Identifying search terms for an electronic document search engine

1 . A computer-implemented method of identifying search terms for an electronic document search engine, comprising:

generating, using a market prediction model, market trend data associated with computing products, including:

for each computing product:

identifying electronic documents associated with the computing product;

calculating, based on the electronic documents, product sentiment, market data, and financial data results associated with the computing product; and

generating, using a market prediction model, the market trend data associated with the computing product based on the product sentiment, market data, and financial data results associated with the computing product;

comparing the market trend data with the product profiles of each of the computing products;

identifying, based on the comparing, target computing components and target features of the market trend data absent from the product profiles of the computing products;

for one or more targeted computing products:

iteratively generating, based on the target computing components, a plurality of layouts of the targeted computing product;

iteratively permutating each of the plurality of layouts of the targeted computing product based on a plurality of combinations of the target features of each of the target computing components of each of the plurality of layouts;

identifying, from a data store, a respective product profile of the computing products, including a list of a plurality of computing components associated with the computing products, wherein the list of the plurality of computing components includes, for each computing component, a plurality of features of the computing component;

for each computing product:

comparing the product profile of the computing product with each of the plurality of permutated layouts of a targeted computing product of the one or more targeted computing products;

identifying, based on the comparing, a particular permutated layout that has a greatest difference in predicted workload with the computing product;

creating a build of the particular permutated layout, wherein the build maximizes a compute capability of the computing product; and

storing, at the storage device, a table indicating the particular permutated layout with respect to the computing product.

2 . The computer-implemented method of claim 1 , further including:

generating the search terms based on the particular permutated layouts for each of the computing products.

3 . The computer-implemented method of claim 1 , further including:

determining, for each of the plurality of permutated layouts of the targeted computing product, a predicted workload of the targeted computing product; and

determining, for each of the computing products, a predicted workload of the computing product.

4 . The computer-implemented method of claim 3 , further including:

for each of the computing products:

comparing, for each of the plurality of permutated layouts of the targeted computing product, the predicted workload of the targeted computing product with the predicted workload of the computing product; and

identifying, based on the comparing, the particular permutated layout that has a greatest difference in predicted workload with the computing product.

5 . An information handling system comprising a processor having access to memory media storing instructions executable by the processor to perform operations, comprising:

generating, using a market prediction model, market trend data associated with computing products, including:

for each computing product:

identifying electronic documents associated with the computing product;

calculating, based on the electronic documents, product sentiment, market data, and financial data results associated with the computing product; and

generating, using a market prediction model, the market trend data associated with the computing product based on the product sentiment, market data, and financial data results associated with the computing product;

comparing the market trend data with the product profiles of each of the computing products;

identifying, based on the comparing, target computing components and target features of the market trend data absent from the product profiles of the computing products;

for one or more targeted computing products:

iteratively generating, based on the target computing components, a plurality of layouts of the targeted computing product;

iteratively permutating each of the plurality of layouts of the targeted computing product based on a plurality of combinations of the target features of each of the target computing components of each of the plurality of layouts;

identifying, from a data store, a respective product profile of the computing products, including a list of a plurality of computing components associated with the computing products, wherein the list of the plurality of computing components includes, for each computing component, a plurality of features of the computing component;

for each computing product:

comparing the product profile of the computing product with each of the plurality of permutated layouts of a targeted computing product of the one or more targeted computing products;

identifying, based on the comparing, a particular permutated layout that has a greatest difference in predicted workload with the computing product;

creating a build of the particular permutated layout, wherein the build maximizes a compute capability of the computing product; and

storing, at the storage device, a table indicating the particular permutated layout with respect to the computing product.

6 . The information handling system of claim 5 , the operations further including:

generating the search terms based on the particular permutated layouts for each of the computing products.

7 . The information handling system of claim 5 , the operations further including:

determining, for each of the plurality of permutated layouts of the targeted computing product, a predicted workload of the targeted computing product; and

determining, for each of the computing products, a predicted workload of the computing product.

8 . The information handling system of claim 7 , the operations further including:

for each of the computing products:

comparing, for each of the plurality of permutated layouts of the targeted computing product, the predicted workload of the targeted computing product with the predicted workload of the computing product; and

identifying, based on the comparing, the particular permutated layout that has a greatest difference in predicted workload with the computing product.

9 . A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

generating, using a market prediction model, market trend data associated with computing products, including:

for each computing product:

identifying electronic documents associated with the computing product;

calculating, based on the electronic documents, product sentiment, market data, and financial data results associated with the computing product; and

generating, using a market prediction model, the market trend data associated with the computing product based on the product sentiment, market data, and financial data results associated with the computing product;

comparing the market trend data with the product profiles of each of the computing products;

identifying, based on the comparing, target computing components and target features of the market trend data absent from the product profiles of the computing products;

for one or more targeted computing products:

iteratively generating, based on the target computing components, a plurality of layouts of the targeted computing product;

iteratively permutating each of the plurality of layouts of the targeted computing product based on a plurality of combinations of the target features of each of the target computing components of each of the plurality of layouts;

identifying, from a data store, a respective product profile of the computing products, including a list of a plurality of computing components associated with the computing products, wherein the list of the plurality of computing components includes, for each computing component, a plurality of features of the computing component;

for each computing product:

comparing the product profile of the computing product with each of the plurality of permutated layouts of a targeted computing product of the one or more targeted computing products;

identifying, based on the comparing, a particular permutated layout that has a greatest difference in predicted workload with the computing product;

creating a build of the particular permutated layout, wherein the build maximizes a compute capability of the computing product; and

storing, at the storage device, a table indicating the particular permutated layout with respect to the computing product.

10 . The non-transitory computer-readable medium of claim 9 , the operations further including:

generating search terms based on the particular permutated layouts for each of the computing products.

11 . The non-transitory computer-readable medium of claim 9 , the operations further including:

determining, for each of the plurality of permutated layouts of the targeted computing product, a predicted workload of the targeted computing product; and

determining, for each of the computing products, a predicted workload of the computing product.

12 . The non-transitory computer-readable medium of claim 11 , the operations further including:

for each of the computing products:

comparing, for each of the plurality of permutated layouts of the targeted computing product, the predicted workload of the targeted computing product with the predicted workload of the computing product; and

identifying, based on the comparing, the particular permutated layout that has a greatest difference in predicted workload with the computing product.