Detection of irregularity in food manufacturing by using conversion pattern

• US 8,635,179 B2
• Filed: 10/22/2010
• Issued: 01/21/2014
• Est. Priority Date: 10/22/2010
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Cao, Rong Zeng, Ding, Wei, He, Xiang Yang, Jiang, Shun, Lee, Juhnyoung, Li, Feng, Liu, Tie, Tian, Chun Hua, Wang, Feng Chun, Zhang, Hao
• Primary Examiner(s): Vincent, David
• Assistant Examiner(s): Sugent, James F
• Application Number:
  US12/910,315
• Publication Number:
  US 20120101972A1
• Time in Patent Office: 1,187 Days
• Field of Search: 706/47, 705/303, 700/95, 235/375
• US Class Current: 706/47
• CPC Class Codes: A23P 10/00 Shaping or working of foodstuffs characterised by the products
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders
• CPC Class Codes: G06Q 50/04 Manufacturing
• CPC Class Codes: Y02P 90/30 Computing systems specially adapted for manufacturing

Abstract

Irregular food manufacturing detection by using conversion pattern in one aspect generates one or more rules associated with amount of resources used to manufacture a food product, collects data associated with a selected manufacturing process of the food product at a selected manufacturer and determines whether the collected data complies with the generated one or more rules. Irregularity may be identified if the collected data does not comply with the generated one or more rules.

Claims

1. A method for detecting irregularity in food manufacturing, comprising:

receiving information associated with resources used in producing food, wherein the information includes a ratio of quantity of resources used to produce an intermediary product of the end product and is obtained using resource consumption data and production data for the food product over a predetermined time span;

generating, using the received information, one or more rules associated with resources used to manufacture a food product, the one or more rules comprising one or more conversion rules that specify amount of resource needed to be consumed for an amount of the food product to be manufactured, the one or more rules generated at least based on historical data associated with resources consumed in manufacturing the food product;

collecting data associated with a selected manufacturing process of the food product at a selected manufacturer, wherein the collected data from the selected manufacturer includes traceable data indicating goods and services provided by the selected manufacturer used to produce the food product;

determining whether the collected data complies with the generated one or more rules by comparing the collected data with the one or more conversion rules to determine whether the collected data satisfies the one or more conversion rules; and

identifying an irregular manufacturing process if the collected data does not comply with the generated one or more rules,

wherein it is determined that the collected data does not comply if the collected data shows a variance above an acceptable range in an amount of resources used in the selected manufacturing process of the food product from the amount of resource specified in the one or more conversion rules,

wherein the variance is used to calculate normal distributions for production rate and bill of material, wherein the production rate indicates the amount of product manufactured and the bill of material is a data model that indicates a relationship between source units and products, including what is produced with what and how many source units are required to produce the product.

2. The method of claim 1, wherein the information includes a ratio of quantity of resources used to produce a per unit item of the food product.

3. The method of claim 1, wherein the resources include materials, utilities, and labor used to produce the food product.

4. The method of claim 1, wherein a processor automatically performs the step of determining and identifying by comparing the collected data with the one or more defined rules.

5. The method of claim 1, further including generating a report associated with the collected data and whether the collected data complies with the generated one or more rules.

6. The method of claim 1, further including:

generating a normal distribution function associated with benchmark data;

comparing the collected data with the normal distribution function to determine whether the collected data is in compliance.

7. A non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform a method of detecting irregularity in food manufacturing, comprising:

receiving information associated with resources used in producing food, wherein the information includes a ratio of quantify of resources used to produce an intermediary product of the end product and is obtained using resource consumption data and production data for the food product over a predetermined time span;

generating, using the received information, one or more rules associated with resources used to manufacture a food product, the one or more rules comprising one or more conversion rules that specify amount of one or more of the resources needed to be consumed for an amount of the food product to be manufactured, the one or more rules generated at least based on historical data associated with resources consumed in manufacturing the food product;

collecting data associated with a selected manufacturing process of the food product at a selected manufacturer, wherein the collected data from the selected manufacturer includes traceable data indicating goods and services provided by the selected manufacturer used to produce the food product;

determining whether the collected data complies with the generated one or more rules by comparing the collected data with the one or more conversion rules to determine whether the collected data satisfies the one or more conversion rules; and

identifying an irregular manufacturing process if the collected data does not comply with the generated one or more rules,

wherein it is determined that the collected data does not comply if the collected data shows a variance above an acceptable range in an amount of resources used in the selected manufacturing process of the food product from the amount of resource specified in the one or more conversion rules,

wherein the variance is used to calculate normal distributions for production rate and bill of material, wherein the production rate indicates the amount of product manufactured and the bill of material is a data model that indicates a relationship between source units and products, including what is produced with what and how many source units are required to produce the product.

8. The program storage device of claim 7, wherein the information includes a ratio of quantity of resources used to produce a per unit item of the food product.

9. The program storage device of claim 7, wherein the resources include materials, utilities, and labor used to produce the food product.

10. The program storage device of claim 7, wherein a processor automatically performs the step of determining and identifying by comparing the collected data with the one or more defined rules.

11. The program storage device of claim 7, further including generating a report associated with the collected data and whether the collected data complies with the generated one or more rules.

12. The program storage device of claim 7, further including:

generating a normal distribution function associated with benchmark data;

comparing the collected data with the normal distribution function to determine whether the collected data is in compliance.

13. A system for detecting irregularity in food manufacturing, comprising:

a processor;

a rule generating module operable to generate one or more rules associated with amount of resources used to manufacture a food product, the one or more rules comprising one or more conversion rules that specify amount of resource needed to be consumed for an amount of the food product to be manufactured, the one or more rules generated at least based on historical data associated with resources consumed in manufacturing the food product, wherein the amount of resources includes a ratio of quantity of resources used to produce a per unit item of the end product and is obtained using resource consumption data and production data for the food product over a predetermined time span;

a data collection module operable to collect data associated with a selected manufacturing process of the food product at a selected manufacturer, wherein the collected data from the selected manufacturer includes traceable data indicating goods and services provided by the selected manufacturer used to produce the food product; and

a compliance checking module operable to determine whether the collected data complies with the generated one or more rules by comparing the collected data with the one or more conversion rules to determine whether the collected data satisfies the one or more conversion rules, and identify irregular manufacturing process if the collected data does not comply with the generated one or more rule,

wherein it is determined that the collected data does not comply if the collected data shows a variance above an acceptable range in an amount of resources used in the selected manufacturing process of the food product from the amount of resource specified in the one or more conversion rules,

wherein the variance is used to calculate normal distributions for production rate and bill of material, wherein the production rate indicates the amount of product manufactured and the bill of material is a data model that indicates a relationship between source units and products, including what is produced with what and how many source units are required to produce the product.