Automated employee training system

Abstract

Aspects of the present disclosure relate to systems and methods for generating and providing training instructions. Specifically, aspects of the present disclosure relate to a network service that dynamically generates training instructions. The network service can generate the training instructions based on a set of inputs generated from each computing device, employees' profile information, dynamically changed working environments, and / or sensor data received from a plurality of sensors deployed at the workspace. The network service can provide potential answers, having a data range to score each answer provided by the employees. The network service can also generate the training instructions sequentially or in random order. In addition, these training instructions can be provided once or recurrently. The network service can also utilize machine learning model to automatically generate the training instructions. The network service can also score each employee's answers and store them as a portion of the employee's profile.

Description

AUTOMATED EMPLOYEE TRAINING SYSTEM

[0001] This application claims the benefit of U.S. Provisional Patent Application No. 63 / 551 ,002, titled “AUTOMATIC EMPLOYEE TRAINING SYSTEM’ filed on February 7, 2024, U.S. Provisional Patent Application No. 63 / 550,999, titled “AUTOMATED WORK INSTRUCTION GENERATING SYSTEM’ filed on February 7, 2024, and U.S. Provisional Patent Application No. 63 / 550,991, titled “AUTOMATED RUN-TIME WORKFLOW ASSIGNMENT SYSTEM’ filed on February 7, 2024 which are hereby incorporated by references in their entireties.BACKGROUND

[0002] Generally described, business administrators can manage workflow resources to operate the business more efficiently. The workflow resources can generally refer to human resources. Specifically, managing the workflow resources can include providing written instructions to individual employees and training the employees according to training instructions. For example, in the context of security monitoring embodiments, a security patrol service provider, such as the business administrator, may develop an overall patrol strategy according to contract parameters and client preference. The business administrator can then delegate responsibilities to patrol officers to implement the patrol strategy. The service provider could manage the patrol officers by providing one or more instructions to each officer during the execution of their duties and also one or more training to each officer based on the instructions provided for each officer.

[0003] As also generally described, computing devices and communication networks can be utilized to exchange data and / or information. In a common application, a computing device can request content from another computing device via the communication network. For example, a computing device can collect various data and utilize a software application to exchange content with a server computing device via the network (e.g., the Internet). Such software applications can include general communication applications for accessing the network, such as browser applications. Such general communication applicationscan access functionality provided by network-based services. The software applications can also include custom or specialized software applications configured to implement specific functionality alone or in combination with network-based services.BRIEF DESCRIPTION OF THE DRAWINGS

[0004] This disclosure is described herein with reference to drawings of certain embodiments, which are intended to illustrate, but not to limit, the present disclosure. It is to be understood that the accompanying drawings, which are incorporated in and constitute a part of this specification, are for the purpose of illustrating concepts disclosed herein and may not be to scale.

[0005] FIG. 1 depicts a block diagram of a system that includes one or more computing devices, sensors, and a network service provider according to one or more embodiments as disclosed herein;

[0006] FIG. 2 is a block diagram of illustrative components of a network service provider according to one or more embodiments as disclosed herein;

[0007] FIG. 3 is an illustrative interaction of generating and providing training instructions that can be utilized in the aspects of an automated training service in one or more embodiments as disclosed herein;

[0008] FIG. 4 is a flow diagram illustrative of a routine for training employees by generating training instructions utilizing the network service provider;

[0009] FIG. 5 depicts a block diagram of a system that includes one or more computing devices, sensors, and a network service provider according to one or more embodiments as disclosed herein;

[0010] FIG. 6 is a block diagram of illustrative components of a network service provider according to one or more embodiments as disclosed herein;

[0011] FIG. 7 is an illustrative interaction of generating instructions that can be utilized in the aspects of workflow monitoring service in one or more embodiments as disclosed herein; and

[0012] FIG. 8 is a flow diagram illustrative of a routine for generating instructions utilizing the network service provider;

[0013] FIG. 9 depicts a block diagram of a system that includes one or more computing devices, managing devices, and an automated run-time workflow assignment system according to one or more embodiments as disclosed herein;

[0014] FIG. 10 is a block diagram of illustrative components of a workflow generation module according to one or more embodiments as disclosed herein;

[0015] FIGs. 11 A and 1 IB are illustrative interactions of workflow generation that can be utilized in the aspects of the workflow assignment in accordance with one or more embodiments as disclosed herein; and

[0016] FIGs. 12A and 12B are flow diagrams illustrative of workflow generation routines utilizing the automated run-time workflow assignment system in accordance with one or more embodiments as disclosed herein.DETAILED DESCRIPTION

[0017] In the following description, various examples will be described. For purposes of explanation, specific configurations, and details are set forth in order to provide a thorough understanding of the examples. However, it will also be apparent to one skilled in the art that the examples may be practiced without specific details. Furthermore, well-known features may be omitted or simplified in order not to obscure the examples being described.Generating Training Instructions

[0018] Generally described, aspects of the present disclosure relate to systems and methods for dynamically generating instructions as part of the execution of workflows. Specifically, aspects of the present disclosure relate to a network service that dynamically generates instructions for individuals (or sets of individuals) and provides the determined instructions prior to, or as part, execution of duties. The network service can determine the instructions based on a master plan and personal profile (e.g., personal attributes) for each employee. The network service can also generate instructions for each employee based on environmental inputs while executing workflow (e.g., execution of one or more tasks). For example, the network service can utilize sensor data received from a plurality of sensorsdeployed at the workspace. In some illustrations, a security service provider may generate a master plan based on their security patrol contracts. Based on this master plan, one or more patrol officers can be assigned for each patrol shift. In these illustrations, the security service provider can generate training instructions based on the assigned duty of each patrol officer. The security service provider can also further utilize the personal profile of each patrol officer to modify or add more training instructions. In addition, a plurality of sensors, such as motion detection sensors, audio record sensors, cameras, etc., can be deployed in the security patrol areas. In this example, the security service provider can receive the information generated from each sensor and process the received information to modify or add additional training instructions. In various embodiments, the security service provider may provide these training instructions to each security patrol officer via wireless communication to a mobile device, visual indications broadcast to the security patrol officer, audible instructions broadcast to the security patrol officer, and the like.

[0019] Illustratively, one or more aspects of the present application correspond to implementation in computer networks in which a plurality of computing devices has been configured in a manner that these computing devices exchange information with a network service provider via the computer networks, such as the wireless network. By way of illustrative example, the plurality of computing devices can correspond to electronic devices utilized by employees who are executing their duties. For example, the employee can utilize their computing device to receive training instructions from the network service provider and also to provide information, such as any reports, while executing their duty. In some examples, such computing devices can provide their current location information to the network service provider in real time or near real time. In some illustrated examples, the computing device can be configured to implement one or more functionalities to facilitate the employees’ performance of their duties. For example, the computing device can be utilized by a security patrol officer, and the officer can utilize the camera functions of the computing device to scan the patrol area. Also, the officer can utilize the communication functions of the computing device to communicate with other patrol officers, supervisors, and the network service provider. These functions can be implemented based on specific applications, and the present disclosure does not limit any type of functionality.

[0020] In accordance with one or more implementations, a plurality of sensors or one or more sensors can be deployed within the workspace. The sensors can, in some embodiments, correspond to stand-alone devices or components that are configured (at least in part) specifically to provide information. For example, a stand-alone temperature sensor configured to measure, collect or generative information regarding environmental conditions. In other embodiments, the sensors can correspond to integrated or combination devices that may be utilized to generate sensor data but may have additional or alternative functionality not specifically configured to provide information. For example, a heating unit that may utilize temperature-based controls for operation and that operational information can be processed to generate environmental condition information. The types of deployed sensors can be determined based on the types of tasks executed in a workflow. In some illustrative embodiments, each of the plurality of sensors may transmit data that is received by the network service provider. The network service provider can process the received data by analyzing attributes included in the data. For example, motion sensors, temperature sensors, and noise sensors can be implemented in a security patrol area, and the network service provider can receive data from these sensors in real time. In this example, the network service provider can process the received data and generate or modify the training instructions. For instance, the network service provider may determine unexpected movement or noise at a patrol area, and the network service provider can generate instructions, such as a question that “what is a protocol when you detect an unexpected person in this patrol area?” After the patrol officer provides a correct answer, the network service provider can allow the security officer to perform the duty.

[0021] In accordance with one or more aspects of the present disclosure, the network service provider can implement one or more machine learned models. Illustratively, machine learned models can be configured to generate output in the form of instructions by monitoring data received from the plurality of sensors and / or the computing devices. For example, a machine learned model can be trained to generate instructions for the employees to perform their duties more efficiently. By way of illustration, the machine learned model can incorporate one or more aspects of a large language model (LLM) in which outputs generated can correspond to structured outputs, such as text, images, and a combination thereof. Specifically, in some embodiments, machine learned models can be configured to generatetraining instructions by curating data related to the duties and personal profile of each employee. The machine learned models may generate the training instructions and provide weight for each training instruction. For example, the machine learned models may weight each training instruction based on the priority of the instructions.

[0022] In some embodiments, the machine learned models can modify the training instructions based on the profile information of each employee and / or the working environments. For example, the machine learned models can modify or add additional training instructions based on the profile information of each employee. The profile of the employee can relate to each employee’s attribute for performing the duty and can include but are not limited to rank (and associated duty), skills, performance history when executing the duty, previous evaluation data, training history of the employees, and the like. In some embodiments, the machine learned models can modify the training instructions based on the profile information of the working environment of each employee. The working environment can include one or more attributes related to the working environment. These attributes can include but are not limited to assigned duties in the environment, required skills, and the like. In some examples, these attributes can be updated by processing data received from various sensors deployed in the workplace. For example, a patrol service provider can receive sensor data from the sensors deployed in the target patrol areas, and the machine learned models utilized by the patrol service provider can generate the training data based on the processing results of the sensor data.

[0023] In general, traditionally, an employer provides training instructions to employees before the employees execute their duties to ensure that the employees know the orders of their duties. These instructions are provided manually, such that the training instructions are provided based on the required duties for each employee. For instance, the employer can have a database that includes training data determined based on employees’ duties. Illustratively, when the duties are assigned to the employees, training instructions can be provided to each employee. The employee may complete the training instructions prior to executing their duties. However, in this conventional system for manually providing the training instructions, these training instructions were already created based on the required employees’ duties. For example, a patrol service provider may generate the training instructions based on required patrol service requirements for each targeted patrol area. In thisexample, the generated instructions can be provided to the patrol officers assigned to the targeted patrol area. Thus, the training instructions are static and cannot be dynamically updated. This limitation can lead to inefficiencies and constraints in training the officers. For example, a security patrol officer might receive a static training instruction generated based only on the required patrol service. However, if the environment of the targeted patrol area is dynamically changed, such that one of the sensors deployed in the targeted patrol area detected a broken window at the base of the building, the current officer would still receive the same training instructions (e.g., general training instruction) to perform the patrol duty. Thus, the patrol officer may not receive training instruction related to a scenario that identified the broken window. This can lead to inefficiencies by not receiving the training instruction adapted to the dynamically changed environment. In addition, the traditional training instructions are provided to the employees regardless of each employee’s skills. For example, a security officer certified for the use of a firearm and other patrol officers who are not certified for use of the firearm may receive the same training instructions. These can result in management inefficiencies for the security service provider. Moreover, it might be challenging for the security service provider’s management to monitor whether each security officer has diligently completed the training instructions.

[0024] To address at least a portion of the deficiencies described above, one or more aspects of the present disclosure relate to systems and methods for providing training instructions by dynamically adapting to the current environment and also each employee’s attributes. Specifically, these systems and methods can dynamically generate training instructions based on each employee’s required duty, profile (e.g., attributes), and working environment profile (e.g., working environment attributes). In some embodiments, the training instructions are generated by utilizing data generated from computing devices and / or one or more sensors associated with the work environment. Illustratively, a network service provider can implement an automated training service. According to one or more embodiments, as disclosed herein, the automated training service may dynamically generate training instructions and provide the generated training instructions to each employee prior to the employees initiating their duty.

[0025] In various embodiments, the automated training service can monitor whether the employees are prepared to initiate their work duties. In some cases, the automatedtraining service can receive input from the computing device utilized by each employee, where the input indicates that the employee is willing to initiate work duty. In some examples, the employee, by utilizing the computing device, can initiate check in (e.g., clock in) function, and the automated training service can receive the initiated check in from the computing device.

[0026] In some embodiments, the automated training service can monitor the location of the employees and determine whether the employees are within the physical range of performing their assigned duties and prepared for performing the duties. For example, the automated training service implemented by a security patrol service provider may monitor the location of the security patrol officers and determine whether these officers are within a post associated with their patrol duty. In some examples, the automated training service can automatically determine the training instructions in response to determining that the patrol officers are within a range of their assigned patrol area. For example, the automated training service may transmit the instructions to the computing device utilized by the individual patrol officer.

[0027] In some embodiments, the automated training service provides the training instructions as questions based on various scenarios (or campaigns) related to the duties. For example, the automated training service can determine questions based on security patrol orders for each post and one or more scenarios related to the patrol service. In various examples, the patrol officer may answer these training instructions (e.g., questions) prior to initiating their patrol duties. In some cases, the automated training service provides the training scenarios with acceptable answers (or a range of acceptable answers). In some examples, these training scenarios can be provided in a certain sequence or randomly. In some cases, these training scenarios can be provided once or recurrently.

[0028] In various examples, the automated training service may analyze an employee’s workflow and generate training instructions by identifying the employee’s required duty. The automated training service can further process these generated training instructions based on the employee’s profile. The profile can include attributes related to the employee, such as rank (and associated duty), skills, performance history when executing the duty, previous evaluation data, training history of the employees, and the like. For example, the training instructions are modified based on the rank of the employee and / or the skills of the employee. Furthermore, the training instructions can be modified based on historicalperformance or evaluation records of the employee. For instance, if the employee, a security patrol officer, previously did not perform a specific duty (or did not meet established service levels), the training instructions can be tailored to this scenario. In another example, if the patrol officer has a special skill, such as a specification of using a type of gun, the training instruction can be related to this special skill. Thus, the automated training service can modify or generate additional training instructions based on an individual employee’s profile or attributes, and the present disclosure does not limit these attributes.

[0029] In some embodiments, the automated training service can generate the training instructions by dynamically adapting to the current working environment. The working environment can include one or more attributes related to the working environment. These attributes can include but are not limited to assigned duties in the environment, required skills, and the like. For example, if a previous patrol officer reported an incident where a broken window was found on a post, the automated training service may generate instructions related to the required patrol protocol in the incident that found a broken window to the next patrol officer assigned to the post.

[0030] In some embodiments, the automated training service may dynamically generate the training instructions by analyzing the workflow related environments in real time or near real time. For example, the automated training service (e.g., implemented by a security patrol service provider) can receive data from one or more sensors deployed in the physical environment. Illustratively, sensors, such as motion sensors, temperature sensors, smoke detectors, humidity sensors, light sensors, noise sensors, occupancy sensors, pressure sensors, etc., can be deployed within a security patrol area. The automated training service may identify one or more events that indicate abnormalities of the one or more data received from these sensors. For example, the noise level detected by the noise sensor is higher than the normal range. In these examples, the automated training service can generate training instructions prior to the patrol officer initiating patrolling the posts. In this example, the patrol officer can be trained by resoling one or more questions generated as the training instructions, thus, the patrol officer can be trained on what the officer needs to do in order to resolve any issue related to the detected abnormalities in the patrol posts. In some cases, a machine learning or artificial intelligence (ML / AI) component can be utilized to generate the training instructions or scenarios automatically. In addition, the ML / AI component can generate additional scenariosupon determining that the employee needs to perform instructions regarding the additional scenarios before performing duty. For example, if the employee’s answer regarding the initial scenarios did not meet the threshold score, the ML / Al component may generate additional training scenarios.

[0031] In some embodiments, the automated training service can include various criteria in providing the training instructions. The criteria can be based on the priority of each instruction provided to the employee. For example, if patrol related instructions include 10 questions to be answered by the employee, each question can have a different weight based on the priority. For example, if a broken window is previously reported in a post area, a question related to the patrol protocol of post-action after discovering the broken window may have a higher weight. In some cases, the patrol officer may not be able to initiate their patrol service until the officer fully training the instructions with the weight above a threshold. In some cases, the automated training service can score each employee’s performance on taking the training scenarios and store the score in the database as profile information for the employee.

[0032] In accordance with one or more aspects of the present disclosure, the automated training service can implement a machine learned model to generate the training instructions by analyzing various data related to the workflow, individual employee’s profile, and / or the dynamically changing working environment. For example, the machine learned model may analyze the current working environment and generate additional training instructions and / or modify existing training instructions. In some embodiments, the machine learned model can be utilized to analyze individual employee’s performance of the duty and update the training instructions. For example, as a patrol officer receives the training instructions, the next training instructions can be automatically updated based on the employee’s level of skill. In addition, the automated training service can provide training instruction in various aspects. For example, the automated training service can generate a training question in various aspects, thus, the employee may need to provide answers in various training instructions that based on the same scenario.

[0033] Although aspects of the present disclosure will be described with regard to illustrative network components, interactions, and routines, one skilled in the relevant art will appreciate that one or more aspects of the present disclosure may be implemented in accordance with various environments, system architectures, customer computing devicearchitectures, and the like. Similarly, references to specific devices, such as a customer computing device, can be considered to be general references and not intended to provide additional meaning or configurations for individual customer computing devices. Additionally, the examples are intended to be illustrative in nature and should not be construed as limiting. For the purpose of description, FIGs. 1-4 are directed to the aspects of generating training instructions, as disclosed herein.

[0034] FIG. 1 depicts a block diagram of an embodiment of the system 100. The system 100 can include a network 104, the network connecting a plurality of computing devices 102, and the network service provider 110. The system 100 can also include a network 106, the network connecting a number of sensors 120, and network service provider 110. Illustratively, the various aspects associated with the network service provider 110 can be implemented as one or more components that are associated with one or more functions or services. The components may correspond to software modules implemented or executed by one or more customer computing devices, which may be separate stand-alone customer computing devices. Accordingly, the components of the network service provider 110 should be considered as a logical representation of the service, not requiring any specific implementation on one or more customer computing devices.

[0035] Networks 104, 106 as depicted in FIG. 1, can connect the network service provider 110 and the computing devices 120 and the sensors 120, respectively. The networks 104, 106 can comprise any combination of wired and / or wireless networks, such as one or more direct communication channels, local area networks, wide area network, personal area network, and / or the Internet, for example. In some embodiments, the communication between the network service provider 110 and the computing devices 102 and / or the sensors 120 may be performed via a short-range communication protocol, such as Bluetooth, Bluetooth low energy (“BLE”), and / or near field communications (“NFC”).

[0036] In some embodiments, the networks 104, 106 may be a private or semiprivate network, such as a corporate or university intranet. The networks 104, 106 may include one or more wireless networks, such as a Global System for Mobile Communications (GSM) network, a Code Division Multiple Access (CDMA) network, a Long Term Evolution (LTE) network, or any other type of wireless network. The networks 104, 106 can use protocols and components for communicating via the Internet or any of the other aforementioned types ofnetworks. For example, the protocols used by the networks 104, 106 may include Hypertext Transfer Protocol (HTTP), HTTP Secure (HTTPS), Message Queue Telemetry Transport (MQTT), Constrained Application Protocol (CoAP), and the like. Protocols and components for communicating via the Internet or any of the other aforementioned types of communication networks are well known to those skilled in the art and, thus, are not described in more detail herein.

[0037] The types of network 104 and network 106 can be the same type of network or different types of network. These types can be determined based on specific applications, and the present disclosure does not limit these types of networks.

[0038] As described in FIG. 1, the network service provider 110 can be communicatively coupled with the computing devices 102 via the network 104. The network service provider 110 can connect any number of computing devices 102. Each computing device 102 can be utilized by an employee and configured to provide work related information. For example, if the network service provider 110 is adapted for the security patrol service provider, the employee can be the patrol officer. In some embodiments, the computing devices 102 can be any computing device such as a desktop, laptop or tablet computer, personal computer, tablet computer, wearable computer, personal digital assistant (PDA), hybrid PDA / mobile phone, mobile phone, smartphone, voice command device, digital media player, and the like. In some embodiments, the computing devices 102 may execute an application (e.g., a browser, a stand-alone application, etc.) that allows a user (e.g., an employee) to access interactive user interfaces, view images, analyses, or aggregated data, and / or the like as described herein. In various embodiments, users (e.g., employees) may interact with the network service provider via various devices. Such interactions may typically be accomplished via interactive graphical user interfaces or voice commands, however, alternatively, such interactions may be accomplished via command line and / or other means.

[0039] In certain instances, the computing device 102 can offer a graphical interface equipped with features designed to display training instructions received from the network service provider 110. For example, the patrol officer can utilize the graphical interface to receive the training instructions and perform the training by reporting any feedback in response to the training instructions. The present disclosure does not limit the functionality types of graphical interfaces, and the types can be determined based on specific applications.

[0040] As described in FIG. 1, the network service provider 110 can be communicatively coupled with the sensors 120 via the network 106. The network service provider 110 can connect any number of sensors 120. The present disclosure does not limit the types of sensors, and the types can be determined based on specific applications. For example, the types of sensors utilized for security patrol can include but are not limited to temperature sensors, proximity sensors, light sensors, motion sensors, gas sensors, image sensors, radar sensors, etc.

[0041] In some embodiments, any suitable type and number of sensors 120 can be deployed in working areas. For example, each security post can include one or more types of sensors 102, where the types and number of sensors can be determined based on the characteristics of the security post.

[0042] The network service provider 110, as shown in FIG. 1, can include an automated training service 114 and database 150. The automated training service 114 can be configured to generate training instructions based on individual employee profiles and workflow and dynamically changing working environment. The workflow can generally refer to an employee’s duty. For instance, the workflow of a patrol officer may encompass their shift timing and the specific responsibilities tied to their patrol duties.

[0043] In some embodiments, the automated training service 114 can provide training instructions to the employees. The training instructions can be work related training instructions, and the employees, prior to executing their job duties, can receive the training instructions from the automated training service 114. In various examples, the automated training service 114 can generate the training instructions by processing data received from the employee’s computing device. For example, when an employee check in (or clock in) to initiate executing the employee’s duty, the automated training service 114 can be triggered to generate the training instructions. In some embodiments, the training instructions can be dynamically generated based on the workflow for each employee.

[0044] In various examples, the automated training service 114 can modify or generate additional training environments by processing individual employee’s profiles. The profile can include attributes related to the employee, such as rank (and associated duty), skills, performance history when executing the duty, previous evaluation data, training history of the employees, and the like. For example, the training instructions are modified based on the rankof the employee and / or the skills of the employee. Furthermore, the training instructions can be modified based on historical performance or evaluation records of the employee. For instance, if the employee, a security patrol officer, did not satisfy performance criteria for a specific duty, the training instructions can be tailored to this scenario. In another example, if the patrol officer has a special skill, such as a specification of using a type of gun, the training instruction can be related to this special skill. In some embodiments, the automated training service can generate the training instructions by dynamically adapting to the current working environment. The working environment can include one or more attributes related to the working environment. These attributes can include but are not limited to assigned duties in the environment, required skills, and the like. For example, if a previous patrol officer reported an incident where a broken window is found at a post, the automated training service may generate instructions related to the required patrol protocol in the incident that found a broken window.

[0045] In certain examples, the automated training service 114 can filter the generated training instructions by using various criteria. For example, each generated training instruction can include weight based on the priority of each instruction, and the automated training service 114 can filter these instructions based on the weight value. In some examples, the criteria can be based on one or more attributes of the employee. For instance, the criteria can be associated with the employee’s previous performance, such that if the employee made a mistake previously, the criteria can be related to the previous mistake, and thus, the employee can be trained to prevent by repeating the same mistake. This criterion can be determined based on the attributes of the employee, and the present disclosure does not limit the criteria to any specific type.

[0046] The network service provider 110 can also include a database 150. The database 150 can store information related to the profile of each employee, workflow, historical attributes of each employee and the working environment, and the like. The database 150 can include any data structure (and / or combinations of multiple data structures) for storing and / or organizing data, including, but not limited to, relational databases (e.g., Oracle databases, PostgreSQL databases, etc.), non-relational databases (e.g., NoSQL databases, etc.), inmemory databases, spreadsheets, comma separated values (CSV) files, extensible markup language (XML) files, TeXT (TXT) files, flat files, spreadsheet files, and / or any other widely used or proprietary format for data storage. Databases are typically stored in one or more datastores. Accordingly, each database referred to herein (e.g., in the description herein and / or the figures of the present application) is to be understood as being stored in one or more data stores. Additionally, although the present disclosure may show or describe data as being stored in combined or separate databases, in various embodiments, such data may be combined and / or separated in any appropriate way into one or more databases, one or more tables of one or more databases, etc.

[0047] The embodiment of the system 100 is merely provided as example purposes, and the present disclosure does not limited to this embodiment. Furthermore, one or more component of the system 100 can be removed or added based on specific applications. For example, the sensors 120 can be deleted in some embodiments.

[0048] FIG. 2 depicts one embodiment of the architecture of an illustrative automated training service 114. The automated training service 114 can be configured to generate training instructions. More specifically, the automated training service 114 can provide instructions to employees in prior to initiating the duty in a dynamically changing environment. The general architecture of the automated training service 114 depicted in FIG. 2 includes an arrangement of computer hardware and software components that may be used to implement aspects of the present disclosure. As illustrated, the automated training service 114 includes a processing unit 202, a network interface 204, a computer-readable medium drive 206, and an input / output device interface 208, all of which may communicate with one another by way of a communication bus. The components of the automated training service 114 may be physical hardware components or implemented in a virtualized environment.

[0049] The network interface 204 may provide connectivity to one or more networks, such as the networks 104 and 106 of FIG. 1. The processing unit 202 may thus receive information and instructions from other computing systems or services via a network. The processing unit 202 may also communicate to and from memory 210 and further provide output information for an optional display via the input / output device interface 208. In some embodiments, the automated training service 114 may include more (or fewer) components than those shown in FIG. 2.

[0050] The memory 210 may include computer program instructions that the processing unit 202 executes in order to implement one or more embodiments. The memory 210 generally includes RAM, ROM, or other persistent or non-transitory memory.The memory 210 may store an operating system 214 that provides computer program instructions for use by the processing unit 202 in the general administration and operation of the automated training service 114. The memory 210 may further include computer program instructions and other information for implementing aspects of the present disclosure. For example, in one embodiment, the memory 210 includes interface software 212 for communicating with other components or services and performing one or more aspects as disclosed herein.

[0051] The memory 210 may include a machine learning component 216. The machine learning component 216 can be configured to analyze data and generate dynamic instructions in accordance with one or more embodiments as disclosed herein. In some embodiments, a number of different types of algorithms may be used by the machine learning component 216 to generate the models. For example, certain embodiments herein may use a logistical regression model, decision trees, random forests, convolutional neural networks, deep networks, or others. However, other models are possible, such as a linear regression model, a discrete choice model, or a generalized linear model. The machine learning algorithms can be configured to adaptively develop and update the models over time based on new input received by the machine learning component 216. For example, the models can be regenerated on a periodic basis as new human physical characteristics or bio information is available to help keep the predictions in the model more accurate as the information evolves over time. In some cases, the machine learning component 216 can be utilized to generate the training instructions or scenarios automatically. In addition, the machine learning component 216 can generate additional scenarios upon determining that the employee needs to perform instructions regarding the additional scenarios before performing duty. For example, if the employee’s answer regarding the initial scenarios did not meet the threshold score, the machine learning component 216 may generate additional training scenarios.

[0052] Some non-limiting examples of machine learning algorithms that can be used to generate and update the parameter functions or prediction models can include supervised and non-supervised machine learning algorithms, including regression algorithms (such as, for example, Ordinary Least Squares Regression), instance-based algorithms (such as, for example, Learning Vector Quantization), decision tree algorithms (such as, for example, classification and regression trees), Bayesian algorithms (such as, for example, Naive Bayes),clustering algorithms (such as, for example, k-means clustering), association rule learning algorithms (such as, for example, Apriori algorithms), artificial neural network algorithms (such as, for example, Perceptron), deep learning algorithms (such as, for example, Deep Boltzmann Machine), dimensionality reduction algorithms (such as, for example, Principal Component Analysis), ensemble algorithms (such as, for example, Stacked Generalization), and / or other machine learning algorithms. These machine learning algorithms may include any type of machine learning algorithm, including hierarchical clustering algorithms and cluster analysis algorithms, such as a k-means algorithm. In some cases, the performing of the machine learning algorithms may include the use of an artificial neural network. By using machinelearning techniques, large amounts (such as terabytes or petabytes) of player interaction data may be analyzed to generate models.

[0053] The memory 210 may include a machine learning component 216. The machine learning component 216 can be configured to analyze data and generate dynamic training instructions in accordance with one or more embodiments, as disclosed herein. In some embodiments, a number of different types of algorithms may be used by the machine learning component 216 to generate the models. For example, certain embodiments herein may use a logistical regression model, decision trees, random forests, convolutional neural networks, deep networks, or others. However, other models are possible, such as a linear regression model, a discrete choice model, or a generalized linear model. The machine learning algorithms can be configured to adaptively develop and update the models over time based on new input received by the machine learning component 216. For example, the models can be regenerated on a periodic basis as new human physical characteristics or bio information is available to help keep the predictions in the model more accurate as the information evolves over time.

[0054] Some non-limiting examples of machine learning algorithms that can be used to generate and update the parameter functions or prediction models can include supervised and non-supervised machine learning algorithms, including regression algorithms (such as, for example, Ordinary Least Squares Regression), instance-based algorithms (such as, for example, Learning Vector Quantization), decision tree algorithms (such as, for example, classification and regression trees), Bayesian algorithms (such as, for example, Naive Bayes), clustering algorithms (such as, for example, k-means clustering), association rule learningalgorithms (such as, for example, Apriori algorithms), artificial neural network algorithms (such as, for example, Perceptron), deep learning algorithms (such as, for example, Deep Boltzmann Machine), dimensionality reduction algorithms (such as, for example, Principal Component Analysis), ensemble algorithms (such as, for example, Stacked Generalization), and / or other machine learning algorithms. These machine learning algorithms may include any type of machine learning algorithm, including hierarchical clustering algorithms and cluster analysis algorithms, such as a k-means algorithm. In some cases, the performing of the machine learning algorithms may include the use of an artificial neural network. By using machinelearning techniques, large amounts (such as terabytes or petabytes) of player interaction data may be analyzed to generate models.

[0055] The memory 210 may include a monitoring component 218. The monitoring component 218 can be configured to monitor the employees to determine whether the employees are prepared to initiate their work duty. In some examples, within a threshold time period before initiating the work, the training instruction can be provided to the employees. For example, this training instruction can be provided to the patrol officer when the officer indicates the readiness of initiating working and / or enters a post.

[0056] In some cases, the computing devices 102 utilized by employees can provide an input that the employees are prepared to initiate working. For example, the computing device 102 may equipped with a functionality that the employee can indicate their readiness to initiate working, such as via selection of check in (or clock in time). These indications can be provided in the computing devices 102 with various graphical representation, and the present disclosure does not limit these types of representations.

[0057] In some embodiments, the computing devices 102 can be equipped with a location tracking system, such as GPS module, and the monitoring component 218 can periodically or continuously receive the location information of the computing devices 102. In these embodiments, the monitoring component 218 can detect that the physical location of the computing device 102 is within proximity to the working area. In addition, the monitoring component 218 can determine whether the employee is prepared to initiate working based on the location of the computing device associated with the employee and the workflow information (e.g., assigned duty) of the employee. For example, if the employee’s workflow indicates that the employee is scheduled to initiate work at 8:00am at location A, themonitoring component 218 automatically determines that the employee is prepared work when the location of the employee’s computing device is indicating in proximity to the location A at or after 8:00AM.

[0058] In various embodiments, the monitoring component 218 can also authenticate the employee’s computing device 102. In some cases, the monitoring component 218 can provide an authentication token, such as an application program interface (API) token to each computing device 102. For example, each computing device 102 may include a unique identifier associated with its token, and the monitoring component 218 can verify these API token identifiers to authenticate the computing device 102. Once, the monitoring component 218 authenticate the computing device 102 by verifying the token, the computing device 102 and the monitoring component 218 can be communicatively coupled.

[0059] The memory 210 can further include an input processing component 220. The input processing component 220 can be configured to analyze input data received from the computing devices 102 and the sensors 120.

[0060] In some embodiments, the input processing component 220 processes the required work requirements for each employee to determine workflows (or duty) associated each employee. In some cases, the workflows can be identified based on a master plan. For example, the master plan of a security patrol service provider can be provided as the hierarchical data. The hierarchical data can include various levels, such that the highest level of the data structure can be a building, the lower layer can be floors, the lower layer can be rooms within the floors, and the lowest layer can be the posts in each room. The master plan may include assigned one or more required workflow for each level of the hierarchical data structure. For example, at the highest level, the master plan may include assigned attributes of the types of patrol areas, required security level, patrol time, etc. In the lowest level of the hierarchical data, such as posts, each post can be associated with the required patrol attributes for each post, such as the number of patrol officials, patrol time, the required capability of the patrol official, and the like. In these embodiments, the workflows can be generated based on the required duty assigned to each post. In some examples, the workflows can be provided in accordance with the shift schedule of patrol officers.

[0061] In some embodiments, the input processing component 220 can receive inputs from computing devices 102. In some examples, the input processing component 220can receive profile information of the employee associated with the computing device 102. In some examples, the profile information corresponds to the employee’s attributes, such as rank (and associated duty), skills, performance history when executing the duty, previous evaluation data, training history of the employees, and the like.

[0062] In some embodiments, the input processing component 220 can receive additional inputs from working environment information stored in the database 150. The working environment can include one or more attributes related to the working environment. These attributes can include but are not limited to assigned duties in the environment, required skills, and the like. In some examples, these attributes can be updated by processing data received from various sensors deployed in the workplace. For example, a patrol service provider can receive sensor data from the sensors deployed in the target patrol areas, and the machine learned models utilized by the patrol service provider can generate the training data based on the processing results of the sensor data.

[0063] The memory 210 can also include training instructions generating component 222. In some embodiments, the training instructions generating component 222 can generate the training instructions based on the workflows of each employee. In various examples, the training instructions generating component 222 can generate a plurality of training instructions associated with the workflow. In these examples, the training instructions generating component 222 can utilize the machine learning component 216 to generate the plurality of training instructions. For example, the machine learning component 216 by utilizing its machine learned models can generate the training instructions in a plurality of scenarios. For instance, the machine learning component 216 utilized by a security patrol service provider can determine the plurality of scenarios associated with the workflow and generate the training instructions based on these scenarios. The generated plurality of training instructions can be stored in the database 150 of the network service provider 110.

[0064] In some embodiments, the training instructions generating component 222 can prioritize the generated instructions based on priority. For example, each training instruction can have its weight that represents the level of the priority. In these embodiments, the training instructions generating component 222 can provide the one or more training instructions to the employee via the computing device by filtering the generated training instructions based on the priority criteria. Further, in these embodiments, the weight of eachtraining instruction can be dynamically changed based on the current working environment and / or employee’s profile. In some cases, the training instructions generating component 222 provides the training scenarios with acceptable answers (or a range of acceptable answers). In some examples, these training scenarios can be provided in a certain sequence or randomly. In some cases, these training scenarios can be provided once or recurrently.

[0065] In various embodiments, the training instructions generating component 222 can further process the generated training instructions based on employee’s profile information. In some examples, the profile information corresponds to the employee’s attributes, such as rank (and associated duty), skills, performance history when executing the duty, previous evaluation data, training history of the employees, and the like. This profile information is stored in the database 150 and constantly updated. For example, the employee’s evaluation data can be constantly updated as the new evaluation data are generated. Furthermore, the employee’s rank can be updated as the employee is promoted.

[0066] In some cases, the training instructions can be updated based on these employee’s profile information. For example, in accordance with the employee’s level of experience or skills, the training instructions can be provided with variance to each employee. In addition, each weight of the training instruction can be varied based on the employee’s profile information. Thus, the training instructions generating component 222 can provide customized (or updated) training instructions to each employee by dynamically adapting its instructions based on each employee’s profile.

[0067] In various examples, the training instructions generating component 222 can further update the training instructions based on the working environment information. For example, if a previous security patrol officer discovered a broken window at a post area, the instructions on the post area can be updated to train the following patrol officer in a scenario of discovering broken windows. In this example, the priority related to the scenario that discovering the broken windows can have a higher weight (e.g., higher priority). Thus, the training instructions generating component 222 can dynamically update its training instructions based on the current working environments.

[0068] In some examples, the training instructions generating component 222 can provide the training instructions to the employee by further filtering the generated training instructions based on the workflows. For example, the training instructions generatingcomponent 222 can filter the training instructions by utilizing one or more criteria defined based on one or more attributes of the employee’s profile. For example, the training instructions generating component 222 can filter the training instructions based on employee’s level of experience and / or skills. In addition, the training instructions generating component 222 can also filter the training instructions based on one or more attributes defined from the working environment. For example, if a previous employee reported an incident, then the training instructions generating component 222 can filter the training instructions to identify instructions related to the reported incident.

[0069] In addition, the training instructions generating component 222 can modify or update the generated training instructions when one or more workflows are changed. For example, if the workflows are related to the security patrol service and that the workflows are changed due to the updated security patrol service contract (e.g., updated security patrol requirements), the training instructions generating component 222 can automatically update the existing training instructions.

[0070] In some embodiments, to ensure the training of the employee, the training instructions generating component 222 can provide a same type of training instructions in various scenarios. Thus, the knowledge of the employee can be ensured by answering the same type of training instructions in these scenarios.

[0071] The memory 210 can further include a post training analysis component 224. In various examples, the training instructions generated at the training instructions generating component 222 can be provided as the questionnaire. For example, when the employee is prepared to initiate work, as determined by monitoring component 218, the training instructions generating component 222 can automatically generate the questions (as the training instructions) and provide these questions to the employee by displaying the questions on the display of the computing device. The present disclosure does not limit the number of questions.

[0072] In some embodiments, the post training analysis component 224 can receive the answers to these questions and verify whether the employee can initiate the work. In some examples, the post training analysis component 224 can verify based on threshold number of correct answers. In some embodiments, the post training analysis component 224 can only verify if the answer(s) are correct. For example, the employee might be required to correctlyanswer those questions associated with high priority training instructions (weight of the instructions). In some examples, the post training analysis component 224 can provide further additional instructions if the employee was not verified. In some cases, the post training analysis component 224 can score each employee’s performance on taking the training scenarios and store the score in the database as profile information for the employee.

[0073] Turning now to FIG. 3, illustrative interactions of the components of the system 100, as shown in FIG. 1, will be described. For purposes of the illustration, it can be assumed that the network service provider 110 has been configured in a manner that implements the automated training service 114. For the purpose of description, FIG 3 can be described with respect to a security patrol service provider. The present application is not intended to be limited to any particular type of service or the number of individual services that may be accessed or generate processing results as part of the execution of an application.

[0074] With reference to FIG. 3, an illustrative interaction of generating processing results that can be utilized in the aspects of automated training service and / or generating instructions will be described. The interaction is illustrative.

[0075] At (1), the automated training service 114 monitors employees to determine whether the employees are prepared to initiate work. The automated training service 114 can be configured to monitor the employees to determine whether they are prepared to initiate their work duties. In some examples, within a threshold time period before initiating the work, the training instruction can be provided to the employees. For example, this training instruction can be provided to the patrol officer when the officer indicates the readiness to initiate working and / or enters a post.

[0076] In some cases, the computing devices 102 utilized by employees can provide an input that the employees are prepared to initiate working. For example, the computing device 102 may equipped with a functionality that the employee can indicate their readiness to initiate working, such as via selection of check in (or clock in time). Such indications can be provided in the computing devices 102 with various graphical representation, and the present disclosure does not limit these types of the representations.

[0077] In some embodiments, the computing devices 102 can be equipped with a location tracking system, such as GPS module, and the automated training service 114 can periodically or continuously receive the location information of the computing devices 102. Inthese embodiments, the automated training service 114 can detect that the physical location of the computing device 102 is within proximity to the working area. In addition, the automated training service 114 can determine whether the employee is prepared to initiate working based on the location of the computing device associated with the employee and the workflow information (e.g., assigned duty) of the employee. For example, if the employee’s workflow indicates that the employee is scheduled to initiate work at 8: 00 am at location A, the automated training service 114 automatically determines that the employee is prepared work when the location of the employee’s computing device is indicating in proximity to the location A at or after 8:00 am.

[0078] In various embodiments, the automated training service 114 can also authenticate the employee’s computing device 102. In some cases, the automated training service 114 can provide an authentication token, such as an application program interface (API) token to each computing device 102. For example, each computing device 102 may include a unique identifier associated with its token, and the automated training service 114 can verify these API token identifiers to authenticate the computing device 102. Once, the automated training service 114 authenticates the computing device 102 by verifying the token, the computing device 102 and the automated training service 114 can be communicatively coupled.

[0079] At (2), the automated training service 114 obtains inputs (e.g., or a set of inputs) from one or more computing devices 102 and processes the obtained inputs. The inputs (e.g., the set of inputs) can include geometry identifiers and time identifiers associated with each of the one or more computing devices. In some examples, the automated training service 114 can receive inputs related to the workflows. For example, the master plan of a security patrol service provider can be provided as hierarchical data. The hierarchical data can include various levels, such that the highest level of the data structure can be a building, the lower layer can be floors, the lower layer can be rooms within the floors, and the lowest layer can be the posts in each room. The master plan may include assigned one or more required workflows for each level of the hierarchical data structure. For example, at the highest level, the master plan may include assigned attributes of the types of patrol areas, required security level, patrol time, etc. In the last level of the hierarchical data, such as posts, each post can be associated with the required patrol attributes for each post, such as the number of patrol officials, patrol time, therequired capability of the patrol official, and the like. In these embodiments, the instruction can be generated based on the workflow assigned to each post. In some examples, the instruction is provided in accordance with the shift schedule of patrol officers. For example, within a threshold time period before initiating the patrol, the instruction can be provided to the patrol officers. In some examples, this instruction can be provided to the patrol officer when the officer enters a post.

[0080] In some examples, the inputs can be obtained from various sensors. For example, various types of sensors can be deployed in workspace, such that, in non-limiting examples, temperature sensors, proximity sensors, light sensors, motion sensors, gas sensors, image sensors, radar sensors, etc., can be deployed for security patrol service provider.

[0081] In some embodiments, the automated training service 114 can receive inputs from computing devices 102. In some examples, the automated training service 114 can receive profile information of the employee associated with the computing device 102. In some examples, the profile information corresponds to the employee’s attributes, such as rank (and associated duty), skills, performance history when executing the duty, previous evaluation data, training history of the employees, and the like.

[0082] In some embodiments, the automated training service 114 can receive additional inputs from working environment information stored in the database 150. The working environment can include one or more attributes related to the working environment. These attributes can include but are not limited to assigned duties in the environment, required skills, and the like. In some examples, these attributes can be updated by processing data received various sensors deployed in the workplace. For example, a patrol service provider can receive sensor data from the sensors deployed in the target patrol areas, and the machine learned models utilized by the patrol service provider can generate the training data based on the processing results of the sensor data.

[0083] In some embodiments, the automated training service 114 obtains a set of additional inputs from a database 150. In some examples, the set of additional inputs includes a set of target areas, and each of the target areas can include one or more sub-areas. The additional inputs may be encoded in an array of values, which can be transmitted via various interfaces.

[0084] At (3), the automated training service 114 generates training instructions. In various examples, the training instructions can be provided as questionnaire. For example, when the employee is prepared to initiate work, the automated training service 114 can automatically generate the questions (as the training instructions in accordance with one or more embodiments disclosed herein) and provide these questions to the employee by displaying the questions on the display of the computing device. The present disclosure does not limit the number of questions.

[0085] In some embodiments, the automated training service 114 can generate training instructions based on the workflows of each employee. In various examples, the automated training service 114 can generate a plurality of training instructions associated with the workflow. In these examples, the automated training service 114 can utilize the machine learning component 216 to generate the plurality of training instructions. For example, the machine learning component 216, by utilizing its machine learned models, can generate the training instructions in a plurality of scenarios. For instance, the machine learning component 216 utilized by a security patrol service provider can determine the plurality of scenarios associated with the workflow and generate the training instructions based on these scenarios. The generated plurality of training instructions can be stored in the database 150 of the network service provider 110.

[0086] In some embodiments, the automated training service 114 can prioritize the generated instructions based on priority. For example, each training instruction can have its weight that represents the level of the priority. In these embodiments, the automated training service 114 can provide the one or more training instructions to the employee via the computing device by filtering the generated training instructions based on the priority criteria. Further, in these embodiments, the weight of each training instruction can be dynamically changed based on the current working environment and / or employee’s profile.

[0087] In various embodiments, the automated training service 114 can further process the generated training instructions based on employee’s profile information. In some examples, the profile information corresponds to the employee’s attributes, such as rank (and associated duty), skills, performance history when executing the duty, previous evaluation data, training history of the employees, and the like. This profile information is stored in the database 150 and constantly updated. For example, the employee’s evaluation data can beconstantly updated as the new evaluation data are generated. Furthermore, the employee’s rank can be updated as the employee is promoted.

[0088] In some cases, the training instructions can be updated based on these employee’s profile information. For example, in accordance with the employee’s level of experience or skills, the training instructions can be provided with variance to each employee. In addition, each weight of the training instruction can be varied based on the employee’s profile information. Thus, the automated training service 114 can provide customized (or updated) training instructions to each employee by dynamically adapting its instructions based on each employee’s profile.

[0089] In various examples, the automated training service 114 can further update the training instructions based on the working environment information. For example, if a previous security patrol officer discovered broken window at a post area, the instructions on the post area can be updated to train the following patrol officer in a scenario of discovering broken windows. In this example, the priority related to the scenario that discovering the broken windows can have a higher weight (e.g., higher priority). Thus, the automated training service 114 can dynamically update its training instructions based on the current working environments.

[0090] In some examples, the automated training service 114 can provide training instructions to the employee by further filtering the generated training instructions based on the workflows. For example, the automated training service 114 can filter the training instructions by utilizing one or more criteria defined based on one or more attributes of the employee’s profile. For example, the automated training service 114 can filter the training instructions based on the employee’s level of experience and / or skills. In addition, the automated training service 114 can also filter the training instructions based on one or more attributes defined from the working environment. For example, if a previous employee reported an incident, then the automated training service 114 can filter the training instructions to identify instructions related to the reported incident.

[0091] In addition, the automated training service 114 can modify or update the generated training instructions when one or more workflows are changed. For example, if the workflows are related to the security patrol service and that the workflows are changed due tothe updated security patrol service contract (e.g., updated security patrol requirements), the automated training service 114 can automatically update the existing training instructions.

[0092] In some embodiments, to ensure the training of the employee, the automated training service 114 can provide the same type of training instructions in various scenarios. Thus, the knowledge of the employee can be ensured by answering the same type of training instructions in these scenarios. In some cases, the automated training service 114 can utilize ML / AI component to generate the training instructions or scenarios automatically. In addition, the automated training service 114 can generate additional scenarios upon determining that the employee needs to perform instructions regarding the additional scenarios before performing duty. For example, if the employee’s answer regarding the initial scenarios did not meet the threshold score, the automated training service 114 may generate additional training scenarios.

[0093] At (4), the automated training service 114 transmits the generated training instructions to the computing device 102. In some examples, these instructions can be displayed on the computing device. At (5), the automated training service 114 receives the answers to these questions, where the answers are provided by the employee associated with the computing device 102.

[0094] At (6), the automated training service 114 analyzes the obtained answers to verify whether the employee can initiate the work. In some examples, the automated training service 114 can verify based on the threshold number of correct answers. In some embodiments, the automated training service 114 can only verify if the answer(s) are correct. For example, the employee might be required to correctly answer those questions associated with high priority training instructions (weight of the instructions). In some examples, the automated training service 114 can provide further additional instructions if the employee was not verified. In some cases, the automated training service 114 can score each employee’s performance on taking the training scenarios and store the score in the database as profile information for the employee.

[0095] Turning now to FIG. 4, An employee training routine 400 based on various aspects, as disclosed in the present disclosure, will be described. For the purpose of illustration, the network service provider 110 described in FIG. 4 is implemented by a security patrol service provider.

[0096] At block 402, the automated training service 114 determines whether the employees are prepared to initiate work. The automated training service 114 can be configured to monitor the employees to determine whether they are prepared to initiate their work duties. In some examples, within a threshold time period before initiating the work, the training instruction can be provided to the employees. For example, this training instruction can be provided to the patrol officer when the officer indicates the readiness to initiate working and / or enter a post.

[0097] In some cases, the computing devices 102 utilized by employees can provide an input that the employees are prepared to initiate working. For example, the computing device 102 may equipped with a functionality that the employee can indicate their readiness to initiate working, such as via selection of check in (or clock in time). These indication can be provided in the computing devices 102 with various graphical representations, and the present disclosure does not limit these types of representations.

[0098] In some embodiments, the computing devices 102 can be equipped with a location tracking system, such as GPS module, and the automated training service 114 can periodically or continuously receive the location information of the computing devices 102. In these embodiments, the automated training service 114 can detect that the physical location of the computing device 102 is within proximity to the working area. In addition, the automated training service 114 can determine whether the employee is prepared to initiate working based on the location of the computing device associated with the employee and the workflow information (e.g., assigned duty) of the employee. For example, if the employee’s workflow indicates that the employee is scheduled to initiate work at 8: 00 am at location A, the automated training service 114 automatically determines that the employee is prepared for work when the location of the employee’s computing device is indicating in proximity to the location A at or after 8:00 am.

[0099] In various embodiments, the automated training service 114 can also authenticate the employee’s computing device 102. In some cases, the automated training service 114 can provide an authentication token, such as an application program interface (API) token to each computing device 102. For example, each computing device 102 may include a unique identifier associated with its token, and the automated training service 114 can verify these API token identifiers to authenticate the computing device 102. Once, theautomated training service 114 authenticates the computing device 102 by verifying the token, the computing device 102 and the automated training service 114 can be communicatively coupled.

[0100] At block 404, the automated training service 114 obtains a set of inputs. In some embodiments, the automated training service 114 obtains the set of inputs from one or more computing devices 102. In some examples, the set of inputs includes geometry identifiers and time identifiers of each of the plurality of computing devices. In some examples, the automated training service 114 can receive inputs related to the workflows. For example, the master plan of a security patrol service provider can be provided as hierarchical data. The hierarchical data can include various levels, such that the highest level of the data structure can be a building, the lower layer can be floors, the lower layer can be rooms within the floors, and the lowest layer can be the posts in each room. The master plan may include assigned one or more required workflow for each level of the hierarchical data structure. For example, at the highest level, the master plan may include assigned attributes of the types of patrol areas, required security level, patrol time, etc. In the lost level of the hierarchical data, such as posts, each post can be associated with the required patrol attributes for each post, such as the number of patrol officials, patrol time, the required capability of the patrol official, and the like. In these embodiments, the instruction can be generated based on the workflow assigned to each post. In some examples, the instruction is provided in accordance with shift schedule of patrol officers. For example, within a threshold time period before initiating the patrol, the instruction can be provided to the patrol officers. In some examples, this instruction can be provided to the patrol officer when the officer enters a post.

[0101] In some examples, the inputs can be obtained from various sensors. For example, various types of sensors can be deployed at workspace, such that, in non-limiting examples, temperature sensors, proximity sensors, light sensors, motion sensors, gas sensors, image sensors, radar sensors, etc., can be deployed for security patrol service provider.

[0102] In some embodiments, the automated training service 114 can receive inputs from computing devices 102. In some examples, the automated training service 114 can receive profile information of the employee associated with the computing device 102. In some examples, the profile information corresponds to the employee’s attributes, such as rank (andassociated duty), skills, performance history when executing the duty, previous evaluation data, training history of the employees, and the like.

[0103] At block 406, the automated training service 114 can receive additional inputs from working environment information stored in the database 150. The working environment can include one or more attributes related to the working environment. These attributes can include but are not limited to assigned duties in the environment, required skills, and the like. In some examples, these attributes can be updated by processing data received from various sensors deployed in the workplace. For example, a patrol service provider can receive sensor data from the sensors deployed in the target patrol areas, and the machine learned models utilized by the patrol service provider can generate the training data based on the processing results of the sensor data. In some examples, the set of additional inputs includes a set of target areas, and each target area includes one or more sub-areas.

[0104] At block 408, the automated training service 114 generates one or more workflows for each of the plurality of sub-areas. In some examples, each workflow of the one or more workflows includes attributes comprising time data and location data associated with corresponding sub-area. In some examples, the attribute of each workflow includes a set of hierarchical data, and the hierarchical data include a plurality of layers, where each layer associated with one or more assigned manifests. In some cases, the location data of the workflows include patrol areas such that a top level of the hierarchical data is a master plan for patrolling the patrol areas, having a plurality of posts, and a lower level of the hierarchical data is a patrolling plan of each post of the plurality of posts. The patrolling plan can include a number of demanded employees and demanded time duration for patrolling corresponding post. In some examples, the attributes of the workflow can further include demanded duty and skills of employee to perform the master plan for patrolling corresponding post.

[0105] In some examples, the machine learning component 216 (shown in FIG. 2) can include a neural network model. The neural network model is configured to dynamically update the workflows. In some examples, the neural network model is configured to collect a set of sensor data from a plurality of sensors operatively coupled with the automated training service, apply the collected set of sensor data to the workflows to the neural network model, and generate updated workflows as results of the application of the collected set of sensor data to the workflows. In some cases, the neural network model is further configured to create atraining set comprising the workflows, the collected set of sensor data, and the updated workflows such that the neural network model is continuously trained by using the training set. The machine learning component 216 can also be configured to dynamically generate the training instructions by utilizing the created training set. In some cases, the set of sensor data includes temperature sensors, object detection sensors, gas sensors, image sensors, and radar sensors.

[0106] In some embodiments, the machine learning component 216 is configured to generate a plurality of training scenarios by modifying one or more sensor data of the collected set of sensor data, applying the modified one or more sensor data to the neural network model, and generating the plurality of training scenarios based on the modified one or more sensor data and results of applying the modified one or more sensor data.

[0107] At block 410, the automated training service 114 generates filtering criteria for each workflow. In some examples, the filtering criteria can include time data and location data such that the time data and location data of each workflow can be filtered by utilizing the filtering criteria, such as the time and location data of the filtering criteria.

[0108] At block 412. the automated training service 114 filter the set of inputs of each workflow based on the filtering criteria. For example, the geometry identifiers and the time identifiers of the plurality of computing devices are filtered based on the time data and the location data, respectively, of the criteria such that each sub-area is associated with one or more workflows, where each workflow of the one or more workflows is associated with identifications of computing devices, corresponding to the filtered set of inputs.

[0109] At block 414, the automated training service 114 generates training instructions. In various examples, the training instructions can be provided as the questionnaire. For example, when the employee is prepared to initiate work, the automated training service 114 can automatically generate the questions (as the training instructions in accordance with one or more embodiments disclosed herein) and provide these questions to the employee by displaying the questions on the display of the computing device. The present disclosure does not limit the number of questions.

[0110] In some embodiments, the automated training service 114 generates training instructions by obtaining a set of manifests associated with each workflow from the database150. For example, the database is configured to store a plurality of workflows and sets of manifests associated with each workflow.

[0111] In some embodiments, the automated training service 114 can generate training instructions based on the workflows of each employee. In various examples, the automated training service 114 can generate a plurality of training instructions associated with the workflow. In these examples, the automated training service 114 can utilize the machine learning component 216 to generate the plurality of training instructions. For example, the machine learning component 216 by utilizing its machine learned models can generate the training instructions in a plurality of scenarios. For instance, the machine learning component 216 utilized by a security patrol service provider can determine the plurality of scenarios associated with the workflow and generate the training instructions based on these scenarios. The generated plurality of training instructions can be stored in the database 150 of the network service provider 110.

[0112] In some embodiments, the automated training service 114 can prioritize the generated instructions based on priority. For example, each training instruction can have its weight that represent the level of the priority. In these embodiments, the automated training service 114 can provide the one or more training instructions to the employee via the computing device by filtering the generated training instructions based on the priority criteria. Further in these embodiments, the weight of each training instruction can be dynamically changed based on the current working environment and / or employee’s profile.

[0113] In various embodiments, the automated training service 114 can further process the generated training instructions based on employee’s profile information. In some examples, the profile information corresponds to the employee’s attributes, such as rank (and associated duty), skills, performance history when executing the duty, previous evaluation data, training history of the employees, and the like. This profile information is stored in the database 150 and constantly updated. For example, the employee’s evaluation data can be constantly updated as new evaluation data are generated. Furthermore, the employee’s rank can be updated as the employee is promoted.

[0114] In some cases, the training instructions can be updated based on these employee’s profile information. For example, in accordance with the employee’s level of experience or skills, the training instructions can be provided with variance to each employee.In addition, each weight of the training instruction can be varied based on the employee’s profile information. Thus, the automated training service 114 can provide customized (or updated) training instructions to each employee by dynamically adapting its instructions based on each employee’s profile.

[0115] In various examples, the automated training service 114 can further update the training instructions based on the working environment information. For example, if a previous security patrol officer discovered a broken window at a post area, the instructions on the post area can be updated to train the following patrol officer in a scenario of discovering broken windows. In this example, the priority related to the scenario that discovering the broken windows can have a higher weight (e.g., higher priority). Thus, the automated training service 114 can dynamically update its training instructions based on the current working environments.

[0116] In some examples, the automated training service 114 can provide the training instructions to the employee by further filtering the generated training instructions based on the workflows. For example, the automated training service 114 can filter the training instructions by utilizing one or more criteria defined based on one or more attributes of the employee’s profile. For example, the automated training service 114 can filter the training instructions based on employee’s level of experience and / or skills. In addition, the automated training service 114 can also filter the training instructions based on one or more attributes defined from the working environment. For example, if a previous employee reported an incident, then the automated training service 114 can filter the training instructions to identify instructions related to the reported incident.

[0117] In addition, the automated training service 114 can modify or update the generated training instructions when one or more workflows are changed. For example, if the workflows are related to the security patrol service and that the workflows are changed due to the updated security patrol service contract (e.g., updated security patrol requirements), the automated training service 114 can automatically update the existing training instructions.

[0118] In some embodiments, to ensure the training of the employee, the automated training service 114 can provide the same type of training instructions in various scenarios. Thus, the knowledge of the employee can be ensured by answering the same type of training instructions in these scenarios.

[0119] In some cases, the automated training service 114 can utilize ML / AI component to generate the training instructions or scenarios automatically. In addition, the automated training service 114 can generate additional scenarios upon determining that the employee needs to perform instructions regarding the additional scenarios before performing duty. For example, if the employee’s answer regarding the initial scenarios did not meet the threshold score, the automated training service 114 may generate additional training scenarios.

[0120] At block 416, the automated training service 114 transmits the generated training instructions to the computing device 102. For example, the automated training service 114 transmits, for each workflow, the generated training instructions associated with each workflow to corresponding computing device such that the corresponding computing device can have the identifications associated with the workflow. In some examples, these instructions can be displayed on the computing device.

[0121] At block 418, the automated training service 114 receives the answers to these questions, where the answers are provided by the employee associated with the computing device 102. In some cases, the automated training service 114 provides the training scenarios with acceptable answers (or a range of acceptable answers). In some examples, these training scenarios can be provided in a certain sequence or randomly. In some cases, these training scenarios can be provided once or recurrently.

[0122] At block 420, the automated training service 114 analyzes the obtained answers to verify whether the employee can initiate the work. In some examples, the automated training service 114 can verify based on the threshold number of correct answers. In some embodiments, the automated training service 114 can only verify if the answer(s) are correct. For example, the employee might be required to correctly answer those questions associated with high priority training instructions (weight of the instructions). In some examples, the automated training service 114 can provide further additional instructions if the employee was not verified. In some cases, the automated training service 114 can score each employee’s performance on taking the training scenarios and store the score in the database as profile information for the employee. The routine 400 is ended at block 422. Although the operations of the routine 400 are described in a particular order, it should be understood that the routine 400 is not limited as such. Operations of the routine 400 may be performed in an alternativeorder, serially, or at least partially in parallel. Further, certain operations may not need to be performed.Automated Workflow Instruction Generating System

[0123] Generally described, aspects of the present disclosure relate to systems and methods for providing instructions (e.g., work instructions) to employees. Specifically, aspects of the present disclosure relate to a network service that dynamically determines instructions for each employee and provides the determined instructions to the employees while executing their duties. The network service can determine the instructions based on a master plan and sensor data received from a plurality of sensors deployed at the workspace. For example, a security service provider may generate a master plan based on performance metrics, service level agreements (SLAs) associated with individual security patrol contracts. Based on this master plan, one or more patrol officers can be assigned for each patrol shift. In addition, a plurality of sensors, such as motion detection sensors, audio record sensors, cameras, etc., can be deployed in the security patrol areas. In this example, the security service provider can receive the information generated from each sensor and process the received information to generate security patrol instructions in real-time or near real-time. In addition, the security service provider may provide the instructions to each security patrol via wireless communication.

[0124] Illustratively, one or more aspects of the present application correspond to implementation in computer networks in which a plurality of computing devices has been configured in a manner that these computing devices exchange information with a network service provider via the computer networks, such as the wireless network. By way of illustrative example, the plurality of computing devices can correspond to electronic devices utilized by employees who are executing their duties. For example, the employee can utilize their computing device to receive instructions from the network service provider and also to provide information, such as any reports, while executing their duty. In some examples, such computing devices can provide their current location information to the network service provider in real time or near real time. In some illustrated examples, the computing device can be configured to implement one or more functionalities to facilitate the employees’ performance of their duties. For example, the computing device can be utilized by a security patrol officer, and the officer can utilize the camera functions of the computing device to scanthe patrol area. Also, the officer can utilize the communication functions of the computing device to communicate with other patrol officers, supervisors, and the network service provider. These functions can be implemented based on specific applications, and the present disclosure does not limit any type of functionality.

[0125] In accordance with one or more implementations, a plurality of sensors or one or more sensors can be deployed within the workspace. These sensors can include any type of information gathering or generating device or component, including but are not limited to. motion sensors, temperature sensors, smoke detectors, humidity sensors, light sensors, noise sensors, occupancy sensors, pressure sensors, etc. The sensors can, in some embodiments, correspond to stand-alone devices or components that are configured (at least in part) specifically to provide information. For example, a stand-alone temperature sensor configured to measure, collect or generative information regarding environmental conditions. In other embodiments, the sensors can correspond to integrated or combination devices that may be utilized to generate sensor data but may have additional or alternative functionality not specifically configured to provide information. For example, a heating unit that may utilize temperature-based controls for operation and that operational information can be processed to generate environmental condition information. The types of the deployed sensors can be determined based on the types of tasks assigned in a workflow. In some illustrative embodiments, each of the plurality of sensors may transmit data (wirelessly or wired) that is received by the network service provider. The network service provider can process the received data by analyzing attributes included in the data. For example, motion sensors, temperature sensors, and noise sensors can be implemented in a defined geographic region (e.g., a security patrol area), and the network service provider can receive data from these sensors in real time. In this example, the network service provider can process the received data and detect any abnormalities. For instance, the network service provider may determine the abnormality by detecting an expected movement or noise at a patrol area during nighttime. After detecting these abnormalities, the network service provider may automatically generate instructions to the duty patrol officers to visually check the patrol area.

[0126] In some cases, the network service provider, upon analyzing the sensor data, can provide notification to various entities, such as business operation administrators, managing officers, on-duty employees, and the like. In some examples, the network serviceprovider can automatically determine and apply one or more corrective actions in addition to providing the notifications. For example, in the context of the network service provider used for a security patrol service, the network service provider may detect abnormalities in certain patrol areas by obtaining and analyzing the sensors. In this example, the network service provider may automatically notify the on-duty patrol officer(s), their supervisors, managing officers, a property owner of the security patrol areas, and the like. Additionally, the network service provider automatically identifies and applies correct actions. For example, if the network service provider determines high temperature by receiving data from a temperature sensor, the network service provider may automatically enable a sprinkler and / or contact the fire department. In some cases, the network service provider may determine whether any action was taken regarding the detected abnormalities. For example, if the network service provider detects a high temperature in a patrol area and no action is taken, the network service provider may notify the managing officer(s), headquarters personnel of the security service provider, and the like. The present disclosure does not limit the types of notifications.

[0127] In accordance with one or more aspects of the present disclosure, the network service provider can implement one or more machine learned models as part of the processing of information to generate processing results. Illustratively, machine learned models can be configured to generate output in the form of instructions by monitoring data received from the plurality of sensors and / or the computing devices. For example, a machine learned model can be trained to generate instructions for the employees to perform their duties more efficiently. By way of illustration, the machine learned model can incorporate one or more aspects of a large language model (LLM) in which outputs generated can correspond to structured outputs, such as text, images, and a combination thereof. In some examples, the machine learned models can be configured to analyze the data received from the plurality of sensors and detect one or more abnormalities among the data. For example, the machine learned model can determine unexpected noise levels compared to the occupancy of a security patrol area and generate instructions in accordance with the determination.

[0128] In some aspects of the present disclosure, the machine learned model can also receive visual information as inputs. Illustratively, the computing devices utilized by the employees and / or cameras installed within a workspace area can scan the surrounding area and transmit the captured images (e.g., videos) to the network service provider. To process thecaptured image according to the machine learned model(s), one or more machine learned models may utilize various types of image processing techniques to modify the input data, such as by identifying a region of interest from the captured image associated with one or more objects within the image. In other embodiments, the machine learned models may be optimized in a manner such that regions of interest data from data inputs may also be preferred for processing. For example, if the machine learned model is configured to monitor the security patrol areas by detecting features that indicate a likelihood of abnormalities within the patrol areas, the machine learning model may detect objects in the areas and analyze whether these objects are risk objects. For example, the machine learned model may score risk score for each detected object. Additionally, the machine learned model may further verify its risk score by generating confidence values. In some embodiments, the machine learned model can be continuously trained based on a threshold confidence of example outputs corresponding to the trained model being used to identify the abnormalities within the workspace areas. For example, the training can be based on the ground truth level of the machine learned model.

[0129] In general, traditional networks that provide instructions to employees rely on providing instructions via tag scanning (e.g., NFC tag) and / or quick response (QR) code scanning. For instance, an employee, such as a security patrol officer, can use a computing device to scan a tag or QR code. The network service provider embeds relevant instructions associated with these tags and QR codes. As such, scanning the tag or code delivers these embedded instructions to the computing device. However, in these conventional networks, the instructions linked to the tag and QR code are static and cannot be dynamically updated. This limitation can lead to inefficiencies and constraints in carrying out the officer’s duties. For example, a security patrol officer might receive a static instruction like checking a particular patrol post. However, if a previous officer already reported a broken window at the base of the building and completed a security check, the current officer would still receive the same instruction to check the same post, potentially leading to a redundant security check. Additionally, when these two officers compile their daily reports, they might include identical information about the first patrol post, leading to redundancy. This can result in management inefficiencies for the security service provider. Moreover, it might be challenging for the security service provider’s management to monitor whether the security officer has diligently carried out the instructions.

[0130] To address at least a portion of the deficiencies described above, one or more aspects of the present disclosure relate to systems and methods for generating instructions by dynamically adapting to the current environment. Specifically, these systems and methods can generate instructions in real time or near real time in dynamically changing environments by utilizing data generated from computing devices and one or more sensors associated with the work environment. Illustratively, a network service provider can implement a workflow monitoring service. According to one or more embodiments, as disclosed herein, the workflow monitoring service may dynamically generate instructions and provide the generated instructions to each employee.

[0131] In various embodiments, the workflow monitoring service can monitor the location of the employees and determine whether the employees are within the physical range of performing their assigned duties. For example, the workflow monitoring service implemented by a security patrol service provider may monitor the location of the security patrol officers and determine whether these officers are within a post associated with their patrol duty. In some examples, the workflow monitoring service can automatically transmit patrol instructions in response to determining that the patrol officers are within a range of their assigned patrol area. For example, the workflow monitoring service may transmit the instructions to the computing device utilized by the individual patrol officer.

[0132] In some embodiments, the workflow monitoring service may analyze the workflow related environments in real time or near real time. For example, the workflow monitoring service (e.g., implemented by a security patrol service provider) can receive data from one or more sensors deployed in the physical environment. Illustratively, sensors, such as motion sensors, temperature sensors, smoke detectors, humidity sensors, light sensors, noise sensors, occupancy sensors, pressure sensors, etc., can be deployed within a security patrol area. The workflow monitoring service may identify one or more events that indicate abnormalities of the one or more data received from these sensors. For example, the noise level detected by the noise sensor is higher than the normal range. In these examples, the workflow monitoring service can automatically generate instructions to the corresponding patrol officers and transmit the automatically generated instructions to the officers. In some examples, the workflow monitoring service can be configured to receive from the sensors associated with the current location of the employee. For example, when a patrol officer walks into a certain post,the sensors associated with the post can automatically generate sensor data and transmit to the workflow monitoring service.

[0133] In accordance with one or more aspects of the present disclosure, the workflow monitoring service can implement a machine learned model to analyze the data generated by the one or more sensors. For example, the machine learned model may analyze noise captured by the noise sensor and determine whether a patrol officer should be deployed to check the post area associated with the noise. In some embodiments, the machine learned model can be utilized to analyze captured images and generate instructions based on the analyzed results. For example, a patrol officer may scan the surrounding area by utilizing the officer’s computing device (e.g., the camera of the computing device) and transmit the scanned images to the workflow monitoring service. The machine learned model may identify one or more objects included in each captured image and generate an output corresponding to a risk score for each object. The risk score output is illustratively a characterization of risk based on the machine learned model training set, reward / penalty model, or a combination thereof. In response to determining that the risk score associated with one or more objects is at or higher than a threshold, the machine learned model may generate an instruction to visually monitor the corresponding area. The machine learned model can also perform retraining its model by using the ground truth level for each anticipated risk score. For example, the machine learned model may verify each risk score by designating with confidence value based on the ground truth level. The machine learned model may perform this retraining continuously. In some cases, the machine learned model may store the images of the identified object or person in the database with the confidence value. Thus, the machine learned model, upon detecting the object or person from the received image, may automatically determine the risk score. The machine learned model can also perform the person’s behavior analysis based on the video (e.g., images) captured by the computing device and / or the sensors.

[0134] In some cases, the workflow monitoring service can generate dynamic instructions based on the employee’s profile. For example, the patrol officers within a post can receive different types of instructions based on each officer’s level of experience. For instance, if the patrol officer is a junior officer, the instruction could be “contact a supervisor and report the incident.” If the patrol officer is a senior officer, the instruction could be “go to the incident area and secure the area.” In addition, if the patrol officer is a supervisor, the instruction couldbe “send two senior officers to the incident area.” In addition, the workflow monitoring service can generate instructions based on the types of incidents. For example, if the incident is related to a weapon found on a floor, the instruction could be “do not touch the found gun, secure the area, and call law enforcement.” Thus, the workflow monitoring service can generate instruction in dynamically changing environments.

[0135] Although aspects of the present disclosure will be described with regard to illustrative network components, interactions, and routines, one skilled in the relevant art will appreciate that one or more aspects of the present disclosure may be implemented in accordance with various environments, system architectures, customer computing device architectures, and the like. Similarly, references to specific devices, such as a customer computing device, can be considered to be general references and not intended to provide additional meaning or configurations for individual customer computing devices. Additionally, the examples are intended to be illustrative in nature and should not be construed as limiting. For the purpose of description, FIGs. 5-8 are directed to the aspects of automated workflow instruction generating system, as disclosed herein

[0136] FIG. 5 depicts a block diagram of an embodiment of the system 100. The system 100 can include a network 104, the network connecting a plurality of computing devices 102 and the network service provider 110. The system 100 can also include a network 106, the network connecting a number of sensors 120 and network service provider 110. Illustratively, the various aspects associated with the network service provider 110 can be implemented as one or more components that are associated with one or more functions or services. The components may correspond to software modules implemented or executed by one or more customer computing devices, which may be separate stand-alone customer computing devices. Accordingly, the components of the network service provider 110 should be considered as a logical representation of the service, not requiring any specific implementation on one or more customer computing devices.

[0137] Networks 104, 106 as depicted in FIG. 5, can connect the network service provider 110 and the computing devices 120 and the sensors 120, respectively. The networks 104, 106 can comprise any combination of wired and / or wireless networks, such as one or more direct communication channels, local area networks, wide area network, personal area network, and / or the Internet, for example. In some embodiments, the communication betweenthe network service provider 110 and the computing devices 102 and / or the sensors 120 may be performed via a short-range communication protocol, such as Bluetooth, Bluetooth low energy (“BLE”), and / or near field communications (“NFC”).

[0138] In some embodiments, the networks 104, 106 may be a private or semiprivate network, such as a corporate or university intranet. The networks 104, 106 may include one or more wireless networks, such as a Global System for Mobile Communications (GSM) network, a Code Division Multiple Access (CDMA) network, a Long Term Evolution (LIE) network, or any other type of wireless network. The networks 104, 106 can use protocols and components for communicating via the Internet or any of the other aforementioned types of networks. For example, the protocols used by the networks 104, 106 may include Hypertext Transfer Protocol (HTTP), HTTP Secure (HTTPS), Message Queue Telemetry Transport (MQTT), Constrained Application Protocol (CoAP), and the like. Protocols and components for communicating via the Internet or any of the other aforementioned types of communication networks are well known to those skilled in the art and, thus, are not described in more detail herein.

[0139] In some implementations, the network 104 can include one or more routers (not shown in FIG. 5). The routers can function as a gateway and can be configured to receive signals from nearby computing devices and route the received signals to the network service provider 110. In some examples, the router can transmit signals that include location information of the nearby computing device 102. In some scenarios, the computing devices 102 may continuously send beacon signals to nearby router(s). The beacon signal can be transmitted at regular intervals and contain identification information, such as the location information of the computing device 102. Thus, the network service provider 110 can continuously receive the location information from the computing devices 102.

[0140] The types of network 104 and network 106 can be the same type of network or different types of network. These types can be determined based on specific applications, and the present disclosure does not limit these types of networks.

[0141] As described in FIG. 5, the network service provider 110 can be communicatively coupled with the computing devices 102 via the network 104. The network service provider 110 can connect any number of computing devices 102. Each computing device 102 can be utilized by an employee and configured to provide work related information.For example, if the network service provider 110 is adapted for the security patrol service provider, the employee can be the patrol officer. In some embodiments, the computing devices 102 can be any computing device such as a desktop, laptop or tablet computer, personal computer, tablet computer, wearable computer, server, personal digital assistant (PDA), hybrid PDA / mobile phone, mobile phone, smartphone, set-top box, voice command device, digital media player, and the like. In some embodiments, the computing devices 102 may execute an application (e.g., a browser, a stand-alone application, etc.) that allows a user (e.g., an employee) to access interactive user interfaces, view images, analyses, or aggregated data, and / or the like as described herein. In various embodiments, users (e.g., employees) may interact with the network service provider via various devices. Such interactions may typically be accomplished via interactive graphical user interfaces or voice commands, however, alternatively, such interactions may be accomplished via command line and / or other means.

[0142] In some embodiments, the computing device 102 can include a camera. The camera can be utilized to capture images. For example, a patrol officer may scan the officer’s surrounding area. The images of the scanned area can be captured by the camera, and the computing device 102 can transmit the captured images to the network service provider 110. In some examples, the camera can be an external device and connected to the computing device 102.

[0143] In certain instances, the computing device 102 can offer a graphical interface equipped with features designed to assist in the performance of an employee’s duties. For example, the patrol officer can utilize the graphical interface to report any security related incidents. In addition, the graphical interface can display instructions received from the network service provider 110. The present disclosure does not limit the functionality types of graphical interface, and the types can be determined based on specific applications.

[0144] As described in FIG. 5, the network service provider 110 can be communicatively coupled with the sensors 120 via the network 106. The network service provider 110 can connect any number of sensors 120. The present disclosure does not limit the types of sensors, and the types can be determined based on specific applications. For example, the types of sensors utilized for security patrol can include but are not limited to temperature sensors, proximity sensors, light sensors, motion sensors, gas sensors, image sensors, radar sensors, etc.

[0145] In some embodiments, any suitable type and number of sensors 120 can be deployed in working areas. For example, each security post can include one or more types of sensors 102, where the types and number of sensors can be determined based on the characteristics of the security post.

[0146] The network service provider 110, as shown in FIG. 5, can include a workflow monitoring service 130 and database 150. The workflow monitoring service 130 can be configured to monitor workflows of the individual employee. The workflow can generally refer to an employee’s duty. For instance, the workflow of a patrol officer may encompass their shift timing and the specific responsibilities tied to their patrol duties.

[0147] In some embodiments, the workflow monitoring service 130 can track the location of the employees. For example, the computing devices 102 utilized by each employee can continuously transmit its location to the workflow monitoring service 130.

[0148] In some embodiments, the workflow monitoring service 130 can provide instructions to the employees. The instructions can be work related instructions, and the employees, while executing their job duties, can receive the instructions from the workflow monitoring service 130. In various examples, the workflow monitoring service 130 can generate the instructions by processing data received from the sensors 120. The instructions can be dynamically generated based on the processing result of the sensor data. For example, the workflow monitoring service 130 can continuously receive sensor data generated from a security patrol area that includes a plurality of posts. In this example, the workflow monitoring service 130 may detect any abnormalities from one or more posts, and the workflow monitoring service 130 can generate instructions based on the detected abnormalities and transmit the generated instructions to nearby patrol officers.

[0149] In certain embodiments, the workflow monitoring service 130 can provide location-based instructions to each employee. For instance, a patrol officer, while covering an area with multiple security posts, may receive specific instructions upon entering each security post.

[0150] In some examples, the workflow monitoring service 130 can receive images (and video clips) that capture the patrol officer’s surrounding area. For instance, the patrol officer may be required to periodically scan the surrounding area, either at specified time intervals or upon entering a new post. In addition, the patrol officer can continuously captureimages and transmit the captured images to the workflow monitoring service 130 via the network 104. Furthermore, the patrol officer can provide any information, such as incidents, in the form of text, voice, etc.

[0151] In various examples, the workflow monitoring service 130 can dynamically generate instructions based on the captured images and / or information received from each employee (e.g., each employee’s computing device). The instructions provided by the workflow monitoring service 130 are dynamically generated based on processing results of sensor data and inputs (e.g., captured images and incident report information) received from the computing devices 102. In addition, the workflow monitoring service 130 can generate the instructions based on the level of experience (or hierarchy) of employees. For example, the patrol officers within a post can receive different types of instructions based on each officer’s level of experience. For instance, if the patrol officer is a junior officer, the instruction could be “contact a supervisor and report the incident.” If the patrol officer is a senior officer, the instruction could be “go to the incident area and secure the area.” In addition, if the patrol officer is a supervisor, the instruction could be “send two senior officers to the incident area.” In addition, the workflow monitoring service can generate instructions based on the types of incident. For example, if the incident is related to a weapon found on a floor, the instruction could be “do not touch the found gun, secure the area, and call law enforcement.” Thus, the workflow monitoring service can generate instruction in dynamically changing environments.

[0152] FIG. 6 depicts one embodiment of the architecture of an illustrative workflow monitoring service 130. The workflow monitoring service 130 can be configured to generate instructions. More specifically, the workflow monitoring service 130 can provide guidance to employees in dynamically changing environments by processing a variety of sensor data and employee input data, such as captured images and reports generated by the computing device. The general architecture of the workflow monitoring service 130 depicted in FIG. 6 includes an arrangement of computer hardware and software components that may be used to implement aspects of the present disclosure. As illustrated, the workflow monitoring service 130 includes a processing unit 602, a network interface 604, a computer-readable medium drive 606, and an input / output device interface 608, all of which may communicate with one another by way of a communication bus. The components of the workflow monitoringservice 130 may be physical hardware components or implemented in a virtualized environment.

[0153] The network interface 604 may provide connectivity to one or more networks, such as the networks 104 and 106 of FIG. 5. The processing unit 602 may thus receive information and instructions from other computing systems or services via a network. The processing unit 602 may also communicate to and from memory 610 and further provide output information for an optional display via the input / output device interface 608. In some embodiments, the workflow monitoring service 130 may include more (or fewer) components than those shown in FIG. 6.

[0154] The memory 610 may include computer program instructions that the processing unit 602 executes in order to implement one or more embodiments. The memory 610 generally includes RAM, ROM, or other persistent or non-transitory memory. The memory 610 may store an operating system 614 that provides computer program instructions for use by the processing unit 602 in the general administration and operation of the workflow monitoring service 130. The memory 610 may further include computer program instructions and other information for implementing aspects of the present disclosure. For example, in one embodiment, the memory 610 includes interface software 612 for communicating with other components or services and performing one or more aspects as disclosed herein.

[0155] The memory 610 may include a machine learning component 616. The machine learning component 616 can be configured to analyze data and generate dynamic instructions in accordance with one or more embodiments as disclosed herein. In some embodiments, a number of different types of algorithms may be used by the machine learning component 616 to generate the models. For example, certain embodiments herein may use a logistical regression model, decision trees, random forests, convolutional neural networks, deep networks, or others. However, other models are possible, such as a linear regression model, a discrete choice model, or a generalized linear model. The machine learning algorithms can be configured to adaptively develop and update the models over time based on new input received by the machine learning component 616. For example, the models can be regenerated on a periodic basis as new human physical characteristics or bio information isavailable to help keep the predictions in the model more accurate as the information evolves over time.

[0156] Some non-limiting examples of machine learning algorithms that can be used to generate and update the parameter functions or prediction models can include supervised and non-supervised machine learning algorithms, including regression algorithms (such as, for example, Ordinary Least Squares Regression), instance-based algorithms (such as, for example, Learning Vector Quantization), decision tree algorithms (such as, for example, classification and regression trees), Bayesian algorithms (such as, for example, Naive Bayes), clustering algorithms (such as, for example, k-means clustering), association rule learning algorithms (such as, for example, Apriori algorithms), artificial neural network algorithms (such as, for example, Perceptron), deep learning algorithms (such as, for example, Deep Boltzmann Machine), dimensionality reduction algorithms (such as, for example, Principal Component Analysis), ensemble algorithms (such as, for example, Stacked Generalization), and / or other machine learning algorithms. These machine learning algorithms may include any type of machine learning algorithm, including hierarchical clustering algorithms and cluster analysis algorithms, such as a k-means algorithm. In some cases, the performing of the machine learning algorithms may include the use of an artificial neural network. By using machinelearning techniques, large amounts (such as terabytes or petabytes) of player interaction data may be analyzed to generate models.

[0157] The memory 610 may include a location monitoring component 618. The location monitoring component 618 can be configured to monitor the location of employees. In some cases, the computing devices 102 utilized by employees can equipped with a location tracking system, such as GPS module, and the location monitoring component 618 can periodically or continuously receive the location information of the computing devices. In alternative cases, the computing devices 102 are connected to one or more routers, and the computing devices 102 transmit a beacon signal with location information to the routers. The routers can transmit the location information to the location monitoring component 618. In some cases, the location monitoring component 618 can set up a geographic boundary (e.g., virtual boundary), such as the geofence. For example, a patrol service provider can set up the geographic boundary for each security patrol area or each post of the patrol area. In this example, when a computing device 102 enters the boundary, the location monitoringcomponent 618 can automatically identify the computing devices 102 information, such as the corresponding patrol officer’s location information.

[0158] The memory 610 can further include an input processing component 620. The input processing component 620 can be configured to analyze input data received from the computing devices 102 and the sensors 120.

[0159] In some embodiments, the input processing component 620 can receive inputs from computing devices 102. In some examples, the input processing component 620 can receive images (and video clips) that capture the patrol officers’ surrounding area. For instance, the patrol officer may be required to periodically scan the surrounding area, either at specified time intervals or upon entering a new post. In addition, the patrol officer can continuously capture images and transmit the captured images to the workflow monitoring service 130 via the network 104. Furthermore, the patrol officer can provide any information, such as incidents, in the form of text, voice, etc.

[0160] In various embodiments, the input processing component 620 can receive inputs from the sensors 120. Various types of sensors can be deployed in the workspace, such that, in non-limiting examples, temperature sensors, proximity sensors, light sensors, motion sensors, gas sensors, image sensors, radar sensors, etc., can be deployed for a security patrol service provider.

[0161] The input processing component 620 can continuously process inputs and identify any abnormalities. These abnormalities can be defined based on specific applications. For instance, in the context of a security patrol service provider, abnormalities could include the detection of unexpected movements, noise levels exceeding a certain threshold, temperatures (and / or humidity) surpassing a set limit, identification of an object resembling a weapon, detection of unknown individuals, and so forth. In some embodiments, the input processing component 620 can utilize the machine learned component 616 to detect the abnormalities by analyzing the input data received from the computing devices 102 and the sensors 120. For example, the input processing component 620 (e.g., by utilizing the machine learning component 616) can analyze the captured images by utilizing various types of image processing techniques, such as by identifying a region of interest from the captured image associated with one or more objects within the image. For example, the input processing component 620 can analyze image data associated with security patrol areas by detectingobjects in the areas and analyzing whether these objects are risk objects. For example, the input processing component 620 may score risk score for each detected object. Additionally, the input processing component 620 may further verify its risk score by generating confidence values. In some embodiments, the machine learning component 616 can be continuously trained based on threshold confidence of example outputs corresponding to the trained model being used to identify the abnormalities within the workspace areas. For example, the training can be based on the ground truth level.

[0162] In some embodiments, the input processing component 620 can analyze the input data by vectorizing the space, such as the targeted patrol areas. For example, the input processing component 620 can vectorize a targeted patrol building and identify the location and area of the post from the vector. For example, a security patrol contract may specify the post area; for example, every 100 square feet of the patrol area needs one patrol official during a certain time. In these examples, the input processing component 620 can vectorize the patrol area, and this vectorized area can be utilized to determine the corresponding post area, such as the 100 square feet. Furthermore, the input processing component 620 can identify the number of post areas based on the vectorized targeted patrol area.

[0163] The memory 610 can also include an instruction generating component 622. In some embodiments, the instruction generating component 622 can provide work related instruction identified based on a master plan. For example, the master plan of a security patrol service provider can be provided as the hierarchical data. The hierarchical data can include various levels, such that the highest level of the data structure can be a building, the lower layer can be floors, the lower layer can be rooms within the floors, and the lowest layer can be the posts in each room. The master plan may include assigned one or more required workflow for each level of the hierarchical data structure. For example, at the highest level, the master plan may include assigned attributes of the types of patrol areas, required security level, patrol time, etc. In the lowest level of the hierarchical data, such as posts, each post can be associated with the required patrol attributes for each post, such as the number of patrol officials, patrol time, required capability of the patrol official, and the like. In these embodiments, the instruction can be generated based on the workflow assigned to each post. In some examples, the instruction is provided in accordance with the shift schedule of patrol officers. For example, within a threshold time period before initiating the patrol, the instruction can be provided tothe patrol officers. In some examples, this instruction can be provided to the patrol officer when the officer enters a post.

[0164] In some embodiments, the instruction can be generated based on the input analyzed results obtained from the input processing component 620. In various examples, the instruction generating component 622 can dynamically generate instructions based on the captured images and / or information received from each employee (e.g., each employee’s computing device). The instructions are dynamically generated based on processing results of sensor data and inputs (e.g., captured images and incident report information) received from the computing devices 102. In addition, the instruction generating component 622 can generate the instructions based on the level of experience (or hierarchy) of employees. For example, the patrol officers within a post can receive different types of instructions based on each officer’s level of experience. For instance, if the patrol officer is a junior officer, the instruction could be “contact a supervisor and report the incident.” If the patrol officer is a senior officer, the instruction could be “go to the incident area and secure the area.” In addition, if the patrol officer is a supervisor, the instruction could be “send two senior officers to the incident area.” In addition, the workflow monitoring service can generate the instructions based on the types of the incidents. For example, if the incident is related to a weapon found on a floor, the instruction could be “do not touch the found gun, secure the area, and call law enforcement.” Thus, the workflow monitoring service can generate instruction in dynamically changing environments. In some examples, the instructions are dynamically provided by associating with the vector representation identified by the input processing component 620. In some embodiments, the instruction generating component 622 can utilize the machine learning component 616 to generate the dynamic instructions.

[0165] In some embodiments, the workflow monitoring service 130, upon generating the instruction from the instruction generating component 622, can provide notification to various entities, such as business operation administrators, managing officers, on-duty employees, and the like. In some examples, the workflow monitoring service 130 can automatically determine and apply one or more corrective actions in addition to providing notifications. These entities can be connected with the workflow monitoring service 130 via the network interface 604 of the workflow monitoring service 130. For example, in the context of the network service provider used for a security patrol service, the workflow monitoringservice 130 may detect abnormalities in certain patrol areas by obtaining and analyzing the sensors. In this example, the workflow monitoring service 130 may automatically notify the on-duty patrol officer(s), their supervisors, managing officers, a property owner of the security patrol areas, and the like. Additionally, the network service provider automatically identifies and applies correct actions. For example, if the workflow monitoring service 130 determines high temperature by receiving data from a temperature sensor, the workflow monitoring service 130 may automatically enable a sprinkler and / or contact the fire department. In some cases, the workflow monitoring service 130 may determine whether any action was taken regarding the detected abnormalities. For example, if the workflow monitoring service 130 detects a high temperature in a patrol area and no action is taken, the workflow monitoring service 130 may notify the managing officer(s), headquarters personnel of the security service provider, and the like. One skilled in the relevant will appreciate that additional or alternative notifications could be include and that any discussed notifications should not be limiting..

[0166] The memory 610 can also include an instruction verification component 624. The instruction verification component 624 can be configured to verify whether the generated instruction is confident. For example, if an instruction is generated, such as “secure a lobby because a gun is found at the lobby,” the patrol officer can verify this information. For instance, the patrol officer can go to the lobby and verify whether the gun is located in the lobby. During the verification, the patrol officer can provide a verification input. For example, if a gun is found at the lobby, the input could be a confirmation input. However, if the patrol officer could not find a gun, instead found a cardboard with a similar shape to the gun, the patrol officer can provide additional input, such as with the image of the cardboard and / or any description. In various examples, these additional inputs can be utilized as ground truth data to retrain the machine learning component 616.

[0167] Turning now to FIG. 7, illustrative interactions of the components of the system 100, as shown in FIG. 5, will be described. For purposes of the illustration, it can be assumed that the network service provider 110 has been configured in a manner that implements the workflow monitoring service 130. For the purpose of description, FIG 3 can be described with respect to a security patrol service provider. The present application is not intended to be limited to any particular type of service or the number of individual services that may be accessed or generate processing results as part of the execution of an application.

[0168] With reference to FIG. 7, an illustrative interaction of generating processing results that can be utilized in the aspects of workflow monitoring service and / or generating instructions will be described. The interaction is illustrative.

[0169] At (1), the computing devices 102 transmit location information to the workflow monitoring service 130. In some cases, the computing devices 102 utilized by employees can equipped with a location tracking system, such as GPS module. In alternative cases, the computing devices 102 are connected to one or more routers, and the computing devices 102 transmit a beacon signal with location information to the routers. The routers can transmit the location information to the location monitoring component 618.

[0170] At (2), the workflow monitoring service 130 monitors the location of computing devices 102. The workflow monitoring service 130 can periodically or continuously receive the location information of the computing devices 102. In some cases, the location monitoring component 618 can set up a geographic boundary (e.g., virtual boundary), such as the geofence. For example, a patrol service provider can set up the geographic boundary for each security patrol area or each post of the patrol area. In this example, when a computing device 102 (or set of computing devices) enters the boundary, the workflow monitoring service 130 can automatically identify the computing devices 102 information, such as the corresponding patrol officer’s location information.

[0171] At (3), the computing devices 102 transmit inputs to the workflow monitoring service 130. In some examples, the workflow monitoring service 130 can receive images (and video clips) that capture the patrol officers’ surrounding area. For instance, the patrol officer may be required to periodically scan the surrounding area, either at specified time intervals or upon entering a new post. In addition, the patrol officer can continuously capture images and transmit the captured images to the workflow monitoring service 130 via the network 104. Furthermore, the patrol officer can provide any information, such as incidents, in the form of text, voice, etc.

[0172] At (4), the workflow monitoring service 130 receives sensor data from the sensors 120. Various types of sensors can be deployed at the workspace, such that, in nonlimiting examples, temperature sensors, proximity sensors, light sensors, motion sensors, gas sensors, image sensors, radar sensors, etc., can be deployed for a security patrol service provider.

[0173] At (5), the workflow monitoring service 130 processes the received inputs and sensor data. In some embodiments, the workflow monitoring service 130 can continuously process inputs and identify any abnormalities. These abnormalities can be defined based on specific applications. For instance, in the context of a security patrol service provider, abnormalities could include the detection of unexpected movements, noise levels exceeding a certain threshold, temperatures (and / or humidity) surpassing a set limit, identification of an object resembling a weapon, detection of unknown individuals, and so forth. In some embodiments, the workflow monitoring service 130 can utilize the machine learned component 616 (shown in FIG. 6) to detect the abnormalities by analyzing the input data received from the computing devices 102 and the sensors 120. For example, the workflow monitoring service 130 (e.g., by utilizing the machine learning component 616) can analyze the captured images by utilizing various types of image processing techniques, such as by identifying a region of interest from the captured image associated with one or more objects within the image. For example, the workflow monitoring service 130 can analyze image data associated with security patrol areas by detecting objects in the areas and analyzing whether these objects are risk objects. For example, the workflow monitoring service 130 may score risk score for each detected object. Additionally, the workflow monitoring service 130 may further verify its risk score by generating confidence values. In some embodiments, the machine learning component 616 can be continuously trained based on threshold confidence of example outputs corresponding to the trained model being used to identify the abnormalities within the workspace areas. For example, the training can be based on the ground truth level.

[0174] In some embodiments, the workflow monitoring service 130 can analyze the input data (and the sensor data) by vectorizing the space, such as the targeted patrol areas. For example, the workflow monitoring service 130 can vectorize a targeted patrol building and identify the location and area of the post from the vector. In some examples, a security patrol contract may specify the post area, such as every 100 square feet of the patrol area needs one patrol official during a certain time. In these examples, the workflow monitoring service 130 can vectorize the patrol area, and this vectorized area can be utilized to determine the corresponding post area, such as the 100 square feet. Furthermore, the workflow monitoring service 130 can identify the number of post areas based on the vectorized targeted patrol area.

[0175] At (6), the workflow monitoring service 130 generates instructions. In some embodiments, the workflow monitoring service 130 can provide work related instruction identified based on a master plan. For example, the master plan of a security patrol service provider can be provided as hierarchical data. The hierarchical data can include various levels, such that the highest level of the data structure can be a building, the lower layer can be floors, the lower layer can be rooms within the floors, and the lowest layer can be the posts in each room. The master plan may include assigned one or more required workflow for each level of the hierarchical data structure. For example, at the highest level, the master plan may include assigned attributes of the types of patrol areas, required security level, patrol time, etc. In the lost level of the hierarchical data, such as posts, each post can be associated with the required patrol attributes for each post, such as the number of patrol officials, patrol time, required capability of the patrol official, and the like. In these embodiments, the instruction can be generated based on the workflow assigned to each post. In some examples, the instruction is provided in accordance with shift schedule of patrol officers. For example, within a threshold time period before initiating the patrol, the instruction can be provided to the patrol officers. In some examples, this instruction can be provided to the patrol officer when the officer enters a post.

[0176] In some embodiments, the instruction can be generated based on the input analyzed results obtained at (5). In various examples, the workflow monitoring service 130 can dynamically generate instructions based on the captured images and / or information received from each employee (e.g., each employee’s computing device). The instructions are dynamically generated based on processing results of sensor data and inputs (e.g., captured images and incident report information) received from the computing devices 102. In addition, the workflow monitoring service 130 can generate the instructions based on the level of experience (or hierarchy) of employees. For example, the patrol officers within a post can receive different types of instructions based on each officer’s level of experience. For instance, if the patrol officer is a junior officer, the instruction could be “contact a supervisor and report the incident.” If the patrol officer is a senior officer, the instruction could be “go to the incident area and secure the area.” In addition, if the patrol officer is a supervisor, the instruction could be “send two senior officers to the incident area.” In addition, the workflow monitoring service can generate instructions based on the types of the incidents. For example, if the incident isrelated to a weapon found on a floor, the instruction could be “do not touch the found gun, secure the area, and call law enforcement.” Thus, the workflow monitoring service can generate instruction in dynamically changing environments. In some examples, the instructions are dynamically provided by associating with the vector representation identified by the workflow monitoring service 130. In some embodiments, the workflow monitoring service 130 can utilize the machine learning component 616 to generate the dynamic instructions. At step (7), the workflow monitoring service 130 can send instructions to the computing devices. These instructions can be transmitted in real time when the workflow monitoring service 130 detects any abnormalities from the received inputs and sensor data. These instructions can also be sent to the computing devices 102 situated near the location where the abnormalities were detected.

[0177] Illustratively, the workflow monitoring service 130 can provide the instructions to various entities, such as business operation administrators, managing officers, on-duty employees, and the like. In some examples, the workflow monitoring service 130 can automatically determine and apply one or more corrective actions in addition to providing notifications. These entities can be connected with the workflow monitoring service 130 via the network interface 604 of the workflow monitoring service 130. For example, in the context of the network service provider used for a security patrol service, the workflow monitoring service 130 may detect abnormalities in certain patrol areas by obtaining and analyzing the sensors. In this example, the workflow monitoring service 130 may automatically notify the on-duty patrol officer(s), their supervisors, managing officers, a property owner of the security patrol areas, and the like. Additionally, the network service provider automatically identifies and applies correct actions. For example, if the workflow monitoring service 130 determines high temperature by receiving data from a temperature sensor, the workflow monitoring service 130 may automatically enable a sprinkler and / or contact the fire department. In some cases, the workflow monitoring service 130 may determine whether any action was taken regarding the detected abnormalities. For example, if the workflow monitoring service 130 detects a high temperature in a patrol area and no action is taken, the workflow monitoring service 130 may notify the managing officer(s), headquarters personnel of the security service provider, and the like. The present disclosure does not limit the types of notifications.

[0178] In some embodiments, the workflow monitoring service 130 can verify the generated instructions. The workflow monitoring service 130 can be configured to verify whether the generated instruction is confident. For example, if an instruction is generated, such as “secure a lobby because a gun is found at the lobby,” the patrol officer can verify this information. For instance, the patrol officer can go to the lobby and verify whether the gun is located in the lobby. During the verification, the patrol officer can provide a verification input. For example, if a gun is found in the lobby, the input could be a confirmation input. However, if the patrol officer could not find a gun and instead found a cardboard with a similar shape to the gun, the patrol officer could provide additional input, such as the image of the cardboard and / or any description. In various examples, these additional inputs can be utilized as ground truth data to retrain the machine learning component 616. For example, the machine learning algorithms of the machine learning component 616 can be configured to adaptively develop and update the models over time based on new input received by the machine learning component 616. For example, the models can be regenerated on a periodic basis as new object characteristics and human physical characteristic or bio information are available to help keep the predictions in the model more accurate as the information evolves over time. In some embodiments, these objects’ characteristics and human physical characteristics or bio information can be stored in the database 150. In these embodiments, the machine learning algorithms trained with these characteristics can also be stored in the database 150.

[0179] Although the interactions illustrated in FIG. 7 are described in a particular order, it should be understood that these interactions are not limited as such. The interactions may be performed in an alternative order, serially, or at least partially in parallel. For example, interactions associated with (3) and (4) may be performed in parallel.

[0180] Turning now to FIG. 8, a workflow instruction generation routine 800 based on various aspects, as disclosed in the present disclosure, will be described. For the purpose of illustration, the routine 800 can be performed by the workflow monitoring service 130 implemented in the network service provider 110.

[0181] At block 802, the workflow monitoring service 130 obtains a set of location information from a plurality of computing devices. In some examples, the set of location information includes geometry identifiers and time identifiers of each of the plurality of computing devices. For illustrations, the computing devices 102 transmit location informationto the workflow monitoring service 130. In some cases, the computing devices 102 utilized by employees can equipped with a location tracking system, such as GPS module. In alternative cases, the computing devices 102 are connected to one or more routers, and the computing devices 102 transmit a beacon signal with location information to the routers. The routers can transmit the location information to the location monitoring component 618.

[0182] At block 804, the workflow monitoring service 130 tracks the location of computing devices 102. In some examples, the workflow monitoring service 130 tracks locations of the plurality of computing devices by analyzing the set of location information within targeted areas, for example, the targeted areas include a plurality of sub-areas. In some examples, each sub-area is vectorized and stored in the memory 610. The workflow monitoring service 130 can periodically or continuously receive the location information of the computing devices 102. In some cases, the location monitoring component 618 can set up a geographic boundary (e.g., virtual boundary), such as the geofence. For example, a patrol service provider can set up the geographic boundary for each security patrol area or each post of the patrol area. In this example, when computing devices 102 enter the boundary, the workflow monitoring service 130 can automatically identify the computing devices 102 information, such as the corresponding patrol officer’s location information.

[0183] At block 806, the workflow monitoring service 130 obtains a set of inputs from the computing devices 102. In some examples, the workflow monitoring service 130 can receive images (and video clips) that capture the surrounding area of the patrol officers. For instance, the patrol officer may be required to periodically scan the surrounding area, either at specified time intervals or upon entering a new post. In addition, the patrol officer can continuously capture images and transmit the captured images to the workflow monitoring service 130 via the network 104. Furthermore, the patrol officer can provide any information, such as incidents, in the form of text, voice, etc.

[0184] At block 808, the workflow monitoring service 130 obtains a set of additional inputs from a plurality of sensors 120 deployed in the targeted areas.. Various types of sensors can be deployed in the workspace, such that, in non-limiting examples, temperature sensors, proximity sensors, light sensors, motion sensors, gas sensors, image sensors, radar sensors, etc., can be deployed for a security patrol service provider.

[0185] At block 810, the workflow monitoring service 130 analyzes the obtained set of inputs and set of additional inputs. In some embodiments, the workflow monitoring service 130 analyzes these inputs by utilizing a machine learning component 616 stored in the memory 610. In some examples, the workflow monitoring service 130 analyzes the set of inputs and the set of additional inputs to determine risk scores associated with the targeted areas such that results of the analysis indicate risk scores of sub-areas associated with the set of inputs. In some embodiments, the machine learning component 616 can include a neural network model trained to generate the risk scores of the sub-areas. In some examples, the neural network model is configured to collect, from a historical data stored in a database, a set of previous inputs, a set of previous additional inputs, and risk scores associated with the set of previous inputs and additional inputs, apply the set of previous inputs and the set of previous additional inputs to the neural network model, generate a set of risk scores associated with corresponding sub-areas associated with the set of previous inputs and the set of previous additional inputs, train the neural network model by verifying the generated set of risk scores with the risk scores associated with the set of previous inputs and additional inputs, and determine the risk scores by using the trained neural network model.

[0186] In some cases, the workflow monitoring service 130 can determine, for each sub-area associated with the set of inputs, whether the risk score is at or above a threshold risk score.

[0187] In some embodiments, the workflow monitoring service 130 processes the received inputs and sensor data. In some embodiments, the workflow monitoring service 130 can continuously process inputs and identify any abnormalities. These abnormalities can be defined based on specific applications. For instance, in the context of a security patrol service provider, abnormalities could include the detection of unexpected movements, noise levels exceeding a certain threshold, temperatures (and / or humidity) surpassing a set limit, identification of an object resembling a weapon, detection of unknown individuals, and so forth. In some embodiments, the workflow monitoring service 130 can utilize the machine learned component 616 (shown in FIG. 2) to detect the abnormalities by analyzing the input data received from the computing devices 102 and the sensors 120. For example, the workflow monitoring service 130 (e.g., by utilizing the machine learning component 616) can analyze the captured images by utilizing various types of image processing techniques, such as byidentifying a region of interest from the captured image associated with one or more objects within the image. For example, the workflow monitoring service 130 can analyze image data associated with security patrol areas by detecting objects in the areas and analyzing whether these objects are risk objects. For example, the workflow monitoring service 130 may score risk score for each detected object. Additionally, the workflow monitoring service 130 may further verify its risk score by generating confidence values. In some embodiments, the machine learning component 616 can be continuously trained based on threshold confidence of example outputs corresponding to the trained model being used to identify the abnormalities within the workspace areas. For example, the training can be based on the ground truth level.

[0188] In some embodiments, the workflow monitoring service 130 can analyze the input data (and the sensor data) by vectorizing the space, such as the targeted patrol areas. For example, the workflow monitoring service 130 can vectorize a targeted patrol building and identify the location and area of the post from the vector. In some examples, a security patrol contract may specify the post area, such as every 100 square feet of the patrol area needs one patrol official during a certain time. In these examples, the workflow monitoring service 130 can vectorize the patrol area, and this vectorized area can be utilized to determine the corresponding post area, such as the 100 square feet. In some embodiments, the workflow monitoring service 130 determines risk score for each attribute of the sensor data. For example, if an attribute of noise sensor, such as a noise level, is above a threshold, the workflow monitoring service 130 may analyze it as a high risk score. Furthermore, the workflow monitoring service 130 can identify the number of post areas based on the vectorized targeted patrol area.

[0189] At block 812, the workflow monitoring service 130 generates workflow instructions such that the workflow monitoring service 130 generates, for each vectorized subarea having the risk score at or above the threshold risk score, workflow instructions. For example, implementing the workflow instructions can mitigate risks of the vectorized subareas, having the risk score at or above the threshold risk score. In some examples, the workflow instructions include a set of hierarchical data, and the hierarchical data include a plurality of layers, where each layer associated with one or more instructions to be performed by one or more employees associated with the one or more computing devices located in proximity to the vectorized sub-areas, having the risk score at or above the threshold risk score.In some cases, the one or more instructions are patrolling a patrol area, where a top level of the hierarchical data is a master plan for patrolling the patrol area, having a plurality of posts, and a lower level of the hierarchical data is a patrolling plan of each post of the plurality of posts.

[0190] In some examples, the neural network model stored in the machine learning component 616 can dynamically generate the workflow instructions by collecting, from the historical data stored in the database, the set of previous inputs, the set of previous additional inputs, and a set of historical risk scores associated with the set of previous inputs and the set of previous additional inputs, applying the set of previous inputs and the set of previous additional inputs to the neural network model, and generating a set of workflow instructions associated with corresponding vectorized sub-areas associated with the set of previous inputs and the set of previous additional inputs. In various examples, wherein the neural network model is further configured to create a training set by comparing the generated set of set of workflow instructions with a historical set of workflow instructions stored in the database, where the historical set of workflow instructions is associated with the set of previous inputs and the set of previous additional inputs. In some examples, the machine learning component 616 is further configured to dynamically generate the workflow instructions by dynamically receiving the set of additional data. Furthermore, the machine learning component 616 can be configured to generate a plurality of workflow instructions by modifying one or more sensor data of the set of additional inputs, applying the modified one or more sensor data to the neural network model, and generating the plurality of workflow instructions based on the modified one or more sensor data. In some cases, the machine learning component 616 can be configured to train the neural network model by updating neural network parameters by comparing the generated set of risk scores and historical set of risk scores stored in the database, the historical set of risk scores associated with the set of previous inputs and the set of previous additional inputs.

[0191] In some embodiments, the workflow monitoring service 130 can provide work related instruction identified based on a master plan. For example, the master plan of a security patrol service provider can be provided as hierarchical data. The hierarchical data can include various levels, such that the highest level of the data structure can be a building, the lower layer can be floors, the lower layer can be rooms within the floors, and the lowest layer can be the posts in each room. The master plan may include assigned one or more requiredworkflow for each level of the hierarchical data structure. For example, at the highest level, the master plan may include assigned attributes of the types of patrol areas, required security level, patrol time, etc. In the lost level of the hierarchical data, such as posts, each post can be associated with the required patrol attributes for each post, such as the number of patrol officials, patrol time, required capability of the patrol official, and the like. In these embodiments, the instruction can be generated based on the workflow assigned to each post. In some examples, the instruction is provided in accordance with the shift schedule of patrol officers. For example, within a threshold time period before initiating the patrol, the instruction can be provided to the patrol officers. In some examples, this instruction can be provided to the patrol officer when the officer enters a post.

[0192] In some embodiments, the instruction can be generated based on the input analyzed results obtained at block 410. In various examples, the workflow monitoring service 130 can dynamically generate instructions based on the captured images and / or information received from each employee (e.g., each employee’s computing device). The instructions are dynamically generated based on processing results of sensor data and inputs (e.g., captured images and incident report information) received from the computing devices 102. In addition, the workflow monitoring service 130 can generate the instructions based on the level of experience (or hierarchy) of employees. For example, the patrol officers within a post can receive different types of instructions based on each officer’s level of experience. For instance, if the patrol officer is a junior officer, the instruction could be “contact a supervisor and report the incident.” If the patrol officer is a senior officer, the instruction could be “go to the incident area and secure the area.” In addition, if the patrol officer is a supervisor, the instruction could be “send two senior officers to the incident area.” In addition, the workflow monitoring service can generate the instructions based on the types of the incidents. For example, if the incident is related to a weapon found on a floor, the instruction could be “do not touch the found gun, secure the area, and call law enforcement.” Thus, the workflow monitoring service can generate instruction in dynamically changing environments. In some examples, the instructions are dynamically provided by associating with the vector representation identified by the workflow monitoring service 130. In some embodiments, the workflow monitoring service 130 can utilize the machine learning component 616 to generate the dynamic instructions.

[0193] At block 814, the workflow monitoring service 130 transmits instructions to the computing devices. These instructions can be transmitted in real time when the workflow monitoring service 130 detects any abnormalities from the received inputs and sensor data. These instructions can also be sent to the computing devices 102 situated near the location where the abnormalities were detected.

[0194] In some embodiments, the workflow monitoring service 130 can verify the generated instructions. The workflow monitoring service 130 can be configured to verify whether the generated instruction is confident. For example, if an instruction is generated, such as “secure a lobby because a gun is found at the lobby,” the patrol officer can verify this information. For instance, the patrol officer can go to the lobby and verify whether the gun is located in the lobby. During the verification, the patrol officer can provide a verification input. For example, if a gun is found at the lobby, the input could be a confirmation input. However, if the patrol officer could not find a gun, instead found a cardboard with a similar shape of the gun, the patrol officer can provide additional input, such as with the image of the cardboard and / or any description. In various examples, these additional inputs can be utilized as ground truth data to retrain the machine learning component 616. For example, the machine learning algorithms of the machine learning component 616 can be configured to adaptively develop and update the models over time based on new input received by the machine learning component 616. For example, the models can be regenerated on a periodic basis as new object characteristics and human physical characteristics or bio information is available to help keep the predictions in the model more accurate as the information evolves over time. In some embodiments, these objects characteristics and human physical characteristics or bio information can be stored in the database 150. In these embodiments, the machine learning algorithms trained with these characteristics can also be stored in the database 150. The routine 800 is ended at block 816.

[0195] In some cases, the workflow monitoring service 130 can provide the instructions to various entities, such as business operation administrators, managing officers, on-duty employees, and the like. These entities can be connected with the workflow monitoring service 130 via the network 104 or 106. For example, in the context of the network service provider used for a security patrol service, the workflow monitoring service 130 may detect abnormalities in certain patrol areas by obtaining and analyzing the sensors. In this example,the workflow monitoring service 130 may automatically notify the on-duty patrol officer(s), their supervisors, managing officers, a property owner of the security patrol areas, and the like. In some cases, the workflow monitoring service 130 may determine whether any action was taken regarding the detected abnormalities. For example, if the workflow monitoring service 130 detects a high temperature in a patrol area and that no action was taken, the workflow monitoring service 130 may notify to the managing officer(s), headquarters personal of the security service provider, and the like. The present disclosure does not limit the types of notifications.

[0196] Although the operations of the routine 800 are described in a particular order, it should be understood that the routine 800 is not limited as such. Operations of the routine 800 may be performed in an alternative order, serially, or at least partially in parallel. Further, certain operations may not need to be performed. For example, operations associated with the block 806 and block 808 may be performed in parallel.

[0197] Although the operations of the routine 800 are described in a particular order, it should be understood that the routine 800 is not limited as such. Operations of the routine 800 may be performed in an alternative order, serially, or at least partially in parallel. Further, certain operations may not need to be performed.Automated Run-Time Workflow Assignment System

[0198] Aspects of the present application relate to systems and methods for generating workflow for employees by identifying the workflow resources in real time or near real time. The workflow resources can include human resources employed by a business entity. The workflow generation can include identifying workflows based on a master plan of the business. The workflow generation can also include updating the identified workflows based on one or more updated attributes. For example, if the business entity is related to providing security patrol service, the workflow resources can include the employed security patrol officials, and the master plan can be the security patrol plans for each contracted security patrol area(s) and / or structure(s). Illustratively, one or more workflows can be generated based on the master plan, such that the workflows can include security patrol posts in each area and patrol time for each post. Individual posts may be associated with geographic boundaries, identifiable landmarks, assigned physical tasks, and various combinations there. The one or more generated workflows can be updated by identifying the updated attributes of the master plan in real-time.For instance, if the number of patrol posts is changed, the previously generated workflows based on the master plan can also be updated. The attributes disclosed herein can generally refer to any attributes used to generate the workflows based on the master plan. For example, if the master plan is related to security patrolling service, the attributes can include but are not limited to the number of patrol posts, types of patrol areas, time duration of patrolling each post, number of required patrol officials, required qualification of patrol officials, and the like. Therefore, in this scenario, details such as the specific location of the patrol post, the duration of the patrol, the duties required during the patrol period, and similar aspects can be formulated into a workflow. This workflow can then be assigned to one or more patrol officers. Even though the present disclosure describes the disclosed embodiments with examples of the security patrol service, these examples are merely provided for example purposes, and the present disclosure is not limited to the security patrol service.

[0199] One or more aspects of the present disclosure relate to generating run-time workflows utilizing an automated run-time workflow assignment system. More specifically, the workflow generation system can generate run-time workflows for a certain duration of time based on the master plan. For example, the automated run-time workflow assignment system may periodically generate workflows associated with a master plan. The duration of each period can be pre-defined and / or dynamically defined based on specific applications. Th present application does not limit the pre-defined duration of each period. In some embodiments, the automated run-time workflow assignment system can identify one or more employees for each workflow and assign the employees.

[0200] In some aspects of the present disclosure, the automated run-time workflow assignment system can generate workflows corresponding to a master plan. In these aspects, the automated run-time workflow assignment system can periodically verify the generated workflows. For example, the automated run-time workflow assignment system can determine whether any of the workflow requirements utilized for the master plan have been changed. For instance, the automated run-time workflow assignment system may identify one or more attributes that can cause modification of one or more workflows of the plurality of workflows (corresponding to the master plan) and update one or more workflows according to the identified one or more attributes.

[0201] In various aspects of the present disclosure, the automated run-time workflow assignment system can obtain and process data collected from various computing devices (e.g., those used by individual employees) and multiple managing devices (e.g., those used by system administrators) configured to provide workflow requirements. In some instances, a security patrol service provider might implement an automated run-time workflow assignment system. This system can collect patrol requirements from managing devices, such as computing devices utilized by a general security patrol administrator or an individual client requesting the security patrol service.

[0202] The automated run-time workflow assignment system can process data received from these managing devices, where the data includes workflow requirements. For example, the data might detail targeted security patrol areas (or structures) and specific patrol requirements, such as time slots and required capabilities for each area. Based on the processing the data, the automated run-time workflow assignment system can generate a master plan. The master plan can include a plurality of workflows that can be determined by processing the received data. In various embodiments, after determining the plurality of workflows, the automated run-time workflow assignment system can identify patrol officers who can be assigned to one or more workflows of the plurality of workflows (e.g., time slots). In some aspects of the present disclosure, one or more workflows of the plurality of workflows associated with a master plan can be updated or modified when workflow attributes are changed. For example, if the master plan is related to security patrolling service, the attributes can include but are not limited to the number of patrol posts, types of patrol areas, time duration of patrolling each post, number of required patrol officials, required qualification of patrol officials, and the like. In this example, the automated run-time workflow assignment system can monitor any changes in these attributes and update corresponding workflows based on the changes.

[0203] In some aspects, the automated run-time workflow assignment system can identify one or more employees according to the workflow and can assign the identified one or more employees to the corresponding workflows. For example, the identification of the patrol officers can be based on one or more required attributes of the security patrol service in relation to the patrol officers. For example, the attributes can be based on quantitative data,such as a level of experience, capability (e.g., capability to use weapons), patrol skills, a level of skill, and the like.

[0204] In some embodiments, the attributes can be determined based on the qualitative data. For example, the qualitative data can include but are not limited to feedback data, historical data associated with individual employee’s evaluation, employee interviews and / or surveys, and the like. In these embodiments, the automated run-time workflow assignment system may identify the qualitative data and vectorize the data for individual employees. For example, if an employee performs a workflow, the feedback from the client, the employee’s supervisor, and / or other peer employees can be converted into a score (e.g., confidence score), such that the positive feedback may increase the score, where the negative feedback may decrease the score. In certain instances, the automated run-time workflow assignment system might sift through the pool of identified employees using a score-based filter, applying a threshold score that varies according to the specific applications. For instance, in the context of a security patrol area demanding highly proficient officers, the required threshold score would be set higher than in zones where a less rigorous security presence suffices.

[0205] In some embodiments, the automated run-time workflow assignment system can further determine employees by further filtering based on the collective performance of each employee. In some examples, the automated run-time workflow assignment system can filter the identified employees based on collective performance data. For example, if the collective performance data indicate that certain employees had poor performance, such as these employees did not come to the work, the automated run-time workflow assignment system may exclude these employees from the pool of identified employees. In some embodiments, the automated run-time workflow assignment system can manage these employees who had poor performance record. For example, the automated runtime workflow assignment system can provide additional incentives to these employees to improve their work performance.

[0206] In certain situations, the automated run-time workflow assignment system may identify one or more employees based on each workflow. For instance, if a workflow identified from a master plan includes a task of 2:00AM patrol of a college dormitory, the system would analyze the necessary attributes for this post (e.g., task(s)) and identify suitablepatrol officers. The system could access its database to find officers available at 2:00AM. This identification might be based on qualitative data, such as survey responses indicating a preference for working at this time, which would result in a higher score. Additionally, officers who have received positive feedback from the same client may also score higher. The identification process could also consider quantitative data like years of experience. Budget constraints could also factor into the scoring, with officers charging rates above the budget receiving lower scores. These attributes and the scoring of each attribute can be determined based on specific applications, and the present disclosure does not limit the type of attributes and their scoring mechanism for the attributes.

[0207] Illustratively, one or more aspects of the present application correspond to the utilization of one or more local devices for facilitating the generation, management and updating of workflows. The local device can be one or more computing devices and configured to provide an interface that can display available workflows by associating it with one or more attributes. For example, the interface can display available workflows by categorizing them based on the attributes such as time, distance, and required capabilities. In some illustrations, the managing device can also be the local device, and the managing device can be configured to provide workflow requirements to the automated run-time workflow assignment system. For example, the managing device implemented by a security service provider may provide targeted security patrol area(s), specific security requirements for each area, and the like.

[0208] Illustratively, one or more aspects of the present application correspond to the utilization of a network service that can implement the automated run-time workflow assignment system. The automated run-time workflow assignment system can generate processing results based on processing the data received from a plurality of computing devices and one or more managing devices. As described above, the automated run-time workflow assignment system can receive workflow data from the managing devices and determine master plan and corresponding workflows based on the master plan.

[0209] Traditionally, managing individual workflows by utilizing resources such as human resources has presented limitations in terms of efficiency. More specifically, traditional workflow generation, typically performed manually, considers only the current workflow plan and resources. In such systems, individual workflows are pre-assigned and lack the flexibility to adapt dynamically to unexpected changes in workflow requirements or staffavailability. In this regard, computational incorporation of attribute data in a manual process is deficient, especially in consideration of the influence (e.g., weights) attributable to different attribute data. For example, a manual selection process is typically not able to determine a consistent balance between multiple attributes such as historical performance data, decaying feedback information, and the like. Accordingly, the influence of individual preferences or bias can be found in manual processes.

[0210] Moreover, traditional workflow generation may struggle in dynamic environments. For instance, if the workflow generation pertains to a security patrol service provider, the traditional system may not be equipped to handle individual requests from thousands of patrol officers when assigning each officer’s workflow. Also, since the workflow assignments are performed by manually, unsuitable employees can be assigned to the workflow, thereby increasing the dissatisfaction for both of the employees and customers.

[0211] To address at least a portion of the deficiencies described above, one or more aspects of the present disclosure relate to systems and methods for assigning workflows for individual employees. Specifically, these systems and methods can generate a master plan and its specific workflows in real time or near real time in by processing data generated from one or more managing devices and generating the required workflows corresponding to the generated master plan.

[0212] Illustratively, an automated run-time workflow assignment system, as disclosed herein, can be communicatively coupled with multiple computing devices and one or more managing devices. In some examples, the managing devices can be used by system administrators and configured to provide workflow requirements to the automated run-time workflow assignment system.

[0213] The workflow requirements can be related to requirements for utilizing workflow resources, such as human resources, and the requirements can vary based on a specific application that implements the system. For instance, if a security patrol service provider implements the system, the workflow information can be related to, but not limited to, types of targeted security patrol areas, number of targeted security patrol areas, duration of patrolling time for each targeted patrol area, and / or patrolling requirements such as required experiences and capabilities of the patrol officials, among others. Furthermore, in this example,the workflow information can be provided as contract documents between the service providers and their clients.

[0214] In some embodiments, the automated run-time workflow assignment system obtains the workflow requirements from the managing devices and identifies specific workflow requirements. In these embodiments, the automated run-time workflow assignment system may parse the obtained workflow requirements and generate a master plan. The automated run-time workflow assignment system can also organize portions of the workflow according to a hierarchical data structure based on the master plan. For example, if the automated run-time workflow assignment system is utilized for a security patrol service provider, the hierarchical data structure can be based on a master plan for the patrolling area(s) and can include, for example, individual data nodes (or identifiable groupings of data) for specific attributes or tasks, such as a targeted security patrol building, floors, and each post included in each floor, relatively from the highest hierarchy to the lowest hierarchy of the data structure. This example is merely provided as an illustrative example, and the present disclosure is not limited to this example.

[0215] In various examples disclosed herein, the automated run-time workflow assignment system may generate a master plan based on the processed results of the workflow requirements obtained from the managing devices. The master plan can represent the workflow requirements at various levels of the data structure. In these embodiments, the automated runtime workflow assignment system can divide the master plan into one or more sub-master plans that correspond to the lowest data level of the hierarchical data structure (e.g., a hierarchical organizational structure). For example, the lowest level of the data structure, posts, can correspond to the sub-master plans. In some embodiments, the automated run-time workflow assignment system further processes these sub-master plans and determines attributes associated with each sub-master plan.

[0216] In various instances, the attributes can include quantitative attributes and qualitative attributes. The quantitative attributes, for example, can be related any attributes related to the sub-master plans that attributes are represented with numbers. For example, in an application of the automated run-time workflow assignment system for the security patrol service provider, the quantitative attributes can include but are not limited to years of experience, number of successful patrols completed, number of incidents resolved, availabilityof the patrol officer, location of the patrol officer, patrol officer’s response time to the incident, rate of the patrol officer, and the like. The qualitative attributes can be identified based on the behavior of the employees, feedback, descriptive information about the employees, etc. For example, the qualitative attributes can include but are not limited to patrol officers’ communication skills, decision-making skills, integrity, interpersonal skills, knowledge of the regulations and patrol policy, customer service skills, etc. These attributes are generally from performance reviews (or descriptions) about the specific patrol official. Additionally, the qualitative attributes can also include the patrol officer’s own feedback, opinion, and / or survey results. These quantitative and qualitative attributes are determined based on specific applications, and the present disclosure does not limit the types of attributes.

[0217] In some examples, one or more attributes can be updated (e.g., changed), and the workflow corresponding to these one or more attributes may need to be updated accordingly. For example, the number of required patrol post areas can be changed. According to one or more embodiments, as disclosed herein, the automated run-time workflow assignment system may monitor these workflow requirement changes and update the workflow accordingly. Illustratively, the automated run-time workflow assignment system may monitor any changes in the workflow requirement and determine whether the existing workflows need to be updated. For example, the automated run-time workflow assignment system, upon identifying the changes in the current workflow requirements, may identify corresponding workflows. Then, the automated run-time workflow assignment system can update the corresponding workflows. In some embodiments, the automated run-time workflow assignment system can update the corresponding workflows during a pre-defined duration and re-evaluate whether these corresponding workflows need to be converted into the original workflows. In alternative embodiments, the updated workflows can be permanently implemented as the workflows associated with the master plan until the automated run-time workflow assignment system identifies any change in the workflow requirements. In other embodiments, the automated run-time workflow assignment system can periodically monitor any changes in the workflow requirements and update the corresponding workflows periodically.

[0218] In some embodiments, the automated run-time workflow assignment system may identify the available employees who can work on one or more workflows. Insome examples, the automated run-time workflow assignment system can access its database and identify the available employees. For example, if the automated run-time workflow assignment system is used by a security patrol service provider, the database of the automated run-time workflow assignment system may store the employed security patrol officer’s information. In some embodiments, the automated run-time workflow assignment system may determine the confidence score for each employee based on the determined workflow and its attributes. For example, if the master plan is patrolling a bank building, the sub-master plan can include patrolling a security room for 24 hours with 2 hour shift. In this example, the automated run-time workflow assignment system may identify various selection attributes, such as the quantitative attributes can include each office with at least 5 years of security patrol experience, more than 95% of successfully completed patrols, having a license to use the pistol, having a zero crime record, located within 5 miles from the bank building, and / or with an hourly rate less than $200. Further, in this example, the qualitative attributes can include each officer’s preference for working patrolling the security area, previous feedback on working at the bank building, knowledge of the regulation, and / or previous customer feedback.

[0219] In some embodiments, the automated run-time workflow assignment system can generate a confidence score for assigning each available employee to the available workflows associated with the sub-master plans. For example, after identifying the above attributes, the automated run-time workflow assignment system may generate a low confidence score (or filter out) for the patrol officers who do not meet the quantitative attributes. The automated run-time workflow assignment system may determine the confidence score of the remaining patrol officers based on the qualitative attributes. For example, each attribute of the qualitative attributes can have a different weight, and the confidence score can be determined based on each employee’s evaluation based on the qualitative attributes. The weight of each attribute and its determination of the confidence score can be different based on the specific applications.

[0220] Although certain illustrative embodiments and examples are disclosed below, inventive subject matter extends beyond the specifically disclosed embodiments to other alternative embodiments and / or uses and to modifications and equivalents thereof. Thus, the scope of the claims appended hereto is not limited by any of the particular embodiments described below. For example, in any method or process disclosed herein, the acts or operationsof the method or process may be performed in any suitable sequence and are not necessarily limited to any particular disclosed sequence. Various operations may be described as multiple discrete operations in turn, in a manner that may be helpful in understanding certain embodiments; however, the order of description should not be construed to imply that these operations are order dependent. Additionally, the structures, systems, and / or devices described herein may be embodied as integrated components or as separate components. For purposes of comparing various embodiments, certain aspects and advantages of these embodiments are described. Not necessarily all such aspects or advantages are achieved by any particular embodiment. Thus, for example, various embodiments may be carried out in a manner that achieves or optimizes one advantage or group of advantages as taught herein without necessarily achieving other aspects or advantages as may also be taught or suggested herein. For the purpose of description, FIGs. 9-12B are directed to the aspects of automated run-time workflow assignment system, as disclosed herein

[0221] FIG. 9. depicts a block diagram of an embodiment of the system 100. The system 100 can include a network 104, the network connecting a number of managing devices 125 and the automated run-time workflow assignment system 110. The system 100 can also include network 106, the network connecting a plurality of computing devices 102, and the automated run-time workflow assignment system 110. Illustratively, the various aspects associated with the automated run-time workflow assignment system 110 can be implemented as one or more components that are associated with one or more functions or services. The components may correspond to software modules implemented or executed by one or more computing devices 102 and / or managing devices 125, which may be separate stand-alone local devices. Accordingly, the components of the automated run-time workflow assignment system 110 should be considered as a logical representation of the service, not requiring any specific implementation on the computing devices 102 and / or the managing devices 125.

[0222] Networks 104, 106 as depicted in FIG. 9., can connect the automated runtime workflow assignment system 110 and the managing devices 125 and the computing devices 120, respectively. The networks 104, 106 can comprise any combination of wired and / or wireless networks, such as one or more direct communication channels, local area networks, wide area network, personal area network, and / or the Internet, for example. In some embodiments, the communication between the automated run-time workflow assignmentsystem 110 and the computing devices 102 and / or the managing devices 125 may be performed via a short-range communication protocol, such as Bluetooth, Bluetooth low energy (“BLE”), and / or near field communications (“NFC”).

[0223] In some embodiments, the networks 104, 106 may be a private or semiprivate network, such as a corporate or university intranet. The networks 104, 106 may include one or more wireless networks, such as a Global System for Mobile Communications (GSM) network, a Code Division Multiple Access (CDMA) network, a Long Term Evolution (LIE) network, or any other type of wireless network. The networks 104, 106 can use protocols and components for communicating via the Internet or any of the other aforementioned types of networks. For example, the protocols used by the networks 104, 106 may include Hypertext Transfer Protocol (HTTP), HTTP Secure (HTTPS), Message Queue Telemetry Transport (MQTT), Constrained Application Protocol (CoAP), and the like. Protocols and components for communicating via the Internet or any of the other aforementioned types of communication networks are well known to those skilled in the art and, thus, are not described in more detail herein.

[0224] The types of network 104 and network 106 can be the same type of network or different types of network. These types can be determined based on specific applications, and the present disclosure does not limit these types of networks.

[0225] As described in FIG. 9., the automated run-time workflow assignment system 110 can be communicatively coupled with the managing devices 125 via the network 104. The automated run-time workflow assignment system 110 can connect any number of managing devices 125. In various embodiments, each managing device 125 can be utilized by a system administrator (e.g., business operation manager, business administrator, etc.) and configured to provide workflow requirements to the automated run-time workflow assignment system. For example, if the automated run-time workflow assignment system is adapted for the security patrol service provider, the system administrator can provide one or more inputs that represent security patrol requirements, such as types of security patrol area(s), number of areas, required patrolling time, required to-do list during the patrolling, number of patrol officials, and the like. The system administrator may provide the inputs in text, contracts, certain formats, etc. In some embodiments, the managing devices 125 can be any computing device such as a desktop, laptop or tablet computer, personal computer, tablet computer,wearable computer, server, personal digital assistant (PDA), hybrid PDA / mobile phone, mobile phone, smartphone, and the like. In some embodiments, the managing devices 125 may execute an application (e.g., a browser, a stand-alone application, etc.) that allows a system administrator to access interactive user interfaces, view images, analyses, or aggregated data, and / or the like as described herein.

[0226] As described in FIG. 9., the automated run-time workflow assignment system 110 can be communicatively coupled with the computing devices 102 via the network 106. The automated run-time workflow assignment system 110 can connect any number of computing devices 102. Each computing device 102 can be utilized by an employee and can be configured to provide work related information. For example, if the automated run-time workflow assignment system is adapted for the security patrol service provider, the employee can be the patrol official. In this example, the computing device 102 may provide an interface that can display the available works for the patrol officials. This interface can be an application programming interface. In some examples, these available works can be provided with various attributes, such as distance (e.g., distance from the location of the official to the targeted patrol area), time slots, capability, compensation, and the like.

[0227] In some embodiments, the computing devices 102 can be any computing device such as a desktop, laptop or tablet computer, personal computer, tablet computer, wearable computer, server, personal digital assistant (PDA), hybrid PDA / mobile phone, mobile phone, smartphone, set top box, voice command device, digital media player, and the like. In some embodiments, the computing devices 102 may execute an application (e.g., a browser, a stand-alone application, etc.) that allows a user (e.g., an employee) to access interactive user interfaces, view images, analyses, or aggregated data, and / or the like as described herein. In various embodiments, users (e.g., employees) may interact with the automated run-time workflow assignment system via various devices. Such interactions may typically be accomplished via interactive graphical user interfaces or voice commands, however alternatively, such interactions may be accomplished via command line, and / or other means.

[0228] The automated run-time workflow assignment system 110, as shown in FIG. 9., can include a machine learned module 112, a workflow generation module 118, and database 150. The workflow generation module 140can be configured to monitor any eventsthat can cause updates or modifications to the existing workflows, and in response detecting the events, the workflow generation module 140can modify the existing workflows. The events can relate to any changes on one or more attributes of workflows or attributes of the employees. The attributes of workflows can correspond to the workflow requirements. For example, if the master plan is related to security patrolling service, the attributes can include but are not limited to the number of patrol posts, types of patrol areas, time duration of patrolling each post, number of required patrol officials, required qualification of patrol officials, and the like. In some embodiments, the attributes of the employee can be determined based on the qualitative data. For example, the qualitative data can include but are not limited to feedback data, historical data associated with individual employee’s evaluation, employee interview and / or survey, and the like. In these embodiments, the automated run-time workflow assignment system may identify the qualitative data and vectorize the data for individual employees. For example, if an employee performed a workflow, the feedback from the client, the employee’s supervisor, and / or other peer employees can be converted into a score (e.g., confidence score), such that the positive feedback may increase the score, where the negative feedback may decrease the score. In some examples, the attributes of the employee can be based on quantitative data, such as a level of experience, capability (e.g., capability to use weapons), patrol skills, a level of skill, and the like. Thus, for example, if the event has occurred, such that the number of patrol post is increase, the workflow generation module 140can automatically generate workflows with respect to the increased number of the patrol posts.

[0229] In some embodiments, the workflow generation module 140can receive workflow requirements from the managing devices 125. For example, if the automated runtime workflow assignment system is implemented for a security patrol service provider, the system administrator can provide one or more inputs that represent security patrol requirements, such as types of security patrol area(s), number of areas, required patrolling time, required to-do list during the patrolling, number of patrol officials, and the like. The workflow generation module 140may process the received workflow requirements and generate a master plan. For example, the workflow generation module 140may process the security patrol contract(s) to determine one or more patrol requirements. In some examples, the workflow generation module 140can process the received workflow requirements (e.g., from the managing devices) and generate a hierarchical data structure. For example, the highest level ofthe data structure can be a building, the lower layer can be floors, the lower layer can be rooms within the floors, and the lowest layer can be posts in each room. This example is merely provided for illustration purposes, and the types of the data structure can be determined based on specific applications.

[0230] In addition, the workflow generation module 140can generate a master plan based on the processed result of the received workflow requirements. The master plan may include one or more required workflows for each level of the hierarchical data structure. For example, at the highest level, the master plan may provide the patrol requirements, such as the types of patrol areas, required security level, patrol time, etc. For the purpose of the description, the lowest level of the organizational structure (e.g., the lowest level represented in a corresponding data structure) can be referred to as sub-master plan. For example, in the submaster plan, the workflow generation module 140may process the lowest level of the data structure by associating it with the required attributes. Further, in this example, if the lowest level of the data structure corresponds to information descriptive of posts, individual posts can be represented as groupings of information (e.g., nodes) with the required patrol attributes for each post, such as the number of patrol officials, patrol time, the required capability of the patrol official, and the like.

[0231] In some examples, each area of the post can be identified by performing vectorization of information associated with a defined area that includes the posts. For example, if a floor includes a number of posts, the workflow generation module 140may perform vectorization of the floor to identify each post area. In some examples, the post area can be provided as text format from the managing device 125, and the workflow generation module 140can process the text format and identify the post area by associating it with the vectorized space of the area. In some instances, the machine learned module 112 can be utilized to generate the vectorized areas.

[0232] In some embodiments, the workflow generation module 140processes these sub-master plans and determines attributes associated with each sub-master plans. In various instances, the attributes can include quantitative attributes and qualitative attributes. The quantitative attributes, for example, can be related to any attributes related to the sub-master plans that attributes are represented with numbers. For example, in an application of the automated run-time workflow assignment system for the security patrol service provider, thequantitative attributes can include but are not limited to years of experience, number of successful patrols completed, number of incidents resolved, availability of the patrol officer, location of the patrol officer, patrol officer’s response time to the incident, rate of the patrol officer, and the like. The qualitative attributes can be identified based on the behavior of the employees, feedback, descriptive information about the employees, etc. For example, the qualitative attributes can include but are not limited to patrol officer’s communication skills, decision-making skills, integrity, interpersonal skills, knowledge of the regulations and patrol policy, customer service skills, etc. These attributes are generally from other people’s reviews (or descriptions) about the specific patrol official. Additionally, the qualitative attributes can also include the patrol officer’s own feedback, opinion, and / or survey results. These quantitative and qualitative attributes are determined based on specific applications, and the present disclosure does not limit the types of attributes.

[0233] In some embodiments, the workflow generation module 140may identify the available employees who can work on one or more sub-master plans. In some examples, the workflow generation module 140can access its database 150 and identify the available employees. For example, if the automated run-time workflow assignment system is used by a security patrol service provider, the database 150 of the automated run-time workflow assignment system 110 may store the employed security patrol officer information. In some embodiments, the workflow generation module 140may determine the confidence score for each employee based on the determined workflow and its attributes. For example, if the master plan is patrolling a bank building, the sub-master plan can include patrolling a security room for 24 hours with 2 hours shift. In this example, the workflow generation module 140may identify the attributes, such as the quantitative attributes can include each office with each least 5 years of security patrol experience, more than 95% of successfully completed patrols, having a license to use pistol, having a zero crime record, located within 5 miles from the bank building, and / or with hourly rate less than $200. Further, in this example, the qualitative attributes can include each officer’s preference for working patrolling the security area, previous feedback on working at the bank building, knowledge of the regulation, and / or previous customer feedback.

[0234] In some embodiments, the workflow generation module 140can generate a confidence score for assigning each available employee to the available workflows associatedwith the sub-master plans. For example, after identifying the above attributes, the workflow generation module 140may generate a low confidence score (or filter out) for the patrol officers who do not meet the quantitative attributes. The workflow generation module 140may determine the confidence score of the remaining patrol officers based on the qualitative attributes. For example, each attribute of the qualitative attributes can have a different weight, and the confidence score can be determined based on each employee’s evaluation based on the qualitative attributes. The weight of each attribute and its determination of the confidence score can be different based on the specific applications.

[0235] In some examples, the workflow generation module 140may transmit the available sub-master plans to the computing devices 102 used by the employees. In various embodiments, the computing device 102 can be configured to receive the available sub-master plans from the workflow generation module 118. In addition, the computing device 102 can provide an interface that can display the available sub-master plans graphically and / or in context. In these embodiments, the employee can monitor the available sub-master plans and select one or more sub-master plans.

[0236] In some examples, the workflow generation module 140may assign the workflow associated with sub-master plans. In some examples, the assignment is based on the determined confidence score.

[0237] Some non-limiting examples of machine learning algorithms used for the machine learning module can include supervised and non-supervised machine learning algorithms, including regression algorithms (such as, for example, Ordinary Least Squares Regression), instance-based algorithms (such as, for example, Learning Vector Quantization), decision tree algorithms (such as, for example, classification and regression trees), Bayesian algorithms (such as, for example, Naive Bayes), clustering algorithms (such as, for example, k-means clustering), association rule learning algorithms (such as, for example, Apriori algorithms), artificial neural network algorithms (such as, for example, Perceptron), deep learning algorithms (such as, for example, Deep Boltzmann Machine), dimensionality reduction algorithms (such as, for example, Principal Component Analysis), ensemble algorithms (such as, for example, Stacked Generalization), and / or other machine learning algorithms. These machine learning algorithms may include any type of machine learning algorithm, including hierarchical clustering algorithms and cluster analysis algorithms, such asa k-means algorithm. In some cases, the performing of the machine learning algorithms may include the use of an artificial neural network. By using machine-learning techniques, large amounts (such as terabytes or petabytes) of player interaction data may be analyzed to generate models.

[0238] FIG. 10 depicts one embodiment of the architecture of an illustrative workflow generation module 118. The workflow generation module 140can be designed to assign one or more employees to the workflows. It does this by acquiring workflow requirement data from managing devices 125, identifying the workflows and their corresponding attributes, and then assigning employees to each workflow. The assignment is based on the results of processing the identified attributes of available employees. The general architecture of the workflow generation module 140depicted in FIG. 10, includes an arrangement of computer hardware and software components that may be used to implement aspects of the present disclosure. As illustrated, the workflow generation module 140includes a processing unit 1002, a network interface 1004, a computer- readable medium drive 1006, and an input / output device interface 1008, all of which may communicate with one another by way of a communication bus. The components of the workflow generation module 140may be physical hardware components or implemented in a virtualized environment.

[0239] The network interface 1004 may provide connectivity to one or more networks, such as the networks 104 and 106 of FIG. 9.. The processing unit 1002 may thus receive information and instructions from other computing systems or services via a network. The processing unit 1002 may also communicate to and from memory 1010 and further provide output information for an optional display via the input / output device interface 1008. In some embodiments, the workflow generation module 140may include more (or fewer) components than those shown in FIG. 10

[0240] The memory 1010 may include computer program instructions that the processing unit 1002 executes in order to implement one or more embodiments. The memory 1010 generally includes RAM, ROM, or other persistent or non-transitory memory. The memory 1010 may store an operating system 1014 that provides computer program instructions for use by the processing unit 1002 in the general administration and operation of the workflow generation module 118. The memory 1010 may further include computer program instructions and other information for implementing aspects of the present disclosure.For example, in one embodiment, the memory 1010 includes interface software 1012 for communicating with other components or services and performing one or more aspects as disclosed herein.

[0241] The memory 1010 may include a master planning component 1016. In some embodiments, the master planning component 1016 can be configured to generate a master plan of workflow by processing workflow requirements received from the managing devices 125. For example, a system administrator (e.g., business operation manager, business administrator, etc.) may provide the workflow requirements to the master planning component 1016. In some scenarios, the workflow requirements can be provided as texts or any type of visual representation. In some examples, the master planning component 1016 may process the received workflow requirements to generate a master plan. The master plan can vary based on the specific applications. For example, the master plan of the application of security patrol service provider can include attributes of targeted patrol area(s), types of area(s), number of area(s), and the like.

[0242] In some embodiments, the master planning component 1016 can process the workflow requirements received from the managing devices and generate a hierarchical data structure. For example, if system 100 is implemented by a security patrol service provider, the hierarchical data can include various levels, such that the highest level of the data structure can be a building, the lower layer can be floors, the lower layer can be rooms within the floors, and the lowest layer can be the posts in each room. The master planning component 1016 may assign one or more required workflow for each level of the hierarchical data structure. For example, at the highest level, the master planning component 1016 may assign attributes of the types of patrol areas, required security level, patrol time, etc. For the purpose of the description, the lowest level of the data structure can be referred to as the sub-master plan. For example, in the sub-master plan, the master planning component 1016 may process the lowest level of the data structure by associating it with the required attributes. Further, in this example, if the lowest level of the data structure is posts, each post can be associated with the required patrol attributes for each post, such as the number of patrol officials, patrol time, required capability of the patrol official, and the like.

[0243] In some scenarios, the master planning component 1016 can vectorize the space of the targeted patrol area. For example, the master planning component 1016 canvectorize a targeted patrol building and identify the location and area of the post from the vector. In some examples, a security patrol contract may specify the post area, such as every 100 square feet of the patrol area needs one patrol official during a certain time. In these examples, the master planning component 1016 can vectorize the patrol area, and this vectorized area can be utilized to determine the corresponding post area, such as the 100 square feet. Furthermore, the master planning component 1016 can identify the number of patrol required officials by identifying the number of post areas based on the vectorized targeted patrol area. For example, if a vectorized size of a building is 10000 square feet, there would be 10 patrol officials needed at the same time slots.

[0244] The memory 1010 can also include a planning component 1018. The planning component 1018 can generate run-time workflows for a certain duration of time based on the master plan. For example, the automated run-time workflow assignment system may periodically generate workflows associated with a master plan. The duration of each period can be pre-defined and / or dynamically defined based on specific applications. Th present application does not limit the pre-defined duration of each period.

[0245] In some embodiments, the planning component 1018 can generate workflows associated with a master plan and periodically verify one or more portions of the workflows. The period can be determined as a pre-defined time period. The present disclosure does not limit the pre-defined period, and the duration can be determined based on specific application. For example, the planning component 1018 can verify the workflows for a duration of 2 weeks. In this example, the planning component 1018 can monitor the workflow attributes and / or the employee attributes that may trigger changes or modifications to the workflows for the duration of 2 weeks. In some examples, the planning component 1018 can detect one or more events that can cause the changes in the workflow requirements. For example, the events can relate to the changes in at least one attributes of the workflow and the employee attributes. For instance, the event can be changes of the workflow requirements, such as changes of the patrol areas and required number of patrol officers in each post. In this instance, the planning component 1018 can detect the events and modify the workflows based on the detected events.

[0246] In various examples, the planning component 1018 can assign employees for each workflow. The planning component 1018 may assign the employees periodically. Insome embodiments, the planning component 1018 may assign the employees to each workflow based on the master plan. Then, the planning component 1018 may monitor whether one or more events are occurring, and upon detecting the one or events, the planning component 1018 can update the existing assigned employees.

[0247] In various embodiments, the planning component 1018 may assign the employees by identifying the available employees who can work on one or more workflows. In some examples, the planning component 1018 can access its database and identify the available employees. For example, if the automated run-time workflow assignment system is used by a security patrol service provider, the database 150 of the automated run-time workflow assignment system may store the employed security patrol officer’s information. In some applications, the planning component 1018 may receive one or more available employees from the computing device 102. For example, the planning component 1018 may transmit the available sub-master plans to the computing devices 102 used by the employees. In various embodiments, the computing device 102 can be configured to receive the available workflows from the planning component 1018. In addition, the computing device 102 can provide an interface that can display the available sub-master plans graphically and / or in context. In these embodiments, the employee can monitor the available workflows and select one or more available workflows.

[0248] The planning component 1018 can also assign the employees by identifying qualified employees from the identified available employees. In some embodiments, the planning component 1018 may determine the confidence score for each available employee based on the determined workflow and its attributes. For example, if the master plan is patrolling a bank building, the sub-master plan can include patrolling a security room for 24 hours with 2 2-hour shift. In this example, the automated run-time workflow assignment system may identify the attributes, such as the quantitative attributes can include each office with each least 5 years of security patrol experience, more than 95% of successfully completed patrols, having a license to use a pistol, having a zero crime records, located within 5 miles from the bank building, and / or with hourly rate less than $200. Further, in this example, the qualitative attributes can include each officer’s preference for working patrolling the security area, previous feedback on working at the bank building, knowledge of the regulation, and / or previous customer feedback.

[0249] In this scenario, the planning component 1018 can evaluate patrol officers based on certain identified attributes. Officers who fail to meet the quantitative criteria may be assigned a low confidence score or excluded entirely. The planning component 1018 then calculates confidence scores for the remaining officers using qualitative attributes. Each qualitative attribute can have a different weight, and the confidence score is determined by evaluating each officer’s performance against these attributes. The weight assigned to each attribute and the resulting confidence score can vary depending on the specific application. In some cases, the planning component 1018 may calculate confidence scores by weighing each of both quantitative and qualitative attributes. The planning component 1018 can also determine which employees are available for each workflow by filtering them based on a threshold confidence score. For instance, the selection of patrol officers for each workflow could be determined by the required confidence score for that workflow. Different workflows may require different confidence scores in some applications. In others, each workflow might have unique attributes and require a distinct threshold confidence score. These workflows, their associated attributes, and required confidence scores can be tailored to suit specific applications.

[0250] In certain instances, the planning component 1018 might sift through the pool of identified employees using a score-based filter, applying a threshold score that varies according to the specific applications. For instance, in the context of a security patrol area demanding highly proficient officers, the required threshold score would be set higher than in zones where a less rigorous security presence suffices.

[0251] In some embodiments, the planning component 1018 can further determine employees by further filtering based on a collective performance of each employee. In some examples, the planning component 1018 can filter the identified employees based on collective performance data. For example, if the collective performance data indicate that certain employees had poor performance, such as these employees did not come to the work, the automated run-time workflow assignment system may exclude these employees from the pool of identified employees. In some embodiments, the planning component 1018 can manage these employees who had poor performance record. For example, the automated run-time workflow assignment system can provide additional incentives to these employees to improve their work performance.

[0252] Turning now to FIGs. 11A and 11B, illustrative interactions of the components of the system 100, as shown in FIG. 9., will be described. For purposes of the illustration, it can be assumed that the automated run-time workflow assignment system 110 has been configured in a manner to implement the workflow generation module 118. For the purpose of description, FIGs 11A and 11B can be described with respect to a security patrol service provider. The present application is not intended to be limited to any particular type of service or the number of individual services that may be accessed or generate processing results as part of the execution of an application.

[0253] With reference to FIG. 11 A, an illustrative interaction of run-time workflows generation and assigning employees to one or more workflows that can be utilized in the aspects of the automated run-time workflow assignment system 110 will be described. The interaction is illustrative. At (1), a system administrator (e.g., business operation manager, business administrator, etc.) may provide the workflow requirements to the automated runtime workflow assignment system 110 via the managing devices 125. In some scenarios, the workflow requirements can be provided as texts or any type of visual representation or format. For example, if the automated run-time workflow assignment system 110 is implemented for a security patrol service provider, the workflow requirements can be provided as the security patrol service contracts.

[0254] At (2), the automated run-time workflow assignment system 110 can generate a master plan. The master plan can define work requirements that can be performed by employees. The master plan can vary based on specific applications. For example, the master plan of the application of security patrol service provider can include attributes of targeted patrol area(s), types of area(s), number of area(s), and the like. In some embodiments, the automated run-time workflow assignment system 110 can process the workflow requirements received from the managing devices and generate a hierarchical data structure. For example, if system 100 is implemented by a security patrol service provider, the hierarchical data can include various levels, such that the highest level of the data structure can be a building, the lower layer can be floors, the lower layer can be rooms within the floors, and the lowest layer can be the posts in each room.

[0255] In some scenarios, the automated run-time workflow assignment system 110 can vectorize the space of the targeted patrol area. For example, the automated run-timeworkflow assignment system 110 can vectorize a targeted patrol building and identify the location and area of the post (e.g., the lowest level of the data structure) from the vector. In some examples, a security patrol contract may specify the post area, such as every 100 square feet of the patrol area needs one patrol official during a certain time. In these examples, the automated run-time workflow assignment system 110 can vectorize the patrol area, and this vectorized area can be utilized to determine the corresponding post area, such as the 100 square feet. Furthermore, the automated run-time workflow assignment system 110 can identify the number of patrol required officials by identifying the number of post areas based on the vectorized targeted patrol area. For example, if a vectorized size of building is 10000 square feet, there would be 10 patrol officials are needed at the same time slot.

[0256] In some embodiments, where the security patrol service provider (or certain applications that employee’s workflows are related to the time shift) is utilizing the automated run-time workflow assignment system 110, the master plan and / or the sub-master plan can include time slots. For example, the plan can include a targeted patrol area or post and its associated shift time. The shift time can be processed to represent time slots.

[0257] At (3), the automated run-time workflow assignment system 110 may generate run-time workflows for a period. More specifically, the automated run-time workflow assignment system 110 can determine one or more required workflows for each level of the hierarchical data structure during a pre-defined period. The duration of each period can be predefined and / or dynamically defined based on specific applications. Th present application does not limit the pre-defined duration of each period. Illustratively, at the highest level of the master plan, the automated run-time workflow assignment system 110 may determine the workflows based on the types of patrol areas, required security level, patrol time, etc. For the purpose of the description, the lowest level of the data structure can be referred to as a sub-master plan. For example, in the sub-master plan, the automated run-time workflow assignment system 110 may process the lowest level of the data structure by associating it with the required workflows. Further, in this example, if the lowest level of the data structure is posts, each post can be associated with the required patrol workflows for each post, such as the number of patrol officials, patrol time, required capability of the patrol official, and the like. Thus, the automated run-time workflow assignment system 110 can determine the workflows during the pre-defined period of time.

[0258] In various embodiments, the automated run-time workflow assignment system 110 can determine attributes for each workflow. In some embodiments, the automated run-time workflow assignment system 110 further processes these sub-master plans and determines attributes associated each sub-master plan. In various instances, the attributes can include quantitative attributes and qualitative attributes. The quantitative attributes, for example, can be related to any attributes related to the sub-master plans that attributes are represented with numbers. For example, in an application of the automated run-time workflow assignment system for the security patrol service provider, the quantitative attributes can include but are not limited to years of experience, number of successful patrols completed, number of incidents resolved, availability of the patrol officer, location of the patrol officer, patrol officer’s response time to the incident, rate of the patrol officer, and the like. The qualitative attributes can be identified based on the behavior of the employees, feedback, descriptive information about the employees, etc. For example, the qualitative attributes can include but are not limited to patrol officers’ communication skills, decision-making skills, integrity, interpersonal skills, knowledge of the regulations and patrol policy, customer service skills, etc. These attributes are generally from other people’s reviews (or descriptions) about the specific patrol official. Additionally, the qualitative attributes can also include the patrol officer’s own feedback, opinion, and / or survey results. These quantitative and qualitative attributes are determined based on specific applications, and the present disclosure does not limit the types of attributes.

[0259] At (4), the automated run-time workflow assignment system 110 may determine employees for each workflow. In some embodiments, the automated run-time workflow assignment system 110 may identify the available employees who can work on one or more sub-master plans. In some examples, the automated run-time workflow assignment system can access its database and identify the available employees. For example, if the automated run-time workflow assignment system is used by a security patrol service provider, the database of the automated run-time workflow assignment system may store the employed security patrol officer’s information. In some applications, the automated run-time workflow assignment system 110 may receive one or more available employees from the computing device 102. For example, the automated run-time workflow assignment system 110 may transmit the available sub-master plans to the computing devices 102 used by the employees.In various embodiments, the computing device 102 can be configured to receive the available sub-master plans from the automated run-time workflow assignment system 110. In addition, the computing device 102 can provide an interface that can display the available sub-master plans graphically and / or in context. In these embodiments, the employee can monitor the available sub-master plans and select one or more sub-master plans.

[0260] Further at (4), the automated run-time workflow assignment system 110 can identify qualified employees from the identified available employees. In some embodiments, the automated run-time workflow assignment system 110 may determine the confidence score for each available employee based on the determined workflow and its attributes. For example, if the master plan is patrolling a bank building, the sub-master plan can include patrolling a security room for 24 hours with 2 hours shift. In this example, the automated run-time workflow assignment system may identify the attributes, such as the quantitative attributes can include each office with each least 5 years of security patrol experience, more than 95% of successful completed patrols, having a license to use pistol, having a zero crime records, located within 5 miles from the bank building, and / or with hourly rate less than $200. Further in this example, the qualitative attributes can include each officer’s preference for patrolling the security area, previous feedback on working at the bank building, knowledge of the regulation, and / or previous customer feedback.

[0261] In this scenario, the automated run-time workflow assignment system 110 can evaluate patrol officers based on certain identified attributes. Officers who fail to meet the quantitative criteria may be assigned a low confidence score or excluded entirely. The automated run-time workflow assignment system 110 then calculates confidence scores for the remaining officers using qualitative attributes. Each qualitative attribute can have a different weight, and the confidence score is determined by evaluating each officer’s performance against these attributes. The weight assigned to each attribute and the resulting confidence score can vary depending on the specific application. In some cases, the automated run-time workflow assignment system 110 may calculate confidence scores by weighing each of both quantitative and qualitative attributes. The automated run-time workflow assignment system 110 can also determine which employees are available for each workflow by filtering them based on a threshold confidence score. For instance, the selection of patrol officers for each workflow in the sub-master plan could be determined by the required confidence score for thatworkflow. Different workflows may require different confidence scores in some applications. In others, each workflow might have unique attributes and require a distinct threshold confidence score. These workflows, their associated attributes, and required confidence scores can be tailored to suit specific applications. In some embodiments, the automated run-time workflow assignment system 110 can utilize the machine learned module 112 to perform portion or all of the step (5).

[0262] In certain instances, the automated run-time workflow assignment system might sift through the pool of identified employees using a score-based filter, applying a threshold score that varies according to the specific applications. For instance, in the context of a security patrol area demanding highly proficient officers, the required threshold score would be set higher than in zones where a less rigorous security presence suffices.

[0263] In some embodiments, the automated run-time workflow assignment system can further determine employees by further filtering based on a collective performance of each employee. In some examples, the automated run-time workflow assignment system can filter the identified employees based on collective performance data. For example, if the collective performance data indicate that certain employees had poor performance, such as these employees did not come to the work, the automated run-time workflow assignment system may exclude these employees from the pool of identified employees. In some embodiments, the automated run-time workflow assignment system can manage these employees who had poor performance record. For example, the automated run-time workflow assignment system can provide additional incentives to these employees to improve their work performance.

[0264] At (5), the automated run-time workflow assignment system 110 can assign the employees to one or more available workflows included in the master plan or sub-master plans. In some embodiments, the assignment is based on the verification by using the confidence score at (5).

[0265] With reference to FIG. 11B, an illustrative interaction of workflows generation and assigning employees to one or more workflows that can be utilized in the aspects of the automated run-time workflow assignment system 110 will be described. The interaction is illustrative.

[0266] At (1), a system administrator (e.g., business operation manager, business administrator, etc.) may provide the workflow requirements to the automated run-time workflow assignment system 110 via the managing devices 125. In some scenarios, the workflow requirements can be provided as texts or any type of visual representation or format. For example, if the automated run-time workflow assignment system 110 is implemented for a security patrol service provider, the workflow requirements can be provided as the security patrol service contracts.

[0267] At (2), the automated run-time workflow assignment system 110 can generate a master plan. The master plan can define work requirements that can be performed by employees. The master plan can vary based on specific applications. For example, the master plan of the application of security patrol service provider can include attributes of targeted patrol area(s), types of area(s), number of area(s), and the like. In some embodiments, the automated run-time workflow assignment system 110 can process the workflow requirements received from the managing devices and generate a hierarchical data structure. For example, if system 100 is implemented by a security patrol service provider, the hierarchical data can include various levels, such that the highest level of the data structure can be a building, the lower layer can be floors, the lower layer can be rooms within the floors, and the lowest layer can be the posts in each room.

[0268] At (3), the automated run-time workflow assignment system 110 may determine one or more required workflows for each level of the hierarchical data structure. For example, at the highest level, the automated run-time workflow assignment system 110 may determine the workflows based on the types of patrol areas, required security level, patrol time, etc. For the purpose of the description, the lowest level of the data structure can be referred to as a sub-master plan. For example, in the sub-master plan, the automated run-time workflow assignment system 110 may process the lowest level of the data structure by associating it with the required workflows. Further, in this example, if the lowest level of the data structure is posts, each post can be associated with the required patrol workflows for each post, such as the number of patrol officials, patrol time, required capability of the patrol official, and the like.

[0269] In some scenarios, the automated run-time workflow assignment system 110 can vectorize the space of the targeted patrol area. For example, the automated run-time workflow assignment system 110 can vectorize a targeted patrol building and identify thelocation and area of the post (e.g., the lowest level of the data structure) from the vector. In some examples, a security patrol contract may specify the post area, such as every 100 square feet of the patrol area needs one patrol official during a certain time. In these examples, the automated run-time workflow assignment system 110 can vectorize the patrol area, and this vectorized area can be utilized to determine the corresponding post area, such as the 100 square feet. Furthermore, the automated run-time workflow assignment system 110 can identify the number of patrol required officials by identifying the number of post areas based on the vectorized targeted patrol area. For example, if a vectorized size of the building is 10000 square feet, there would be 10 patrol officials are needed at the same time slot.

[0270] In some embodiments, where the security patrol service provider (or certain applications that employee’s workflows are related to the time shift) is utilizing the automated run-time workflow assignment system 110, the master plan and / or the sub-master plan can include time slots. For example, the plan can include a targeted patrol area or post and its associated shift time. The shift time can be processed to represent time slots.

[0271] In some embodiments, the automated run-time workflow assignment system 110 further processes these sub-master plans and determines attributes associated each sub-master plan. In various instances, the attributes can include quantitative attributes and qualitative attributes. The quantitative attributes, for example, can be related to any attributes related to the sub-master plans that attributes are represented with numbers. For example, in an application of the automated run-time workflow assignment system for the security patrol service provider, the quantitative attributes can include but are not limited to years of experience, number of successful patrols completed, number of incidents resolved, availability of the patrol officer, location of the patrol officer, patrol officer’s response time to the incident, rate of the patrol officer, and the like. The qualitative attributes can be identified based on the behavior of the employees, feedback, descriptive information about the employees, etc. For example, the qualitative attributes can include but are not limited to patrol officers’ communication skills, decision-making skills, integrity, interpersonal skills, knowledge of the regulations and patrol policy, customer service skills, etc. These attributes are generally from other people’s reviews (or descriptions) about the specific patrol official. Additionally, the qualitative attributes can also include the patrol officer’s own feedback, opinion, and / or surveyAlresults. These quantitative and qualitative attributes are determined based on specific applications, and the present disclosure does not limit the types of attributes.

[0272] At (4), the automated run-time workflow assignment system 110 periodically verify one or more portions of the workflows. The period can be determined as a pre-defined time period. The present disclosure does not limit the pre-defined period, and the duration can be determined based on specific application. For example, the automated runtime workflow assignment system 110 can verify the workflows for a duration of 2 weeks. In this example, the automated run-time workflow assignment system 110 can monitor the workflow attributes and / or the employee attributes that may trigger a changes or modifications to the workflows for the duration of 2 weeks. In some examples, the automated run-time workflow assignment system 110 can detects one or more events that can cause changes in the workflow requirements. For example, the events can relate to the changes in at least one attribute of the workflow and the employee attributes. For instance, the event can be changes of the workflow requirements, such as changes of the patrol areas and the required number of patrol officers in each post. At (5), the automated run-time workflow assignment system 110 can modify the workflows based on the detected events.

[0273] At (6), the automated run-time workflow assignment system 110 may determine employees for each workflow. In some embodiments, the automated run-time workflow assignment system 110 may identify the available employees who can work on one or more sub-master plans. In some examples, the automated run-time workflow assignment system can access its database and identify the available employees. For example, if the automated run-time workflow assignment system is used by a security patrol service provider, the database of the automated run-time workflow assignment system may store the employed security patrol officer’s information. In some applications, the automated run-time workflow assignment system 110 may receive the one or more available employees from the computing device 102. For example, the automated run-time workflow assignment system 110 may transmit the available sub-master plans to the computing devices 102 used by the employees. In various embodiments, the computing device 102 can be configured to receive the available sub-master plans from the automated run-time workflow assignment system 110. In addition, the computing device 102 can provide an interface that can display the available sub-masterplans graphically and / or in context. In these embodiments, the employee can monitor the available sub-master plans and select one or more sub-master plans.

[0274] Further at (6), the automated run-time workflow assignment system 110 can identify qualified employees from the identified available employees. In some embodiments, the automated run-time workflow assignment system 110 may determine confidence score for each available employee based on the determined workflow and its attributes. For example, if the master plan is patrolling a bank building, the sub-master plan can include patrolling a security room for 24 hours with 2 hours shift. In this example, the automated run-time workflow assignment system may identify the attributes, such as the quantitative attributes can include each office with each least 5 years of security patrol experience, more than 95% of successfully completed patrols, having a license to use a pistol, having a zero crime records, located within 5 miles from the bank building, and / or with hourly rate less than $200. Further, in this example, the qualitative attributes can include each officer’s preference for patrolling the security area, previous feedback on working at the bank building, knowledge of the regulation, and / or previous customer feedback.

[0275] In this scenario, the automated run-time workflow assignment system 110 can evaluate patrol officers based on certain identified attributes. Officers who fail to meet the quantitative criteria may be assigned a low confidence score or excluded entirely. The automated run-time workflow assignment system 110 then calculates confidence scores for the remaining officers using qualitative attributes. Each qualitative attribute can have a different weight, and the confidence score is determined by evaluating each officer’s performance against these attributes. The weight assigned to each attribute and the resulting confidence score can vary depending on the specific application. In some cases, the automated run-time workflow assignment system 110 may calculate confidence scores by weighing each of both quantitative and qualitative attributes. The automated run-time workflow assignment system 110 can also determine which employees are available for each workflow by filtering them based on a threshold confidence score. For instance, the selection of patrol officers for each workflow in the sub-master plan could be determined by the required confidence score for that workflow. Different workflows may require different confidence scores in some applications. In others, each workflow might have unique attributes and require a distinct threshold confidence score. These workflows, their associated attributes, and required confidence scorescan be tailored to suit specific applications. In some embodiments, the automated run-time workflow assignment system 110 can utilize the machine learned module 112 to perform a portion or all of the step (6).

[0276] At (7), the automated run-time workflow assignment system 110 can assign the employees to one or more available workflows included in the master plan or sub-master plans. In some embodiments, the assignment is based on the verification by using the confidence score.

[0277] FIG. 12A describes a routine 1200 for generating run-time workflows. The routine 1200 can correspond to the illustrative interaction described in FIG. 11 A. For the purpose of illustration, the routine 1200 can be performed by the automated run-time workflow assignment system 110 provided by a network service provider.

[0278] At block 1202, the automated run-time workflow assignment system 110 obtains a set of inputs from a database 150 included in the automated run-time workflow assignment system. In some examples, the set of inputs includes a set of target areas, and each target area includes a plurality of sub-areas.

[0090] At block 1204, the automated run-time workflow assignment system 110 generates, by utilizing a machine learning component stored in the memory 1010, a master plan based on the set of inputs. In some examples, the master plan includes a set of hierarchical data, and the hierarchical data can include a plurality of layers, where each layer is associated with one or more vectorized sub-areas and associated workflows. In some cases, the machine learning component is stored in the memory as a module. In some examples, the master plan includes vectorized identifications of each of the plurality of sub-areas and workflows for each identified sub-area, and the machine learning component includes a neural network model configured to collect, from a historical data stored in a database, a historical plurality of sub-areas and historical workflows associated with each sub-area of the historical plurality of sub-areas, apply the historical data the neural network model, generate a set of workflows associated with the historical data, train the neural network model by updating neural network parameters by comparing the generated set of workflows associated with the historical plurality of sub-areas and the historical workflows associated with each sub-area of the historical plurality of sub-areas, and generate the workflows associated to each vectorized identified sub-area. In some examples, the workflows are patrolling a patrol area, where a top level of the hierarchical data is patrolling the patrol area,having a plurality of posts, wherein a lower level of the hierarchical data is a patrolling plan of each post of the plurality of posts. In some cases, the automated run-time workflow assignment system is configured to periodically updates the master plan, and the master plan can include a number of demanded employees for each workflow.

[0279] At block 1206, the automated run-time workflow assignment system 110 determines, by accessing the database 150, one or more manifests associated with the identified workflow. In some examples, the manifest of each identified workflow includes location information and time information. In various embodiments, the database 150 can be configured to store a plurality of manifests associated with a plurality of workflows.

[0280] At block 1208, the automated run-time workflow assignment system 110 accesses the database 150 to identify profile information of a plurality of employee identifications. In some examples, the profile information comprising geometry identifiers and time identifiers of each of the plurality of employee identifications. In some examples, the automated run-time workflow assignment system is communicatively coupled with one or more employee computing devices, and each employee is configured to manage corresponding profile information by accessing the database via associated employee computing device.

[0281] At block 1210, the automated run-time workflow assignment system 110 determines, for each vectorized sub-area, one or more employee identifications by comparing the geometry and time identifiers of each of the plurality of employees with the location information and time information included in the manifest of each workflow.

[0282]

[0912] At block 1212, the automated run-time workflow assignment system 110 assigns each workflow to identified corresponding one or more employee identifications. In some embodiments, the neural network model is configured to assign the identified employee identifications to the workflows by collecting, from the database, a set of attributes of each of the identified employee identifications, where the set of attributes include quantitative attributes and qualitative attributes, vectorizing each of the quantitative attributes and qualitative attributes, applying the vectorized quantitative attributes and qualitative attributes to the neural network model, generating, for each identified employee identification, a confidence score by applying the vectorized quantitative attributes and the qualitative attributes to the neural network model, prioritizing, for each workflow, the identified employee identifications based on the confidence score of each of the identified employee identifications,and assigning the identified employee identifications to the workflows based on prioritization results. In some cases, the machine learning component is further configured to dynamically assign the identified employee identifications to the workflows by dynamically updating the quantitative attributes and qualitative attributes of the identified employees. In various embodiments, the automated run-time workflow assignment system is configured monitor the confidence score.

[0283] In some embodiments, the automated run-time workflow assignment system is further configured receive the set of inputs from an external computing device. Additionally, the automated run-time workflow assignment system is further configured to authenticate the external computing device by receiving an application program interface token from the external computing device and verifying the received application program interface token. The routine 1200 can end at block 1214.

[0284] Although the operations of the routine 1200 are described in a particular order, it should be understood that the routine 1200 is not limited as such. Operations of the routine 1200 may be performed in an alternative order, serially, or at least partially in parallel. Further, certain operations may not need to be performed. For example, operations associated with the block 1206 and block 1208 may be performed in parallel.

[0285] Although the operations of the routine 1200 are described in a particular order, it should be understood that the routine 1200 is not limited as such. Operations of the routine 1200 may be performed in an alternative order, serially, or at least partially in parallel. Further, certain operations may not need to be performed.

[0286] FIG. 12B describes a routine 1250 for generating run-time workflows. The routine 1250 can correspond to the illustrative interaction described in FIG. 1 IB.

[0287] At block 1252, a system administrator (e.g., business operation manager, business administrator, etc.) may provide the workflow requirements to the automated runtime workflow assignment system 110 via the managing devices 125. In some scenarios, the workflow requirements can be provided as texts or any type of visual representation or format. For example, if the automated run-time workflow assignment system 110 is implemented for a security patrol service provider, the workflow requirements can be provided as the security patrol service contracts.

[0288] At block 1254, the automated run-time workflow assignment system 110 can generate a master plan. The master plan can define work requirements that can be performed by employees. The master plan can vary based on specific applications. For example, the master plan of the application of security patrol service provider can include attributes of targeted patrol area(s), types of area(s), number of area(s), and the like. In some embodiments, the automated run-time workflow assignment system 110 can process the workflow requirements received from the managing devices and generate a hierarchical data structure. For example, if system 100 is implemented by a security patrol service provider, the hierarchical data can include various levels, such that the highest level of the data structure can be a building, the lower layer can be floors, the lower layer can be rooms within the floors, and the lowest layer can be the posts in each room.

[0289] Further at block 1254, the automated run-time workflow assignment system 110 may determine one or more required workflows for each level of the hierarchical data structure. For example, at the highest level, the automated run-time workflow assignment system 110 may determine the workflows based on the types of patrol areas, required security level, patrol time, etc. For the purpose of the description, the lowest level of the data structure can be referred to as a sub-master plan. For example, in the sub-master plan, the automated run-time workflow assignment system 110 may process the lowest level of the data structure by associating it with the required workflows. Further, in this example, if the lowest level of the data structure is posts, each post can be associated with the required patrol workflows for each post, such as the number of patrol officials, patrol time, required capability of the patrol official, and the like.

[0290] In some scenarios, the automated run-time workflow assignment system 110 can vectorize the space of the targeted patrol area. For example, the automated run-time workflow assignment system 110 can vectorize a targeted patrol building and identify the location and area of the post (e.g., the lowest level of the data structure) from the vector. In some examples, a security patrol contract may specify the post area, such as every 100 square feet of the patrol area needs one patrol official during a certain time. In these examples, the automated run-time workflow assignment system 110 can vectorize the patrol area, and this vectorized area can be utilized to determine the corresponding post area, such as the 100 square feet. Furthermore, the automated run-time workflow assignment system 110 can identify thenumber of patrol required officials by identifying the number of post areas based on the vectorized targeted patrol area. For example, if a vectorized size of the building is 10000 square feet, there would be 10 patrol officials are needed at the same time slot.

[0291] In some embodiments, where the security patrol service provider (or certain applications that employee’s workflows are related to the time shift) is utilizing the automated run-time workflow assignment system 110, the master plan and / or the sub-master plan can include time slots. For example, the plan can include a targeted patrol area or post and its associated shift time. The shift time can be processed to represent time slots.

[0292] In some embodiments, the automated run-time workflow assignment system 110 further processes these sub-master plans and determines attributes associated each sub-master plan. In various instances, the attributes can include quantitative attributes and qualitative attributes. The quantitative attributes, for example, can be related to any attributes related to the sub-master plans that attributes are represented with numbers. For example, in an application of the automated run-time workflow assignment system for the security patrol service provider, the quantitative attributes can include but are not limited to years of experience, number of successful patrols completed, number of incidents resolved, availability of the patrol officer, location of the patrol officer, patrol officer’s response time to the incident, rate of the patrol officer, and the like. The qualitative attributes can be identified based on the behavior of the employees, feedback, descriptive information about the employees, etc. For example, the qualitative attributes can include but are not limited to patrol officers’ communication skills, decision-making skills, integrity, interpersonal skills, knowledge of the regulations and patrol policy, customer service skills, etc. These attributes are generally from other people’s reviews (or descriptions) about the specific patrol official. Additionally, the qualitative attributes can also include the patrol officer’s own feedback, opinion, and / or survey results. These quantitative and qualitative attributes are determined based on specific applications, and the present disclosure does not limit the types of attributes.

[0293] At block 1256, the automated run-time workflow assignment system 110 determine whether an event is detected. In some examples, the automated run-time workflow assignment system 110 periodically verify one or more portions of the workflows. The period can be determined as a pre-defined time period. The present disclosure does not limit the predefined period, and the duration can be determined based on specific application. For example,the automated run-time workflow assignment system 110 can verify the workflows for a duration of 2 weeks. In this example, the automated run-time workflow assignment system 110 can monitor the workflow attributes and / or the employee attributes that may trigger a changes or modifications to the workflows for the duration of 2 weeks. In some examples, the automated run-time workflow assignment system 110 can detects one or more events that can cause the changes in the workflow requirements. For example, the events can relate to the changes in at least one attributes of the workflow and the employee attributes. For instance, the event can be changes of the workflow requirements, such as changes of the patrol areas and required number of patrol officers in each post. If the event is detected the routine 1250 proceed to block 1258. If no event is detected, the routine proceed to block 1260.

[0294] At block 1258, the automated run-time workflow assignment system 110 can modify the workflows based on the detected events.

[0295] At block 1260, the automated run-time workflow assignment system 110 may determine employees for each workflow. In some embodiments, the automated run-time workflow assignment system 110 may identify the available employees who can work on one or more sub-master plans. In some examples, the automated run-time workflow assignment system can access its database and identify the available employees. For example, if the automated run-time workflow assignment system is used by a security patrol service provider, the database of the automated run-time workflow assignment system may store the employed security patrol officer’s information. In some applications, the automated run-time workflow assignment system 110 may receive the one or more available employees from the computing device 102. For example, the automated run-time workflow assignment system 110 may transmit the available sub-master plans to the computing devices 102 used by the employees. In various embodiments, the computing device 102 can be configured to receive the available sub-master plans from the automated run-time workflow assignment system 110. In addition, the computing device 102 can provide an interface that can display the available sub-master plans graphically and / or in context. In these embodiments, the employee can monitor the available sub-master plans and select one or more sub-master plans.

[0296] Further, at block 1260, the automated run-time workflow assignment system 110 can identify qualified employees from the identified available employees. In some embodiments, the automated run-time workflow assignment system 110 may determine theconfidence score for each available employee based on the determined workflow and its attributes. For example, if the master plan is patrolling a bank building, the sub-master plan can include patrolling a security room for 24 hours with 2 hours shift. In this example, the automated run-time workflow assignment system may identify the attributes, such as the quantitative attributes can include each office with each least 5 years of security patrol experience, more than 95% of successfully completed patrols, having a license to use a pistol, having a zero crime records, located within 5 miles from the bank building, and / or with hourly rate less than $200. Further in this example, the qualitative attributes can include each officer’s preference for patrolling the security area, previous feedback on working at the bank building, knowledge of the regulation, and / or previous customer feedback.

[0297] In this scenario, the automated run-time workflow assignment system 110 can evaluate patrol officers based on certain identified attributes. Officers who fail to meet the quantitative criteria may be assigned a low confidence score or excluded entirely. The automated run-time workflow assignment system 110 then calculates confidence scores for the remaining officers using qualitative attributes. Each qualitative attribute can have a different weight, and the confidence score is determined by evaluating each officer’s performance against these attributes. The weight assigned to each attribute and the resulting confidence score can vary depending on the specific application. In some cases, the automated run-time workflow assignment system 110 may calculate confidence scores by weighing each of both quantitative and qualitative attributes. The automated run-time workflow assignment system 110 can also determine which employees are available for each workflow by filtering them based on a threshold confidence score. For instance, the selection of patrol officers for each workflow in the sub-master plan could be determined by the required confidence score for that workflow. Different workflows may require different confidence scores in some applications. In others, each workflow might have unique attributes and require a distinct threshold confidence score. These workflows, their associated attributes, and required confidence scores can be tailored to suit specific applications. In some embodiments, the automated run-time workflow assignment system 110 can utilize the machine learned module 112 to perform portion or all of the block 1260.

[0298] In certain instances, the automated run-time workflow assignment system might sift through the pool of identified employees using a score-based filter, applying athreshold score that varies according to the specific applications. For instance, in the context of a security patrol area demanding highly proficient officers, the required threshold score would be set higher than in zones where a less rigorous security presence suffices.

[0299] In some embodiments, the automated run-time workflow assignment system can further determine employees by further filtering based on a collective performance of each employee. In some examples, the automated run-time workflow assignment system can filter the identified employees based on collective performance data. For example, if the collective performance data indicate that certain employees had poor performance, such as these employees did not come to the work, the automated run-time workflow assignment system may exclude these employees from the pool of identified employees. In some embodiments, the automated run-time workflow assignment system can manage these employees who had poor performance record. For example, the automated run-time workflow assignment system can provide additional incentives to these employees to improve their work performance.

[0300] At block 1262, the automated run-time workflow assignment system 110 can assign the employees to one or more available workflows included in the master plan or sub-master plans. In some embodiments, the assignment is based on the verification by using the confidence score at block 1260. The routine 1250 can be ended at block 1264.

[0301] Although the operations of the routine 1250 are described in a particular order, it should be understood that the routine 1200 is not limited as such. Operations of the routine 1250 may be performed in an alternative order, serially, or at least partially in parallel. Further, certain operations may not need to be performed. For example, operations associated with the block 1206 and block 1208 may be performed in parallel.

[0302] Although the operations of the routine 1250 are described in a particular order, it should be understood that the routine 1250 is not limited as such. Operations of the routine 1200 may be performed in an alternative order, serially, or at least partially in parallel. Further, certain operations may not need to be performed.EXAMPLE EMBODIMENTS I

[0303] Clause 1. A system for dynamically generating employee training instructions in network-based services, the system comprising:one or more computing devices associated with a processor and a memory for executing computer-executable instructions to implement an automated training service, wherein the automated training service is configured to: obtain a set of inputs from a plurality of computing devices, wherein the set of inputs comprises geometry identifiers and time identifiers of each of the plurality of computing devices; obtain a set of additional inputs from a database communicatively coupled with the automated training service, the set of additional inputs comprising a set of target areas, each target area comprising a plurality of subareas; generate one or more workflows for each of the plurality of sub-areas, each workflow of the one or more workflows comprises attributes comprising time data and location data; generate, for each workflow, filtering criteria, having the attributes; filter, for each workflow, the set of inputs based on the filtering criteria by filtering the geometry identifiers and the time identifiers of the plurality of computing devices based on the time data and the location data of the criteria such that each sub-area is associated with one or more workflows, each workflow of the one or more workflows associated with identifications of computing devices, corresponding to the filtered set of inputs; generate, for each workflow, one or more training instructions by obtaining a set of manifests associated with each workflow from the database, wherein the database is configured to store a plurality of workflows and sets of manifests associated with each workflow; and transmit, for each workflow, the generated training instructions associated with each workflow to one or more computing devices, having the identifications associated with each workflow.

[0304] Clause 2. The system of Clause 1, wherein the attributes of each workflow comprises a set of hierarchical data, the hierarchical data comprising a plurality of layers, each layer associated with one or more assigned manifests.

[0305] Clause 3. The system of Clause 2, wherein the location data of the workflows include patrol areas, wherein a top level of the hierarchical data is a master plan for patrolling the patrol areas, having a plurality of posts, wherein a lower level of the hierarchical data is a patrolling plan of each post of the plurality of posts, and wherein the patrolling plan comprises number of demanded employees and demanded time duration for patrolling corresponding post.

[0306] Clause . The system of Clause 3, wherein attributes of the workflow further comprise demanded duty and skills of employee to perform the master plan for patrolling corresponding post.

[0307] Clause 5. The system of Clause 1, wherein the memory stores a machine learning component, the machine learning component including a neural network model configured to dynamically update the workflows, wherein the neural network model is configured to: collect a set of sensor data from a plurality of sensors operatively coupled with the automated training service, apply the collected set of sensor data to the workflows to the neural network model, and generate updated workflows as results of the application of the collected set of sensor data to the workflows.

[0308] Clause 6. The system of Clause 5, wherein the neural network model is further configured to create a training set comprising the workflows, the collected set of sensor data, and the updated workflows, wherein the neural network model is continuously trained by using the training set.

[0309] Clause 7. The system of Clause 6, wherein the machine learning component is further configured to dynamically generate the training instructions by utilizing the created training set.

[0310] Clause 8. The system of Clause 5, wherein the set of sensor data comprises temperature sensors, object detection sensors, gas sensors, image sensors, and radar sensors.

[0311] Clause 9. The system of Clause 5, wherein the machine learning component is configured to generate a plurality of training scenarios by modifying one or moresensor data of the collected set of sensor data, applying the modified one or more sensor data to the neural network model, and generating the plurality of training scenarios based on the modified one or more sensor data and results of applying the modified one or more sensor data.

[0312] Clause 10. The system of Clause 1, wherein the automated training service is further configured to authenticate the computing device by receiving an application program interface token from the plurality of computing devices and verifying the received application program interface token.

[0313] Clause 11. The system of Clause 1 , wherein the automated training service is further configured to receive answers to the generated training instructions from the one or more computing devices, having the identifications associated with each workflow, and filter the one or more computing devices, having the identifications associated with each workflow by verifying the received answers.

[0314] Clause 12. A system for dynamically generating employee training instructions in network-based services, the system comprising: one or more computing devices associated with a processor and a memory for executing computer-executable instructions to implement an automated training service, wherein the automated training service is configured to: obtain a set of additional inputs from a database communicatively coupled with the automated training service, the set of additional inputs comprising a set of target areas, each target area comprising a plurality of subareas; generate one or more workflows for each of the plurality of sub-areas, each workflow of the one or more workflows comprises attributes comprising time data and location data; generate, for each workflow, one or more training instructions by obtaining a set of manifests associated with each workflow from the database, wherein the database is configured to store a plurality of workflows and sets of manifests associated with each workflow; transmit, for each workflow, the generated training instructions associated with each workflow to target computing devices communicatively coupled with the automated training service.

[0315] Clause 13. The system of Clause 12, wherein the attributes of each workflow comprises a set of hierarchical data, the hierarchical data comprising a plurality of layers, each layer associated with one or more assigned manifests.

[0316] Clause 14. The system of Clause 13, wherein the location data of the workflows include patrol areas, wherein a top level of the hierarchical data is a master plan for patrolling the patrol areas, having a plurality of posts, wherein a lower level of the hierarchical data is a patrolling plan of each post of the plurality of posts, and wherein the patrolling plan comprises number of demanded employees, and demanded time duration for patrolling corresponding post.

[0317] Clause 15. The system of Clause 12, wherein the memory stores a machine learning component, the machine learning component including a neural network model configured to dynamically update the workflows, wherein the neural network model is configured to: collect a set of sensor data from a plurality of sensors operatively coupled with the automated training service, apply the collected set of sensor data to the workflows to the neural network model, and generate updated workflows as results of the application of the collected set of sensor data to the workflows.

[0318] Clause 16. The system of Clause 15, wherein the neural network model is further configured to create a training set comprising the workflows, the collected set of sensor data, and the updated workflows, wherein the neural network model is continuously trained by using the training set.

[0319] Clause 17. The system of Clause 16, wherein the set of sensor data comprises temperature sensors, object detection sensors, gas sensors, and image sensors, radar sensors.

[0320] Clause 18. The system of Clause 16, wherein the machine learning component is configured to generate a plurality of training scenarios by modifying one or more sensor data of the collected set of sensor data, applying the modified one or more sensor data to the neural network model, and generating the plurality of training scenarios based on the modified one or more sensor data and results of applying the modified one or more sensor data.

[0321] Clause 19. The system of Clause 12, wherein the target computing devices are associated with employees pre-assigned to each workflow.

[0322] Clause 20. A method for dynamically generating employee training instructions in network-based services, the method comprising: obtaining a set of inputs from a plurality of computing devices, wherein the set of inputs comprises geometry identifiers and time identifiers of each of the plurality of computing devices; obtaining a set of additional inputs from a database, the set of additional inputs comprising a set of target areas, each target area comprising a plurality of sub-areas; generating one or more workflows for each of the plurality of sub-areas, each workflow of the one or more workflows comprises attributes comprising time data and location data; generating, for each workflow, filtering criteria, having the attributes; filtering, for each workflow, the set of inputs based on the filtering criteria by filtering the geometry identifiers and the time identifiers of the plurality of computing devices based on the time data and the location data of the criteria such that each subarea is associated with one or more workflows, each workflow of the one or more workflows associated with identifications of computing devices, corresponding to the filtered set of inputs; generating, for each workflow, one or more training instructions by obtaining a set of manifests associated with each workflow from the database, wherein the database is configured to store a plurality of workflows and sets of manifests associated with each workflow; and transmitting, for each workflow, the generated training instructions associated with each workflow to one or more computing devices, having the identifications associated with each workflow.EXAMPLE EMBODIMENTS II

[0323] Clause 1. A system for dynamically providing workflow instructions in network-based services, the system comprising:one or more computing devices associated with a processor and a memory for executing computer-executable instructions to implement a workflow monitoring service, wherein the workflow monitoring service is configured to: obtain a set of location information from a plurality of computing devices, wherein the set of location information comprises geometry identifiers and time identifiers of each of the plurality of computing devices; track locations of the plurality of computing devices by analyzing the set of location information within targeted areas, wherein the targeted areas include a plurality of sub-areas, and wherein each sub-area is vectorized and stored in the memory; obtain a set of inputs from one or more of the plurality of computing devices located in the targeted areas, wherein the set of inputs comprises one or more captured images captured in one of the sub-areas; obtain a set of additional inputs from a plurality of sensors deployed in the targeted areas; analyze, by utilizing a machine learning component stored in the memory, the set of inputs and the set of additional inputs to determine risk scores associated with the targeted areas, wherein results of the analysis indicate risk scores of sub-areas associated with the set of inputs, wherein the machine learning component comprises a neural network model trained to generate the risk scores of the sub-areas, the neural network model is configured to: collect, from a historical data stored in a database, a set of previous inputs, a set of previous additional inputs, and risk scores associated with the set of previous inputs and additional inputs, apply the set of previous inputs and the set of previous additional inputs to the neural network model, generate a set of risk scores associated with corresponding subareas associated with the set of previous inputs and the set of previous additional inputs,train the neural network model by verifying the generated set of risk scores with the risk scores associated with the set of previous inputs and additional inputs, and determine the risk scores by using the trained neural network model; determine, for each sub-area associated with the set of inputs, whether the risk score is at or above a threshold risk score; generate, for each vectorized sub-area having the risk score at or above the threshold risk score, workflow instructions, the workflow instructions configured to mitigate risks of the vectorized sub-areas, having the risk score at or above the threshold risk score; and transmit the generated workflow instructions to one or more computing devices located in proximity to the vectorized sub-areas, having the risk score at or above the threshold risk score, wherein the one or more computing devices are identified based on the obtained set of location information.

[0324] Clause 2. The system of Clause 1, wherein the workflow instructions comprise a set of hierarchical data, the hierarchical data comprising a plurality of layers, each layer associated with one or more instructions to be performed by one or more employees associated with the one or more computing devices located in proximity to the vectorized sub-areas, having the risk score at or above the threshold risk score.

[0325] Clause 3. The system of Clause 2, wherein the one or more instructions are patrolling a patrol area, wherein a top level of the hierarchical data is a master plan for patrolling the patrol area, having a plurality of posts, wherein a lower level of the hierarchical data is a patrolling plan of each post of the plurality of posts.

[0326] Clause d. The system of Clause 1, wherein the neural network model is further configured to dynamically generate the workflow instructions by: collecting, from the historical data stored in the database, the set of previous inputs, the set of previous additional inputs, and a set of historical risk scores associated with the set of previous inputs and the set of previous additional inputs, applying the set of previous inputs and the set of previous additional inputs to the neural network model, andgenerating a set of workflow instructions associated with corresponding vectorized sub-areas associated with the set of previous inputs and the set of previous additional inputs.

[0327] Clause 5. The system of Clause 4, wherein the neural network model is further configured to create a training set by comparing the generated set of set of workflow instructions with a historical set of workflow instructions stored in the database, the historical set of workflow instructions associated with the set of previous inputs and the set of previous additional inputs.

[0328] Clause 6. The system of Clause 4, wherein the machine learning component is further configured to dynamically generate the workflow instructions by dynamically receiving the set of additional data.

[0329] Clause 7. The system of Clause 4, wherein the machine learning component is configured to generate a plurality of workflow instructions by modifying one or more sensor data of the set of additional inputs, applying the modified one or more sensor data to the neural network model, and generating the plurality of workflow instructions based on the modified one or more sensor data.

[0330] Clause 8. The system of Clause 1, wherein the machine learning component is configured to train the neural network model by updating neural network parameters by comparing the generated set of risk scores and historical set of risk scores stored in the database, the historical set of risk scores associated with the set of previous inputs and the set of previous additional inputs.

[0331] Clause 9. The system of Clause 1 , wherein the plurality of sensors comprises temperature sensors, object detection sensors, gas sensors, image sensors, and radar sensors.

[0332] Clause 10. The system of Clause 1, wherein the workflow monitoring service is further configured to authenticate the computing device by receiving an application program interface token from the plurality of computing devices and verifying the received application program interface token.

[0333] Clause 11. The system of Clause 1, wherein the neural network model is further configured to determine the risk scores by identifying objects detected in the set of inputs.

[0334] Clause 12. A system for dynamically providing workflow instructions in network-based services, the system comprising: one or more computing devices associated with a processor and a memory for executing computer-executable instructions to implement a workflow monitoring service, wherein the workflow monitoring service is configured to: obtain a set of inputs from a plurality of computing devices located in targeted areas, the targeted areas, including a plurality of sub-areas, each sub-area being vectorized, and the set of inputs comprising one or more captured images captured in one of the vectorized sub-areas; obtain a set of additional inputs from a plurality of sensors deployed in the targeted areas; analyze, by utilizing a machine learning component stored in the memory, the set of inputs and the set of additional inputs to determine risk scores associated with the targeted areas, wherein results of the analysis indicate risk scores of sub-areas associated with the set of inputs, wherein the machine learning component comprises a neural network model configured to: collect, from a historical data stored in a database, a set of previous inputs and a set of previous additional inputs, apply the set of previous inputs and the set of previous additional inputs to the neural network model, and generate a set of risk scores associated with corresponding subareas associated with the set of previous inputs and the set of previous additional inputs, determine, for each sub-area associated with the set of inputs, whether the risk score is at or above a threshold risk score; and generate, for each vectorized sub-area having the risk score at or above the threshold risk score, workflow instructions, the workflow instructions configured to mitigate risks of the vectorized sub-areas, having the risk score at or above the threshold risk score.

[0335] Clause 13. The system of Clause 12, wherein the workflow instructions comprise a set of hierarchical data, the hierarchical data comprising a plurality of layers, each layer associated with one or more instructions to be performed by one or more employees associated with the one or more computing devices located in proximity to the vectorized sub-areas, having the risk score at or above the threshold risk score.

[0336] Clause 14. The system of Clause 13, wherein the one or more instructions are patrolling a patrol area, wherein a top level of the hierarchical data is a master plan for patrolling the patrol area, having a plurality of posts, wherein a lower level of the hierarchical data is a patrolling plan of each post of the plurality of posts.

[0337] Clause 15. The system of Clause 12, wherein the neural network model is further configured to dynamically generate the workflow instructions by: collecting, from the historical data stored in the database, the set of previous inputs, the set of previous additional inputs, and a set of historical risk scores associated with the set of previous inputs and the set of previous additional inputs, applying the set of previous inputs and the set of previous additional inputs to the neural network model, and generating a set of workflow instructions associated with corresponding vectorized sub-areas associated with the set of previous inputs and the set of previous additional inputs.

[0338] Clause 16. The system of Clause 15, wherein the machine learning component is further configured to dynamically generate the workflow instructions by dynamically receiving the set of additional data.

[0339] Clause 17. The system of Clause 4, wherein the machine learning component is configured to generate a plurality of workflow instructions by modifying one or more sensor data of the set of additional inputs, applying the modified one or more sensor data to the neural network model, and generating the plurality of workflow instructions based on the modified one or more sensor data.

[0340] Clause 18. The system of Clause 12, wherein the machine learning component is configured to train the neural network model by updating neural network parameters by comparing the generated set of risk scores and historical set of risk scores storedin the database, the historical set of risk scores associated with the set of previous inputs and the set of previous additional inputs.

[0341] Clause 19. The system of Clause 12, wherein the workflow monitoring service is further configured to transmit the generated workflow instructions to one or more computing devices located in the vectorized sub-areas, having the risk score at or above the threshold risk score.

[0342] Clause 20. A method for dynamically providing workflow instructions in network-based services, the method comprising: obtaining a set of location information from a plurality of computing devices, wherein the set of location information comprises geometry identifiers and time identifiers of each of the plurality of computing devices; tracking locations of the plurality of computing devices by analyzing the set of location information within targeted areas, wherein the targeted areas include a plurality of sub-areas, and wherein each sub-area is vectorized; obtaining a set of inputs from one or more of the plurality of computing devices located in the targeted areas, wherein the set of inputs comprises one or more captured images captured in one of the sub-areas; obtaining a set of additional inputs from a plurality of sensors deployed in the targeted areas; analyzing, by utilizing a machine learning component, the set of inputs and the set of additional inputs to determine risk scores associated with the targeted areas, wherein results of the analysis indicate risk scores of sub-areas associated with the set of inputs, wherein the machine learning component comprises a neural network model configured to: collect, from a historical data stored in a database, a set of previous inputs and a set of previous additional inputs, apply the set of previous inputs and the set of previous additional inputs to the neural network model, and generate a set of risk scores associated with corresponding sub-areas associated with the set of previous inputs and the set of previous additional inputs,determining, for each sub-area associated with the set of inputs, whether the risk score is at or above a threshold risk score; generating, for each vectorized sub-area having the risk score at or above the threshold risk score, workflow instructions, the workflow instructions configured to mitigate risks of the vectorized sub-areas, having the risk score at or above the threshold risk score; and transmitting the generated workflow instructions to one or more computing devices located in proximity to the vectorized sub-areas, having the risk score at or above the threshold risk score, wherein the one or more computing devices are identified based on the obtained set of location information.EXAMPLE EMBODIMENTS III

[0343] Clause 1. A system for dynamically providing workflow assignments, the system comprising: one or more computing devices associated with a processor and a memory for executing computer-executable instructions to implement an automated run-time workflow assignment system, wherein the automated run-time workflow assignment system is configured to: obtain a set of inputs from a database included in the automated runtime workflow assignment system, the set of inputs comprising a set of target areas, each target area comprising a plurality of sub-areas; generate, by utilizing a machine learning component stored in the memory, a master plan based on the set of inputs, wherein the master plan includes vectorized identifications of each of the plurality of sub-areas and workflows for each identified sub-area, and wherein the machine learning component comprises a neural network model configured to: collect, from a historical data stored in a database, a historical plurality of sub-areas and historical workflows associated with each sub-area of the historical plurality of sub-areas, apply the historical data the neural network model, generate a set of workflows associated with the historical data,train the neural network model by updating neural network parameters by comparing the generated set of workflows associated with the historical plurality of sub-areas and the historical workflows associated with each sub-area of the historical plurality of sub-areas, and generate the workflows associated to each vectorized identified sub-area, determine, by accessing the database, one or more manifests associated with the identified workflow, the manifest of each identified workflow comprising location information and time information, the database configured to store a plurality of manifests associated with a plurality of workflows; access the database to identify profile information of a plurality of employee identifications, the profile information comprising geometry identifiers and time identifiers of each of the plurality of employee identifications; determine, for each vectorized sub-area, one or more employee identifications by comparing the geometry and time identifiers of each of the plurality of employees with the location information and time information included in the manifest of each workflow; and assign each workflow to identified corresponding one or more employee identifications.

[0344] Clause 2. The system of Clause 1, wherein the master plan comprise a set of hierarchical data, the hierarchical data comprising a plurality of layers, each layer associated with one or more vectorized sub-areas and associated workflows.

[0345] Clause 3. The system of Clause 2, wherein the workflows are patrolling a patrol area, wherein a top level of the hierarchical data is patrolling the patrol area, having a plurality of posts, wherein a lower level of the hierarchical data is a patrolling plan of each post of the plurality of posts.

[0346] Clause . The system of Clause 1, wherein the neural network model is configured to assign the identified employee identifications to the workflows by:collecting, from the database, a set of attributes of each of the identified employee identifications, the set of attributes comprising quantitative attributes and qualitative attributes, vectorizing each of the quantitative attributes and qualitative attributes, applying the vectorized quantitative attributes and qualitative attributes to the neural network model, generating, for each identified employee identification, a confidence score by applying the vectorized quantitative attributes and the qualitative attributes to the neural network model, prioritizing, for each workflow, the identified employee identifications based on the confidence score of each of the identified employee identifications, and assigning the identified employee identifications to the workflows based on prioritization results.

[0347] Clause 5. The system of Clause 4, wherein the machine learning component is further configured to dynamically assign the identified employee identifications to the workflows by dynamically updating the quantitative attributes and qualitative attributes of the identified employees.

[0348] Clause 6. The system of Clause 4, wherein the automated run-time workflow assignment system is configured monitor the confidence score.

[0349] Clause 7. The system of Clause 1 , wherein the automated run-time workflow assignment system is further configured receive the set of inputs from an external computing device.

[0350] Clause 8. The system of Claim 7, wherein the automated run-time workflow assignment system is further configured to authenticate the external computing device by receiving an application program interface token from the external computing device and verifying the received application program interface token.

[0351] Clause 9. The system of Clause 1 , wherein the automated run-time workflow assignment system is communicatively coupled with one or more employee computing devices, and wherein each employee is configured to manage corresponding profile information by accessing the database via associated employee computing device.

[0352] Clause 10. The system of Clause 1 , wherein the automated run-time workflow assignment system is configured to periodically updates the master plan.

[0353] Clause 11. The system of Clause 1, wherein the master plan comprises a number of demanded employees for each workflow.

[0354] Clause 12. A system for dynamically providing workflow assignments, the system comprising: one or more computing devices associated with a processor and a memory for executing computer-executable instructions to implement an automated run-time workflow assignment system, wherein the automated run-time workflow assignment system is configured to: obtain a set of inputs from a database included in the automated runtime workflow assignment system, the set of inputs comprising a set of target areas, each target area comprising a plurality of sub-areas; generate a master plan based on the set of inputs, wherein the master plan includes vectorized identifications of each of the plurality of sub-areas and workflows for each identified sub-area; determine, by accessing the database, one or more manifests associated with the identified workflow, the manifest of each identified workflow comprising location information and time information, the database configured to store a plurality of manifests associated with a plurality of workflows; access the database to identify profile information of a plurality of employee identifications, the profile information comprising geometry identifiers and time identifiers of each of the plurality of employee identifications; determine, for each vectorized sub-area, one or more employee identifications by comparing the geometry and time identifiers of each of the plurality of employees with the location information and time information included in the manifest of each workflow; and assign each workflow to identified corresponding one or more employee identifications.

[0355] Clause 13. The system of Clause 12, wherein the master plan comprise a set of hierarchical data, the hierarchical data comprising a plurality of layers, each layer associated with one or more vectorized sub-areas and associated workflows.

[0356] Clause 14. The system of Clause 13, wherein the workflows are patrolling a patrol area, wherein a top level of the hierarchical data is patrolling the patrol area, having a plurality of posts, wherein a lower level of the hierarchical data is a patrolling plan of each post of the plurality of posts.

[0357] Clause 15. The system of Clause 12, wherein the automated runtime workflow assignment system comprises a neural network model stored in the memory, the neural network model configured to assign the identified employee identifications to the workflows by: collecting, from the database, a set of attributes of each of the identified employee identifications, the set of attributes comprising quantitative attributes and qualitative attributes, vectorizing each of the quantitative attributes and qualitative attributes, applying the vectorized quantitative attributes and qualitative attributes to the neural network model, generating, for each identified employee identification, a confidence score by applying the vectorized quantitative attributes and the qualitative attributes to the neural network model, prioritizing, for each workflow, the identified employee identifications based on the confidence score of each of the identified employee identifications, and assigning the identified employee identifications to the workflows based on prioritization results.

[0358] Clause 16. The system of Claim 15, wherein the neural network model is further configured to dynamically assign the identified employee identifications to the workflows by dynamically updating the quantitative attributes and qualitative attributes of the identified employees.

[0359] Clause 17. The system of Clause 15, wherein the automated runtime workflow assignment system is configured monitor the confidence score.

[0360] Clause 18. The system of Clause 12, wherein the automated runtime workflow assignment system is further configured receive the set of inputs from an external computing device.

[0361] Clause 19. A method of dynamically assigning one or more workflows to employees, the method comprising: obtaining a set of inputs from a database, the set of i...

Claims

WHAT IS CLAIMED:

1. A system for dynamically generating employee training instructions in network-based services, the system comprising: one or more computing devices associated with a processor and a memory for executing computer-executable instructions to implement an automated training service, wherein the automated training service is configured to: obtain a set of inputs from a plurality of computing devices, wherein the set of inputs comprises geometry identifiers and time identifiers of each of the plurality of computing devices; obtain a set of additional inputs from a database communicatively coupled with the automated training service, the set of additional inputs comprising a set of target areas, each target area comprising a plurality of subareas; generate one or more workflows for each of the plurality of sub-areas, each workflow of the one or more workflows comprises attributes comprising time data and location data; generate, for each workflow, filtering criteria, having the attributes; filter, for each workflow, the set of inputs based on the filtering criteria by filtering the geometry identifiers and the time identifiers of the plurality of computing devices based on the time data and the location data of the criteria such that each sub-area is associated with one or more workflows, each workflow of the one or more workflows associated with identifications of computing devices, corresponding to the filtered set of inputs; generate, for each workflow, one or more training instructions by obtaining a set of manifests associated with each workflow from the database, wherein the database is configured to store a plurality of workflows and sets of manifests associated with each workflow; and transmit, for each workflow, the generated training instructions associated with each workflow to one or more computing devices, having the identifications associated with each workflow.

2. The system of Claim 1 , wherein the attributes of each workflow comprises a set of hierarchical data, the hierarchical data comprising a plurality of layers, each layer associated with one or more assigned manifests.

3. The system of Claim 2, wherein the location data of the workflows include patrol areas, wherein a top level of the hierarchical data is a master plan for patrolling the patrol areas, having a plurality of posts, wherein a lower level of the hierarchical data is a patrolling plan of each post of the plurality of posts, and wherein the patrolling plan comprises number of demanded employees and demanded time duration for patrolling corresponding post.

4. The system of Claim 3, wherein attributes of the workflow further comprise demanded duty and skills of employee to perform the master plan for patrolling corresponding post.

5. The system of Claim 1, wherein the memory stores a machine learning component, the machine learning component including a neural network model configured to dynamically update the workflows, wherein the neural network model is configured to: collect a set of sensor data from a plurality of sensors operatively coupled with the automated training service, apply the collected set of sensor data to the workflows to the neural network model, and generate updated workflows as results of the application of the collected set of sensor data to the workflows.

6. The system of Claim 5, wherein the neural network model is further configured to create a training set comprising the workflows, the collected set of sensor data, and the updated workflows, wherein the neural network model is continuously trained by using the training set.

7. The system of Claim 6, wherein the machine learning component is further configured to dynamically generate the training instructions by utilizing the created training set.

8. The system of Claim 5, wherein the set of sensor data comprises temperature sensors, object detection sensors, gas sensors, image sensors, and radar sensors.

9. The system of Claim 5, wherein the machine learning component is configured to generate a plurality of training scenarios by modifying one or more sensor data of thecollected set of sensor data, applying the modified one or more sensor data to the neural network model, and generating the plurality of training scenarios based on the modified one or more sensor data and results of applying the modified one or more sensor data.

10. The system of Claim 1, wherein the automated training service is further configured to authenticate the computing device by receiving an application program interface token from the plurality of computing devices and verifying the received application program interface token.

11. The system of Claim 1, wherein the automated training service is further configured to receive answers to the generated training instructions from the one or more computing devices, having the identifications associated with each workflow, and filter the one or more computing devices, having the identifications associated with each workflow by verifying the received answers.

12. A system for dynamically generating employee training instructions in network-based services, the system comprising: one or more computing devices associated with a processor and a memory for executing computer-executable instructions to implement an automated training service, wherein the automated training service is configured to: obtain a set of additional inputs from a database communicatively coupled with the automated training service, the set of additional inputs comprising a set of target areas, each target area comprising a plurality of subareas; generate one or more workflows for each of the plurality of sub-areas, each workflow of the one or more workflows comprises attributes comprising time data and location data; generate, for each workflow, one or more training instructions by obtaining a set of manifests associated with each workflow from the database, wherein the database is configured to store a plurality of workflows and sets of manifests associated with each workflow; and transmit, for each workflow, the generated training instructions associated with each workflow to target computing devices communicatively coupled with the automated training service.

13. The system of Claim 12, wherein the attributes of each workflow comprises a set of hierarchical data, the hierarchical data comprising a plurality of layers, each layer associated with one or more assigned manifests.

14. The system of Claim 13, wherein the location data of the workflows include patrol areas, wherein a top level of the hierarchical data is a master plan for patrolling the patrol areas, having a plurality of posts, wherein a lower level of the hierarchical data is a patrolling plan of each post of the plurality of posts, and wherein the patrolling plan comprises number of demanded employees, and demanded time duration for patrolling corresponding post.

15. The system of Claim 12, wherein the memory stores a machine learning component, the machine learning component including a neural network model configured to dynamically update the workflows, wherein the neural network model is configured to: collect a set of sensor data from a plurality of sensors operatively coupled with the automated training service, apply the collected set of sensor data to the workflows to the neural network model, and generate updated workflows as results of the application of the collected set of sensor data to the workflows.

16. The system of Claim 15, wherein the neural network model is further configured to create a training set comprising the workflows, the collected set of sensor data, and the updated workflows, wherein the neural network model is continuously trained by using the training set.

17. The system of Claim 16, wherein the set of sensor data comprises temperature sensors, object detection sensors, gas sensors, and image sensors, radar sensors.

18. The system of Claim 16, wherein the machine learning component is configured to generate a plurality of training scenarios by modifying one or more sensor data of the collected set of sensor data, applying the modified one or more sensor data to the neural network model, and generating the plurality of training scenarios based on the modified one or more sensor data and results of applying the modified one or more sensor data.

19. The system of Claim 12, wherein the target computing devices are associated with employees pre-assigned to each workflow.

20. A method for dynamically generating employee training instructions in network-based services, the method comprising: obtaining a set of inputs from a plurality of computing devices, wherein the set of inputs comprises geometry identifiers and time identifiers of each of the plurality of computing devices; obtaining a set of additional inputs from a database, the set of additional inputs comprising a set of target areas, each target area comprising a plurality of sub-areas; generating one or more workflows for each of the plurality of sub-areas, each workflow of the one or more workflows comprises attributes comprising time data and location data; generating, for each workflow, filtering criteria, having the attributes; filtering, for each workflow, the set of inputs based on the filtering criteria by filtering the geometry identifiers and the time identifiers of the plurality of computing devices based on the time data and the location data of the criteria such that each subarea is associated with one or more workflows, each workflow of the one or more workflows associated with identifications of computing devices, corresponding to the filtered set of inputs; generating, for each workflow, one or more training instructions by obtaining a set of manifests associated with each workflow from the database, wherein the database is configured to store a plurality of workflows and sets of manifests associated with each workflow; and transmitting, for each workflow, the generated training instructions associated with each workflow to one or more computing devices, having the identifications associated with each workflow.

Images