Intelligent recommendations for program code

Patent metadata

Field	Value
Publication number	US-11520564-B2
Application number	US-202117153504-A
Country	US
Kind code	B2
Filing date	Jan 20, 2021
Priority date	Jan 20, 2021
Publication date	Dec 6, 2022
Grant date	Dec 6, 2022

Abstract

Embodiments are provided for intelligent recommendations for program code. In some embodiments, a system can include a processor that executes computer-executable components stored in memory. The computer-executable components can include an evaluation component that determines that first program code pertains to a defined category representing a defined cost to execute the first program code by a cloud computing service. The computer-executable components also can include a recommendation component that generates a recommendation for second program code that satisfies a similarity criterion with respect to the first program code. The second program code pertains to a category representing a cost to execute the second program code by the cloud computing service, where the cost is less than the defined cost.

First claim

What is claimed is:

1. A system, comprising:
a processor that executes computer-executable components stored in memory, the computer-executable components comprising,
an evaluation component that determines that first program code pertains to a defined category representing a defined cost to execute the first program code by a cloud computing service;
a recommendation component that generates a recommendation for second program code that satisfies a similarity criterion with respect to the first program code, the second program code pertaining to a category representing a cost to execute the second program code by the cloud computing service, wherein the cost is less than the defined cost; and
a report component that sends a notification about the second program code, wherein the notification comprises formatting information defining a text attribute to display the text at a display device.

2. The system of claim 1 , wherein the first program code comprises a first reusable segment of program code and the second program code comprises a second reusable segment of program code.

3. The system of claim 1 , wherein the notification is of the second program code being available.

4. The system of claim 3 , wherein the notification comprises text identifying the category, the text attribute being specific to the category.

5. The system of claim 4 , wherein the report component further sends a notification of the first program code pertaining to the defined category, and wherein the notification comprises second text identifying the defined category and further comprises second formatting information defining a second text attribute to display the second text at the display device, the second text attribute being specific to the defined category.

6. The system of claim 1 , wherein the similarity criterion dictates that a similarity metric is greater than a threshold value, the similarity metric comprising one of a defined number of words in bag-of-words model or a defined Euclidean distance in an embeddings space, and wherein the computer-executable components further comprise,
a similarity component that determines the similarity metric for the second program code; and
an assessment component that compares the similarity metric to the threshold value.

7. The system of claim 1 , wherein the evaluation component that generates a classification attribute designating the first program code as pertaining to the defined category, and wherein the evaluation component generates the classification attribute by,
receiving a code sequence corresponding to the first program code;
receiving a vector identifying a cost model to access the cloud computing service, the cost model being retained in a customized data repository;
generating multiple weights by applying a machine-learning model to the code sequence and the vector, wherein a first weight of the multiple weights represents a probability that the code sequence pertains to a first particular category representing a particular cost for accessing the cloud computing service, and wherein a second weight of the multiple weights represents a probability that the code sequence pertains to a second particular category representing a second particular cost for accessing the cloud computing service;
determining that a largest weight of the multiple weights corresponds to the defined category; and
assigning the classification attribute to a label identifying the defined category.

8. The system of claim 7 , wherein applying the machine-learning model comprises applying a bidirectional encoder representations for transformers (BERT) model to the code sequence and the vector.

9. A computer-implemented method, comprising:
determining, by a computing system operatively coupled to a processor, that first program code pertains to a defined category representing a defined cost to execute the first program code by a cloud computing service;
generating, by the computing system, a recommendation for second program code that satisfies a similarity criterion with respect to the first program code, the second program code pertaining to a category representing a cost to execute the second program code by the cloud computing service, wherein the cost is less than the defined cost; and
sending, by the computing system, a notification about the second program code to a user device, wherein the sending comprises sending formatting information defining a text attribute to display the text at a display device.

10. The computer-implemented method of claim 9 , further comprising sending, by the computing system, the second program code to a user device.

11. Computer-implemented method of claim 9 , wherein the notification is of the second program code being available.

12. The computer-implemented method of claim 11 , wherein the sending further comprises:
sending text identifying the category
the text attribute being specific to the category.

13. The computer-implemented method of claim 12 , further comprising sending a second notification of the first program code pertaining to the defined category, wherein the sending the second notification comprises:
sending second text identifying the defined category; and
sending second formatting information defining a second text attribute to display the second text at the display device, the second text attribute being specific to the defined category.

14. The computer-implemented method of claim 9 , wherein the similarity criterion dictates that a similarity metric exceeds a threshold value, the similarity metric comprising one of a defined number of words in bag-of-words model or a defined Euclidean distance in an embeddings space, and wherein the generating comprises:
determining the similarity metric for the second program code; and
determining that the similarity metric exceeds the threshold value.

15. The computer-implemented method of claim 9 , further comprising generating, by the computing system, a classification attribute that designates the first program code as pertaining to the defined category.

16. A computer program product for provision of recommendations for program code, the computer program product comprising a computer-readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
determine, by the processor, that first program code pertains to a defined category representing a defined cost to execute the first program code by a cloud computing service; and
generate, by the processor, a recommendation for second program code that satisfies a similarity criterion with respect to the first program code, the second program code pertaining to a category representing a cost to execute the second program code by the cloud computing service, wherein the cost is less than the defined cost, wherein the similarity criterion dictates that a similarity metric exceeds a threshold value, the similarity metric comprising one of a defined number of words in bag-of-words model or a defined Euclidean distance in an embeddings space.

17. The computer program product of claim 16 , wherein the computer-executable instructions are further executable to cause the processor to send the second program code to a user device.

18. The computer program product of claim 16 , wherein the computer-executable instructions are further executable to cause the processor to send a notification of the second program code.

19. The computer program product of claim 16 , and wherein the computer-execut

Assignees

• IBM

Inventors

• Malvankar Abhishek
• Rosenthal Sara
• Fonseca Carlos A
• Ayachitula Naga A

Classifications

• G06F16/285

  Clustering or classification · CPC title

• G06F8/30 Primary

  Creation or generation of source code · CPC title

• G06F8/33 Primary

  Intelligent editors · CPC title