Configure physical classroom resources

Abstract

A computer-executed method comprising: identifying and quantifying, by one or more processors, physical classroom resources (151) in a classroom (200) based on sensor measurements received from sensors (153) in the classroom (200), wherein the physical classroom resources (151) are inanimate physical objects that are components of the classroom;Determining, by one or more processors, of limitations of physical classroom resources (151) that impede learning by pupils in the classroom (200), based on sensor readings from the sensors (153) in the classroom, wherein the limitations are caused by physical defects in one or more of the physical classroom resources (151) that result in a reduction of the pupils' ability to learn in the classroom (200), and wherein the reduction is based on a focus determination and a group affect determination (812), wherein the focus determination is a determination of how defective objects adversely affect the learning focus of an individual pupil, and wherein the group affect determination (812) is a determination of how the defective objects adversely affect the learning foci of all pupils in the classroom (200);Identify, by one or more processors, the reduction in the pupils' ability to learn in the classroom (200), based on a decrease in the learning focus of the individual pupil and a decrease in the learning foci of all pupils in the classroom, the reduction being caused by the physical defects in the physical classroom resource(s) (151); Train, by one or more processors, a neural network to detect changes in the physical classroom resources (151) based on previous sensor readings describing earlier states of the physical classroom resources (151) in the classroom (200); Generate, by the one or more processors, a set of instructions based on the detected changes in the physical classroom resources (151);The instruction set is transmitted by one or more processors to an automatic unit to execute specified logical functions with respect to the detected changes to the physical classroom resources (151); the automatic unit repairs physical defects in one or more physical classroom resources (151) according to the specified logical functions; the one or more processors receive new sensor readings describing new changes to the physical classroom resources (151); and the one or more processors retrain the neural network with the new sensor readings to further detect changes to the physical classroom resources (151).

Description

BACKGROUND The present invention relates to the field of configuring physical resources, in particular configuring physical resources in a classroom. More precisely, the present invention relates to optimizing the configuration of physical resources in a classroom. US 2014 / 0335497 A1 discloses a computer-implemented system and method for adaptive teaching and learning in which students are dynamically grouped and regrouped based on their monitored learning progress, digital learning objects are pedagogically prioritized and dynamically displayed, teachers can specify group-specific learning progress limits and uniform content for all devices, and content providers receive aggregated feedback and can provide learning objects as portable stand-alone playback modules. US2013 / 0226674 A1 discloses a method, process and system for collecting, compiling, generating and analyzing data and providing outputs based thereon, wherein various functional engines integrate performance, behavior and expenditure data of educational actors to capture and derive more accurate metrics and causal relationships between these actors. SUMMARY In one embodiment of a computer-executed method of the present invention, one or more processors identify and quantify physical classroom resources in a classroom based on sensor measurements received from sensors in the classroom, wherein the physical classroom resources are inanimate physical objects that are components of the classroom. Furthermore, one or more processors detect limitations of physical classroom resources that hinder learning by students in the classroom, based on sensor readings from the sensors in the classroom, wherein the limitations are caused by physical defects in one or more of the physical classroom resources, resulting in a reduction of the students' ability to learn in the classroom, and wherein the reduction is based on a focus detection and a group affect detection, wherein the focus detection is a detection of how defective objects adversely affect the learning focus of an individual student, and wherein the group affect detection is a detection of how the defective objects adversely affect the learning focus of all students in the classroom. Furthermore, one or more processors identify the reduction in the students' ability to learn in the classroom, based on a decrease in the learning focus of the individual student and a decrease in the learning foci of all students in the classroom, with the reduction being caused by the physical defects in the physical classroom resources. Furthermore, one or more processors train a neural network to detect changes in the physical classroom resources based on previous sensor readings describing the earlier states of these resources. The processor(s) then generate a set of instructions based on these detected changes. Finally, the processor(s) transmit this instruction set to an automated unit to execute predefined logical functions related to these changes. The automated unit then repairs the physical defects in one or more classroom resources according to these predefined logical functions. Furthermore, one or more processors receive new sensor readings describing new changes to the physical classroom resources; and retrain the neural network with the new sensor readings to further detect changes to the physical classroom resources. Further embodiments of the present invention include a computer system and a computer program product. BRIEF DESCRIPTION OF THE DRAWINGS Embodiments of the present invention will now be described by way of example only, with reference to the accompanying drawings, in which: Fig. 1 represents an exemplary system and network according to one or more embodiments of the present invention; Fig. 2 illustrates an exemplary classroom monitored according to one or more embodiments of the present invention; Fig. 3 represents an exemplary person and environment analysis of a classroom according to one or more embodiments of the present invention; Fig. 4 illustrates an exemplary object recognition module used according to one or more embodiments of the present invention; Fig. 5 represents an exemplary handler of immovable objects used according to one or more embodiments of the present invention; Fig.Figure 6 illustrates an exemplary handler of moving objects used according to one or more embodiments of the present invention; Figure 7 illustrates an exemplary notification detection module used according to one or more embodiments of the present invention; Figure 8 illustrates an exemplary cognitive reasoning module used according to one or more embodiments of the present invention; Figure 9 illustrates an exemplary feedback handler used according to one or more embodiments of the present invention; Figure 10 illustrates a first exemplary method according to one or more embodiments of the present invention; Figure 11 illustrates a second exemplary method according to one or more embodiments of the present invention; Figure12 represents a cloud computing environment according to an embodiment of the present invention; and Fig. 13 represents abstraction model layers of a cloud computing environment according to an embodiment of the present invention. DETAILED DESCRIPTION With reference to the figures, and in particular to Fig. 1, a block diagram of an exemplary system and network according to one or more embodiments of the present invention is shown. In some embodiments, part or all of the exemplary architecture, including both the hardware and software shown as belonging to or contained in the computer 101, can be downloaded and / or executed from the software delivery server 149; and / or optionally use one or more classroom resource(s) 151. Some embodiments use the monitoring computer 201 shown in Fig. 2. With further reference to Fig. 1, the exemplary computer 101 includes a processor(s) 103, which is / are operationally connected to a system bus 105, which also operationally connects various internal and external components. The processor(s) 103 can embody or utilize one or more processor core(s) 123. A video adapter 107, which drives / supports a screen 109, is also connected to the system bus 105. The system bus 105 is connected via a bus bridge 111 to an input / output (I / O) bus 113. An I / O interface 115 is connected to the I / O bus 113. The I / O interface 115 enables data exchange with various I / O units, including a keyboard 117, a mouse 119, a slot 121 (which may include storage units such as CD-ROM drives, multimedia interfaces, etc.), and an external USB port(s) 125. While the format of the ports connected to the I / O interface 115 can be any format known to those skilled in the art in computer architecture, some or all of these ports are Universal Serial Bus (USB) ports in one or more embodiments. As shown, a network interface 129 is also connected to the system bus 105. The network interface 129 can be a hardware network interface, such as a network interface card (NIC), etc. The computer 101 is able to exchange data with a software delivery server 149 and / or classroom resource(s) 151 via the network interface 129 and a network 127. The network 127 can include (but is not limited to) one or more external networks—such as a wide area network (WAN) and / or a network of networks, such as the Internet—and / or one or more internal networks, such as an Ethernet network or a virtual private network (VPN). In one or more embodiments, the network 127 includes a wireless network, such as a Wi-Fi network, and a cellular network.An exemplary embodiment of the present invention utilizes a network “cloud” environment, which is discussed with reference to Fig. 12 and Fig. 13. Referring again to Fig. 1, a hard disk drive interface 131 is also connected to the system bus 105. The hard disk drive interface 131 forms the interface to a hard disk drive 133. In some embodiments, the hard disk drive 133 is a non-volatile form of main memory for storing and filling the system main memory 135 (e.g., a volatile form of main memory, such as so-called random access memory (RAM)), which is also connected to the system bus 105. In some embodiments, the system main memory can be considered a lowest level of volatile main memory in the computer 101. The system main memory 135 may include additional, higher levels of volatile main memory (not shown), including, but not limited to, cache memory, registers, and buffer memory. Logic and / or data (not shown) located in the system main memory 135 may include or be part of an operating system (OS) 137 and application programs 143. In some embodiments, some or all of the system main memory 135 may be shared or distributed across one or more systems. For example, the application programs 143 could be distributed across one or more software delivery servers 149 or other systems. The operating system (OS) 137 includes a shell 139 to provide transparent user access to resources such as application programs 143. In general, the shell 139 is a program that provides an interpreter and an interface between the user and the operating system. More specifically, the shell 139 (sometimes referred to as a command processor) can execute commands entered into a command-line user interface or commands from a file. In other words, the shell 139 can act as a command interpreter. While the shell 139 is a text-based, line-oriented user interface, the present invention equally supports other user interface modes, such as graphical, speech-based, gesture-based, and so on. As illustrated, the shell 139 can be considered the highest level of an operating system software hierarchy.The shell can also provide a prompt, interpret commands entered via the keyboard, mouse or other user input media, and send the interpreted command(s) to the appropriate (e.g., lower) levels of the operating system (e.g., a kernel 141) for processing. As shown, the operating system 137 also contains a kernel 141, which contains (hierarchically) lower levels of functionality for the operating system 137. Some (non-limiting) examples of kernel functions include: providing essential services required by other parts of the operating system 137 and application programs 143, including main memory management, process and task management, disk management, and mouse and keyboard management. The application programs 143 may include a renderer, shown here as an example of a browser 145. The browser 145 contains program modules and instructions (not shown) that enable a World Wide Web (WWW) client (i.e., the computer 101) to send and receive network messages to and from the network 127 (e.g., the Internet via Hypertext Transfer Protocol (HTTP) messaging) and thus enable data exchange with the software delivery server 149 and other systems. In some embodiments, the application programs 143 include a program for improving classroom resources (PICR) 147. In this example, the PICR 147 contains program instructions (software) designed to execute processes and / or functions according to the present invention, such as (but not limited to) those described with reference to Figures 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12 to 13. In some embodiments, the PICR 147 is downloaded from the software delivery server 149 (on demand or just-in-time), with the software in the form of the PICR 147 being downloaded, for example, only when it is needed for execution.In some embodiments of the present invention, the software deployment server 149 can perform all (or many) of the functions belonging to the present invention (including the execution of the PICR 147), so that the computer 101 consequently no longer needs to use its internal data processing resources. In some embodiments of the present invention, the computer 101 is able to remotely exchange data with, test, and / or control aspects of a classroom resource 151, such as computers, video monitors, projectors, telecommunications units, Wi-Fi hotspot routers / access points, etc. One example of such control can be achieved by sending control packets over the network 127 to logic (e.g., software) belonging to one or more of the classroom resources 151. The control packets thus adjust the classroom resource(s) 151 by repairing them (e.g., installing a software patch), turning them on, adjusting their volume or brightness (e.g., on a video monitor), etc. In some embodiments of the present invention, the computer 101 is able to exchange data remotely with sensor(s) 153, which may include a video camera, a microphone, a chemical sensor, a light sensor, etc. In one or more embodiments of the present invention, these sensor(s) 153 provide sensor measurements (e.g., video, audio, chemical data, etc.) about stationary objects (e.g., broken furniture, broken windows, etc.) and / or moving objects (e.g., teachers, students, animals, etc.) in a classroom such as the classroom 200 shown in Fig. 2. The hardware elements shown in Computer 101 are not intended to be exhaustive, but rather representative, in order to highlight important components required by the present invention. For example, Computer 101 may include alternative main memory units such as flash memory, magnetic tape cartridges, DVDs (digital versatile disks), Bernoulli cassettes, etc. These and other variations are intended to be within the scope of the present invention. One or more embodiments of the present invention provide a method and system for identifying and / or analyzing a need for managing classroom artifacts (e.g., broken chairs, broken windows, doors, noise levels, attendance, student behavior, etc.). This enables the identification of an insight based on this need and the recommendation of ways to improve resource allocation and classroom management based on this insight. In one or more embodiments of the present invention, a recommendation agent is automatically triggered based on a recipient cohort analysis.This means that once the classroom and / or its resources and / or its users have been identified (through a recipient cohort analysis that identifies who and what is in the classroom), the recommendation agent recommends, based on what is currently in the classroom, what changes should be made to the classroom. It is important for school principals to be familiar with the key metrics of the school systems they oversee. These key metrics include: school attendance patterns; classroom effectiveness, measured in terms of student participation; and the condition of facilities such as classrooms, the school environment, and other school equipment. Visual analytics, as a key technology, measures these three metrics and reports them to management in real time. For example, the system can use facial recognition to identify students in a classroom. Based on the interaction between the teacher and student activity during class, a report on teaching effectiveness is generated. Furthermore, based on visual images of the facility, the system reports major changes or anomalies, such as broken furniture or missing doors. Many people share classroom environments. This shared use can present challenges at various levels (e.g., preschool, K-12, higher education). Classrooms may be occupied when a lesson is about to begin, tables and desks may be dirty, previous students may have left trash behind, bins may be overflowing, blackboards may be covered in text from other lessons, chairs, windows, and doors may have been broken, moved, or put in the wrong place, equipment may be broken or malfunctioning, and so on. Some lessons may have more students signed up than teachers can accommodate (i.e., an excessively high student-teacher ratio) or too few chairs to seat all the students. Furthermore, a classroom seating arrangement may be inconvenient based on the type of lesson planned. Teachers or school principals are most successful in addressing learning difficulties when they anticipate potential problems arising from environmental conditions or behavioral issues and decide on intervention in advance. The present invention thus presents classroom technologies for instrumenting artifacts in a classroom to complement the direct follow-up of instructions by colleagues, examiners, and trainers. Thus, one or more embodiments of the present invention utilize systems, tools, structures, practices, etc., to measure student-teacher, student-content, student-student, etc., engagements for behavioral analysis; to understand the context and classroom environment in which a student learns; and to correlate how this affects their learning outcomes, etc. This is achieved by capturing / storing multimedia data (e.g., images, video, audio) about the user, the classroom, and school artifacts (chairs, doors, windows, toilets, water sources, etc.). Deriving information from this data consequently impacts student, classroom, and school management by assisting teachers and administrators in making informed decisions and reporting major problems or changes in the facility, such as broken furniture or missing doors, based on visual images of the facility, etc. Thus, the present invention provides classroom monitoring and / or management tools that promote interactions, in context, with users in an attempt to improve a classroom environment. Furthermore, the present invention provides classroom monitoring and / or management processes that use visual analytics to continuously evaluate classroom artifacts and events, transmit these analyzed results to a cognitive processing unit, and notify teachers and relevant authorities of problems with interactions, behavior, the state of the classroom environment, etc. As described herein, the present invention presents a method and system for designing a classroom to facilitate learning while providing continuous metrics and constructive insights into teaching and administrative practices, utilizing visual analytics and a real-time cognitive dashboard as key technologies. For a given set of real-time classroom multimedia artifacts, the present invention analyzes and generates a cognitive dashboard to assist classroom teachers, school administrators, and other decision-makers. This is achieved by analyzing multimedia artifacts (e.g., classroom images, video, etc.) captured by low-cost units, which are used to calculate a classroom's "classroom index," including detected non-human, stationary, and / or moving objects.This allows the system to update the cognitive dashboard in real time and notify relevant users (e.g., via a Short Message Service (SMS) notification). In one or more embodiments, the system just described monitors and records classroom video and audio. A computer-based cognitive agent then analyzes the classroom scene (including the condition of furniture, windows, equipment, etc.) and prompts the appropriate system to take corrective action. Thus, the present invention tracks and analyzes classroom artifacts (e.g., chairs, windows, doors, noises, attendance, student behavior, etc.) to provide needs-based recommendations for automatic environmental improvement. The artifacts are managed based on the needs of the group using the system, such as providing notifications about classroom equipment requiring maintenance, assisting with resource allocation, etc. The automatic recommendations / notifications reduce teacher distractions and contribute to positive student outcomes. With reference to Fig. 2, it is assumed that a classroom 200 is monitored by a camera 202, which, together with the sensor(s) 253, is an example of the sensor(s) 153 shown in Fig. 1. It is further assumed that the camera 202 and other sensors 253 are remotely monitored in real time by a monitoring computer 201 (analogous to the computer 101 shown in Fig. 1) via a data transmission enabled by the network 227 (analogous to the network 127 shown in Fig. 1).For the purpose of explanation, the invention will now be discussed with reference to video images transmitted from the camera 202 to the monitoring computer 201, although it should be clear that similar analyses / operations described below can be performed by the monitoring computer 201 on sensor measurements received from other types of sensors found on the sensor(s) 253, such as audio recording, chemical detection, vibration sensing, etc. It should also be clear that the monitoring computer 201 uses a program such as PICR 147, shown in Fig. 1, to perform the operations described below. As described herein, the camera 202 and / or the sensor(s) 253 monitor the condition of stationary and / or moving objects in classroom 202. For example, camera 202 can send video images from window 204 (which has no defects) and / or from broken window 206 (which has a broken pane of glass 205) to the monitoring computer 201. Furthermore, camera 202 can send video images from both desk 212 (which is in good condition) and / or from broken desk 214 (which is broken apart). Additionally, camera 202 can send video images of a student 210 and / or another moving object 216 (e.g., a teacher in a classroom, an animal such as a pet in a classroom, a pest such as a rat, a wild bird, etc.). Furthermore, a screen 208 (e.g., a video monitor connected to a data processing unit, a video player, the internet, etc.) may be broken. This non-functional state of the screen 208 can be visually detected by the camera 202 or determined by the monitoring computer 201 via a network 227. That is, the monitoring computer 201 can remotely monitor the state and capabilities of the screen 208 by sending it test packets, remotely monitoring components of the screen 208, etc., to determine that the screen 208 is currently not functioning. Thus, the present invention identifies the presence of broken immovable objects (e.g., the broken window 206, the non-functional screen 208, the broken desk 214) and / or undamaged immovable objects (e.g., the window 204 and / or the desk 212) and / or movable objects (e.g., the student 210 and / or the movable object 216) in order to adjust the condition of the immovable / movable objects (e.g., location, functionality, repair status, etc.) in order to improve the condition of one or more of the immovable objects. With reference to Fig. 3, a person and environment analysis process carried out by the monitoring computer 201 according to one or more embodiments of the present invention is shown. As shown in Fig. 3, videos 301 recorded from classroom 200 (e.g., from the video camera 202 shown in Fig. 2) are sent through an object filter 303, which uses image recognition to identify the stationary and moving objects in the classroom in real time. If the object filter 303 identifies a particular object as a moving object, an analysis 305 of the moving object determines what type of moving object it is. If, based on facial identification 309, it is a student, information from a longitudinal database 307 is sent to a cognitive processing agent (e.g., part of the PICR 147 shown in Fig. 1), which sends an image of the student to a classroom monitor web screen 313 (e.g., part of the monitoring computer 201) and / or a mobile unit 315 (e.g., a smartphone used by a school principal). As shown in Fig. 4, an additional detail of an object recognition module (e.g., the object filter 303 shown in Fig. 3) is shown. A video 402 is sent to a frame splitter 404, which is capable of separating moving objects from stationary objects in the video 402 by means of a variety of processes. For example, the PICR 147 can assign thermal measurements from the sensor(s) 253 to video frames recorded by the camera 202 in order to distinguish moving objects (e.g., the student 210, who emits heat at body temperature) from stationary objects (e.g., the broken desk 214, which is at room temperature, or the broken window 206, which has a different temperature than the window 204 due to the presence of the broken pane 205). Furthermore, image recognition can identify certain background objects, such as those that barely move (e.g., desk 212) or never move (e.g.,the window 204 or the screen 208), recognize and then disregard such objects by means of the background subtraction 406 shown in Fig. 4. Thus, background subtraction 406 causes stationary objects detected in the video to be sent to a stationary object handler 410, which is described in more detail in Fig. 5. When the object filter 303 shown in Fig. 3 determines that the video image is the video image of a moving object, a surface detector 408 determines whether the object (which is not part of the background) is moving or stationary by determining the object's temperature, texture, etc., which provide an indication that the object is moving. This determination is made in the query block 412 in Fig. 4. If the observed object is stationary, it is sent (like the background images) to the stationary object handler 410. However, if the query block 412 determines that the video image is the video image of a moving object, this video image is sent to a moving object handler 414, which is shown in Fig. 5.Section 6 is described in more detail. Referring to the detail of the stationary object handler 410 shown in Fig. 5, video images of objects 501 are sent to a model verification program 503, which compares the video images with known images of moving and stationary objects, as described in decision block 507. If the video images show the features of moving objects, they are sent to the moving object handler 514 (which is similar to the moving object handler 414 shown in Fig. 4). However, if the video images show the features of stationary objects (decision block 507), they are sent to a model deviation verification program 505, which compares the images of the stationary objects with known models of stationary objects found in system memory 515. If the video image of a particular stationary object matches a model of a particular stationary object (i.e.,If the video image matches various characteristics such as shape, color, size, etc. (“no deviation”), a copy of the video image is sent to system memory 515 in a file reserved for such video files. However, if the video image does not match a file of a known model, the image is sent to a cognitive agent 513, which performs further analysis of the video image (e.g., matching it to other images based on matching shapes, colors, etc.). Referring to the detail of the moving object handler 414 shown in Fig. 6, the video images of objects 602 are sent to a design generator 604, which creates an animated "stick figure" that shows the shape, movement, size, etc., of the moving object in the video. Simultaneously, the video images of objects 602 are sent to a face detector 612 (assuming that the moving object detected in Fig. 4 is a human). If the face detector determines that the video image of the moving object captures a person's face from the front (decision block 618), a face recognition function 620 uses face recognition software to identify which person is in the video. Even if the image does not show the face sufficiently from the front to identify the person in the video, a face affect analysis function 614 is still able to identify the person (from images taken from the side, etc.).), to determine whether the person is attentive, happy, looking around, etc. As shown in evaluation block 606, if the system is able to recognize the person's face (using the face recognition function 620) and generate a stick figure (using the design generator 604), it has sufficient information to identify the person and output an identification assignment 608 for that person. As shown in the body language analysis function 610, the system is also able to analyze the movement of the person in the video to determine whether that person is restless (indicated by frequent and / or jerky movements of the generated stick figure corresponding to the person's video), calm (indicated by calm body movements represented by the generated stick figure), etc. Based on the identity of the person in the video (from the identification mapping 608), the movement of the person in the video (from the body language analysis function 610) and the facial expressions of the person in the video (from the facial affect analysis function 614), which are combined by the combinatorial logic 616, a cognitive agent 622 is able to determine the emotional state of the person (e.g. attentive, distracted, inattentive, anxious, etc.) by means of the process shown in Fig. 7. Once the cognitive agent 622 combines the identification, facial, and body movements of a person in the video (events from the cognitive agent shown in block 701 in Fig. 7), a category matching component 703 matches these features with a specific student or a specific lesson (e.g., student's age, subject matter being taught, etc.). User preference records 705 are then used to prioritize 711 whether and / or when corrective action needs to be taken on stationary objects in the classroom. An example of a user preference record 705 entry is that a user may prefer that a particular resource is always turned on (e.g., a video monitor). Thus, this user prefers that the video monitor is always operational.However, the same user might not care at all if the video monitor has a crack, as long as it still works. Therefore, it doesn't matter to the user whether the crack is repaired. This leads to decision block 709 deciding that notifications and instructions for correcting the problematic immovable objects can be sent to a user dashboard 707 (used by a school principal) at the end of the day, or alternatively, that an immediate notification must be sent without delay to a user display unit 713 (used, for example, by school maintenance staff). Either way, all notifications are stored in a system database 715 for future use (in future cases that correspond to the characteristics / conditions shown in the current video) for an action record database. With reference to Fig. 8, an additional detail of the cognitive agent 622 shown in Fig. 6 is shown. The cognitive agent 622 inputs deviations 802 of the stationary object (e.g., the broken pane of glass 205 shown in Fig. 2) into an impact detection function 804, which determines the impact such broken objects have on the students in the classroom. The determination of this impact is supported / confirmed by records in the database 806, which describe the previous attendance, grades, events, etc., that occurred for one or more students in the classroom in response to the presence of broken objects in the classroom. At the same time, the results of the analysis of the moving object, described in Fig. 6, are used to make a focus determination 808 (how the broken objects in the classroom affect the focus of an individual student) and a group affect determination 812 (how the broken objects in the classroom affect the totality of students in the classroom). As shown in the combinatorial logic 814, the effect on the student (from the effect detection function 804) caused by a broken object in the classroom, as well as the effect on the student and the entire classroom caused by a broken object (from the focus detection 808 and the group effect detection 812), are used to generate a notification to correct the object that is currently experiencing a deviation (e.g., is broken). This notification is sent to a notification handler 816, which sends the notification to the user dashboard 707 and / or to the user display unit 713 shown in Fig. 7. As shown in the "Feedback" block 818, the teacher can provide feedback in the classroom regarding the positive, negative, or neutral effect that fixing the problem with the defective object had on one or more of the students in the classroom. This feedback is fed into an impact learning component 820, which learns 1) what effect fixing the problem had and 2) whether similar corrective actions / corrections should be applied in the future under similar circumstances. Exemplary types of feedback 818 and how they are generated are shown in Fig. 9. As shown in Fig. 9, the feedback can be a speech response 901, which passes through a speech conversion unit 903, or a text response 907, which goes directly to a response decoder 909 that interprets (by means of text analysis) what the responses state. As shown in block 911, all feedback responses are stored in a system database 905. If the response decoder interprets the response as suggesting an improvement or change to the action, it is sent to a cognitive agent 913, which makes such changes. For example, if the teacher responds with a message stating that repairing the broken pane of glass 205 with a wooden board has indeed led to increased discomfort among the students in the classroom, the suggestion might be to replace the broken pane of glass with new glass. With reference to Fig. 10, operations performed by one or more processors and / or other hardware units in a first exemplary method according to one or more embodiments of the present invention are shown. According to the initiator block 1001, one or more processors (e.g. in the monitoring computer 201 shown in Fig. 2) monitor stationary classroom resources (e.g. the broken window 206, the broken desk 214, etc.) in a classroom (e.g. classroom 200) based on sensor measurements from one or more monitoring units (e.g. the camera 202 and / or the sensor(s) 253) in the classroom, as shown in block 1003. As described in block 1005, one or more processors evaluate the states of the stationary classroom resources (e.g., Are they broken or in good condition? Where are they located? etc.). As described in Block 1007, one or more processors identify immobile classroom resources whose states result in limitations of physical classroom resources that hinder learning by students in the classroom (e.g., the non-functional screen 208 shown in Fig. 2 cannot be used to display a video about a topic presented to student 210, thus hindering that student's ability to learn about that topic). As described in Block 1009, one or more processors identify the presence of moving objects and activities by moving objects (e.g., the moving object 216 shown in Fig. 2) in the classroom that hinder the students' learning in the classroom. For example, the presence of a visitor in the classroom may hinder the students' ability to concentrate and not be distracted. As described in Block 1011, one or more processors then establish a classroom index of the classroom (i.e., an index of how conducive the classroom is to the student's ability to learn material in the classroom) based on the states of the immovable objects and the presence of the movable objects and the activities by the movable objects in the classroom. As shown in query block 1013, one or more processors determine whether the classroom index exceeds a predefined threshold. If so, and as described in block 1015, one or more processors issue instructions to modify the static classroom resources whose states result in restrictions that hinder student learning in the classroom. For example, one or more processors can generate and issue instructions to replace physical classroom resources, which have the limitations of physical classroom resources, with other physical classroom resources that do not have the limitations of physical classroom resources. In a further embodiment / example of the present invention, the limitations of physical classroom resources are caused by a physical arrangement of the physical classroom resources, such as chairs arranged in rows rather than in a circle, which is more conducive to collaborative learning. Consequently, one or more processors generate instructions to rearrange the physical classroom resources. In another embodiment / example of the present invention, the limitations of physical classroom resources are caused by a defect in one of the physical classroom resources (e.g., the screen 208 shown in Fig. 2 is not functioning). Consequently, one or more processors generate instructions to repair the defect in the physical classroom resource(s), such as sending an instruction to screen 208, establishing a connection to a specific Internet Protocol (IP) address, accessing a specific port, etc., resulting in curriculum information being displayed on screen 208. The sequence shown in Fig. 10 ends at the final block 1017. In one embodiment of the present invention, one or more processors train a cognitive system (e.g., the cognitive agent 513 shown in Fig. 5) to detect changes to the physical classroom resources based on previous sensor readings that describe previous states of the physical classroom resources in the classroom. For example, the cognitive agent 513 detects that the broken window 206 did not have a broken pane of glass 205 yesterday, but does today. The one or more processors then transmit the detected changes (e.g., the new presence of the broken pane of glass 205) to the physical classroom resources to a unit that modifies the physical classroom resources. That is, an automated unit may enter classroom 200 and repair the broken window 206.Furthermore, if screen 208 was working yesterday but is dark today, the monitoring computer 201 can send instructions to logic in screen 208 to fix a software problem, connect screen 208 to an IP address on the Internet, etc. In one embodiment of the present invention, one or more processors detect limitations of physical classroom resources that hinder student learning in the classroom based on an analysis of video feeds from the classroom, audio feeds from the classroom, and student recordings from the classroom. That is, the system identifies, based on an analysis of video feeds from the classroom (so that defective stationary objects are visually identified), audio feeds from the classroom (so that defective stationary objects are acoustically identified (e.g., by noises generated by screen 208)), and classroom problems such as students talking over each other, etc.Identified) as well as student records of students in the classroom (which identify the progress of students' ability to learn material) establish that the limitations of physical classroom resources (the immovable objects) are indeed detrimental to students' learning ability. In one embodiment of the present invention, one or more processors display images of the stationary classroom resources and movable objects in the classroom, along with a description of the instructions for modifying the stationary classroom resources, on a graphical user interface (GUI) on a remote computer. One or more processors receive instructions from the remote computer to further modify the stationary classroom resources based on these images and the description of the instructions for modifying the stationary classroom resources. One or more processors then further modify the stationary classroom resources based on the instructions from the remote computer.This means that the activities shown herein can be displayed on various resources such as the user dashboard 707 or the user display unit 713, shown in Fig. 7, to let an administrator know that resources in the classroom can be changed (e.g., screen 208 can be changed to improve the learning environment in classroom 200). With reference to Fig. 11, operations performed by one or more processors and / or other hardware units in a second exemplary method according to one or more embodiments of the present invention are shown. Following initiator block 1101, one or more processors identify and quantify physical classroom resources in the classroom based on sensor readings received from sensors in a classroom, as described in block 1103. One or more processors then detect limitations of physical classroom resources that hinder learning by students in the classroom, based on sensor readings from the sensors in the classroom, as described in Block 1105. As described in Block 1107, one or more processors detect one or more of the limitations of physical classroom resources (e.g., defects that lead to a decrease in students' ability to learn in a classroom) among the physical classroom resources identified by the sensor measurements. As described in block 1109, one or more processors adapt the one or more physical classroom resources based on one or more detected constraints of physical classroom resources. The sequence shown in Fig. 11 ends at the final block 1111. As in the invention described in Fig. 10, a single embodiment of the invention described in Fig. 11 further comprises training, by one or more processors, a cognitive system to detect changes to the physical classroom resources based on previous sensor readings describing previous states of the physical classroom resources in the classroom; and transmitting, by one or more processors, detected changes to the physical classroom resources to a unit that modifies the physical classroom resources. As in the invention described in Fig. 10, a single embodiment of the invention described in Fig. 11 further comprises the generation, by one or more processors, of instructions to replace one or more of the physical classroom resources, which have the limitations of physical classroom resources, with one or more other physical classroom resources, which do not have the limitations of physical classroom resources. As in the invention described in Fig. 10, the limitations of physical classroom resources in a single embodiment of the invention described in Fig. 11 are caused by a physical arrangement of the physical classroom resources, and the invention described in Fig. 11 further features the generation, by one or more processors, of instructions to rearrange one or more of the physical classroom resources in order to eliminate the limitations of physical classroom resources. As in the invention described in Fig. 10, the limitations of physical classroom resources in a single embodiment of the invention described in Fig. 11 are caused by a defect in one of the physical classroom resources, and the invention described in Fig. 11 further features the generation, by one or more processors, of instructions to repair the defect in one of the physical classroom resources. As in the invention described in Fig. 10, a single embodiment of the invention described in Fig. 11 further comprises the detection, by one or more processors, of the limitations of physical classroom resources that hinder learning by students in the classroom, based on an analysis of video feeds from the classroom, audio feeds from the classroom, and student recordings of students in the classroom. Thus, as described herein in one or more embodiments of the present invention, a processor-based analysis uses multimedia inputs (e.g., video stream, image, audio) and context provided by the device (e.g., camera, mobile phone, tablet), an electronic timetable, and crowdsourced information such as best practices and benchmarks. The analysis process can take into account historical records (e.g., of students, classrooms, resources) and cohorts (e.g., performance reports, resource indices). The identification and analysis of classroom resources focuses, among other things, on filtering objects, identifying and comparing them with benchmark artifacts from other classrooms or schools using visual analytics that indicate a classroom environment of poor or good quality. When recognizing and analyzing student behavior in the classroom, the focus is, among other things, on searching for patterns in attendance, activity, behavior, and interactions from a multimedia input that indicate a poor environment and undesirable student outcomes. According to one or more embodiments of the present invention, a custom object-filtering software utility receives a video data stream from one or more units (predominantly low-cost units) or a previously recorded source via a wireless network and server solution or a peer-to-peer protocol. It uses background subtraction, surface detection, and software utilities to distinguish between moving and stationary objects. The object identification process uses the objects and further categorizes them. Categorizations for moving objects include: human, student, guest, teacher, administrator, researcher, class pet, human arm, human leg, human face, eyes, head, torso, and so on.Categories for immobile objects include, but are not limited to, chairs, desks, tables, walls, floors, trays, telephones, pens, posters, light fixtures, chalkboards, whiteboards, staplers, laptops, and more. Object categorization is enabled through logged model matching and individual recognition and identification. A custom object recognition tool is employed, consisting of a data store containing object models and a neural network trained to recognize the objects represented by the models. According to one or more embodiments of the present invention, movable object models, such as students / teachers / administrators, originate from a system configuration in which the class list and frontal facial images of staff members are loaded into the system along with their names. Using this registered information, the system identifies people in the classroom when they enter and look into the camera. Following biometric identification, the system identifies the individual and tracks their movements throughout the entire recording period. Combined with the system's human limb recognition and gaze detection capabilities, the system further categorizes moving objects based on body language.For example, a student who sits quietly and writes in a notebook would be categorized as busy, but if the teacher is speaking and the majority of the student's eyes are not on the teacher, the categorization indicates that the teacher is not engaging with the student. According to one or more embodiments of the present invention, a mechanism allows teacher input to help correct an incorrect system label of a student affect. According to one or more embodiments of the present invention, the system learns and labels student and teacher affects by capturing movements, body language, interactions, and conversations with a teacher. Affect instances include, but are not limited to: boredom, irritation, joy, flow experiences, and frustration. According to one or more embodiments of the present invention, a cognitive agent intervenes based on object analysis, stored records (of student performance, class lists, topics, exam grades, etc.), and observed behaviors. The cognitive agent is trained to understand the affective meanings of body language. The cognitive agent is further trained to understand the interplay of meanings behind human interaction. While the system is in use, a video of the classroom is continuously recorded and fed to the cognitive system for recommendations. The cognitive system is thus trained on a wealth of virtually unlimited video material of human interaction available on the web. Some of these interactions are described as, for example, the pervasive affect of the scene (e.g., everyone listened quietly) and the affect of outside individuals (e.g.,Simon was frustrated and showed this by shaking his head vigorously. After the cognitive system was trained, it applied scene understanding to the classroom videos given to it. To ensure that the user receives only the desired notifications, one or more embodiments of the present invention employ a rating system that assigns a level of importance and a categorization to each notification. For example, it is unlikely that many teachers would want to receive notifications every minute informing them that the students are paying attention. This type of notification is usually obvious to teachers of all experience levels. This level of information, referred to as logged information (all identifiable events / pervasive affect / individual affect), is logged. However, receiving notifications about all this information may distract teachers more than it helps them. Therefore, other levels of notification importance and categorization are established.In various embodiments of the present invention, notifications are based on the results of the analysis of moving or immovable objects and the interaction of both, which leads to notification categories. Notification categories include, but are not limited to: People, Environment, Individual, Group, Extremely Positive, Positive, Slightly Positive, Extremely Negative, Negative, Slightly Negative, Neutral, and Status. The system described herein allows a user / administrator to specify types of information and situations about which they wish to be notified immediately and / or for review purposes only. In selecting which situations to be notified about, they can choose from three actions: log, notify immediately, or notify at the end of the day. Different stakeholders may need to be informed about different situations. For example, a teacher might configure the system to notify them of negative and extremely negative events involving groups of students.A facility manager can configure the system to notify him of negative environmental situations, allowing him to prioritize acquisitions. In addition to reporting classroom situations, the present invention allows for user feedback via text or speech. Recognizing that the cognitive component is not infallible, the present invention includes a feedback system that allows users to relabel a situation they have been notified about and / or suggest alternative corrections to resolve problems involving stationary objects in the classroom. After receiving corrective feedback, the cognitive agent / component retains a record indicating that a situation was mislabeled and uses this knowledge when labeling future situations. Notifications are made using the invention's dashboard, which is a web-based application that includes a smartphone interface. In some embodiments, the present invention provides a standardized classroom monitoring and management unit. For example, if the classroom environment is so poor that students subsequently become unengaged, the present invention is of great benefit for notifying the teacher. The system is thus designed to detect and report classroom environments and identify students using low- or high-resolution video. In further embodiments, the present invention provides a facial identification utility. This utility is an intelligent facial detector in that it uses contextual information, including location and time, to obtain a class directory. Consequently, faces are compared against a very small dataset, which allows for a lower identification threshold, further facilitating operation when using low-resolution image processing. A wireless connection (e.g., a Wi-Fi connection to the internet) in the classroom allows a teacher to interact with the unit via a wireless network-and-server solution or a peer-to-peer solution. Additional custom software utilities allow the administrator or teacher to easily use a virtual teacher assistant for the classroom that monitors student behavior while the teacher focuses on something else. In one or more embodiments, the present invention provides a system and a method for generating a cognitive dashboard for the users of a learning environment, comprising one or more sensor elements that detect the objects and events in the learning environment, log information about the expected activities, identities, and entities in the learning environment; a processing element capable of processing the available sensor and log information; and / or one or more computational engines for performing sensory analytics to calculate presence, activity, behavior, and interaction; and one or more computational engines for performing sensory analytics to determine the state of the individual elements (e.g.,to calculate the state of the learning environment infrastructure (chair, desk, wall color); a calculation engine to aggregate the state of individual elements into an overall classroom state for effective learning based on continuous multimedia information captured by cost-effective units, dynamic classroom activities, and other contextual information; a display engine capable of showing on-screen trends in attendance, activity, behavior, and interactions that indicate less desirable student outcomes; an interaction engine capable of engaging in dialogue with the user about analysis results, whose ability to effect change is highly likely; and / or a virtual teacher assistant for the classroom that can keep an eye on student behavior while the teacher focuses on something else. In one embodiment of the present invention, recognizing the need to manage classroom artifacts includes monitoring classroom resources, facial recognition, student attendance detection, etc. In one embodiment of the present invention, the analysis of a need is determined and shaped by an analysis of a past history of resources, an individual student or a cohort. In one embodiment of the present invention, benchmark matching includes visual analysis of low-quality video and images, the use of an evaluation utility for resources from other classrooms in the same school or from other schools, monitoring of resource quality and communication, etc. One or more embodiments of the present invention can be implemented in a cloud computing environment. It should be clarified from the outset that the implementation of the teachings presented herein is not limited to a cloud computing environment, although this disclosure contains a detailed description of cloud computing. Rather, embodiments of the present invention can be implemented together with any other type of data processing environment, now known or subsequently invented. Cloud computing is a service delivery model that enables seamless, on-demand network access to a shared pool of configurable computing resources (e.g., networks, network bandwidth, servers, processing power, main memory, storage, applications, virtual machines, and services) that can be rapidly provisioned and released with minimal management overhead or interaction with a service provider. This cloud model can include at least five properties, at least three service models, and at least four implementation models. The features are as follows: On-Demand Self-Service: A cloud user can unilaterally and automatically provide data processing functions such as server time and network storage as needed, without requiring human interaction with the service provider. Broad Network Access: Functions are available over a network, accessed through standard mechanisms that support use by heterogeneous thin or thick client platforms (e.g., mobile phones, laptops, and PDAs). Resource pooling: The provider's data processing resources are pooled to serve multiple users using a multi-tenant model, with various physical and virtual resources being dynamically allocated and reassigned as needed. There is a perceived location independence, as the user generally has no control over or knowledge of the exact location of the provided resources, but may be able to define a location at a higher level of abstraction (e.g., country, state, or data center). Rapid Elasticity: Features can be deployed quickly and elastically for rapid horizontal scaling (scale out), in some cases automatically, and released quickly for rapid scale-in. To the user, the available features often appear unlimited and can be purchased in any quantity at any time. Measured Service: Cloud systems automatically control and optimize resource usage by employing a measurement function at a certain level of abstraction appropriate for the type of service (e.g., storage, processing, bandwidth, and active user accounts). Resource consumption can be monitored, controlled, and reported, creating transparency for both the provider and the user of the service. The service models are as follows: Software as a Service (SaaS): The function provided to the user is to use the provider's applications running in a cloud infrastructure. The applications are accessible from various client devices via a thin-client interface such as a web browser (e.g., web-based email). The user does not manage or control the underlying cloud infrastructure, including the network, servers, operating systems, storage, or even individual application functions, with the possible exception of limited user-specific application configuration settings. Platform as a Service (PaaS): The function provided to the user is to deploy applications created or obtained by a user, using programming languages ​​and tools supported by the provider, in the cloud infrastructure. The user does not manage or control the underlying cloud infrastructure, including the network, servers, operating systems, storage, or even individual application functions, with the possible exception of limited user-specific application configuration settings.Infrastructure as a Service (IaaS): The functionality provided to the user consists of providing processing, storage, networking, and other basic data processing resources, enabling the user to deploy and run any software, including operating systems and applications. The user does not manage or control the underlying cloud infrastructure but has control over operating systems, storage, deployed applications, and potentially limited control over selected network components (e.g., host firewalls). The deployment models are as follows: Private Cloud: The cloud infrastructure is operated solely for one organization. It can be managed by the organization or a third party and can be located on the organization's own premises or in external premises. Community Cloud: The cloud infrastructure is shared by multiple organizations and supports a specific user community with common concerns (e.g., mission, security requirements, policies, and regulatory compliance considerations). It can be managed by the organizations or a third party and can be located on the organization's own premises or in external premises. Public Cloud: The cloud infrastructure is made available to the general public or a large industry group and is owned by an organization that sells cloud services.Hybrid Cloud: Cloud infrastructure is a composition of two or more clouds (private, community, or public) that remain separate entities but are interconnected by a standardized or proprietary technology that enables data and application portability (e.g., cloud audience distribution for load balancing between clouds). A cloud computing environment is service-oriented, focusing on statelessness, low coupling, modularity, and semantic interoperability. At the heart of cloud computing is an infrastructure that comprises a network of interconnected nodes. With reference to Fig. 12, the illustrative cloud computing environment 50 is depicted. As shown, the cloud computing environment 50 has one or more cloud computing nodes 10 with which local data processing units used by cloud users, such as the electronic assistant (PDA, personal digital assistant) or mobile phone 54A, the desktop computer 54B, the laptop computer 54C, and / or the automotive computer system 54N, can exchange data. The nodes 10 can exchange data with each other. They can be grouped physically or virtually into one or more networks, such as private, community, public, or hybrid clouds (not shown), as described above, or into a combination thereof. This enables the cloud computing environment 50 to offer infrastructure, platforms, and / or software as a service, for which a cloud user does not need to maintain resources on a local data processing unit.It should be noted that the types of data processing units 54A to 54N shown in Fig. 12 are for illustrative purposes only, and that the data processing nodes 10 and the cloud computing environment 50 can exchange data with any type of computer unit via any type of network and / or any type of network-accessible connection (e.g., using a web browser). With reference to Fig. 13, a set of functional abstraction layers provided by the cloud computing environment 50 (Fig. 12) is shown. It should be clear from the outset that the components, layers, and functions shown in Fig. 13 are for illustrative purposes only and that embodiments of the invention are not limited thereto.As shown, the following layers and corresponding functions are provided: A hardware and software layer 60 contains hardware and software components. Examples of hardware components include mainframe computers 61; servers 62 based on the RISC (Reduced Instruction Set Computer) architecture; servers 63; blade servers 64; storage units 65; and networks and network components 66. In some embodiments, software components include network application server software 67 and database software 68. The virtualization layer 70 provides an abstraction layer from which the following examples of virtual entities can be provided: virtual servers 71; virtual storage 72; virtual networks 73, including virtual private networks; virtual applications and operating systems 74; and virtual clients 75. In one example, the administration layer 80 can provide the functions described below. Resource provisioning 81 provides the dynamic procurement of data processing resources and other resources used to perform tasks within the cloud computing environment. Metering and pricing 82 provides cost tracking for the use of resources within the cloud computing environment and billing for the consumption of these resources. In one example, these resources might include application software licenses. Security provides identity verification for cloud users and tasks, as well as protection for data and other resources. A user portal 83 provides users and system administrators with access to the cloud computing environment.Service scope management (84) provides the allocation and management of cloud computing resources so that the required service objectives are met. Service level agreement (SLA) planning and fulfillment (85) provides the advance planning and procurement of cloud computing resources for which a future requirement is anticipated, in accordance with an SLA. A workload layer 90 provides examples of the functionality for which the cloud computing environment can be used. Examples of workloads and functions that can be provided by this layer include: mapping and navigation 91; software development and lifecycle management 92; provision of training in virtual classrooms 93; data analytics processing 94; transaction processing 95; and classroom resource configuration and enhancement processing 96, which can perform one or more features of the present invention. The terminology used herein serves only to describe certain embodiments and should not be construed as limiting the present invention. The singular forms "a", "an" and "the" are intended to include the plural forms when used herein, unless the context clearly indicates otherwise. It is further noted that the terms "has" and / or "having" when used in this description denote the presence of specified features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other / further features, integers, steps, operations, elements, components, and / or groups thereof. The corresponding structures, materials, actions, and equivalents of all means or step-plus-function elements in the following claims are intended to include any structure, material, or action for performing the function in conjunction with further claimed elements, which are claimed individually. The description of various embodiments of the present invention is provided for illustrative and explanatory purposes but is not intended to be exhaustive or limited to the present invention as disclosed. Many modifications and variations are apparent to a person skilled in the art without deviating from the scope of the present invention.The embodiment was chosen and described in order to best explain the basic ideas of the present invention and its practical application, and to enable other skilled persons to understand the present invention with regard to various embodiments with different modifications, as are suitable for the respective intended use. The methods described in the present invention can be executed using a VHDL (Hardware Description Language) program and a VHDL chip. VHDL is an exemplary entry-level design language for field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), and other similar electronic devices. (Only) as a further example, one or more of the computer-executed (e.g., in software) methods described herein can be replicated by a hardware-based VHDL program, which can then be applied to a VHDL chip such as an FPGA. The present invention may be a system, a method, and / or a computer program product at any possible level of integration of technical details. The computer program product may include a computer-readable storage medium (or media) on which computer-readable program instructions are stored to induce a processor to execute aspects of the present invention. A computer-readable storage medium can be a physical unit capable of retaining and storing instructions for use by a system to execute instructions. For example, a computer-readable storage medium can be an electronic storage unit, a magnetic storage unit, an optical storage unit, an electromagnetic storage unit, a semiconductor storage unit, or any suitable combination thereof, without limitation. A non-exhaustive list of more specific examples of computer-readable storage media includes the following: a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), and erasable programmable read-only memory (EPROM).Flash memory), static random-access memory (SRAM), portable compact storage disk-read-only memory (CD-ROM), DVD (digital versatile disc), USB flash drive, floppy disk, a mechanically coded unit such as punched cards or raised structures in a groove on which instructions are stored, and any suitable combination thereof. A computer-readable storage medium shall not, in its use herein, be understood as volatile signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., light pulses guided by a fiber optic cable), or electrical signals transmitted by a wire. The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to individual data processing units or, via a network such as the internet, a local area network, a wide area network, and / or a wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission lines, wireless transmission, routing computers, firewalls, switching units, gateway computers, and / or edge servers. A network adapter card or network interface in each data processing unit receives computer-readable program instructions from the network and forwards them for storage on a computer-readable storage medium within the respective data processing unit.Computer-readable program instructions for executing the steps of the present invention can be assembly instructions, ISA (Instruction Set Architecture) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, Smalltalk, C++, etc., as well as conventional procedural programming languages ​​such as C or similar languages. The computer-readable program instructions can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server.In the latter case, the remotely located computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be established with an external computer (for example, via the internet using an internet service provider). In some embodiments, electronic circuits, including, for example, programmable logic circuits, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), can execute computer-readable program instructions by using state information from the computer-readable program instructions to personalize the electronic circuits to perform aspects of the present invention. Aspects of the present invention are described herein with reference to flowcharts and / or block diagrams or diagrams of methods, devices (systems), and computer program products according to embodiments of the invention. It is pointed out that each block of the flowcharts and / or block diagrams or diagrams, as well as combinations of blocks in the flowcharts and / or block diagrams or diagrams, can be executed by means of computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a specialized computer, or another programmable data processing device to create a machine, such that the instructions executed via the processor of the computer or other programmable data processing device generate a means of implementing the functions / steps specified in the block(s) of the flowcharts and / or block diagrams or charts.These computer-readable program instructions may also be stored on a computer-readable storage medium capable of controlling a computer, programmable data processing device, and / or other units to function in a particular manner, such that the computer-readable storage medium on which instructions are stored has a manufactured product, including instructions that implement aspects of the function / step specified in the block(s) of the flowchart and / or block diagrams or charts. The computer-readable program instructions can also be loaded onto a computer, other programmable data processing device or other unit to cause the execution of a series of process steps on the computer or other programmable device or other unit in order to generate a process executed on a computer, such that the instructions executed on the computer, other programmable device or other unit implement the functions / steps specified in the block(s) of the flowcharts and / or block diagrams or charts. The flowcharts and block diagrams or charts in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this context, each block in the flowcharts or block diagrams or charts can represent a module, segment, or part of instructions that includes one or more executable instructions for performing the specific logical function(s). In some alternative embodiments, the functions specified in the block may occur in a different order than shown in the figures. For example, two blocks shown consecutively may in reality be executed essentially simultaneously, or the blocks may sometimes be executed in reverse order depending on the corresponding functionality.It should also be noted that each block of the block diagrams or charts and / or flowcharts, as well as combinations of blocks in the block diagrams or charts and / or flowcharts, can be implemented by special hardware-based systems that perform the specified functions or steps, or execute combinations of special hardware and computer instructions. Having thus described embodiments of the present invention of the present application in detail and by reference to illustrative embodiments thereof, it is evident that modifications and variants are possible without deviating from the scope of the present invention as defined in the attached claims.

Claims

A computer-executed method comprising: identifying and quantifying, by one or more processors, physical classroom resources (151) in a classroom (200) based on sensor measurements received from sensors (153) in the classroom (200), wherein the physical classroom resources (151) are inanimate physical objects that are components of the classroom;Determining, by one or more processors, of limitations of physical classroom resources (151) that impede learning by pupils in the classroom (200), based on sensor readings from the sensors (153) in the classroom, wherein the limitations are caused by physical defects in one or more of the physical classroom resources (151) that result in a reduction of the pupils' ability to learn in the classroom (200), and wherein the reduction is based on a focus determination and a group affect determination (812), wherein the focus determination is a determination of how defective objects adversely affect the learning focus of an individual pupil, and wherein the group affect determination (812) is a determination of how the defective objects adversely affect the learning foci of all pupils in the classroom (200);Identify, by one or more processors, the reduction in the pupils' ability to learn in the classroom (200), based on a decrease in the learning focus of the individual pupil and a decrease in the learning foci of all pupils in the classroom, the reduction being caused by the physical defects in the physical classroom resource(s) (151); Train, by one or more processors, a neural network to detect changes in the physical classroom resources (151) based on previous sensor readings describing earlier states of the physical classroom resources (151) in the classroom (200); Generate, by the one or more processors, a set of instructions based on the detected changes in the physical classroom resources (151);The instruction set is transmitted by one or more processors to an automatic unit to execute specified logical functions with respect to the detected changes to the physical classroom resources (151); the automatic unit repairs physical defects in one or more physical classroom resources (151) according to the specified logical functions; the one or more processors receive new sensor readings describing new changes to the physical classroom resources (151); and the one or more processors retrain the neural network with the new sensor readings to further detect changes to the physical classroom resources (151). A computer-executed method according to claim 1, further comprising: replacing one or more of the physical classroom resources (151) which have the limitations of physical classroom resources (151) with one or more other physical classroom resources which do not have the limitations of physical classroom resources (151). A computer-executed method according to claim 1, wherein the limitations of physical classroom resources (151) are further caused by a physical arrangement of the physical classroom resources (151), and wherein the computer-executed method further comprises: rearranging one or more of the physical classroom resources (151) to eliminate the limitations of physical classroom resources (151). A computer-executed method according to claim 1, further comprising: Determining, by one or more processors, the limitations of physical classroom resources (151) that hinder learning by students in the classroom (200), based on an analysis of video feeds (301) from the classroom, audio feeds from the classroom (200), and student recordings of students in the classroom. A system comprising: one or more processors; one or more computer-readable memories connected to the one or more processors; one or more non-transitory, computer-readable storage media;and program instructions stored on at least one of the one or more computer-readable storage media for execution by at least one of the one or more processors via at least one of the one or more computer-readable memory, wherein the stored program instructions are executed to perform a method comprising: identifying and quantifying, by one or more processors, physical classroom resources (151) in a classroom (200) based on sensor readings received from sensors (153) in the classroom (200), wherein the physical classroom resources (151) are inanimate physical objects that are components of the classroom;Determining, by one or more processors, of limitations of physical classroom resources (151) that impede learning by pupils in the classroom (200), based on sensor readings from the sensors (153) in the classroom, wherein the limitations are caused by physical defects in one or more of the physical classroom resources (151) that result in a reduction of the pupils' ability to learn in the classroom (200), and wherein the reduction is based on a focus determination and a group affect determination (812), wherein the focus determination is a determination of how defective objects adversely affect the learning focus of an individual pupil, and wherein the group affect determination (812) is a determination of how the defective objects adversely affect the learning foci of all pupils in the classroom (200);Identify, by one or more processors, the reduction in the pupils' ability to learn in the classroom (200), based on a decrease in the learning focus of the individual pupil and a decrease in the learning foci of all pupils in the classroom, the reduction being caused by the physical defects in the physical classroom resource(s) (151); Train, by one or more processors, a neural network to detect changes in the physical classroom resources (151), based on previous sensor readings describing prior states of the physical classroom resources (151) in the classroom (200); Generate, by the one or more processors, a set of instructions based on the detected changes in the physical classroom resources (151);The instruction set is transmitted by one or more processors to an automatic unit to execute specified logical functions with respect to the detected changes in the physical classroom resources (151); the automatic unit repairs physical defects in one or more physical classroom resources (151) according to the specified logical functions; the one or more processors receive new sensor readings describing new changes in the physical classroom resources (151); and the one or more processors retrain the neural network with the new sensor readings to further detect changes in the physical classroom resources (151). Computer program product for optimizing physical classroom resources (151), wherein the computer program product comprises a non-transitory, computer-readable memory unit containing program instructions embodied therein, wherein the program instructions are computer-readable and executable to perform a procedure comprising: identifying and quantifying, by one or more processors, physical classroom resources (151) in a classroom (200) based on sensor measurements received from sensors (153) in the classroom (200), wherein the physical classroom resources (151) are inanimate physical objects that are components of the classroom;Determining, by one or more processors, of limitations of physical classroom resources (151) that impede learning by pupils in the classroom (200), based on sensor readings from the sensors (153) in the classroom, wherein the limitations are caused by physical defects in one or more of the physical classroom resources (151) that result in a reduction of the pupils' ability to learn in the classroom (200), and wherein the reduction is based on a focus determination and a group affect determination (812), wherein the focus determination is a determination of how defective objects adversely affect the learning focus of an individual pupil, and wherein the group affect determination (812) is a determination of how the defective objects adversely affect the learning foci of all pupils in the classroom (200);Identify, by one or more processors, the reduction in the pupils' ability to learn in the classroom (200), based on a decrease in the learning focus of the individual pupil and a decrease in the learning foci of all pupils in the classroom, the reduction being caused by the physical defects in the physical classroom resource(s) (151); Train, by one or more processors, a neural network to detect changes in the physical classroom resources (151) based on previous sensor readings describing earlier states of the physical classroom resources (151) in the classroom (200); Generate, by the one or more processors, a set of instructions based on the detected changes in the physical classroom resources (151);The instruction set is transmitted by one or more processors to an automatic unit to execute specified logical functions with respect to the detected changes to the physical classroom resources (151); the automatic unit repairs physical defects in one or more physical classroom resources (151) according to the specified logical functions; the one or more processors receive new sensor readings describing new changes to the physical classroom resources (151); and the one or more processors retrain the neural network with the new sensor readings to further detect changes to the physical classroom resources (151).

Images