Sentiment analysis for obtaining updated sustainability data for enterprise action plans
An enterprise system may include one or more devices that perform respective operations of an enterprise and a sustainability platform system to determine a sentiment regarding input data by monitoring one or more input data sources based on monitoring parameters associated with aspects of sustainability of the enterprise. Additionally, the sustainability platform system may determine if changes to the input data are likely to have occurred based on the sentiment, and, if so, trigger a data search for the new input data. The sustainability platform system may also obtain the new input data via the input data sources based on the data search, generate one or more sustainability action plans for improving sustainability parameters of the enterprise based on the new input data, and send one or more commands to the devices to adjust their respective operations according to the one or more sustainability action plans.
1 . An enterprise computing system comprising:
one or more computer devices configured to perform one or more respective operations of an enterprise; and
a sustainability platform computing system configured to:
determine a sentiment regarding input data by monitoring one or more input data sources based on monitoring parameters associated with aspects of sustainability of the enterprise, wherein determining the sentiment is based on a sentiment analysis of a context of the input data of the one or more input data sources, and wherein the sentiment analysis comprises:
estimating individual sentiments of a plurality of input data sources regarding the input data from the context; and
estimating the sentiment based on a weighted average of the individual sentiments of the plurality of input data sources, wherein different individual sentiments comprise different weightings of the weighted average;
determine if changes to the input data are likely to have occurred, defining new input data, based on the sentiment;
in response to determining that the changes have occurred, trigger a data search for the new input data;
obtain the new input data via the one or more input data sources based on the data search;
generate one or more sustainability action plans for improving one or more sustainability parameters of the enterprise based on the new input data, wherein generating the one or more sustainability action plans comprises:
determining at least one abatement technology estimated to improve the one or more sustainability parameters based on the new input data and a sustainability model of the enterprise, wherein the sustainability model is representative of a state of operations of the enterprise; and
generating the one or more sustainability action plans based on the at least one abatement technology;
generate the sustainability model based on the new input data;
simulate an effect of the one or more sustainability action plans on the one or more sustainability parameters over a period of time based on the new input data to generate one or more simulated sustainability parameters, wherein the one or more sustainability parameters comprise a carbon footprint of the one or more computer devices, a water usage of the one or more computer devices, a waste output of the one or more computer devices, a greenhouse gas emission of the one or more computer devices, or any combination thereof; and
in response to determining that the one or more simulated sustainability parameters are within one or more thresholds, send one or more commands to the one or more computer devices to adjust the one or more respective operations according to the one or more sustainability action plans, wherein the one or more respective operations are associated with controlling a flow of hydrocarbons from a subsurface region via one or more pumps, one or more wellheads, one or more artificial lifts, or any combination thereof.
2 . The enterprise computing system of claim 1 , wherein the new input data comprises regulation data that has changed since a previous search of the one or more input data sources, carbon credit data that has changed since the previous search of the one or more input data sources, abatement technology data that has changed since the previous search of the one or more input data sources, or any combination thereof.
3 . The enterprise computing system of claim 1 , wherein the sentiment analysis comprises performing a trend analysis on a frequency of occurrence of one or more key words of the monitoring parameters.
4 . The enterprise computing system of claim 1 , wherein the sustainability platform computing system is configured to obtain the new input data from the one or more input data sources by:
querying one or more databases of the one or more input data sources for the new input data;
scraping the new input data from the one or more input data sources via a large language model machine learning algorithm; or
both.
5 . The enterprise computing system of claim 4 , wherein the one or more input data sources comprise government regulatory websites, social media websites, news publication websites, product catalogs corresponding to the one or more devices, or any combination thereof.
6 . The enterprise computing system of claim 1 , wherein the sustainability platform computing system is configured to determine if the changes to the input data have occurred based on a comparison of one or more characteristic values of the sentiment to one or more threshold values.
7 . The enterprise computing system of claim 1 , wherein the sentiment analysis comprises determining an urgent sentiment, an anger sentiment, a happy sentiment, a worrisome sentiment, a neutral sentiment, or any combination thereof of the context of the input data.
8 . A method comprising:
determining, via a computing system, a sentiment regarding input data by monitoring one or more input data sources based on monitoring parameters associated with aspects of sustainability of an enterprise, wherein determining the sentiment is based on a sentiment analysis of a context of the input data of the one or more input data sources, and wherein the sentiment analysis comprises:
estimating individual sentiments of a plurality of input data sources regarding the input data from the context; and
estimating the sentiment based on a weighted average of the individual sentiments of the plurality of input data sources, wherein different individual sentiments comprise different weightings of the weighted average;
determining, via the computing system, if changes to the input data are likely to have occurred, defining new input data, based on the sentiment;
in response to determining that the changes have occurred, triggering, via the computing system, a data search for the new input data;
obtaining, via the computing system, the new input data via the one or more input data sources based on the data search;
generating, via the computing system, one or more sustainability action plans for improving one or more sustainability parameters of the enterprise based on the new input data, wherein generating the one or more sustainability action plans comprises:
determining at least one abatement technology estimated to improve the one or more sustainability parameters based on the new input data and a sustainability model of the enterprise, wherein the sustainability model is representative of a state of operations of the enterprise; and
generating the one or more sustainability action plans based on the at least one abatement technology;
generating, via the computing system, the sustainability model based on the new input data;
simulating, via the computing system, an effect of the one or more sustainability action plans on the one or more sustainability parameters over a period of time based on the new input data to generate one or more simulated sustainability parameters, wherein the one or more sustainability parameters comprise a carbon footprint of one or more devices, a water usage of the one or more devices, a waste output of the one or more devices, a greenhouse gas emission of the one or more devices, or any combination thereof; and
in response to determining that the one or more simulated sustainability parameters are within one or more thresholds, sending, via the computing system, one or more commands to the one or more devices of the enterprise to adjust one or more respective operations of the one or more devices according to the one or more sustainability action plans, wherein the one or more respective operations are associated with controlling a flow of hydrocarbons from a subsurface region via one or more pumps, one or more wellheads, one or more artificial lifts, or any combination thereof.
9 . The method of claim 8 , wherein obtaining the new input data from the one or more input data sources comprises:
querying one or more databases of the one or more input data sources for the new input data, wherein the one or more input data sources comprise government regulatory websites, social media websites, news publication websites, product catalogs corresponding to the one or more devices, or any combination thereof;
scraping the new input data from the one or more input data sources via a large language model machine learning algorithm; or
both.
10 . The method of claim 8 , comprising determining, via the computing system, if the changes to the input data have occurred based on a comparison of one or more characteristic values of the sentiment to one or more threshold values.
11 . The method of claim 8 , wherein the new input data comprises regulation data that has changed since a previous search of the one or more input data sources, carbon credit data that has changed since the previous search of the one or more input data sources, abatement technology data that has changed since the previous search of the one or more input data sources, or any combination thereof.
12 . The method of claim 8 , wherein the sentiment analysis comprises performing a trend analysis on a frequency of occurrence of one or more key words of the monitoring parameters.
13 . The method of claim 8 , wherein the sentiment analysis comprises determining an urgent sentiment, an anger sentiment, a happy sentiment, a worrisome sentiment, a neutral sentiment, or any combination thereof of the context of the input data.
14 . A non-transitory, machine-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
determining a sentiment regarding input data by monitoring one or more input data sources based on monitoring parameters associated with aspects of sustainability of an enterprise, wherein determining the sentiment is based on a sentiment analysis of a context of the input data of the one or more input data sources, and wherein the sentiment analysis comprises:
estimating individual sentiments of a plurality of input data sources regarding the input data from the context; and
estimating the sentiment based on a weighted average of the individual sentiments of the plurality of input data sources, wherein different individual sentiments comprise different weightings of the weighted average;
determining if changes to the input data are likely to have occurred, defining new input data, based on the sentiment;
in response to determining that the changes have occurred, triggering a data search for the new input data;
obtaining the new input data via the one or more input data sources based on the data search;
generating one or more sustainability action plans for improving one or more sustainability parameters of the enterprise based on the new input data, wherein generating the one or more sustainability action plans comprises:
determining at least one abatement technology estimated to improve the one or more sustainability parameters based on the new input data and a sustainability model of the enterprise, wherein the sustainability model is representative of a state of operations of the enterprise; and
generating the one or more sustainability action plans based on the at least one abatement technology:
generating the sustainability model based on the new input data;
simulating an effect of the one or more sustainability action plans on the one or more sustainability parameters over a period of time based on the new input data to generate one or more simulated sustainability parameters, wherein the one or more sustainability parameters comprise a carbon footprint of one or more devices, a water usage of the one or more devices, a waste output of the one or more devices, a greenhouse gas emission of the one or more devices, or any combination thereof; and
in response to determining that the one or more simulated sustainability parameters are within one or more thresholds, sending one or more commands to the one or more devices of the enterprise to adjust one or more respective operations of the one or more devices according to the one or more sustainability action plans, wherein the one or more respective operations are associated with controlling a flow of hydrocarbons from a subsurface region via one or more pumps, one or more wellheads, one or more artificial lifts, or any combination thereof.
15 . The non-transitory, machine-readable medium of claim 14 , wherein the sentiment analysis comprises performing a trend analysis on a frequency of occurrence of one or more key words of the monitoring parameters.
16 . The non-transitory, machine-readable medium of claim 15 , wherein the new input data comprises regulation data that has changed since a previous search of the one or more input data sources, carbon credit data that has changed since the previous search of the one or more input data sources, abatement technology data that has changed since the previous search of the one or more input data sources, or any combination thereof.
17 . The non-transitory, machine-readable medium of claim 15 , wherein the sentiment analysis comprises determining an urgent sentiment, an anger sentiment, a happy sentiment, a worrisome sentiment, a neutral sentiment, or any combination thereof of the context of the input data.
18 . The non-transitory, machine-readable medium of claim 14 , comprising machine-readable instructions that, when executed by the one or more processors of a machine, cause the machine to obtain the new input data from the one or more input data sources by:
querying one or more databases of the one or more input data sources for the new input data;
scraping the new input data from the one or more input data sources via a large language model machine learning algorithm; or
both.
19 . The non-transitory, machine-readable medium of claim 18 , wherein the one or more input data sources comprise government regulatory websites, social media websites, news publication websites, product catalogs corresponding to the one or more devices, or any combination thereof.
20 . The non-transitory, machine-readable medium of claim 14 , comprising machine-readable instructions that, when executed by the one or more processors of a machine, cause the machine to determine if the changes to the input data have occurred based on a comparison of one or more characteristic values of the sentiment to one or more threshold values.