System and method for matching patrons, servers, and restaurants within the food service industry
A system and method of combining table management software and customer experience skills by generating profiles of patrons, servers, and restaurants and using machine learning algorithms on those profiles to build more intimate relationships between patrons, food service establishments, and food service professionals. Trait matching provides optimized matchmaking between patrons and servers who share certain commonalities while also balancing the table management operations. Machine learning algorithms may be used to identify patterns of commonality that would not otherwise be recognized. This system allows patrons to choose servers at an establishment over a plurality of electronic devices by using the cluster analysis results. It provides servers more lateral work experience between participating restaurants, and restaurants more power to operate smoothly and build highly cohesive teams.
1. A system for matching patrons and servers at restaurants, comprising:
a computing device comprising a memory, a processor, and a data storage device;
a database residing in the data storage device, the database comprising profiles of patrons and servers and information about external factors;
a profile mapping and recommendation engine comprising a plurality of programming instructions stored in the memory, and operating on the processor, wherein the plurality of programming instructions, when operating on the processor, cause the computing device to:
retrieve a patron's profile from the database;
retrieve the server profiles from the database;
retrieve a plurality of external factors from the database;
map the patron's profile, the server profiles, and the plurality of external factors in a computational graph and use graph analysis algorithms to identify a plurality of servers who are most connected with the patron in the computational graph, wherein patrons are mapped to servers according to the following process:
patrons are initially mapped to servers according to a first clustering algorithm in which a first variance measures discrepancies between the patrons and servers by probability distribution and a second variance measures discrepancies between the patrons and servers by overall stationary distribution; and
for patrons matching two or more servers in the first clustering algorithm, those patrons are then mapped to servers according to a second clustering algorithm in which a shortest path between each patron and each server in the computational graph is calculated; and
match the patron to one of the servers in the plurality of servers based on the mapping and on the plurality of external factors.
2. The system of claim 1 , wherein the database further comprises restaurant profiles.
3. The system of claim 2 , wherein an individual server's profile and the restaurant profiles are mapped in a computational graph that is used to identify a plurality of restaurants who are most connected with the individual server.
4. The system of claim 3 , wherein the individual server is matched with a restaurant from the plurality of restaurants.
5. The system of claim 4 , wherein a portion of the information for the patron, server, or restaurant profiles is received from a social media account.
6. The system of claim 1 , wherein the patron selects a setting on the mobile device, wherein the setting is the purpose of the patron's visit, and the setting is stored in the patron's profile.
7. A method for matching patrons and servers at restaurants, comprising the steps of:
retrieving a patron's profile from a database;
retrieving the server profiles from the database; and
retrieving a plurality of external factors from the database;
mapping the patron's profile, the server profiles, and the plurality of external factors in a computational graph and use graph analysis algorithms to identify a plurality of servers who are most connected with the patron in the computational graph, wherein patrons are mapped to servers according to the following process:
patrons are initially mapped to servers according to a first clustering algorithm in which a first variance measures discrepancies between the patrons and servers by probability distribution and a second variance measures discrepancies between the patrons and servers by overall stationary distribution; and
for patrons matching two or more servers in the first clustering algorithm, those patrons are then mapped to servers according to a second clustering algorithm in which a shortest path between each patron and each server in the computational graph is calculated; and
matching the patron to one of the servers in the plurality of servers based on the mapping and on the plurality of external factors.
8. The method of claim 7 , wherein the database further comprises restaurant profiles.
9. The method of claim 8 , wherein an individual server's profile and the restaurant profiles are mapped in a computational graph that is used to identify a plurality of restaurants who are most connected with the individual server.
10. The method of claim 9 , wherein the individual server is matched with a restaurant from the plurality of restaurants.
11. The method of claim 10 , wherein a portion of the information for the patron, server, or restaurant profiles is received from a social media account.
12. The method of claim 7 , wherein the patron selects a setting on the mobile device, wherein the setting is the purpose of the patron's visit, and the setting is stored in the patron's profile.