Intellectual property model parameter training and utilization

1 . A system, comprising:

one or more processors; and

non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:

receiving, via a secure user interface, a request to procure financing for an entity;

querying, based at least in part on receiving the request, a first dataset for first data representing intellectual property assets associated with the entity;

querying, based at least in part on receiving the request, a second dataset for second data representing business information associated with the entity;

querying a third dataset for third data representing completed transactions to procure financing for other entities, the third dataset indicating:

financing amounts for the completed transactions; and

quality scores associated with the completed transactions;

generating a machine learning model configured to generate quality scores;

generating a training dataset that includes a transformed version of at least a portion of the third data, wherein the transformed version is configured to be utilized more readily by the machine learning model than the third data;

training the machine learning model utilizing the training dataset such that a trained machine learning model is generated, wherein the trained machine learning model comprises an improved version of the machine learning model with changed parameters from the machine learning model;

receiving feedback data indicating performance of the trained machine learning model;

retraining the trained machine learning model utilizing the feedback data such that a retrained machine learning model is generated, wherein the retrained machine learning model comprises a further improved version of the trained machine learning model with further changed parameters from the retrained machine learning model;

generating, utilizing the retrained machine learning model and based at least in part on the first data and the second data, a first quality score associated with the intellectual property assets, the first quality score indicating one or more of:

a degree of coverage associated with the intellectual property assets;

a degree of opportunity for expanding coverage of the intellectual property assets; and

a degree of exposure associated with the intellectual property assets;

determining an upper-limit financing threshold based at least in part on the third data, the upper-limit financing threshold indicating upper-limit financing amounts across quality scores;

determining a lower-limit financing threshold based at least in part on the third data, the lower-limit financing threshold indicating lower-limit financing amounts across quality scores;

determining, utilizing the first quality score associated with the intellectual property assets and based at least in part on the upper-limit financing threshold, an upper-limit financing amount to associate with the intellectual property assets;

determining, utilizing the first quality score associated with the intellectual property assets and based at least in part on the lower-limit financing threshold, a lower-limit financing amount to associate with the intellectual property assets;

transmitting a command, via a network, to a client device, the command being configured to initiate an application and to display a user interface;

displaying, via the user interface in response to the command, at least one of the first quality score, the upper-limit financing threshold, lower-limit financing threshold, the upper-limit financing amount, or the lower-limit financing amount; and

wherein the user interface is dynamically updated based at least in part on receiving new user input data.

2 . The system of claim 1 , the operations further comprising:

determining a first weighting parameter to apply to the degree of coverage, the degree of coverage indicating at least a quantity of the intellectual property assets, a breadth of the intellectual property assets, and a market alignment of the intellectual property assets to at least one market associated with the entity;

determining a second weighting parameter to apply to the degree of opportunity, the degree of opportunity indicating at least a number of intellectual property applications associated with the entity, a first intellectual property application filing velocity associated with the entity, and a second intellectual property application filing velocity associated with entities in the at least one market;

determining a third weighting parameter to apply to the degree of exposure, the degree of exposure indicating at least an intellectual property validity probability and litigation metrics associated with the intellectual property assets; and

wherein the trained machine learning model is configured to determine quality scores utilizing the first weighting parameter, the second weighting parameter, and the third weighting parameter.

3 . The system of claim 1 , the operations further comprising:

establishing a scale of quality scores, the scale indicating a minimum possible quality score and a maximum possible quality score;

for individual ones of the completed transactions, associating the quality scores with the scale;

determining maximum financing amounts provided in the completed transactions for individual ones of the quality scores;

extrapolating the maximum financing amounts across various quality scores on the scale;

determining minimum financing amounts provided in the completed transactions for individual ones of the quality scores;

extrapolating the minimum financing amounts across the various quality scores on the scale; and

wherein:

determining the upper-limit financing threshold is based at least in part on extrapolating the maximum financing amounts across the various quality scores on the scale; and

determining the lower-limit financing threshold is based at least in part on extrapolating the minimum financing amounts across the various quality scores on the scale.

4 . The system of claim 1 , the operations further comprising:

determining an intellectual property portfolio size associated with individual ones of the completed transactions;

determining a variance from a given financing amount associated with the individual ones of the completed transactions based at least in part on the intellectual property portfolio size; and

wherein:

determining the upper-limit financing threshold is based at least in part on the variance; and

determining the lower-limit financing threshold is based at least in part on the variance.

5 . A computer-implemented method, comprising:

receiving first data representing intellectual property assets associated with an entity;

receiving second data representing business information associated with the entity;

identifying third data representing completed transactions for other entities, the third data indicating:

financing amounts for the completed transactions; and

quality scores associated with the completed transactions;

generating a machine learning model configured to generate quality scores;

generating a training dataset that includes a transformed version of at least a portion of the third data, wherein the transformed version is configured to be utilized more readily by the machine learning model than the third data;

training the machine learning model utilizing the training dataset such that a trained machine learning model is generated, wherein the trained machine learning model comprises an improved version of the machine learning model with changed parameters from the machine learning model;

receiving feedback data indicating performance of the trained machine learning model;

retraining the trained machine learning model utilizing the feedback data such that a retrained machine learning model is generated, wherein the retrained machine learning model comprises a further improved version of the trained machine learning model with further changed parameters from the retrained machine learning model;

generating, utilizing the retrained machine learning model and based at least in part on the first data and the second data, a first quality score associated with the intellectual property assets;

determining an upper-limit financing threshold based at least in part on the third data;

determining, utilizing the first quality score and based at least in part on the upper-limit financing threshold, a financing amount to associate with the intellectual property assets;

transmitting a command, via a network, to a client device, the command being configured to initiate an application and to display a user interface;

displaying, via the user interface in response to the command, at least one of the first quality score, the upper-limit financing threshold, or the financing amount; and

wherein the user interface is dynamically updated based at least in part on receiving new user input data.

6 . The computer-implemented method of claim 5 , wherein the first quality score is based at least in part on a degree of coverage of the intellectual property assets, a degree of opportunity to expand coverage of the intellectual property assets, and a degree of exposure associated with the intellectual property assets, and the computer-implemented method further comprises:

determining a first weighting parameter to apply to the degree of coverage;

determining a second weighting parameter to apply to the degree of opportunity;

determining a third weighting parameter to apply to the degree of exposure, the first weighting parameter differing from the second weighting parameter and the third weighting parameter, the second weighting parameter differing from the third weighting parameter; and

wherein the trained machine learning model is configured to determine quality scores utilizing the first weighting parameter, the second weighting parameter, and the third weighting parameter.

7 . The computer-implemented method of claim 5 , further comprising:

determining maximum financing amounts provided in the completed transactions;

extrapolating the maximum financing amounts across various quality scores on a scale;

determining minimum financing amounts provided in the completed transactions;

extrapolating the minimum financing amounts across the various quality scores on the scale; and

wherein determining the upper-limit financing threshold is based at least in part on extrapolating the maximum financing amounts.

8 . The computer-implemented method of claim 5 , further comprising:

determining an intellectual property portfolio size associated with individual ones of the completed transactions;

determining a variance from a given financing amount associated with the individual ones of the completed transactions based at least in part on the intellectual property portfolio size; and

wherein determining the upper-limit financing threshold is based at least in part on the variance.

9 . The computer-implemented method of claim 5 , further comprising:

receiving a request to procure financing for the entity, the request indicating a requested financing amount;

determining that the requested financing amount is greater than the upper-limit financing threshold; and

generating a user interface configured to indicate:

that the requested financing amount is greater than the upper-limit financing threshold; and

a finance amount that satisfies the upper-limit financing threshold.

10 . The computer-implemented method of claim 5 , further comprising:

determining a financing median based at least in part on the upper-limit financing threshold and a lower-limit financing threshold; and

wherein determining the financing amount includes determining the financing amount from the financing median associated with the first quality score.

11 . The computer-implemented method of claim 5 , further comprising:

parsing a first dataset for the first data utilizing an entity identifier associated with the entity;

parsing a second dataset for the second data utilizing the entity identifier; and

parsing a third dataset for the third data utilizing a requested financing amount specified by the entity.

12 . The computer-implemented method of claim 5 , further comprising:

receiving further feedback data associated with the financing amount; and

updating the retrained machine learning model utilizing the further feedback data.

13 . A system, comprising:

one or more processors; and

non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:

receiving first data representing intellectual property assets associated with an entity;

receiving second data representing business information associated with the entity;

identifying third data representing completed transactions for other entities, the third data indicating:

financing amounts for the completed transactions; and

quality scores associated with the completed transactions;

generating a machine learning model configured to generate quality scores;

generating a training dataset that includes a transformed version of at least a portion of the third data, wherein the transformed version is configured to be utilized more readily by the machine learning model than the third data;

training the machine learning model utilizing the training dataset such that a trained machine learning model is generated, wherein the trained machine learning model comprises an improved version of the machine learning model with changed parameters from the machine learning model;

receiving feedback data indicating performance of the trained machine learning model;

retraining the trained machine learning model utilizing the feedback data such that a retrained machine learning model is generated, wherein the retrained machine learning model comprises a further improved version of the trained machine learning model with further changed parameters from the retrained machine learning model;

generating, utilizing the retrained machine learning model and based at least in part on the first data and the second data, a first quality score associated with the intellectual property assets;

determining an upper-limit financing threshold based at least in part on the third data;

determining, utilizing the first quality score and based at least in part on the upper-limit financing threshold, a financing amount to associate with the intellectual property assets;

transmitting a command, via a network, to a client device, the command being configured to initiate an application and to display a user interface;

displaying, via the user interface in response to the command, at least one of the first quality score, the upper-limit financing threshold, or the financing amount:

wherein the user interface is dynamically updated based at least in part on receiving new user input data.

14 . The system of claim 13 , wherein the first quality score indicates a degree of coverage of the intellectual property assets, a degree of opportunity to expand coverage of the intellectual property assets, and a degree of exposure associated with the intellectual property assets, and the operations further comprise:

determining a first weighting parameter to apply to the degree of coverage;

determining a second weighting parameter to apply to the degree of opportunity;

determining a third weighting parameter to apply to the degree of exposure, the first weighting parameter differing from the second weighting parameter and the third weighting parameter, the second weighting parameter differing from the third weighting parameter; and

wherein the trained machine learning model is configured to determine quality scores utilizing the first weighting parameter, the second weighting parameter, and the third weighting parameter.

15 . The system of claim 13 , the operations further comprising:

determining maximum financing amounts provided in the completed transactions;

extrapolating the maximum financing amounts across various quality scores on a scale;

determining minimum financing amounts provided in the completed transactions;

extrapolating the minimum financing amounts across the various quality scores on the scale; and

wherein determining the upper-limit financing threshold is based at least in part on extrapolating the maximum financing amounts.

16 . The system of claim 13 , the operations further comprising:

determining an intellectual property portfolio size associated with individual ones of the completed transactions;

determining a variance from a given financing amount associated with the individual ones of the completed transactions based at least in part on the intellectual property portfolio size; and

wherein determining the upper-limit financing threshold is based at least in part on the variance.

17 . The system of claim 13 , the operations further comprising:

receiving a request to procure financing for the entity, the request indicating a requested financing amount;

determining that the requested financing amount is greater than the upper-limit financing threshold; and

generating a user interface configured to indicate:

that the requested financing amount is greater than the upper-limit financing threshold; and

a finance amount that satisfies the upper-limit financing threshold.

18 . The system of claim 13 , the operations further comprising:

determining a financing median based at least in part on the upper-limit financing threshold and a lower-limit financing threshold; and

wherein determining the financing amount includes determining the financing amount from the financing median at the first quality score.

19 . The system of claim 13 , the operations further comprising:

parsing a first dataset for the first data utilizing an entity identifier associated with the entity;

parsing a second dataset for the second data utilizing the entity identifier; and

parsing a third dataset for the third data utilizing a requested financing amount specified by the entity.

20 . The system of claim 13 , the operations further comprising:

receiving further feedback data associated with the financing amount; and

updating the retrained machine learning model utilizing the further feedback data.