Automatic correlation of items and adaptation of item attributes using object recognition
The technology includes an example method for parsing data to determine corollary objects and adapt attributes of the corollary objects using the data. In some implementations, the method may include receiving one or more images, performing text recognition to determine recognized text in the one or more images, and determining data cells containing information associated with a first item. The method may then classify one or more of the determined data cells, and may identify key cells in the determined data cells based on the classification of the one or more determined data cells. Correlations between information contained in the key cells and a second item, the second item including an interchangeable item to the first item may be determined, and the method may adjust attributes associated with the second item based on defined parameters and the recognized text.
1. A computer-implemented method comprising:
receiving, by a computer, one or more images;
performing, by the computer, text recognition to determine recognized text in the one or more images;
determining, by the computer, data cells containing information associated with a first item;
classifying, by the computer, one or more of the determined data cells;
identifying, by the computer, key cells in the determined data cells based on the classification of the one or more determined data cells;
determining, by the computer, one or more first attributes of the first item based on information contained in the key cells;
determining, by the computer, a second item based on a correlation of a common attribute between the one or more first attributes of the first item and one or more second attributes of the second item, the second item including an interchangeable item to the first item; and
adjusting, by the computer, a certain attribute of the one or more second attributes associated with the second item based on the certain attribute being different from the one or more first attributes.
2. The computer-implemented method of claim 1 , further comprising:
receiving, by the computer, user input identifying a portion of the one or more images; and
performing, by the computer, the text recognition on the portion of the one or more images to determine the recognized text.
3. The computer-implemented method of claim 1 , wherein classifying the one or more of the determined data cells includes identifying a category of data in the one or more of the determined data cells based on a particular format, the particular format representing an expected layout of information in the one or more images.
4. The computer-implemented method of claim 1 , wherein classifying the one or more of the determined data cells includes identifying a category of data in the one or more of the determined data cells using a neural network trained using a plurality of images and classified data cells.
5. The computer-implemented method of claim 1 , wherein determining correlations between the information contained in the key cells and the second item includes identifying the second item based on the identified key cells.
6. The computer-implemented method of claim 5 , wherein identifying the second item based on the identified key cells includes cross-referencing the information contained in the key cells with information relating to the second item to identify the second item.
7. The computer-implemented method of claim 5 , wherein determining the second item based on the correlation of the common attribute includes determining a conversion factor representing a correlation of a first unit of measure of the first item and a second unit of measure of the second item.
8. The computer-implemented method of claim 7 , wherein adjusting the certain attribute of the one or more second attributes associated with the second item includes adjusting a quantity of the second item based on the conversion factor and a quantity of the first item.
9. The computer-implemented method of claim 8 , wherein adjusting the certain attribute of the one or more second attributes associated with the second item based on defined parameters and the recognized text includes adjusting a price of the second item based on the conversion factor and the quantity of the first item.
10. The computer-implemented method of claim 1 , wherein the one or more images includes multiple images, the multiple images including multiple invoices, each of the multiple invoices including at least one item.
11. A system comprising:
one or more processors; and
a non-transitory computer memory storing instructions that, when executed by the one or more processors, cause the system to:
receive one or more images;
perform text recognition to determine recognized text in the one or more images;
determine data cells containing information associated with a first item;
classify one or more of the determined data cells;
identify key cells in the determined data cells based on the classification of the one or more determined data cells;
determine one or more first attributes of the first item based on information contained in the key cells;
determine a second item based on a correlation of a common attribute between the one or more first attributes of the first item and one or more second attributes of the second item, the second item including an interchangeable item to the first item; and
adjust a certain attribute of the one or more second attributes associated with the second item based on the certain attribute being different from the one or more first attributes.
12. The system of claim 11 , wherein the instructions, when executed by the one or more processors, further cause the system to
receive user input identifying a portion of the one or more images, and
perform the text recognition on the portion of the one or more images to determine the recognized text.
13. The system of claim 11 , wherein classifying the one or more of the determined data cells includes identifying a category of data in the one or more of the determined data cells based on a particular format, the particular format representing an expected layout of information in the one or more images.
14. The system of claim 11 , wherein classifying the one or more of the determined data cells includes identifying a category of data in the one or more of the determined data cells using a neural network trained using a plurality of images and classified data cells.
15. The system of claim 11 , wherein determining correlations between the information contained in the key cells and the second item includes identifying the second item based on the identified key cells.
16. The system of claim 15 , wherein identifying the second item based on the identified key cells includes cross-referencing the information contained in the key cells with information relating to the second item to identify the second item.
17. The system of claim 15 , wherein determining the second item based on the correlation of the common attribute includes determining a conversion factor representing a correlation of a first unit of measure of the first item and a second unit of measure of the second item.
18. The system of claim 17 , wherein adjusting the certain attribute of the one or more second attributes associated with the second item includes adjusting a quantity of the second item based on the conversion factor and a quantity of the first item.
19. The system of claim 18 , wherein adjusting the certain attribute of the one or more second attributes associated with the second item based on defined parameters and the recognized text includes adjusting a price of the second item based on the conversion factor and the quantity of the first item.
20. The system of claim 11 , wherein the one or more images includes multiple images, the multiple images including multiple invoices, each of the multiple invoices including at least one item.