Methods and systems for physiologically informed network searching

1. A system for physiologically informed network searching, the system comprising a computing device designed and configured to:

receive a biological extraction from a user;

generate a cohort-specific index classifier, wherein the index classifier comprises a machine-learning model trained by training data comprising a plurality of user physiological data records and a plurality of user cohort labels configured to receive biological extractions as inputs and output web search indices, the cohort-specific index classifier further comprising a classification algorithm configured to:

cluster a plurality of user physiological data records to a plurality of user cohort labels, wherein:

the plurality of user cohort labels is created using a feature learning algorithm configured to detect co-occurrences of sets of physiological data by:

dividing physiological data from a given user into a plurality of sub-combinations to create a plurality of physiological data sets using a cluster analysis configured to:

 generate an initial set of user cohort labels from an initial set of user physiological data of a plurality of users; and

 iteratively identify new clusters to generate new user cohort labels, wherein the physiological data is classified as a function of the generated new user cohort labels;

evaluating which physiological data sets tend to co-occur with which other physiological data sets as a function of a degree of a similarity index value;

each user cohort label from the plurality of user cohort labels is correlated to the plurality of physiological data having a greatest degree of similarity to the biological extraction from the user; and

rank the web search indices as a function of a cohort relevance heuristic;

output, from the cohort-specific index classifier, a physiologically linked web index, wherein the physiologically linked web index further comprises physiological data of past biological extractions of the user;

receive, from the user, a search query;

determine at least a hidden state as a function of the search query, wherein determining the hidden state comprises:

parsing the search query into sequential tokens;

generating a hidden state model of at least a chain of tokens; and

determining the at least a hidden state as a function of the at least a hidden state model;

generate, using the physiologically linked web index, the at least a hidden state and the search query, a ranked search result, wherein the ranking is determined by:

calculating an overall rank by aggregating a relevance rank, a keyword score, a user history rank, and an inverted index score; and

applying a weight factor to the overall rank;

receive, from the user, the user's phenotype, wherein the user's phenotype comprises the user's behavioral history; and

remove, as a function of the user's behavioral history, specific search results from the previously generated ranked search results.

2. The system of claim 1 , wherein the classification algorithm further comprises a K-nearest neighbors classification algorithm.

3. The system of claim 1 , wherein the computing device is further configured to generate the index classifier.

4. The system of claim 1 , wherein the feature learning algorithm further comprises a k-means clustering algorithm.

5. The system of claim 1 , wherein the computing device is further configured to generate a physiologically linked index.

6. The system of claim 5 , wherein generating the physiologically linked index further comprises modifying a general web index as a function of cohort data.

7. The method of claim 5 , wherein generating the physiologically linked index further comprises generating the physiologically linked index using a web crawler program.

8. The method of claim 7 , wherein the web crawler program is further configured to evaluate web page relevance using a cohort relevance heuristic.

9. The system of claim 8 , wherein the computing device is further configured to generate the cohort relevance heuristic using a supervised machine-learning process.

10. A method of physiologically informed network searching, the method comprising:

receiving, at a computing device, a biological extraction from a user;

generating, by the computing device, a cohort-specific index classifier, wherein the index classifier comprises a machine-learning model trained by training data comprising a plurality of user physiological data records and a plurality of user cohort labels configured to receive biological extractions as inputs and output web search indices, the cohort-specific index classifier further comprising a classification algorithm for:

clustering a plurality of user physiological data records to a plurality of user cohort labels, wherein:

the plurality of user cohort labels is created using a feature learning algorithm configured to detect co-occurrences of sets of physiological data by:

dividing physiological data from a given user into a plurality of sub-combinations to create a plurality of physiological data sets using a cluster analysis configured to:

 generate an initial set of user cohort labels from an initial set of user physiological data of a plurality of users; and

 iteratively identify new clusters to generate new user cohort labels, wherein the physiological data is classified as a function of the generated new user cohort labels;

evaluating which physiological data sets tend to co-occur with which other physiological data sets as a function of a degree of similarity index value;

each user cohort label from the plurality of user cohort labels is correlated to the plurality of physiological data having a greatest degree of similarity to the biological extraction from the user; and

ranking the web search indices as a function of a cohort relevance heuristic;

outputting, by the computing device and from the cohort-specific index classifier, a physiologically linked web index, wherein the physiologically linked web index further comprises physiological data of past biological extractions of the user;

receiving, from the user, a search query;

determining, by the computing device, at least a hidden state as a function of the search query, wherein determining the at least a hidden state comprises:

parsing the search query into sequential tokens;

generating a hidden state model of at least a chain of tokens; and

determining the at least a hidden state as a function of the hidden state model;

generating, using the physiologically linked web index, the at least a hidden state and the search query, a ranked search result, wherein the ranking is determined by:

calculating an overall rank by aggregating a relevance rank, a keyword score, a user history rank, and an inverted index score; and

applying a weight factor to the overall rank;

receiving, from the user, the user's phenotype, wherein the user's phenotype comprises the user's behavioral history; and

removing, as a function of the user's behavioral history, specific search results from the previously generated ranked search results.

11. The method of claim 10 , wherein the classification algorithm further comprises a K-nearest neighbors classification algorithm.

12. The method of claim 10 further comprising generating the index classifier.

13. The method of claim 10 , wherein the feature learning algorithm further comprises a k-means clustering algorithm.

14. The method of claim 10 further comprising generating a physiologically linked index.

15. The method of claim 14 , wherein generating the physiologically linked index further comprises modifying a general web index as a function of cohort data.

16. The method of claim 14 , wherein generating the physiologically linked index further comprises generating the physiologically linked index using a web crawler program.

17. The method of claim 16 , wherein the web crawler program is further configured to evaluate web page relevance using a cohort relevance heuristic.

18. The system of claim 1 , wherein the physiological data of past biological extractions of the user includes at least a mean corpuscular hemoglobin concentration.