IPC분류정보
국가/구분 |
United States(US) Patent
등록
|
국제특허분류(IPC7판) |
|
출원번호 |
US-0617437
(2006-12-28)
|
등록번호 |
US-8527324
(2013-09-03)
|
발명자
/ 주소 |
|
출원인 / 주소 |
- Oracle OTC Subsidiary LLC
|
대리인 / 주소 |
Kilpatrick Townsend & Stockton LLP
|
인용정보 |
피인용 횟수 :
5 인용 특허 :
30 |
초록
▼
A sales automation system and method, namely a system and method for scoring sales representative performance and forecasting future sales representative performance. These scoring and forecasting techniques can apply to a sales representative monitoring his own performance, comparing himself to oth
A sales automation system and method, namely a system and method for scoring sales representative performance and forecasting future sales representative performance. These scoring and forecasting techniques can apply to a sales representative monitoring his own performance, comparing himself to others within the organization (or even between organizations using methods described in application), contemplating which job duties are falling behind and which are ahead of schedule, and numerous other related activities. Similarly, with the sales representative providing a full set of performance data, the system is in a position to aid a sales manager identify which sales representatives are behind others and why, as well as help with resource planning should requirements, such as quotas or staffing, change.
대표청구항
▼
1. A computer readable storage medium having stored thereon executable program code for a sale automation method, where when the program code is executed by a processor is operable to perform said method comprising: providing a central repository of machine learned and top performer sales data profi
1. A computer readable storage medium having stored thereon executable program code for a sale automation method, where when the program code is executed by a processor is operable to perform said method comprising: providing a central repository of machine learned and top performer sales data profiles and a repository of raw sales data;extracting raw sales data from the repository of raw sale data;extracting machine learned and top performer sales data profiles from the central repository;machine learning central sales data patterns based on a forecasting formulation of raw historical sales models, the forecasting of raw historical sales models based on raw sales data, wherein machine learning central sales data patterns comprises calculating a revenue goal attainment for a sales person during a sales period, classifying performance of the sales person based on the calculated revenue goal attainment, calculating a revenue variance for the sales person during the sales period, calculating a difference between the extracted learned sales pipeline models and sales transaction data for the sales person during the sales period, calculating a difference between an idealized model and the sales transaction data for the sales person during the sales period, and repeating said machine learning central sales data patterns for each sales period and for each sales person;machine learning new sale data profiles based on a formulation of learned sales models, the formulation of learned sales models based on machine learned and top performer data profiles, wherein machine learning new sales data profiles comprises selecting a random sales person, comparing transaction data for the random sales person to learned sales pipeline models and the idealized model, reinforcing the idealized model when the transaction data for the random sales person fits the idealized model, and reinforcing the learned sales pipeline models when the transaction data for the random sales person fits the learned sales pipeline models, and repeating said machine learning new sales data profiles for each learning algorithm and each time step;storing the new sales data profiles and central sales data patterns to the central repository; andscoring performance of central sales data patterns based on the machine learned new sales data profiles. 2. The computer readable storage medium as recited in claim 1 wherein said method further comprises: extracting heuristics from the central repository; andlearning the new sales data profile and central sales data patterns based on the extracted heuristics. 3. The computer readable storage medium as recited in claim 2 where scoring performance comprises: assigning a quality score based on comparative grading of new sales data profiles relative to machine learned and top performer data profiles; andassigning an absolute grading relative to new sales data profiles based on ideal sales data. 4. The computer readable storage medium as recited in claim 1 wherein the learning step is performed using one of a machine learning approach, a reinforcement learning approach, a fuzzy logic approach, or a M/M/s queuing network approach. 5. The computer readable storage medium as recited in claim 1, wherein extracting raw sales data and machine learned and top performer sales data profiles comprises: extracting revenue goals for sales period;extracting learned revenue profiles for the sales period;extracting idealized revenue profiles for the sales period;extracting learned pipeline analysis data;extracting learned sales pipeline models for a sales strategy;querying sales transaction data for the sales period; andextracting a seasonality model for the sales period. 6. The computer readable storage medium as recited in claim 5, further comprising: using a smoothing method on the extracted data;excluding erroneous or biased data points from the smoothed extracted data;classifying a quality score for each sales transaction based on a quality heuristic; andaccumulating data and scores to a sales person subject of each transaction. 7. A method for sales automation comprising: providing a central repository of machine learned and top performer sales data profiles and a repository of raw sales data;extracting raw sales data from the repository of raw sale data;extracting machine learned and top performer sales data profiles from the central repository;machine learning, by a processor, central sales data patterns based on a forecasting formulation of raw historical sales models, the forecasting of raw historical sales models based on raw sales data, wherein machine learning central sales data patterns comprises calculating a revenue goal attainment for a sales person during a sales period, classifying performance of the sales person based on the calculated revenue goal attainment, calculating a revenue variance for the sales person during the sales period, calculating a difference between the extracted learned sales pipeline models and sales transaction data for the sales person during the sales period, calculating a difference between an idealized model and the sales transaction data for the sales person during the sales period, and repeating said machine learning central sales data patterns for each sales period and for each sales person;machine learning new sale data profiles based on a formulation of learned sales models, the formulation of learned sales models based on machine learned and top performer data profiles, wherein machine learning new sales data profiles comprises selecting a random sales person, comparing transaction data for the random sales person to learned sales pipeline models and the idealized model, reinforcing the idealized model when the transaction data for the random sales person fits the idealized model, and reinforcing the learned sales pipeline models when the transaction data for the random sales person fits the learned sales pipeline models, and repeating said machine learning new sales data profiles for each learning algorithm and each time step;storing the new sales data profiles and central sales data patterns to the central repository; andscoring performance of central sales data patterns based on the machine learned new sales data profiles. 8. The method as recited in claim 7 wherein said method further comprises: extracting heuristics from the central repository; andlearning the new sales data profile and central sales data patterns based on the extracted heuristics. 9. The method as recited in claim 8 where scoring performance comprises: assigning a quality score based on comparative grading of new sales data profiles relative to machine learned and top performer data profiles; andassigning an absolute grading relative to new sales data profiles based on ideal sales data. 10. The method as recited in claim 7 wherein the learning step is performed using one of a machine learning approach, a reinforcement learning approach, a fuzzy logic approach, or a M/M/s queuing network approach. 11. The method as recited in claim 7, wherein extracting raw sales data and machine learned and top performer sales data profiles comprises: extracting revenue goals for sales period;extracting learned revenue profiles for the sales period;extracting idealized revenue profiles for the sales period;extracting learned pipeline analysis data;extracting learned sales pipeline models for a sales strategy;querying sales transaction data for the sales period; andextracting a seasonality model for the sales period. 12. The method as recited in claim 11, further comprising: using a smoothing method on the extracted data;excluding erroneous or biased data points from the smoothed extracted data;classifying a quality score for each sales transaction based on a quality heuristic; andaccumulating data and scores to a sales person subject of each transaction. 13. A system comprising: a processor; anda memory coupled with and readable by the processor and storing a set of instructions which, when executed by the processor, cause the processor to automate sales by:providing a central repository of machine learned and top performer sales data profiles and a repository of raw sales data;extracting raw sales data from the repository of raw sale data;extracting machine learned and top performer sales data profiles from the central repository;machine learning central sales data patterns based on a forecasting formulation of raw historical sales models, the forecasting of raw historical sales models based on raw sales data, wherein machine learning central sales data patterns comprises calculating a revenue goal attainment for a sales person during a sales period, classifying performance of the sales person based on the calculated revenue goal attainment, calculating a revenue variance for the sales person during the sales period, calculating a difference between the extracted learned sales pipeline models and sales transaction data for the sales person during the sales period, calculating a difference between an idealized model and the sales transaction data for the sales person during the sales period, and repeating said machine learning central sales data patterns for each sales period and for each sales person;machine learning new sale data profiles based on a formulation of learned sales models, the formulation of learned sales models based on machine learned and top performer data profiles, wherein machine learning new sales data profiles comprises selecting a random sales person, comparing transaction data for the random sales person to learned sales pipeline models and the idealized model, reinforcing the idealized model when the transaction data for the random sales person fits the idealized model, and reinforcing the learned sales pipeline models when the transaction data for the random sales person fits the learned sales pipeline models, and repeating said machine learning new sales data profiles for each learning algorithm and each time step;storing the new sales data profiles and central sales data patterns to the central repository; andscoring performance of central sales data patterns based on the machine learned new sales data profiles. 14. The system as recited in claim 13 wherein said method further comprises: extracting heuristics from the central repository; andlearning the new sales data profile and central sales data patterns based on the extracted heuristics. 15. The system as recited in claim 14 where scoring performance comprises: assigning a quality score based on comparative grading of new sales data profiles relative to machine learned and top performer data profiles; andassigning an absolute grading relative to new sales data profiles based on ideal sales data. 16. The system as recited in claim 13 wherein the learning step is performed using one of a machine learning approach, a reinforcement learning approach, a fuzzy logic approach, or a M/M/s queuing network approach. 17. The system as recited in claim 13, wherein extracting raw sales data and machine learned and top performer sales data profiles comprises: extracting revenue goals for sales period;extracting learned revenue profiles for the sales period;extracting idealized revenue profiles for the sales period;extracting learned pipeline analysis data;extracting learned sales pipeline models for a sales strategy;querying sales transaction data for the sales period; andextracting a seasonality model for the sales period. 18. The system as recited in claim 17, further comprising: using a smoothing method on the extracted data;excluding erroneous or biased data points from the smoothed extracted data;classifying a quality score for each sales transaction based on a quality heuristic; andaccumulating data and scores to a sales person subject of each transaction.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.