can reject the price recommendations for runs that have a discount higher than 40% or approve all batch runs that show an improvement of 5% for revenue.
-
Recalculate the key performance metrics. For example, a user can reject recommendations that have a discount higher than 70% and recalculate the metrics.
-
Q&A. This integration helps in answering a user's most frequently asked questions. For example, a user can ask about promotions and the Q&A tab brings up the relevant questions and answers related to the term promotions.
A user can enable the Oracle Digital Assistant by clicking the microphone symbol. A user can say a particular question (utterance) to a voice-enabled device, and the utterance is converted into text and mapped to an intent/entity using existing Natural Language Processing algorithms such as Oracle Intelligent Bots. Once the intent/entity has been identified, it is sent to a pricing solution such as LPO, which then performs the appropriate processes and returns information.
Some examples of the conversation for the above use cases are provided below. The user utterance is prefixed with User and the response from ODA is prefixed with Bot.
Sample Conversation:
User: Give me optimal revenue for 310200_black across all price zones?
Bot: The optimal revenue for 310200_black across all price zones is $6,037,232.19. Explain Show SQL
User: Explain
Bot: The optimal revenue for 310200_black is $6,037,232.19, indicating a potential maximum earnings for this product. This value can serve as a benchmark for evaluating the product's current performance. To further optimize revenue, it may be beneficial to analyze pricing strategies across different zones and adjust them accordingly to maximize earnings. Additionally, monitoring sales trends and adjusting inventory levels can help to minimize losses and ensure the product is meeting its full revenue potential. Show SQL
User: Show SQL
Bot: Bot: Please give me a few moments to generate your query. Query Generated
User: What is the performance at loc 1 for 310190_blue?
Bot: The performance at loc 1 for 310190_blue is a revenue of $30,432,810.86, which is higher than the optimal revenue of $29,780,414.02. Explain Show SQL
User: Explain
Bot: The current revenue of $30,432,810.86 for 310190_blue is 1.8% higher than the optimal revenue of $29,780,414.02. This suggests that the product is performing better than expected. However, without historical data, it's difficult to determine if this is a trend or an anomaly. Nevertheless, the positive difference between current and optimal revenue indicates a strong performance at loc 1 for 310190_blue.
User: Give me optimal revenue for 310200_black for each price zone?
Bot: The optimal revenue for 310200_black varies across different price zones. The highest optimal revenue is $5,862,708.03 in price zone 24, followed by $78,640.64 in price zone 16, $52,362.44 in price zone 19, $25,502.90 in price zone 20, and $18,018.18 in price zone 22.
User: Can you give me from highest to lowest?
Bot: The optimal revenue from highest to lowest is $5,862,708.03 in price zone 24, $78,640.64 in price zone 16, $52,362.44 in price zone 19, $25,502.90 in price zone 20, and $18,018.18 in price zone 22.
User: Can you aggregate it over all price zones?
Bot: The aggregated optimal revenue across all price zones is $6,037,232.19.
User: Give me the number of promotions used for 627688040_blue
Bot: Please provide either price zone or location to proceed.
User: Price zone 24
Bot: The number of promotions used for 627688040_blue at price zone 24 is 10523.788. Explain Show SQL
User: Explain
Bot: The total promotions used for 627688040_blue at price zone 24 is 10523.788, indicating a significant promotional activity for this product at this price zone. This high number of promotions could be a strategic move to drive sales, clear inventory, or increase brand visibility. However, without prior data, it's difficult to determine if this is an optimal performance or if there's room for improvement. Further analysis on sales data and customer response to these promotions would provide more insights on the effectiveness of this strategy.
User: How about markdowns?
Bot: The total markdowns used is $17,188,948.53.
User: What departments are present in this division?
Bot: The departments present in this division are Women's Activewear, Women's Tops, Women's Bottoms, Beverages, Men's Activewear, Kitchen Appliances, and Men's Tops.
User: What is the optimal revenue for Beverages department?
Bot: The optimal revenue for the Beverages department is $5,349,576.20.
User: Give me the remaining inventory for item 310200_black in all price zones except ones starting with s and i?
Bot: The total remaining inventory for item 310200_black in all price zones except ones starting with s and i is 71091 units.
User: Give me the remaining inventory for item 310200_black for price zone 19?
Bot: The remaining inventory for item 310200_black in price zone 19 is 3682.