CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] The present patent application claims the priority benefit of US. provisional patent application number 62/817,445 filed March 12, 2019 and titled "System for Alteration of Product in Light of Social Media Feedback," the disclosure of which is incorporated by reference herein.

BACKGROUND OF THE INVENTION

1 Field of the Disclosure

[0002] The present disclosure of this invention is generally related to providing data to computing devices regarding products sold in the marketplace. More specifically, the present disclosure is directed to sending recommendations to computers regarding a cannabinoid- infused product.

2. Description of the Related Art

[0003] Cannabis is a flowering plant that includes three species or sub-species, namely sativa, indica and ruderalis. Cannabis has long been used for hemp fiber, oils, medicinal purposes, and as a recreational drug. Cannabis contains a unique class of terpeno-phenolic compounds known as cannabinoids or phy tocannabinoids that have been extensively studied since the discovery of the chemical structure of tetrahydrocannabinol ("D9-THC"), commonly known as THC, and tetrahydrocannabinolic acid ("THCA"). THC is the main constituent responsible for psychoactive effects. The majority of these compounds are secreted by glandular trichromes that occur abundantly on the floral calyxes and bracts of female cannabis plants. When used by humans medicinally or recreationally, cannabis can be consumed through a variety of routes, including vaporizing or smoking dried flower buds and leaf portions, resins, extracted oils or waxes. However, in recent years many medicinal patients, as well as recreational users, have begun to prefer consuming cannabis in edible form, by eating lozenges, candies, or baked goods, drinking beverages, or by taking capsules. Collectively, any product form containing cannabis can be referred to as a cannabis product.

[0004] Currently, there is no software system in place for intensive tracking of the cannabis product as required to satisfy legislation and enforce compliance. The system of intensive tracking is commonly known as "seed to sale" tracking software as a service ("SaaS"). The "seed to sale" SaaS systems may be used to collect and incorporate consumer feedback for cannabis products into their processes. There is no way for companies to implement consumer concerns such as (1) a lack of potency in a certain product, (2) if a specific product is out of stock, or (3) suggest using different cannabis strains and / or products in different form factors such as sublingual, vaporizables, or edibles.

[0005] There is therefore a need for improved systems and methods of evaluating public opinion regarding specified cannabis-infused products and product alteration based on the same.

SUMMARY OF THE PRESENTLY CLAIMED INVENTION

[0006] The present disclosure is related to methods, non-transitory computer readable storage media, and apparatuses for product modification based on social media feedback. Methods consistent with the present disclosure may include collecting data from various sources regarding specified cannabinoid-infused products, identifying the cannabinoid-infused product evaluating one or more words from the collected data regarding the product, assigning a score to the product based on the one or more words, and sending a recommendation regarding the product to a designated recipient device based on the assigned score.

[0007] Further embodiments of the presently claimed invention may be implemented as non-transitory computer readable storage medium executable by a processor to perform a method consistent with the methods herein. Such method may include collecting data from computers regarding a cannabinoid-infused product, identifying the cannabinoid-infused product, evaluating one or more words from the collected data regarding the product, assigning a score to the product based on the one or more words, and sending a recommendation regarding the product to a computer based on the assigned score.

[0008] An apparatus consistent with the present disclosure may include a memory and a processor that executes instructions out of the memory to collect data from computers regarding a cannabinoid-infused product identify the cannabinoid-infused product, evaluate one or more words from the collected data regarding the product, assign a score to the product based on the one or more words, and send a recommendation regarding the product to a computer based on the assigned score.

BRIEF DESCRIPTIONS OF THE DRAWINGS

[0009] FIG. 1 illustrates network environment in which a system for social media-based product modification may be implemented.

[0010] FIG.2 is a flowchart illustrating an exemplary method for cannabinoid data distribution.

[0011] FIG. 3 is a flowchart illustrating an exemplary method for filtering social media for cannabinoid data.

[0012] FIG.4 is a flowchart illustrating an exemplary method for managing cannabinoid data structures.

[0013] FIG. 5 is a flowchart illustrating an exemplary method for making recommendations based on cannabinoid data in social media.

[0014] FIG. 6 illustrates a computing system that may be used to implement an

embodiment of the present invention.

DETAILED DESCRIPTION

[0015] The present disclosure is directed to providing solutions to current problems within the cannabis industry by providing information to entities that have a vested interest in selling cannabinoid-infused products. The present invention provides feedback in the form of recommendations for "seed to sale" tracking software as a service (SasS) companies. Methods and apparatus consistent with the present disclosure may collect data from growers

(cultivators), manufacturers, distributors, or retailers regarding cannabinoid-infused products produced or sold by these entities. Comments posted on social media may also be collected to identify whether consumers are satisfied with a particular product. These comments may be used to identify recommendations that may be sent to respective entities such that their products may be improved over time.

[0016] FIG. 1 illustrates network environment in which a system for social media-based product modification may be implemented. Such network environment may include cultivator system 110, manufacturing system 120, distributor system 130, retail system 140, and social media system /feedback system 150. In certain instances, feedback may be received through a private portal, through a public portal, or both.

[0017] Each of the cultivator system 110, manufacture (MFG) system 120, distributor (DIST) system 130, retail system 140, and a social media feedback system 150 may be computer system that include a processor (CPU), a memory, a database, and sensors. In certain instances, a particular computer system may be configured to perform functions consistent with a combination of cultivator system 110, MFG system 120, DIST system 120, retail system 140, or social media/feedback system 150. For example, a single computer may perform the functions of MFG system 120 and a DIST system 130. While the social media system/feedback network 150 is illustrated as being a single system, a social media system and a feedback system may be implemented at different computing devices. In such instances, the feedback system may allow private communications while the social media system may allow public communications.

[0018] Note that cultivator system 110 includes processor HOP, memory (Mem) 110M, cultivator (C) database 110DB, and sensors 110S. MFG system 120 includes processor 120P, memory 120M, MFG database 120DB, and sensors 120S. DIST system 130 indudes processor 130P, memory 130M, distribution database 130DB, and sensors 130S. Retail system 140 includes processor 140P, memory 140M, retail (RTL) database 140DB, and sensors 140S. Social media/feedback system 150 indudes processor 150P, memory 150M, social media (SM) database 150DB, and sensors 150S.

[0019] Each of the respective memories illustrated in FIG. 1 include instructions that may be assodated with a respective software module. Memory 110M of cultivator system 110 may store instructions that when executed by processor 110P manage operations at a growing facility, memory 120M of MFG system 120 may store instructions that when executed by processor 120P manage operations at a manufacturer, memory 130M at DIST system 130 may store instructions that when executed by a processor 130P manage operations at a distributor, and memory 140M at retail system 140 may store instructions that when executed by processor 140P manage operations at a retailer.

[0020] Memory 150M at social media/feedback system 150 may store instructions for providing feedback from the public that may be sent to or that is accessible by cultivator system 110, MFG system 120, DIST system 130, retail system 140, or social media/feedback system 150. This feedback may also be available for other members of the general public. As such, feedback received via social media/feedback system 150 from other computers could be received by computers that belong to individual persons or entities (i.e. could be accessible by members of the general public via respective computing devices). Alternatively or additionally, certain feedback data may be private feedback that allows individual entities to provide private feedback data to other entities.

[0021] For example, in an instance when a manufacture wishes to beta-test a new product with a select set of consumers, each of those consumer could be provided a sample of a new product that members of the select set of consumers could try and provide feedback on. Such a process could include multiple iterations that would allow the manufacture to identify a version of a product that was likely to be commercially successful During the time when these Beta tests were being performed, feedback from the select set of consumers could be kept private. After the Beta testing product feedback from the general public could be received and shared with other members of the public via respective computing devices. As such, instructions included in any of the memories could allow for the private sharing of data, for the public sharing of data, or both. This sharing could be based on a product classification. Such classifications could include Beta testing, Alpha testing, or released product, for example.

[0022] A cultivator may be inclusive of a person or entity that grows and upkeeps the cannabis plants until these plants Eare ready to be harvested and be provided to a manufacturing process. Cultivator system 110 may include devices and systems associated with the cultivator and configured to collect plant data through various sensors 11QS and this sensed data may be stored in cultivator database 110DB. This received data may be sent social media feedback system 150. Cultivator database 110DB may store the data collected from the various sensors 110S. Data stored in database 110DB may include a unique plant identification number, a plant date, a harvest date, and a cannabinoid potency (e.g. cannabinoid concentration or total amount of cannabinoids).

[0023] A plurality of cultivator sensors 110S may be included in cultivator system 110. These sensors may include motion sensors, temperature sensors, humidity sensors, cameras, microphones, radiofrequency receivers, a thermal imager, a radar device, a lidar device, an ultrasound device, a speaker, wearable devices, etc. Each of these sensors 120S may be used to collect data about plants or seeds.

[0024] A manufacturer may be an entity that takes the fully mature cannabis plant and converts it into the final or intermediate product (e.g., the flower, oils, ointments, edibles, capsules, etc.). In some cases, the cultivator and manufacturer may be the same entity.

Manufacturer system 120 collects data from a manufacturing process through various sensors

120S. This sensor data may be stored in MFG database 120DB. The data stored in MFG database 120DB may be sent to the social media/feedback system 150 to be shared with one or more other computers (publicly or privately).

[0025] A manufacturer database 120DB may store data collected from the various stages of a manufacturing process, data sensed by sensors 120S may be provided to processor 120P for processing and storage. MFG database 120DB may store the unique plant identification number assigned by a cultivator, a final product type, a form factor, a percentage of a cannabinoid (e.g. THCA or THC), a product identification number, and a product name, etc.

[0026] A plurality of manufacturer sensors 120S may include motion sensors, temperature sensors, humidity sensors, cameras, microphones, radiofrequency receivers, a thermal imager, a radar device, a lidar device, an ultrasound device, a speaker, wearable devices, etc. This collected data may be used to collect data about an extraction or other processes performed during the production of the consumer product.

[0027] The distributor is an agent who supplies goods to stores, retailers, or other businesses that sell to consumers. Distributor system 130 may collect the data related to a distribution process using various sensors 130S. This sensor data may be stored or be processed and stored in the distributor database 130DB. Data stored in this distributor database 130DB may be sent to the social media/feedback system 150 to be shared with one or more other computers (publicly or privately). Distributor database 130DB may store data collected from various stages of the distribution process by collecting data from sensors 130S. The distributer database 130DB may store the product identification number identified by a manufacturer, the product name, a ship date, a delivery date, and a quantity.

[0028] A plurality of distributor sensors 130S may include motion sensors, temperature sensors, humidity sensors, cameras, microphones, radiofrequency receivers, a thermal imager, a radar device, a lidar device, an ultrasound device, a speaker, wearable devices etc. Data received from sensors 130S may be used to collect data about the distribution of consumer products.

[0029] A retailer of cannabis products may be a retail store that sells cannabis products.

Retail system 140 may collect data from a point of sale device using various sensors 104S. This collected data may be stored retailer database 150DB and this data may be sent to social media/feedback system 150. Retail database may be used to store data collected from the various stages of sales process using sensors 140S at retail system 140. Retail database 140DB the product identification number identified by the manufacturer, a product name, an arrival date, a quantity, and a cost. All of the information could be compared to information stored in DIST database 130DB that was shared with social media/feedback system 150 when a product delivery is verified. As such, methods consistent with the present disclosure may allow a retailer and distributor to validate that an order has been fulfilled correctly. This process could include collecting scanned information that identifies a product using visual codes or codes received via electromagnetic signals. Such codes may be in the form of a barcode, a quick response (QR) code, or a code stored on a near field data communication (NFC) chip. Sensors 140S at retail system may include motion sensors, temperature sensors, humidity sensors, cameras, microphones, a radiofrequency receiver, a thermal imager, a radar device, a lidar device, an ultrasound device, a speaker, wearable devices etc. Sensors 140S may be used to collect data about the sale or other processes prior to a cannabinoid-infused product being sold or as the cannabinoid-infused product has been sold.

[0030] Social media interactions may be any form of electronic communication (e.g., websites for social networking and microblogging), through which users create online communities to share information, identification numbers, personal messages, and/or other content such as videos, pictures, etc. Social media data may be collected various social media sites that mention one or more product(s) that were or are sold at relevant retailers. In certain instances, processor 150P at social media system 150 may receive and score social media posts by assigning posts a metric score. These metric scores may be stored in the social media database 150DB. This information may be shared with a feedback system at a different computer or with feedback software processes when functions consistent with feeding back information to certain computers is performed. As such, social media system 150 may store collected from one or more social media sites or platforms in social media database 150DB. The social media database 150DB may store information that identifies a product name, a product score, user comments, and keywords.

[0031] The communication network 160 may be a wired and/or a wireless network. When wireless, communication network 160 may be implemented using communication techniques such as visible light communication ("VLC"), worldwide interoperability for microwave access ("WiMAX"), long term evolution ("LTE"), wireless local area network ("WLAN"), infrared ("IR") communication, public switched telephone network ("PSTN"), radio waves, and other communication techniques known in the art. The communication network 160 may allow ubiquitous access to shared pools of configurable system resources and higher-level services that can be rapidly provisioned with minimal management effort. This may occur using communications that travel over the Internet and this process may rely on sharing of resources to achieve coherence and economies of scale, like a public utility. This may allow third-party organizations to focus on their core businesses instead of expending resources on computer infrastructure and maintenance.

[0032] Functions performed by a feedback system consistent with the present disclosure may include receiving or collecting data from cultivator system 110, MFG system 120, distributor system 130, retailer system 140, and possibly from social media sites (such as social media system 150). This feedback system may then store all of this collected data a feedback database. Instructions executed by a processor at the feedback system may analyze data to see if the data received from the social media sites indicates whether various products are trending up or down. Based upon these trends and the keywords taken from social media posts (i.e. not potent, effects take too long, etc.) may allow the feedback network to identify one or more recommendations that may be sent to any of the cultivator system 110, the MFG system 120, the DIST system 130, the retail system 140, or the social media system 150. The feedback system may also display these recommendations on a display, for example in a graphical user interface (GUI).

[0033] Such a feedback system may also include a recommendation database that stores recommendations that relate to how a product is being discussed on social media. These recommendations may be used by a cultivator, a manufacturer, a distributor, or a retailer when those entities identify ways in which they can improve their products or services. For example, the form factor of the product may be adjusted to provide the consumers with a new product using the same materials.

[0034] The feedback system may accept inputs from users or provide outputs to the users, or may perform both the actions. These user inputs and outputs may be received from one or more social media sites. For example, a user am interact with a user interface using one or more user-interactive objects and devices. The user-interactive objects and devices may include any of user input buttons, switches, knobs, levers, keys, trackballs, touchpads, cameras, microphones, motion sensors, heat sensors, inertial sensors, touch sensors, or a combination of the above. Further, these interfaces may either be implemented as a command line interface (CLI), a GUI, a voice interface, or a web-based user-interface.

[0035] FIG.2 is a flowchart illustrating an exemplary method for cannabinoid data distribution. Such method may include a series of steps performed by a computer programmed to collect, store, and share data with other computer systems regarding the production, distribution, sale, and consumption of cannabinoid-infused products. As such, the steps illustrated in FIG. 2 may be consistent with activities performed at cultivator system 110, MFG system 120, DIST system 130, retail system 140, or a social media/feedback system 150.

[0036] The method begins with step 210, where sensor or other data is received. This data may be stored in a database in step 220, and a request to receive this data may be received in step 230. Step 240 may identify whether the request was received from an authorized source (e.g. a registered user or an authorized computer). When the request is not from an authorized source program flow may move back to step 210, where additional sensor or other data is received. When the request is from an authorized source, program flow may move to step 250, where the requested data is sent to a computer from which the request was received. While the method of FIG. 2 may generally be consistent with any of a computer belonging to a cultivator, a manufacturer, a distributor, a retailer, or a social media/feedback system each of these steps may be optimized for a particular use. For example, data collected and shared by a cultivator may be optimized for collecting plant growth data and data collected and shared by a manufacturer may be optimized for collecting and sharing information relating to the manufacturer of a cannabis product (e.g. an edible product, a concentrate, an isolate, a vape cartridge, or trimmed flower material).

[0037] In respect to a cultivator, various sensors may be placed in a cultivation warehouse, grow house, in a field, or elsewhere at a grow site when data is collected about plants grown by the cultivator. Data collected by a cultivator system 110 may be stored in a database and may be shared with other computers. For example, data from the cultivator may be shared with a computer of a manufacturer and the manufacturer may then schedule a date when an extraction could be performed. In certain instances, growth data may identify a date when certain plants will be optimally mature or be optimally dried and the manufacturer could then arrange to perform an extraction of cannabinoids from those plants on that date. The sensor data received by a cultivator system may also include user inputs that may be received via various user devices (e.g., computers, laptops, smart phones, tablets, etc.). These user inputs may include user observations collected during a plant/ s life cycle. This sensor data may be stored in a cultivator database and this data may then be shared with other computers (e.g. computers of a manufacturer, a distributor, a retailer, a social media site, or of a feedback system).

[0038] Table 1 illustrates a set of data that may be stored at a database of a cultivator. The data in table 1 cross-references a plant identifier with a harvest date, a planting date, a total plant weight, and a cannabinoid percentage. The harvest date is the date when the plants) were cut down and the plant date may be either a date that a seed was placed in a growth medium or may be a date with a seedling was placed in soil. The total weight in table 1 may be a weight of the plant after it has been dried and the cannabinoid percentage may be used to identify a total mass of cannabinoids included in a mass of dry plant matter. Note that Plant ID #15932 was planted on 8/1/2019, was harvested on 12/3/2018, had a dry weight of 5 pounds (Lbs), and a cannabinoid percentage of 18%. The total mass of cannabinoids included in plant ID #15932 may be calculated by multiplying the total weight by the cannabinoid percentage in decimal format:

5 Lbs * 0.20 = 1 Lbs or about 0.454 Kilograms.

Table 1: Cultivator Database Data

[0039] Other information that could be stored in a cultivator database may include, yet are not limited to plant origin data, cultivar data (e.g. indica, sativa, hybrid), plant sex (e.g. male, female, or hermaphrodite), unique radio-frequency identification ("RFID") or near filed data communication (NFC) tag codes, nutrients, additives, treatments, schedules, harvest data, yields, test results, costs, sales, and user observations collected through various user devices.

[0040] In respect to a manufacturer, the method of FIG. 2 may be used to collect data from various sensors at a manufacturing site and this data may be stored in a database. This collected data may also be shared with other computers. This could allow customers of the manufacturer to identify when their favorite product will be available for purchase from a distributor or a retailer. This sensor data may include user inputs that have been received from various user devices (e.g. computers, laptops, smart phones, tablets, etc.). These user inputs may include observations made during a manufacturing process. The data collected by these sensors or user inputs may be used to identify that employees are following a set of guidelines or rules for manufacturing a product. For example, camera image data may be used to identify that employees are wearing gloves and face masks when required. This collected data may be stored in a manufacturer database and then this data may be shared with other devices after a request has been received.

[0041] Table 2 illustrates data that may be stored in a database of a manufacturer that identifies details about cannabinoid-infused products made by the manufacturer. Table 2 identifies that several different types of products that have been made from the same plant matter or type of plant matter identified by plant identifier #15932. Note that the type of products included in table 1 are hard candy, flower, and oil that respectively correspond to a 'form factor' of sublingual, smoke, and vapor. The form factors listed in table 2 identify that the carmabinoids included in a hard candy will be absorbed sublingually (e.g. through tissues in the mouth and possibly the digestive system of a person), that cannabinoids included in the flower can be consumed by smoking the flower, and that the oil may be inhaled as a vapor using a vaporizing device. Note that even though each of the different products were manufactured from the same type of plant material, each include different amounts (milligrams) or a different concentrations (percentage) of cannabinoids. This is because products such as hard candy or oil configured to be vaporized include other materials that may be combined in different relative proportions during a manufacturing process, where a product like a flower only includes raw dried plant matter that may have been trimmed. The various product identifiers of table 2 indicate that each of these products were made using plant matter #15932 and also include other numbers that uniquely identify the product. The data in table 2 indicate that a total quantity of 150 Lemon Drops, 2 pounds of Blue Haze flower, and 50 pieces of Brand Name THC Vape Oil were produced by the manufacturer from plant matter #15932.

Table 2: Manufacturer Database Data

[0042] It should be noted that table 2 includes several examples of what might be contained in a manufacturer database. Other exemplary data that could be stored in a manufacturer database include, yet are not limited to batch history information, a unique identification number (e.g. a barcode, a quick response code, or an RFID/NFC code), conversions performed during the manufacturing process (e.g. decarboxylation or chemical reactions), a production identification number, ingredients, additives, test results, costs, sale volume numbers, and collected user observations.

[0043] In respect to a distributor, the method of FIG. 2 may be used to collect data from sensors at a distributor and share that data with other computers. These distributor sensors may be located in a distribution warehouse when materials are organized, stored, and prepared for shipment to retailers or customers. A computer of the distributor may collect and store this sensor data. Data collected by the distributor computer may include user inputs that received from various user devices, such as computers, laptops, smart phones, tablets, etc. The sensor data and user input data may be stored in a distributor database after which the distributor computer may receive a request for data stored in the distributor database. This data may then be sent to other computer systems based on this request In one instance, data may be sent to a computer of a feedback network and this feedback computer may allow others to identify that a product inventory is available for purchase from the distributor.

[0044] Table 3 illustrates data that may be stored at a distributor database. The data in table 3 identifies a product identifier, a product name, a ship date, a delivery date, a quantity, and a store location. Note that each of the different product identifiers include a first set of characters/numbers followed by a second set of numbers. This first set of characters/numbers (#15932) correspond to a product of Lemon Drops with different SKUs of the product (0115, 0116 & 0117). Each of these different sets of numbers may have meaning to a manufacturer or to the distributor; they could identify a type of plant matter from which the respective products were made, for example. Alternatively or additionally, these sets of numbers may identify a batch or lot of product, a manufacturing date, or other information. Each of the different products identified in table 3 were shipped to different retailers on different dates, each were delivered to a respective retailer (or store location) on different dates, and each delivery include a different quantity of these cannabis infused Lemon Drops products.

Table 3: Distributor Database Data

[0045] It should be noted that table 3 includes examples of what could be stored in a distributor database. Other exemplary information that could be stored in a distributor database include, yet are not limited to, transportation manifests, online ordering receipts, scheduling data, cross-corporation invoices, purchase orders, market exchanges, e-mails, text messages, and collected user observations. Data stored at this distributor database could also include video of the distribution site that may be evaluated later when an investigation is performed to identify how or why certain products that should be stored at the distributor have disappeared. As such, data stored at the distributor database could be used to identify thieves.

[0046] In respect to a retailer, the method of FIG. 2 may be used to collect data from various sensors at a retail store. These sensors could collect information relating to a selling process at the store and this data could be used to identify whether employees of the store are following proper procedures when cannabinoid products are sold. Here again, collected sensor data may include video of activities that occur at a location when cannabis products are received, sold, or shipped. Data collected by a computer of a retailer may include data received from users that was received by the retail computer from various user devices, such as computers, laptops, smart phones, tablets, etc. The sensor data and user input data may be stored in a retailer database and this data may be shared with other computers. For example, data collected by a retail computer may be shared with a computer of a feedback network. In such instances, this data may be shared after a request is received from the feedback computer.

[0047] Table 4 illustrates products of Lemon Drops that arrived at different retailers

(Retailer 1-3) on December 7, 2018. Table 4 identifies different - yet similar product identifiers, different quantities, and different prices that may be paid to purchase different quantities of the Lemon Drops products.

Table 4: Retailer Database Data [0048] It should be noted that table 4 includes a few examples of data that could be stored at a retailer database. Other exemplary data that could be stored at the retailer database include, yet are not limited to point of sale data, label data, inventory data, invoice data, pricing data, marketing campaign data, sale volumes, costs, losses, and observations collected from employees or customers. Observations provided by these employees or customers may have been received at a retailer computer from other computing devices.

[0049] FIG.3 is a flowchart illustrating an exemplary method for filtering social media for cannabinoid data. Such method may be performed upon data from a social media network or system device.

[0050] The method begins with step 310, where social media conversations or posts are monitored regarding corresponding or predetermined topics. For example, topics monitored may relate to products of interest to a cultivator, manufacturer, distributor, and/or retailer. The monitored conversations/posts are then analyzed to respectively assess each conversation top- level interest, (i.e., pro, con, or indifferent) and a top-level interest value may be assigned in step 320. Then the influence level of each user or author of a social media conversation is identified. One or more of these users/authors may be respectively assigned a value in step 340. The values generated in steps 320 and 340 may then be processed to generate an aggregated real-time product score at step 330. The product and product score may also be stored in a social media database in step 330. Next, comments or conversation information on the social media site or platform may be extracted in step 350. The extracted comments may also be stored in the social media database in step 350. Keywords included in the comments may then be extracted and stored in step 360. The keywords may be based on a list of words describing the product (i.e. the product description and labels), a list of keywords provided by the cultivator, manufacturer, distributor, or retailer, and/or a list provided by a feedback network computer. The computer at the social media network/system may then connect to the computer of the feedback network. The social media module may then receive a request from the feedback network computer to retrieve data from the social media database in step 380. After the request is received, data associated with the request may be provided to the feedback network computer and program flow may move back to step 310, where additional social media comments and conversations may be monitored.

[0051] Table 5 illustrates data that may be stored at a database of a social media network that has been extracted from social media comments that have been received at a social media network. Table 5 identifies a product name identifying the Lemon Drops product, a product score, comments, and keywords that were from the comments. Note that keywords extracted from a first comment indicate that the Lemon Drops products were "not potent enough." Keywords extracted from a second comment indicate that the Lemon Drops product took "took long to feel anything" and that keywords extracted from a third comment indicate that the Lemon Drops product were weak and included "no THC." Scores assigned to each of these products are respectively 25, 35, and 30. These scores may have been generated from the negative comments and keywords included in table 2 using a system where a score of 100 corresponds to a perfect product score. As such, scores ranging from 25 to 35 indicate that consumers are not satisfied with the Lemon Drops product

Table 5: Social Media Database Product Comments and Scores

[0052] FIG.4 is a flowchart illustrating an exemplary method for managing cannabinoid data structures. Such method may be performed by a feedback network system or device. The method may begin with step 410, where data is received and stored from a cultivator. Next steps 420-440 respectively receive and store information from databases of a manufacturer, a distributor, and a retailer. In certain instances, data relating to particular products could be organized and stored in a database at the feedback computer. Next in step 450, data stored in a database of the social media network may be received and stored. All of the data received and stored from the respective databases may have been received after a communication connection was formed with a different computer and after requests were sent to those different computers. As such, this process could occur continuously over time, where a feedback computer constantly polls other computer for information. After all of this data has been collected, a set of instructions associated with evaluating information relating to different products in step 460 may be initiated/executed. Actions performed in step 460 may include receiving social media comments, extracting keywords from those comments, and calculating a score for products associated with the comments.

[0053] A feedback computer may collect all of the data illustrated in tables 1-5 that were previously discussed and this data may be stored in a database at the feedback computer. As such the data stored in the database computer may include data collected by a cultivator, a manufacturer, a distributor, a retailer, and one or more social media sites.

[0054] FIG.5 is a flowchart illustrating an exemplary method for making recommendations based on cannabinoid data in social media. Such method may be performed on data provided by social media or other feedback sources. Such data may be filtered, organized, and used to generate recommendations.

[0055] The method may be performed by a feedback computer consistent with the present disclosure. In step 510, feedback data may be filtered by product. For example, all comments or keywords relating to the Lemon Drops product may be organized into a group in step 510.

Next, an average social media score may be calculated in step 520, top keywords may be identified in step 530, and those top keywords may be compared to recommendations stored in a recommendations database. Next in step 550, a recommendation that matches the keywords may be identified and that recommendation may be sent to the computer of a cultivator, a manufacturer, a distributor, or a retailer. [0056] In the method of FIG. 5, keyword determination may be accomplished by counting the most re-occurring words, comparing the keywords to a list provided by a feedback network computer, comparing keywords to a list of words of interest from the cultivator, manufacturer, distributor, or retailer. Note that this process may result in a manufacturer adjusting potency of a product through recommendations stored in a recommendation database. This process may also be used by retailers and/or distributors if social media comments are complaining about an item out of stock, complimenting the price of aspect of a product (i.e., too costly/too much supply), and many other factors that may affect the cultivator, manufacturer, distributor, and/or retailer.

[0057] Table 6 illustrates information that may be stored in a recommendation database. The data in table 6 cross-references a current product form factor or type with a score, top keywords associated with a respective score, and with a recommendation that may be provided to users or to cultivators, manufacturers, distributors, or retailers. Note that the product types (form factors) in table 6 relate to products that are delivered sublingually to a patent. Low scores of 0- 20 relate to very negative key words (e.g. terrible). Such low scores of 0-20 are coupled to recommendations that recommend making a product from stronger ingredients. As the score increases, recommendations provided change. A score of 21-40 may cause a recommendation to be provided to users that recommend that they switch to a different type (or form factor) product. Higher scores may be associated with recommendations that range from a moderate, small, or no change to a given product. As such, the recommendation database may provide recommendations that indicate whether a particular product is acceptable or not.

Table 6: Recommendations Database Data

[0058] One skilled in the art will appreciate that, for this and other processes and methods disclosed herein, the functions performed in the processes and methods may be implemented in differing order. Furthermore, the outlined steps and operations are only provided as examples, and some of the steps and operations may be optional, combined into fewer steps and operations, or expanded into additional steps and operations without detracting from the essence of the disclosed embodiments. In certain instances, the recommendation database may store identifiers or rules that identify specific computers to which a type of recommendation should be sent.

[0001] FIG. 6 illustrates a computing system that may be used to implement an

embodiment of the present invention. The computing system 600 of FIG. 6 includes one or more processors 610 and main memory 620. Main memory 620 stores, in part, instructions and data for execution by processor 610. Main memory 620 can store the executable code when in operation. The system 600 of FIG. 6 further includes a mass storage device 630, portable storage medium drive(s) 640, output devices 650, user input devices 660, a graphics display 670, peripheral devices 680, and network interface 695.

[0002] The components shown in FIG. 6 are depicted as being connected via a single bus 690. However, the components may be connected through one or more data transport means. For example, processor unit 610 and main memory 620 may be connected via a local microprocessor bus, and the mass storage device 630, peripheral device(s) 680, portable storage device 640, and display system 670 may be connected via one or more input/output (I/O) buses. [0003] Mass storage device 630, which may be implemented with a magnetic disk drive or an optical disk drive, is a non-volatile storage device for storing data and instructions for use by processor unit 610. Mass storage device 630 can store the system software for implementing embodiments of the present invention for purposes of loading that software into main memory 620.

[0004] ^' Portable storage device 640 operates in conjunction with a portable non-volatile storage medium, such as a FLASH memory, compact disk or Digital video disc, to input and output data and code to and from the computer system 600 of FIG. 6. The system software for implementing embodiments of the present invention may be stored on such a portable medium and input to the computer system 600 via the portable storage device 640.

[0005] Input devices 660 provide a portion of a user interface. Input devices 660 may include an alpha-numeric keypad, such as a keyboard, for inputting alpha-numeric and other information, or a pointing device, such as a mouse, a trackball, stylus, or cursor direction keys. Additionally, the system 600 as shown in FIG. 6 includes output devices 650. Examples of suitable output devices include speakers, printers, network interfaces, and monitors.

[0006] Display system 670 may include a liquid crystal display (LCD), a plasma display, an organic light-emitting diode (OLED) display, an electronic ink display, a projector-based display, a holographic display, or another suitable display device. Display system 670 receives textual and graphical information, and processes the information for output to the display device. The display system 670 may include multiple-touch touchscreen input capabilities, such as capacitive touch detection, resistive touch detection, surface acoustic wave touch detection, or infrared touch detection. Such touchscreen input capabilities may or may not allow for variable pressure or force detection.

[0007] Peripherals 680 may include any type of computer support device to add additional functionality to the computer system. For example, peripheral device(s) 680 may include a modem or a router.

[0008] Network interface 695 may include any form of computer interface of a computer, whether that be a wired network or a wireless interface. As such, network interface 695 may be an Ethernet network interface, a BlueTooth™ wireless interface, an

802.11 interface, or a cellular phone interface.

[0009] The components contained in the computer system 600 of FIG.6 are those typically found in computer systems that may be suitable for use with embodiments of the present invention and are intended to represent a broad category of such computer

components that are well known in the art. Thus, the computer system 600 of FIG. 6 can be a personal computer, a hand held computing device, a telephone ("smart" or otherwise), a mobile computing device, a workstation, a server (on a server rack or otherwise), a

minicomputer, a mainframe computer, a tablet computing device, a wearable device (such as a watch, a ring, a pair of glasses, or another type of jewelry/clothing/accessory ), a video game console (portable or otherwise), an e-book reader, a media player device (portable or otherwise), a vehicle-based computer, some combination thereof, or any other computing device. The computer can also include different bus configurations, networked platforms, multi-processor platforms, etc. The computer system 600 may in some cases be a virtual computer system executed by another computer system. Various operating systems can be used including Unix, Linux, Windows, Macintosh OS, Palm OS, Android, iOS, and other suitable operating systems.

[0010] The present invention may be implemented in an application that may be operable using a variety of devices. Non-transitory computer-readable storage media refer to any medium or media that participate in providing instructions to a central processing unit (CPU) for execution. Such media can take many forms, including, but not limited to, non-volatile and volatile media such as optical or magnetic disks and dynamic memory, respectively. Common forms of non-transitory computer-readable media include, for example, a floppy disk, a flexible disk, a hard disk, magnetic tape, any other magnetic medium, a CD-ROM disk, digital video disk (DVD), any other optical medium, RAM, PROM, EPROM, a FLASH EPROM, and any other memory chip or cartridge.

[0011] While various flow diagrams provided and described above may show a particular order of operations performed by certain embodiments of the invention, it should be understood that such order is exemplary (e.g., alternative embodiments can perform the operations in a different order, combine certain operations, overlap certain operations, etc.).