Implementing Einstein OCR
Download as PPTX, PDF0 likes422 views
The document provides an overview of Einstein OCR and how to implement it. It discusses Einstein Vision and Language services, everyday use cases for Einstein OCR like scanning licenses and business cards, prerequisites for accessing the Einstein APIs, and building a smart record create component using the Einstein OCR API. It also covers key considerations like language support and accuracy testing, and provides references for more information.
Implementing Einstein OCR
- 1. Implementing Einstein OCR @msrivastav13 | mohith.shrivastava@salesforce.com Mohith Shrivastava, Lead Developer Evangelist
- 2. Forward-Looking Statement Statement under the Private Securities Litigation Reform Act of 1995: This presentation contains forward-looking statements about the company’s financial and operating results, which may include expected GAAP and non-GAAP financial and other operating and non-operating results, including revenue, net income, diluted earnings per share, operating cash flow growth, operating margin improvement, expected revenue growth, expected current remaining performance obligation growth, expected tax rates, the one-time accounting non-cash charge that was incurred in connection with the Salesforce.org combination; stock- based compensation expenses, amortization of purchased intangibles, shares outstanding, market growth and sustainability goals. The achievement or success of the matters covered by such forward-looking statements involves risks, uncertainties and assumptions. If any such risks or uncertainties materialize or if any of the assumptions prove incorrect, the company’s results could differ materially from the results expressed or implied by the forward-looking statements we make. The risks and uncertainties referred to above include -- but are not limited to -- risks associated with the effect of general economic and market conditions; the impact of geopolitical events; the impact of foreign currency exchange rate and interest rate fluctuations on our results; our business strategy and our plan to build our business, including our strategy to be the leading provider of enterprise cloud computing applications and platforms; the pace of change and innovation in enterprise cloud computing services; the seasonal nature of our sales cycles; the competitive nature of the market in which we participate; our international expansion strategy; the demands on our personnel and infrastructure resulting from significant growth in our customer base and operations, including as a result of acquisitions; our service performance and security, including the resources and costs required to avoid unanticipated downtime and prevent, detect and remediate potential security breaches; the expenses associated with new data centers and third-party infrastructure providers; additional data center capacity; real estate and office facilities space; our operating results and cash flows; new services and product features, including any efforts to expand our services beyond the CRM market; our strategy of acquiring or making investments in complementary businesses, joint ventures, services, technologies and intellectual property rights; the performance and fair value of our investments in complementary businesses through our strategic investment portfolio; our ability to realize the benefits from strategic partnerships, joint ventures and investments; the impact of future gains or losses from our strategic investment portfolio, including gains or losses from overall market conditions that may affect the publicly traded companies within the company's strategic investment portfolio; our ability to execute our business plans; our ability to successfully integrate acquired businesses and technologies, including delays related to the integration of Tableau due to regulatory review by the United Kingdom Competition and Markets Authority; our ability to continue to grow unearned revenue and remaining performance obligation; our ability to protect our intellectual property rights; our ability to develop our brands; our reliance on third-party hardware, software and platform providers; our dependency on the development and maintenance of the infrastructure of the Internet; the effect of evolving domestic and foreign government regulations, including those related to the provision of services on the Internet, those related to accessing the Internet, and those addressing data privacy, cross-border data transfers and import and export controls; the valuation of our deferred tax assets and the release of related valuation allowances; the potential availability of additional tax assets in the future; the impact of new accounting pronouncements and tax laws; uncertainties affecting our ability to estimate our tax rate; the impact of expensing stock options and other equity awards; the sufficiency of our capital resources; factors related to our outstanding debt, revolving credit facility, term loan and loan associated with 50 Fremont; compliance with our debt covenants and lease obligations; current and potential litigation involving us; and the impact of climate change. Further information on these and other factors that could affect the company’s financial results is included in the reports on Forms 10-K, 10-Q and 8-K and in other filings it makes with the Securities and Exchange Commission from time to time. These documents are available on the SEC Filings section of the Investor Information section of the company’s website at www.salesforce.com/investor. Salesforce.com, inc. assumes no obligation and does not intend to update these forward-looking statements, except as required by law.
- 3. Agenda ● Overview of Einstein Vision and Einstein Language ● Which Einstein Vision or Language Service is right for you? ● Introduction to Einstein OCR ● Everyday use cases for Einstein OCR ● Prerequisites - Einstein Vision & Language APIs ● Building a smart Record Create LWC Component using Einstein OCR API ● Key Considerations ● References
- 4. Overview of Einstein Vision and Language Einstein Vision enables you to tap into the power of AI and train deep learning models to recognize and classify images at scale. You can train a new model or use a pre trained classifier. Einstein Language Create natural language processing models to classify the intent of text or to classify text as positive, negative, and neutral. Salesforce provides easy to use APIs.
- 6. Einstein OCR provides OCR (optical character recognition) models that detect alphanumeric text in an image. Single Rest API endpoint where you can send parameters with predefined models and tasks Introduction to Einstein OCR ModelID Usage Task Parameter OCRModel ● Business Card ● Unformatted text ● contact ● text tabulatev2 ● table data ● table
- 7. Everyday Use Cases of Einstein OCR Footer ● License verification using a driver’s license photo ID ● Scanning serial numbers on products ● Scanning readings on medical devices ● Reading business card data for lead/contact capture ● Reading data from price sheets or schedule templates Note that for all the above use cases, OCR reduces the need for manual data entry.
- 8. • Sign up at https://api.einstein.ai/signup • PEM key has to be stored securely. Please do take care of all security measures to ensure it is securely stored. • If you are building an appexchange app, use protected custom settings or custom metadata to store. • If you are storing in salesforce files make sure it is encrypted before it is stored and the file is private and shared with only users having specific permission Prerequisites : Einstein Vision and Language APIs
- 9. JWT Flow Client Application Authorization Server(/v2/oauth2/token) Resource Server(Einstein API) 2 1 3 1. The application requests authorization to the einstein.ai authorization server. 2. Einstein.ai on successful authorization responds with an access token 3. Using access token the client application can access the Einstein API resources
- 10. Demo Explore Einstein OCR APIs using CURL tool
- 11. Installing Einstein Vision and Language Model Builder Install in sandbox/prod using the appexchange link below. Note the package is from salesforce Labs and offered for free. https://appexchange.salesforce.com/appxListingDetail?listingId=a0N3A00000Ed1V8UAJ Install in scratch orgs from command line below sfdx force:package:install --package=04t0b000001uZBPAA2 ****PackageId change with new package release so always make sure you have latest Assign perms sfdx force:user:permset:assign --permsetname "Einstein_Playground"
- 12. Demo Smart Record Create Component https://github.com/msrivastav13/ocrDemo
- 13. ● Einstein OCR only supports english language. Note that Einstein Intent APIs support multiple language ● If you are using OCR with license or photo Id and want to map more entities than standard ones like phone, website, name or address use bounding box coordinates since most of times bounding boxes for two images are approximately same. ● Make sure to test your implementation with combinations of test data (images in this case) to find accuracy of the algorithms. Key Considerations
- 14. References API Reference - https://metamind.readme.io/reference Developer Documentation on Einstein Vision and Language - https://metamind.readme.io/ Einstein Platform Developer Center - https://developer.salesforce.com/developer-centers/ein- platform/