BR112019021298B1 - INTEGRATED SYSTEM FOR DIGITALIZED PEST CONTROL MANAGEMENT FOR A LOCATION AND METHOD TO SIMULTANEOUSLY MONITOR AND TREAT THE LOCATION AGAINST PESTS - Google Patents

Abstract

The present disclosure provides an ability to use an array of data inputs to input a network and thereby provides a real-time scalable database. The present invention is innovative in its ability to maximize the consumer interface with a pest control system, thereby enabling maximum effectiveness for current and future projects, as well as a high level of compatibility with planning-type ancillary functions, financial, regulatory.

Description

CROSS REFERENCE TO RELATED ORDERS

[0001] This application claims the benefit of Application No. US 15/485,838, filed on April 12, 2017, the contents of which are incorporated into this document by reference in its entirety.

BACKGROUND 1. Field

[0002] The present invention is a logic-based pest control management system that includes machine learning so that, in real time, optimal performance of one or more pest control platforms can be achieved. More preferably, the present invention generates and maintains a database that has machine learning capability in order to achieve optimal placement and type of pest control platforms for a location during use or even as a design of a control system. of pests before implantation. The output of this management system can optimize pest control system design, but also display machine-learned recommendations and history on a platform that is useful to business owners, pest control operators, auditors, and/or consumers.

2. Description of Related Art

[0003] Documents US4682145, US6792395, US6937156, US7395161, US7656300, US8830071 refer to pest monitoring systems and/or devices with specific consideration with the use of hardware and/or software integrations so that the presence of pests, especially rodents, can be made more readily known to the end user.

[0004] Document US4682145 mentions a pest monitoring device that is digitally linked to observe the presence of pests, especially rodents, from a central location. The '145 patent uses a connected system of detectors to transmit a unique signal to a receiver to determine if and on which detector a pest is located. Document US6792395 uses remote sensing and monitoring of a hardware and software interface to send data that is sensed (e.g., pressure, camera, humidity) via electrical signal to a computer server system; the same also includes the software interface for displaying the results of said signal. Document US6937156 is a detector and/or collector that includes a capacitance detection circuit to create a signal to be transmitted as an output to notify a likely scenario that a pest has entered a monitored area. Document US7395161 makes use of polymodal sensors to collect data on a server network for analysis. The '161 patent considers the use of a biological pest expert to examine the data with the intent of repositioning the sensors and/or collectors to improve the system. Document US7656300 refers to the digitalization of all aspects to monitor pests with the intention of automating the system as well as possible. The '300 patent aims to monitor pests, specifically rodents, by transmitting a signal from the detectors to local or remote communication servers to issue an alarm and/or logarithm recording using infrared motion and/or temperature sensors, mechanical entrapment sensors, or optical sensors to detect and communicate the presence of a rodent. Document US8830071 refers to the wireless transmission of information from each pest detector. The '071 patent uses a wireless communication circuit and a radio frequency receiver, which provides the data collector as a form of communication port to enable user interface of the compiled data.

[0005] Some published US patent applications include a description of smart data for agricultural use. For example, document US 2016/0150744 published on June 2, 2016 discloses a system for applying a pesticide to a crop, which comprises a collector and counter device that generates information of an insect quantity, and sends the quantity information of insects through a communication network. The data collection platform gathers environmental parameter information and insect quantity information through the communication network. A data analytics platform that analyzes historical monitoring data is also provided. Environmental parameter information and insect quantity information are also used to generate a control criterion; and a pesticide application control device is used to control the amount of the pesticide to be applied to the crop based on the control criteria. The '744 order thus uses information related to which pests are present in order to determine which pesticide should be applied in real time.

[0006] In another published application, document US 2015/0208636 published on July 30, 2015, a method of detecting a condition of biological activity is described, which comprises: positioning one or more polymodal sensors that detect data related to at least two conditions in at least one zone; accumulate the data in at least one data collector to generate a local knowledge base. The '636 application focuses on a slightly complex polymodal system that requires detection of at least two parameters to determine the presence of a biological activity which then, in turn, causes the system to react accordingly to treat the pest.

BRIEF SUMMARY OF THE INVENTION

[0007] In each of the prior art, the main objective is to detect the presence of a pest and notify a management system with an attempt to quickly observe where the pests are. The present invention, on the other hand, relates to the use of digital sensor signals that are communicated wirelessly over a network to a database for observation along with the ability to use this data for a wide variety of purposes; namely, the use of this data for analysis of current systems for improved pest control projects and future types and designs of pest control systems provides environmental and/or structural constraints. The immediately described technology allows for constant and autonomous improvement of current and future pest control systems. There is a need to collect and analyze data in a pest control application so that from a central location the type and number or density of pests are known, but also utilize this historical data to make more informed decisions. educated regarding placement and types of pest traps, types of pest control agent or chemical and dosage rates, and general system status. Furthermore, this machine learning infrastructure would trigger future pest control management system design by analyzing other system designs in combination with external factors (i.e., environmental conditions). The present invention uses a specific type of sensor to collect and transmit relevant data to a signal processor. This centralized data collection can then be effectively analyzed so that the system status is known and conclusions for improvement are readily understood using integrated software. The system, which uses machine learning, also optionally has the ability to optimize pest control collector operation and location placement using this system situation history data as well as external data. The object of the present invention is not only to detect and collect pests; The same search provides insight into how pest types and locations relate to system installation layout and external conditions. This will ultimately increase effectiveness and reduce costs and risks.

[0008] As an example, the present invention preferably uses a wireless alert sensor, namely vibrating switches, to detect the presence of a pest. The switch incorporates two metallic elements that are electrically charged using a small battery, creating analogue-type signaling with a small payload (i.e. 6 bytes). When a pest enters the collector, the charged metal elements connect and complete the circuit, which transmits the signal to an off-site station. In one embodiment, the collector sensor comprises one or more of the devices described in US Patent Application No. 62,443,384, filed on January 6, 2017, the contents of which are incorporated herein by reference in their entirety. . By using simple sensors, which is all that is necessary for the present invention to work, a high degree of accuracy and reliability is provided. This does not mean that more advanced sensors could optionally be used if desired for any reason. Non-limiting examples of other sensor options include: bluetooth, RFID, camera, infrared, capacitance, piezoelectric, bioimpedance, motion, and/or any possible mechanism known or hereinafter contemplated with the capability of detecting pests and transmitting the signal to an outside station. of the location.

[0009] When a pest is detected by the sensor, this signal is transmitted to a centralized computer, preferably with cloud-based networking capabilities. This enables seamless connectivity between sensor status and a central location for easier access in pest control management. The network is responsible for transmitting customized signal data to a database for analysis. Custom signal data refers to selecting only the data that is relevant for analysis. This can be sensor status, location, environmental conditions inside and outside a facility, time of day, types of pest control agents and their dosages, and any other situation that is considered useful for understanding and optimizing the control system. pest control and/or cost and risk reduction.

[0010] When the signal is transmitted via network to a remote center for analysis, the pertinent data must be displayed in a manner that is intuitive for the viewer to quickly understand the current status of the pest control system. Specifically, as an example, an interior map of the facility can identify (with the use of appropriate software) the system status can be displayed by converting sensor signals into quantitative or qualitative descriptions of how effective the pest control system is. is designed. In this way, the viewer can make recommendations to manually improve the system by moving collectors, changing agents and/or dose rates, or making temporary or permanent structural changes to the facility itself or its surrounding layout. This software also has the ability to generate reports that are useful for understanding the infestation situation which is useful for pest control operators, facility managers and auditors. Finally, this software is machine learning and fully capable of determining trend analysis and recommendations in it. Machine learning means that the highly advantageous system includes artificial intelligence (AI) that provides the system with the ability to learn without being explicitly programmed. Machine learning focuses on analyzing trends and the development of computer programs that can change when exposed to new data. The machine learning process is similar to that of data extraction, also trend analysis. That is, in accordance with the present invention, most, or even all, of the relevant data can be statistically analyzed to influence future facility layouts, geographic locations, types of collectors to use, agent types, and dose rates for use, and other elements that can be designed to reduce pest infestation. The purpose of the software is to continually optimize the pest control system and make changes to existing systems or influence the design of future systems.

[0011] Although collecting, analyzing, displaying and improving, the pest control system has intuitive benefit for reducing infestation of a current or future installation, there are greater benefits for reducing cost and risk. Optimizing the number, type and location of collectors reduces the cost of purchasing unnecessary collectors or placing collectors in ineffective locations. Understanding what type of mechanism to use to best control the potential for pests, as well as possible dosages, type of barrier or containment, or similar is complete with a system of the present invention. This ability reduces cost by ensuring the minimum quantity of the current agent (or agents) is used throughout a facility and/or the appropriate barrier or remedy is used to maximize results at any given time based on the machine learning capability of the method and system. This is applicable to improving systems already on site and knowing this data also minimizes the trial and error approach required when designing a new facility and its pest control system, which also reduces time, energy and money for the control operation. of pests.

[0012] There are health and environmental benefits to adopting the present invention. Operators are more knowledgeable about types of agents that are used and are aware that collectors need to be maintained and reduce exposure to some of the chemicals. For this same reason, the pest control system can be designed to be more environmentally friendly, which means minimizing specific chemicals released into the environment. The software also has the ability to learn and recommend changes to products used in pest control to combat physiological changes or behavioral resistance to the current system. This learning system will allow comparative analysis of performance for a given product against a given pest. Over time, by including an element of self-learning, the system can learn to propose products that are best suited to a pest in specific locations.

[0013] The machine learning database of the present invention creates a system that has the ability to be optimized across many specific accounts. A facility's layout and factors such as where pest resources (i.e., food, water, shelter) are located allow a written algorithm to determine the optimal number and pest type sensors to effectively monitor the facility. By more strategically placing sensors, the object reduces unnecessary collector costs and minimizes audit failures for inadequate monitoring of pest infestation. And, since the system is self-learning, statistical or predictive analysis can achieve more reliable assurance that pest management is optimized depending on conditions, especially to adhere to regulatory standards, thereby reducing risk sensitivity. of business.

[0014] A system of the present invention has the ability to track pesticide use at the level of individual applicators. This is beneficial for determining agent type and dosage that is effective for controlling pests; it can also adjust chemical compositions or concentrations of automatic or manual sprinklers by sending a signal to the applicators. A non-limiting example of a possible arrangement of a digital sprinkler suitable for use in combination with the present invention is disclosed in document EP 16178766.8 filed July 11, 2016, serial number US 62/360548 filed July 11, 2016 . Document EP 16178764.3 filed on July 11, 2016, serial number US 62/360,555 filed on July 11, 2016, and document PCT 2016/0255826 published on September 8, 2016, the contents of which are incorporated into this document by reference title in its entirety.

[0015] In some embodiments, the software could signal applicators, both automatic and manual, to digitally control the pesticide used and could ensure that the required amount of pesticide is used, thereby reducing costs and time. This can be accomplished either by generating a report for employees or even smart applicators for the sprinkler to be electronically or manually aware of both the type and pesticide installed. In terms of human performance, the software has the ability to track how effectively individuals are performing pest control installation and maintenance. Statistical conclusions can be drawn for time and cost for applicators to perform work related to pest control system maintenance, which is useful for managers to index or benchmark in an effort to reduce costs and risk. Managers could make employee changes, implement additional training, or manually improve the process in an effort to reduce the time to maintain the system. The data derived from the software is especially useful for statistical and qualitative analysis so that the current process can be improved and so that the implementation of new processes can be implemented with best practices in place.

[0016] The software integrates pest sensor data with external data to draw additional conclusions about the installation situation. Ambient monitors, building maps, installation sensors, and other sensors can be transmitted over the same network to the same remote computing location to be analyzed. Environmental monitors such as time, temperature, humidity, etc. can be correlated with the presence of pests, especially comparing these data with data from pest sensors. Documented operations, such as distributions with building maps, or structural layouts of specific environments, presence of resources such as food, etc. can be compared with data from other sensors to optimize the best layout of a future installation and/or the layout of the pest control system. And installation sensors such as outdoor, air flow, indoor temperatures, etc. can provide insight into how these conditions affect pest presence. All these sensors work in harmony to understand the entire building condition associated with the presence of pests, which is captured by the pest sensors. This also includes the integration of external weather and meteorological data that also provides a correlation with pest invasion prediction based on an event, series of events or conditions. The ability to use all harmonic data in a meaningful way is especially powerful for reporting. Due to a facility's current and future layout, pest sensors, environmental, installation, and times and types of operations (i.e., resource distribution), the method of pest control in place can be reported. Types, quantities, dates, times can be used to more accurately understand the situation of an installation. This is useful for billing, inventory management, improving processes, and government standard adherence (USDA, EPA, FDA, etc.). The system can automatically schedule supply orders, request maintenance employees for a specific location, alert for inconsistencies or emergency conditions, and reduce the time required to audit a facility as non-limiting examples of what is provided for by the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS

The patent or application file contains at least one drawing executed in color. Copies of this patent or patent application publication with color drawing (or drawings) will be provided by the Office upon request and payment of the necessary fee. Figures 1 to 8 represent embodiments as described herein.

DETAILED DESCRIPTION OF A PREFERRED MODALITY

[0017] Figure 1 defines a suitable flowchart that represents an embodiment of the present invention.

[0018] This management platform consists of:

[0019] Inputs, which may be from sensors, monitors, integrated devices, or other collected pest control data that can be transferred via a communication network.

[0020] Network, specifically continuous connectivity between device inputs into usable data. This is especially useful for this Internet of Things application. This seamless connectivity enables constant, autonomous detection and monitoring of all pest control and detection inputs in any location.

[0021] Database, which is maintained and optimized to display data in an approvable and usable form. This is especially useful in the previously mentioned machine learning process in order to optimize placement of pest control devices and/or systems. This is relevant both for pest control configuration validation and in predictive projects that provide similar environments, layouts, etc.

[0022] Software, which allows a user interface to display usable data to the consumer in a manner that allows the consumer to quickly make adjustments to the system, creating a feedback loop that attempts to maximize effectiveness; This, in turn, will attempt to reduce costs and risks for the consumer by creating a smarter, learnable system for pest control.

[0023] An objective of the platform is to introduce consumers to improved pest control devices and detection that enable an innovative increase in data collection and analysis. This digitized data, which is highlighted in Figure 2, is valuable to the consumer so that more knowledge is known about pest detection. The platforms serve as a product that enables augmented strategy across pesticide types, locations, dosage rates/times, and pest control device types and locations. Thus, the improved ability to understand and analyze how this digital data influences pest frequency and type allows for more thoughtful pest control design and a reduction in cost and risk to the consumer.

[0024] The value of data collection is expanded by an analytical feedback system, which has an even higher added value for the consumer. The ability to continuously monitor and change pest control systems improves the effectiveness of the systems, thereby allowing for reduced long-term pest control costs at a particular facility. Furthermore, the machine learning process can be adopted while designing a pest control system for a new facility - whereas environmental, structural and preliminary pest assumptions would also reduce the associated costs and risks while installing a pest control system. .

[0025] As an example, consider a building with insect and rodent infestation. The present invention takes into account detection monitoring and/or collectors for both insects and rodents within the structural constraints of the building. Since the system is real-time, continuous data related to the type and location of pests is output to a usable interface so that collectors can be adjusted (i.e., pest hotspots according to the room layout of a construction). The present invention also takes into consideration a compilation of this data to strategically launch a pest control system in a new construction - compare historical data and understanding of environmental conditions, structural layouts in Figure 2 to more effectively initialize a pest control system. pests with the aim of reducing costs and risks.

[0026] This data-driven, continuous improvement system has intuitive benefits for pest control and food processor consumers; It also has benefits related to auditing commercial buildings for pests. The US Food and Drug Administration and Environmental Protection Agency, for example, would have improved confidence in a working system with the emergence of the platform, which can generate reports that would indicate the location, type and number of pests, location, type and number of collectors, and also the effect of building layout, environmental impact (see Figure 2) on the type, number and location of pests. This machine learning process creates a system that will minimize pests that become undetected and/or trapped; it also allows quick analysis and display of the pest control system within a building.

[0027] A further example of an existing installation is shown, for example, in Figure 3. A representative output of the software includes a layout of a particular installation that documents the location of various sensors. The program would represent 3 environmental sensors that continuously capture time-stamped data about temperature, humidity, airflow, etc. so that the condition of different environments is understood from a central location. Installation 2 sensors represent actions within the installation that could influence the presence of pests (i.e. door openings). Several collectors are oriented within the installation layout and sensors 1 are shown in the layout so that the status of these sensors is readily available to a central location for analysis.

[0028] Continuing with the example, consider an alert on a sensor in a particular environment of an installation. In Figure 3, it is understood that there is an alert at the processing facility. The operator also has the ability to investigate this environment and, in Figure 4, the situation of the environment is quickly understood. Historical and current data is represented in a readable format and the operator can quickly see where the alert is derived. In this example, pest sensor 1.3 indicates an alert and the operator can investigate to see what triggered the alert and actions to solve the problem.

[0029] Figure 5 indicates specific sensor data related to the collector that is installed. Continuing with this example, it is clear that this collector is used as a trap and to exterminate cockroaches due to the conditions indicated in the software. The chemical agents, manufacturer, technician are displayed and a description of the alert is displayed for review. Based on the continuous learning system, automated or recommended actions are submitted to an appropriate party and the software will indicate how to improve the system to the required degree of specificity.

[0030] In connection with the present invention, an important aspect lies in the ability to predict with high clarity high and low risk areas for different levels, depending on the type of environment in which the system would be used. Examples of high-risk applications include operations where there is any potential for 3rd party audits, dealer audits, FDA inspections, pharmaceutical facilities, and the like. Possible lower risk operations include, pet food, sensitive electronics, hospital/health care, warehouse, transportation and other environments where pests are intended to be eradicated but the priority is somehow lower than in environments with adverse consequences.

[0031] According to the present invention, the algorithm will “independently” search the nature of the business operation and/or, optionally, it will be in the customer's description whether the business has a high or low risk. Then, the algorithm derives the number of required collectors or treatments and locations based on facility size, and independent factors such as the specific business, what the risk is like, whether there have been failures in the past, and the nature of such failures (deficiencies, fines , product withdrawals/recall).

[0032] Alternatively or in addition, the algorithm can search for dependent factors such as the environment (climate/humidity/population) and current pest biology/behavior of the pest. For example, the algorithm can be configured so that pest activity (i.e., a mouse) will be monitored and cataloged over time, and then the number or collectors and/or treatment locations can be defined by situational analysis. . In an area where no mice have been located in a given period of time (i.e., 12 months), there is a standard arrangement. In other areas where there was perhaps 1 mouse/12 months, then there is a +1 to the standard in that location. In still other areas where more than 1 mouse was observed in 12 months, then +2 is added to the standard.

[0033] Furthermore, when constructing a situational analysis for collector placement, the algorithm will perform a location assessment to determine a usual location definition. For example, there will be an analysis of customary features such as whether external doors exist and if so, how many, structural integrity fails in any location, spilled food, external rubbish, open water source, canteen/kitchen/break environments, handling of raw material, raw material storage, finished goods storage, etc. Microhabitats include proximity to water, food, shelter, and warmth. Each of these factors will be assigned a definition and numerical reference of importance for the algorithm to calculate and further differentiate how the placement should be performed. For each habitual resource, the algorithm will assign a number of treatment areas and/or sinks based on machine learning prioritization as data is collected over time for multiple locations.

[0034] The risk profile module will then advantageously be based on already developed choices and data that recommend a placement for high-risk business operations, low-risk business operations based on how many business failures have been observed or were expected to be observed based on your criteria (less than 1, equal to 1, or greater than 1). For a high-risk area where there is already 1 failure or 1 failure is predicted from machine learning, the algorithm may suggest 1.5 collectors per 30 meters (100 linear feet), whereas for the same business but with no failures recorded or expected, the algorithm would suggest 1.25 collectors per 30 meters (100 linear feet). If the business is low risk as illustrated above, the algorithm would suggest 1.25 collectors per 100 linear feet for areas of 1 failure or 1 predicted failure and 1.0 collectors per 30 meters (100 linear feet) for areas with no failures or no anticipated failure. These recommendations are merely illustrative, but provide a clear sense of how the inventive algorithm would work to predict a placement design and modifications thereto over time for a given operation.

[0035] In Figure 6, an overview of a system according to the present invention is shown. According to the figure, in an advantageous embodiment, the pest control platform 10 is optionally equipped with a monitor 12 to transmit a signal to a conduit communication port 14, optionally via LoRaWAN 16, a wide area network. low power. This mode of telecommunications, as previously described, can be wired or wireless; The conduit communications port 14 exists to manage the radio frequency modules 20 and/or communications 18 that are connected to the pest control platform 10. The data is then sent over the Internet to a Backend Digital Pest Management System 22, which incorporates customizable services in accordance with the present invention. The Simple Notification System (SNS) 24 allows automatic notification (i.e., email, text message, integrated mobile order push notification) of an irregularity or even specific system situation. A 26 User Management capability is optionally included and serves to add/remove/edit operators as well as preview performances. Also as shown in Figure 6, an Edge Service 28 is advantageously included to allow control of telecommunications device (or devices) to also include an Application Load Compensator (ALB) 30 to automatically direct telecommunications traffic based on network availability. network. The backend system 22 also includes a virtualization component 32 intended to optimize computing power of the system 10 as associated with the software using this information. The virtual representation of data storage includes the ability to configure whether the system uses the data on an automatic or manual basis.

[0036] The other components of the Backend Digital Pest Management System 22 enable customization of the installation 34, consumer 36, or frontend display 38. The data can also be used to create distributed chronological records 40, which could be streaming data through of any desired engine, such as Amazon Kinesis Web Service (AWS) 42. This chronological record of data 40, or even streaming data, could be used for auditing, continuous improvement, consumer reporting, or any other means of understanding complete history or even current system.

[0037] End users should ideally be presented with the data-based system situation in an easy readable format. The User Interface (UI) 44 or Representational State Transfer (REST) 46 create an advantageous interface that enables interoperability between all systems over the Internet. The display from the pest management system 10 can be effectively sent to a mobile app for backend display 48 or even to a backend web portal 50 so that administrative reporting and oversight can be quickly and readily understood by managers and/or consumers and /or contractors.

EXAMPLES

[0038] Example 1 represented in Figure 7 presents a generalized scheme that illustrates how the system is used to optimize monitoring for pest incidence.

[0039] Each account that is monitored is marked with descriptive features for a facility, such as the nature of the business, its location, the size of the facility, the type (or types) of pests considered, or the type (or types) of monitors employed. Two site-specific tests are then completed. One looks at abiotic factors that enable pest incidence in a facility, such as the number of exterior openings (e.g., doors, loading docks, windows) through which pests could travel. Another looks at biotic factors that support pest incidence within a facility, such as open food or water sources. Results of these tests are run through an algorithm (scheme) to determine the number and placement of pest monitors; for example, a monitor is placed on either side of doors that serve as entry points for pests or a monitor is located within a prescribed distance of food and water sources in which pests frequently travel. As a base number of monitor locations determined in this manner, recent history of pest activity at a facility is cross-referenced to increase the number of monitors at locations with a history record of pest activity. Finally, the user can apply one of two risk quotients to further modify the number of monitors employed when considering the record of previous pest incidents reflected in audits or historical inspections, and a more subjective quotient related to the risk tolerance for the business particular.

[0040] The previous process will define the recommended placement scheme for monitors within a facility to detect the presence of pests. Once the system is operated, and individual pest reports accumulate, the system can “learn” and further optimize pest monitor placements in response to ongoing pest activity within the facility itself or, by extraction from a “library ” of implementing monitoring in other facilities with similar businesses, facility size, location, etc. In this way, the number and placement of monitors can be optimized (increased or reduced, or repositioned) to minimize the cost of pest monitoring hardware while maintaining pest incidence within acceptable limits defined for the facility.

[0041] Example 2 depicted in Figure 8 presents a generalized scheme that illustrates how the system is employed to optimize pest management, in particular, the application of pesticide formulations to mitigate the incidence of pests in a facility.

[0042] Each account that is serviced is marked with descriptive features for a facility, such as the nature of the business, its location, the size of facility, or the type (or types) of pests encountered. In each service, the characteristics of the pesticide application event are recorded, such as on what date the pesticide was applied, in what concentration and in what volume. This pesticide application treatment event record is recorded in the database for analysis. Analyzes performed on cumulative treatment events are diverse, but any number of examples can observe some of these ideas. In one example, the database may access external databases for temperature and precipitation events at the location and these may be correlated with the frequency of treatment events to learn how time affects the persistence/effectiveness of a particular pesticide used. The system can also be configured to query multiple “libraries” that summarize government or private restrictions on when or where a particular pesticide can be used, and can send alerts to a technician (via connected app devices) to prevent unintentional violations. adversely affect the pest management firm's compliance record. A pest management firm may establish thresholds a priori, or a posteriori conducted analysis of treatment events, to flag outliers in treatment events where corrective action is required. For example, when tracking applications across all its technicians, the firm can establish limits on application volumes or even service time, as indicated by the arithmetic mean x plus or minus one standard deviation Std(x). By this means, the firm can identify employees who are applying too much pesticide or who are not spending enough time to properly maintain the facility. With this insight, the firm can direct employees to training resources to ensure compliance with service company standards or industry standard practice based on treatment analysis records for similar facilities from a wide variety of companies whose data is in the database main.

[0043] In response to an interface with optimized pest monitoring described in Example 1, the user can establish thresholds for pest incidence that signal the need for treatment in a facility by an appropriate arithmetic formula. Whenever the pest detection system (or systems) report incidences of pests above such thresholds, the optimized pest management system can generate an alert that notifies the applicator of the need for additional service at a facility. The analyzes are positioned to modify this need by service alert as follows. A particular product may be recommended if, for example, the time since the last service is less than expected.

[0044] Based on records from a single firm or a wide variety of firms, the expected duration of pest suppression after a treatment can be established, as determined by the arithmetic mean x plus or minus one standard deviation Std(X). Deviation from this threshold could be suggestive of insufficient performance of either the applicator, or the chemical, or both. There may be a certain tolerance of 67% or perhaps 90% of the ideal before triggering is performed to alert an end user.

[0045] For each chemical rate R, there is a pest suppression period x. Then, Std(x) and the mean x are determined.

[0046] Over time, pest suppression is measured, and if it falls below tolerance, the alert is determined to be appropriate.

[0047] Additionally, to prevent development of physiological resistance in a pest population to a particular pesticide, the user can establish a scheduled rotation between or among different pesticides and the analyzes will keep track of sequential use of a pesticide within a facility and recommend the next product to be used in the resistance of a management scheme. Insufficient performance outside of a normative result may also serve to alert the user to a risk for developing resistance or other conditions that reduce the effectiveness of the system as a whole.

[0048] These examples illustrate how the system can be used to regulate pesticide application events, in terms of frequency or quality, by insights from distribution data. Furthermore, through interactions with an integration for pest alerts derived from a pest monitoring system, analyzes can optionally be altered as desired to optimize pest management in a facility by minimizing the cost and risk associated with pesticide treatments while maintaining the incidence of pests within acceptable limits defined for the installation.

Claims (16)

1. Integrated system for digitalized pest control management for a location, the system CHARACTERIZED by the fact that it comprises: - a computer, or a cloud-based network, or both that are configured to receive location-specific data from a sensor wireless alert and an environment sensor, and process specific location data to create a database; - a location-specific pest control device configured to send and receive location-specific data, the pest control platform comprising a pesticide applicator, and a remote monitoring device comprising the wireless alert sensor, the sensor wireless alert configured to generate and receive specific location data; - the environmental sensor, the environmental sensor configured to collect environmental data external to the pest control platform, the environmental data comprising temperature, humidity, or air flow, or any combination thereof; - wherein: the computer, or the cloud-based network, or both are configured to use machine learning using an artificial intelligence-based algorithm that analyzes location-specific data, environmental data, historical data, and a structural layout comprising the location to generate a recommended protocol for arranging the pest control platform, the recommended protocol capable of being updated in real time, the location specific data comprises a pest type and a pest number, the location specific data and the environmental data constitutes live data, historical data comprises a past pest incident, the computer, or cloud-based network, or both is configured to predict a probability of the pest type and pest number at the location, and the system allows the display of one or more aspects of the system in a mobile application. 2. System, according to claim 1, CHARACTERIZED by the fact that the pest control platform comprises one or more pesticide applicator devices configured to connect to a network. 3. System, according to claim 1 or 2, CHARACTERIZED by the fact that the pesticide applicator comprises: - a portable device comprising one or more of the following components: - a container for holding a diluent, - a distribution port , - a feeder configured to feed the diluent toward an applicator, - a connector configured to reversibly connect a replaceable cartridge containing a concentrate to the applicator device, - a feeder configured to feed the concentrate diluent, - a control, - a replaceable cartridge comprising a connector configured to reversibly connect the cartridge to the device, and a memory unit, - a mobile computer system, and - an external computer system that is configured to mount a communications link to the applicator device control unit, the cartridge memory unit, or the mobile computer system, or any combination thereof, in order to transmit information about a spraying process that has occurred. 4. System according to any one of claims 1 to 3, CHARACTERIZED by the fact that the computer, or the cloud-based network, or both are configured to generate a list of recommended actions based on the recommended protocol to improve the system to a necessary degree of specificity and optimize a positioning and number of the remote monitoring device. 5. System, according to any one of claims 1 to 4, CHARACTERIZED by the fact that the remote monitoring device comprises: a base comprising a distal end and a proximal end, and the wireless alert sensor, the wireless alert comprising a two-mode switch comprising a first metallic element and a second metallic element, and a signal unit, wherein the first metallic element and the second metallic element are electrically separated at the distal end of the base and electrically connected to the signal unit at the proximal end of the base, thus forming an open circuit, whereby, when the first metallic element comes into contact with the second metallic element, thus forming a closed circuit, so that the signal unit signal transmits a signal to an external receiver. 6. System according to any one of claims 1 to 5, CHARACTERIZED by the fact that the computer, or the cloud-based network, or both are configured for additional use of real-time data and historical data from locations other than the location to prepare the recommended protocol. 7. System, according to any one of claims 1 to 6, CHARACTERIZED by the fact that the pest control platform monitors the presence of the pest and its identity, and data related to the presence and identity are processed by the computer, or by the cloud-based network, or both to create instructions for the pest control platform to achieve optimal performance while minimizing the impact of the pest. 8. System, according to any one of claims 1 to 7, CHARACTERIZED by the fact that the system comprises a plurality of pest control platforms comprising the pest control platform, or a plurality of environmental sensors comprising the pest control sensor. environment, or both. 9. Method for simultaneously monitoring and treating location against pests, using the system, as defined in any one of claims 1 to 8, the method CHARACTERIZED by the fact that it comprises: - receiving specific location data by the computer, or by the network cloud-based, or both pest control platform, - receive environmental data from the environmental sensor, and - generate the recommended protocol. 10. Method, according to claim 9, CHARACTERIZED by the fact that it further comprises determining a customary definition of the location for use in generating the recommended protocol. 11. Method, according to claim 9 or 10, CHARACTERIZED by the fact that it further comprises validating and implementing the recommended protocol in which the recommended protocol can be controlled actively or passively. 12. Method, according to any one of claims 9 to 11, CHARACTERIZED by the fact that it further comprises generating a report using the database identifying a recommended change in a treatment protocol, a pest species, or success of the treatment protocol. treatment over a chosen period of time, or any combination thereof. 13. Method, according to any one of claims 9 to 12, CHARACTERIZED by the fact that it further comprises predicting the level of risk. 14. Method, according to any one of claims 9 to 13, CHARACTERIZED by the fact that it comprises: inserting a risk profile for the location based on the use of the location and degree of risk tolerance; insert the structural layout, wherein the structural layout identifies a critical point comprising a food preparation area, a food storage area, a potential pest invasion storage area, a shelter area, linen storage, a damp area, a wet area, or low-lying water, or any combination thereof; determining physical environment and climate criteria of the location by user input of parameters at a data entry point; compare the critical point, the climate criterion, and the physical environment criterion with historical data; and generate a proposed treatment scheme for the location. 15. Method, according to any one of claims 9 to 14, CHARACTERIZED by the fact that it further comprises sending the display of the pest management system to the mobile application, or a web portal, or both. 16. Method, according to any one of claims 9 to 15, CHARACTERIZED by the fact that the display of the pest management system comprises representing a virtual representation of the pesticide applicator and the remote monitoring device.