Adaptive robot evaluation system for multidimensional educational quality monitoring

Abstract

We provide an adaptive robot evaluation system for multidimensional educational quality monitoring. [Solution] The system (100) comprises a mobile support structure (102), a sensing assembly (104), a data interface unit (106), a memory unit (108), a processing unit (110), and a control unit (112). The processing unit (110) performs techniques to generate multidimensional groupings that correlate physical evidence with institutional information, calculates quality indicators, and evaluates data sufficiency, and instructs the control unit (112) to autonomously reposition the equipment towards undervalued zones. As a result, the system (100) can transmit aggregated performance indicators and metadata to a central repository to support organizational analysis, governance, compliance, and decision-making.

Description

Technical Field

[0001] The present invention relates to an automated computer-implemented system and apparatus for the evaluation and monitoring of educational outcomes, and more specifically, to an adaptive robotic device that physically moves through an educational institution's environment while collecting, integrating, and transmitting multidimensional outcome data across various areas of academics, finance, community engagement, and research. Further, the present invention relates to integrating robot sensing into an educational institution's data ecosystem, data governance framework, and centralized repository to enable multimodal data collection, automated quality assessment, and dynamic decision-making support.

Background Art

[0002] Educational institutions are increasingly adopting business intelligence platforms, data warehouses, and data visualization tools to support performance evaluation, accreditation acquisition, strategic planning, and regulatory compliance. However, many existing platforms rely on fragmented data sources and employ manual or semi-automatic extraction processes, lacking direct real-time connectivity to the physical environment. This results in insufficient visibility into operational situations that impact academic outcomes, leading to delays and inconsistencies. For example, universities often operate multiple unintegrated information systems such as student affairs management platforms, financial systems, community engagement registers, research indexes, and external government databases, each managed by different departments and with un-unified data standards and update protocols, resulting in siloed, unreliable, and untraceable information. Uploaded documents have shown cases where distributed systems and external data sources such as system global areas, system global information, system global views, system global utilities, SoftLand, and SoftTexPart lack traceability, real-time integration, and standardized governance, leading to inconsistencies in institutional reporting and limiting timely decision-making.

[0003] While modern systems incorporate organizational dashboards for performance monitoring, their implementation still relies on manual update cycles, flat file uploads, or semi-automated extraction, transformation, and loading procedures, creating responsiveness bottlenecks. These shortcomings are particularly problematic under regulatory frameworks that mandate continuous quality assurance, transparency, metadata traceability, and standardized performance metrics required by the European General Data Protection Regulation, INTERNATIONAL 27001, and national legislation on data protection and institutional accreditation. Furthermore, existing solutions lack mechanisms to capture real-world behavioral, acoustic, environmental, and spatial data generated within educational spaces, despite the recognition of the importance of these physical variables to student motivation, academic performance, quality of education, infrastructure utilization, and research productivity.

[0004] Attempts to address data fragmentation by introducing centralized repositories and governance frameworks offer conceptual clarity, but are inherently passive in terms of physical data acquisition. Centralized data warehouses are forced to rely on data already present in transactional systems, leaving a large amount of operationally critical data, such as student movement patterns, classroom occupancy, environmental quality, and collaboration dynamics, unrecorded. In such a passive data ecosystem, it is impossible to construct multidimensional educational quality metrics that integrate physical indicators, institutional metadata, social behavior information, funding usage, and research outcomes.

[0005] The submitted claims describe the introduction of a robotic device capable of physically moving through the environment of an educational institution, repositioning sensing devices, and acquiring physical measurements related to educational outcome categories. This device dynamically adjusts its operation based on data deficiencies and gaps. Such a device can directly acquire metrics related to environmental comfort, acoustic activity, student posture, spatial density, and collaboration patterns. These are essential for objectively and multidimensionally evaluating academic quality. However, no existing system integrates robotic sensing, multidimensional institutional data governance, automated prioritization of missing physical measurements, and real-time transmission of structured performance metrics to an institutional repository.

[0006] Therefore, there is a technical need for adaptive robotic systems that can physically collect real-time data, integrate organizational records, identify defects in stored parameters, and dynamically reallocate sensing operations, while maintaining compliance with metadata standards, data quality requirements, and regulatory frameworks. This would bridge the gap between passive digital repositories and active physical learning environments.

[0007] The modern field of educational quality monitoring is dominated by software-centric architectures centered around corporate resource planning platforms, learning management systems, business intelligence dashboards, and institutional data warehouses. Each of these is designed to integrate structured records for administrative decision-making. These systems have emerged in response to increasing regulatory pressures requiring universities to provide empirical evidence regarding student achievement, resource utilization, community engagement, and research productivity. Most implementations are based on centralized information systems that extract, transform, and visualize records from transactional databases, aiming to convert operational data into performance indicators. However, despite their widespread adoption, these systems face fundamental architectural limitations, including reliance on manual update cycles, fragmented data sources, processing delays, and weak integration with the physical learning environment. Traditional implementations often fail to incorporate real-time physical indicators such as student movement, acoustic activity, environmental comfort, and social interaction patterns, despite their strong correlation with academic performance, engagement, well-being, and resource utilization.

[0008] The case of Bernardo O'Higgins University highlights a characteristic weakness inherent in the current technological ecosystem supporting quality monitoring. The university employed incompatible systems across areas such as academic management, financial management, community engagement, organizational planning, research data, human resources, and digital certification. Each system functioned independently and was managed by separate departments with unified data standards, reporting standards, and governance procedures. Workflows were shaped by a siloed architecture, with each system autonomously storing and processing data without structured interoperability or real-time synchronization. This isolation resulted in frequent inconsistencies in outcome reporting, delays in data validation, and inconsistencies stemming particularly from differing definitions of performance metrics related to enrollment, retention, graduation, budget allocation, procurement cycles, and strategic indicators. Because reporting depended on the interpretation, methodology, and internal processes of the departments responsible for creating the reports, these inconsistencies compromised the institution's integrity, reliability, and compliance with certification standards.

[0009] To address fragmentation, several attempts were made to implement business intelligence solutions using visualization tools such as Microsoft Power Business Intelligence. These platforms were designed to provide unified dashboards integrating extracted data from multiple systems, allowing senior decision-makers to understand aggregated trends and performance indicators at the organizational and departmental levels. However, these solutions relied heavily on manual or semi-automated update procedures, flat file uploads, orphaned extracts, transformations, loading processes, and ad-hoc query tuning, hindering real-time monitoring. This reliance on human intervention led to operational risks, error propagation, procedural delays, version inconsistencies, and reporting failures due to inconsistent update frequencies across data sources. Furthermore, these visualization solutions lacked connectivity with core transaction systems and external knowledge repositories, limiting traceability, standardization, and auditability. Analysts were forced to perform redundant validation processes before publishing reports.

[0010] Another significant limitation of existing solutions lies in their exclusive reliance on transactional data models. While this captures administrative records, it ignores the physical, behavioral, environmental, and contextual factors that shape academic performance. Conventional systems store only information on grades, attendance, financial transactions, survey results, and program outcomes, but they cannot measure the dynamic interactions that occur within classrooms, laboratories, studios, workshops, libraries, and collaborative workspaces. They cannot detect whether the educational environment is overcrowded, inappropriate, unpleasant, noisy, or unengaging. They also cannot determine whether teaching methods promote active participation or whether students are isolated, distracted, fatigued, and socially isolated. Consequently, analyses of educational institutions derived from these platforms are based on partial representations of the educational process and overlook crucial determinants of learning effectiveness.

[0011] Existing approaches also lack a standardized governance structure that can ensure metadata traceability, security, lineage, or regulatory compliance across multi-domain information ecosystems. Despite several frameworks proposing data governance models, implementation in educational institutions often remains informal, resource-constrained, and fragmented. The lack of clear data ownership, management responsibilities, operational roles, access controls, and audit mechanisms increases vulnerability to organizational risk, particularly in environments regulated by complex legal frameworks such as the General Data Protection Regulation, national privacy laws, authentication protocols, and government reporting requirements. Referenced documents point out that existing systems lack a clear accountability structure, unified metric definitions, and standardized calculation methods, leading to inconsistent or unreliable analytical results, and explain the need for governance roles such as CTO, data owner, data controller, and compliance officer to manage the institution's data lifecycle.

[0012] The technical limitations of the software-centric model are further exacerbated by cultural and organizational barriers. Many organizations operate without a consistent data culture, leading to inconsistencies in metric interpretation, unified tool usage, and limited user proficiency on analytics platforms. The fragmented software ecosystem requires users to navigate multiple interfaces, extraction methods, filtering workflows, and reporting conventions, increasing training complexity and delaying adoption. The lack of standardized documentation and common operational frameworks results in knowledge gaps and repetitive training cycles, reducing organizational efficiency and undermining the transformative potential of analytics platforms.

[0013] While attempts to implement integrated data warehouses have improved interoperability, they remain passive repositories dependent on input from upstream systems. They are unable to autonomously collect data, validate input, or identify new gaps in the organization's understanding. Their architecture is inherently reactive, merely aggregating historical information rather than proactively monitoring real-world situations that impact performance and student experience. Without real-time acquisition of behavioral, environmental, and spatial data, data warehouses cannot support predictive analytics, early risk detection, adaptive resource allocation, or targeted intervention strategies. As a result, educational institutions remain reliant on post-hoc analysis, hindering timely decision-making in a rapidly changing educational environment.

[0014] Emerging research explores computer vision, acoustic analysis, and environmental sensing for learning analytics, but implementations remain experimental, software-dependent, or fixed. None of these provide a sustained, adaptive physical mobile system capable of autonomously moving through the organizational environment, autonomously repositioning sensors, and detecting gaps in measurement range. Existing fixed sensing systems are inherently limited by field of view, obstruction, environmental noise, and static coverage. They cannot dynamically adjust height, angle, or trajectory, nor can they access distributed environments beyond the confines of fixed installations. Efforts to introduce mobile robots in educational settings have primarily focused on service robots, assistive devices, remote presence systems, and educational tools. These devices are not designed for multidimensional performance monitoring, organizational data integration, metadata traceability, or automated gap detection, and therefore do not address systematic monitoring challenges.

[0015] Therefore, current technologies lack an integrated solution that can unify an organizational data ecosystem by integrating autonomous physical sensing, dynamic environmental observation, and a multidimensional evaluation framework. Existing solutions cannot integrate physical measurements and institutional metadata, categorize them into performance categories, identify missing or invalid parameters, or autonomously reallocate sensing resources without human intervention. Furthermore, traditional architectures cannot support scalable, evidence-based decision-making in line with regulatory governance, certification standards, and data quality assurance protocols, especially in environments characterized by heterogeneous systems, manual processes, and fragmented organizational structures.

[0016] Therefore, significant technical challenges remain unresolved. Educational institutions lack systems to collect real-time physical indicators, standardize cross-domain information, maintain metadata lineages, support predictive analytics, and autonomously adapt sensing strategies in response to information deficiencies. The absence of such integrated cyber-physical solutions continues to limit institutions' ability to obtain timely, accurate, comprehensive, and actionable educational intelligence. [Overview of the project] [Problems that the invention aims to solve]

[0017] The primary objective of this invention is to provide an adaptive robot evaluation system capable of acquiring multidimensional performance data across academic, financial, community service, and research domains within an educational institution environment. Furthermore, it aims to enable the automatic acquisition of physical navigation, dynamic sensor placement, and physical measurements based on acoustic, environmental, positional, and proximity data, and to integrate these into the educational institution's data governance and data warehouse ecosystem. Another objective is to provide a system that continuously evaluates stored data to detect gaps in performance categories, prompts autonomous robot repositioning, path selection, sensor orientation adjustment, or stationary stabilization, and collects sufficient data for reliable institutional analysis. Yet another objective is to enable standardized representation, storage, transmission, and traceability of acquired data, and to comply with the organization's metadata framework, regulatory protocols, and security requirements. Yet another objective is to provide a system that can support predictive analytics, strategic planning, certification processes, regulatory audits, and evidence-based institutional decision-making. [Means for solving the problem]

[0018] The present invention provides an adaptive robotic device comprising a mobile chassis, a mobile mechanism, a mechanically adjustable sensing assembly, and multiple electronic units that jointly perform the physical acquisition, storage, evaluation, and transmission of multidimensional performance metrics. The device includes image, sound, environmental, and proximity sensors mounted on a mobile platform consisting of a rotary and lifting linkage mechanism. Data acquired from the physical environment is integrated with organizational data received from a distributed system and stored in a storage device. It is then aggregated by a processing unit and categorized into multidimensional groups related to academic, financial, community contribution, and research performance.

[0019] This device includes a control unit that directs robot movement and sensor positioning in the event of incomplete stored data, thereby ensuring the continuous acquisition of performance metrics. A communication unit transmits structured metrics and associated physical metadata to a centralized repository or data warehouse, enabling traceability, governance, and standardized analysis. Thus, the system functions as a cyber-physical data generator, extending organizational intelligence from passive digital extraction to active robotic observation and automated measurement.

[0020] This invention aims to achieve a comprehensive transformation of educational quality monitoring by introducing a cyber-physical system capable of autonomously observing, acquiring, processing, and transmitting multidimensional performance data. The primary objective of this invention is to create an adaptive robotic device capable of capturing dynamic physical parameters (occupancy characteristics, spatial distribution, environmental conditions, acoustic activity, behavioral indicators, etc.) that are not represented by conventional transactional datasets, while physically moving through educational, administrative, and research environments. By achieving autonomous mobility and mechanically adjustable sensing capabilities, it aims to overcome the inherent limitations of software-centric monitoring systems that lack access to on-site evidence of educational dynamics. Another objective of this invention is to integrate physical measurements with institutional data originating from academic, financial, community collaboration, and research systems to construct a high-precision multidimensional data structure that describes institutional performance from a comprehensive perspective. This integration solves long-standing fragmentation challenges and provides analytical depth to support certification, regulatory compliance, and data-driven strategic planning.

[0021] A further objective of this invention is to enable the system to intelligently detect insufficient or outdated measurements across different performance categories and autonomously modify its operation to perform targeted data acquisition. This reduces the need for manual intervention and significantly improves the completeness and reliability of performance metrics. To support this objective, this invention enables the robotic device to dynamically reposition sensors and change routes within the facility environment based on gaps in the stored data. This ensures that physical evidence is continuously updated in contextual relevance. Another objective is to incorporate a robust communication and storage mechanism for transmitting and storing acquired data to a centralized repository or data warehouse, ensuring traceability, auditability, and interoperability with visualization tools, analytical frameworks, and organizational governance systems. By ensuring standardized storage and metadata integrity, the system supports quality assurance, data genealogy tracking, and automated compliance reporting.

[0022] Furthermore, this invention aims to support predictive analytics, early risk detection, performance forecasting, and strategic intervention planning by providing a rich data stream that integrates physical, behavioral, environmental, and administrative metrics. By bridging the gap between cyber infrastructure and the real-world educational environment, it enhances institutions' ability to evaluate learning effectiveness, infrastructure utilization, student engagement, and operational efficiency with unprecedented resolution. Another objective of this invention is to minimize the delay between event occurrence and data availability, enabling rapid decision-making in scenarios where timeliness is critical, such as student well-being, resource management, certification audits, and safety compliance. Finally, this invention aims to establish a scalable platform that not only meets current analytical demands but also incorporates additional sensors, data sources, machine learning models, and governance protocols as organizational requirements evolve, ensuring long-term adaptability, sustainability, and strategic value. [Effects of the Invention]

[0023] The adaptive robot evaluation system (100) for multi-dimensional education quality monitoring according to the present invention includes a movement support structure (102), a detection assembly (104), a data interface unit (106), a memory unit (108), a processing unit (110), and a control unit (112). The processing unit (110) executes techniques for generating multi-dimensional grouping that associates physical evidence and institutional information, calculates quality indicators, evaluates data sufficiency, and instructs the control unit (112) to autonomously relocate the device towards the undervalued zones. As a result, this system (100) can transmit the aggregated performance indicators and metadata to a central repository, and assist in organizational analysis, governance, compliance, and decision-making.

Brief Description of the Drawings

[0024] These features, aspects, and advantages of the present invention, as well as other features, aspects, and advantages, will be better understood by reading the following detailed description in conjunction with the accompanying drawings. In the drawings, the same reference numerals indicate the same parts throughout the drawings.

[0025] FIG. 1 shows a block diagram of an adaptive robot device for multi-dimensional education quality monitoring.

[0026] Furthermore, those skilled in the art will understand that the elements in the drawings are shown for simplicity and are not necessarily drawn to actual scale. For example, the flowcharts show the methods in terms of the most prominent steps involved to assist in understanding the aspects of the present disclosure. Also, regarding the configuration of the device, one or more of the components of the device may be represented by conventional symbols in the drawings, and the drawings show only the specific details relevant to understanding the embodiments of the present disclosure in sufficient detail to be easily understood by those skilled in the art who enjoy the description of this specification without obscuring the drawings.

Embodiments for Carrying Out the Invention

[0027] For the purpose of facilitating the understanding of the principle of the proposed solution, specific terms are used in the description thereof by reference to the embodiments shown in the drawings. However, this is not intended to limit the scope of the invention, and it should be understood that changes and further improvements in the illustrated system, as well as further applications of the inventive principle shown therein, are within the scope normally conceivable by those skilled in the art.

[0028] Those skilled in the art will understand that the foregoing general description and the following detailed description are for the purpose of illustrating and explaining the present invention and are not intended to limit it.

[0029] Expressions such as "in one aspect", "in another aspect" or similar expressions throughout this specification mean that a particular function, structure, or feature described in relation to an embodiment is included in at least one embodiment. Therefore, the appearance of expressions such as "in one embodiment", "in another embodiment" and similar expressions throughout this specification does not necessarily refer to the same embodiment.

[0030] "Comprising", "being a thing that comprises" or other similar expressions are intended to be non-exclusive inclusion. A process or method that includes a list of steps does not include only those steps, but may include other steps not explicitly described or inherent in the process or method. Similarly, one or more devices, subsystems, elements, structures, or components preceded by "...comprising" do not exclude the presence of other devices, other subsystems, other elements, other structures, other components, additional devices, additional subsystems, additional elements, additional structures, additional components, provided there are no further restrictions.

[0031] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as commonly understood by those skilled in the art to which the present invention pertains. The systems, methods, and embodiments described in this specification are illustrative only and are not intended to be limiting.

[0032] The embodiments described herein will be described in detail below with reference to the attached drawings. Referring to Figure 1, a block diagram of an adaptive robotic device for multidimensional educational quality monitoring is shown. System 100 includes: a mobile support structure (102) comprising a chassis (102a), multiple drive wheels, electric drive motors, and motion control interfaces that enable the device to move through the educational, administrative, and research environments of an educational facility; a mechanically adjustable sensing assembly (104) mounted on the mobile support structure. The sensing assembly includes image sensors, sound sensors, environmental sensors, and proximity sensors and is supported on a mobile platform assembly with a rotation and lifting link mechanism driven by actuators. The mobile platform assembly has a data interface unit (106) mounted on the chassis and electrically connected to the sensing assembly to receive institutional information originating from the educational facility's distributed academic systems, financial systems, community collaboration systems, and research systems in order to acquire physical measurements related to occupancy, occupancy in the educational performance monitoring area, movement, acoustic activity, and environmental conditions; and a memory unit (108) mounted on the chassis and electrically connected to the data interface unit and the sensing assembly. This memory unit stores both physical measurements acquired by the sensing assembly and institutional information received by the data interface unit, and is configured to maintain the relationship between the stored information and each performance category used by the facility to assess the quality of education. A processing unit (110) mounted on the chassis and electrically connected to the memory unit. The processing unit is configured to combine the stored physical measurements and stored institutional information to perform multidimensional grouping corresponding to the facility's academic performance, financial performance, community contribution performance, and research performance; a control unit (112) mounted on the chassis and electrically connected to the processing unit and the motion control interface. The control unit is configured to direct the operation of the mobile support structure and actuate the rotation and lifting linkages of the mobile platform assembly based on the absence or lack of stored physical measurements related to at least one performance category; a communication unit (114) mounted on the chassis and electrically connected to the memory unit, including a transmitter.The communication unit is configured to transmit multidimensional grouping and associated stored physical measurements to a central repository; the communication unit (114) includes a transmitter mounted on the chassis and electrically connected to a memory unit, which is configured to transmit multidimensional grouping and associated stored physical measurements to a central repository of the educational facility; the mobile support structure, sensing assembly, data interface unit, memory unit, processing unit, control unit, and communication unit are mechanically supported by the chassis, interconnected by electrical conductors, and work together to physically move through the facility environment, mechanically position sensing components, and acquire physical measurements related to multidimensional educational quality monitoring.

[0033] In one embodiment, a mechanically adjustable sensing assembly (104) comprises a motor-driven rotary joint and an actuator-driven elevation linkage, which physically position the sensing assembly toward student gathering areas, instruction focus areas, laboratory benches, and administrative work interaction spaces. If the control unit determines, based on accumulated information, that the physical measurements of academic engagement, research activities, and administrative work occupancy related to educational quality monitoring are insufficient, it operates the rotary joint and elevation linkage to mechanically reposition the sensing assembly.

[0034] In one embodiment, the moving unit includes a differential drive mechanism with independent drive wheels and rotary encoders, which are arranged to physically control the linear and rotational movement of the device. The control unit also modulates the movement of the wheels to move toward the institution's educational, financial, or community-oriented facilities if the processing unit indicates that stored physical measurements related to academic performance, utilization of financial resources, or community engagement are missing or incomplete.

[0035] In one embodiment, the chassis (102a) includes vibration damping structures consisting of elastic isolators, mechanical suspension elements, or compliant mounts, which are arranged to isolate the sensing assembly from the movement of the chassis, thereby reducing motion-induced strains that occur during the acquisition of physical parameters related to student posture, spatial density, acoustic communication, and environmental comfort in educational environments where accurate quality monitoring is required.

[0036] In one embodiment, a sensing assembly (104) is mounted on a telescopic mast structure that is mechanically extendable and retractable from the chassis by a linear actuator to change its height from the floor. This mast structure is positioned to extend above seating or laboratory furniture to physically measure, without interference, student distribution, instructional gestures, and collaborative movement patterns related to academic performance indicators recognized by the educational facility.

[0037] In one embodiment, the mobile support structure (102) has a compact wheelbase and a steerable front axle and is positioned to traverse narrow spaces between desks, benches, and facility furniture. This allows the sensing assembly to physically collect measurements from student seating areas, equipment workspaces, and collaborative work zones, contributing to the evaluation of academic performance, research productivity, and infrastructure utilization by educational institutions.

[0038] In one embodiment, the chassis (102a) includes a deployable stabilizing support consisting of mechanically actuated legs or pads that extend to contact the floor surface during a stationary sensing operation. This stabilizing support reduces chassis movement and enables consistent acquisition of physical parameters related to instructional activities, student engagement, and environmental stability, which are used for multidimensional educational quality monitoring.

[0039] In one embodiment, a mechanically adjustable sensing assembly (104) is configured to position physical sensors toward predetermined locations within an educational environment, including a podium, team seating area, demonstration station, or equipment installation site, such mechanical positioning provides physical measurements that can be used to identify academic performance levels, levels of collaborative engagement, and resource utilization patterns perceived by the educational institution.

[0040] In one embodiment, the mobile unit is equipped with a route-selection type mechanical drive system that physically guides the device along predefined routes corresponding to academic buildings, financial management offices, regional collaboration centers, and research laboratories of educational facilities, thereby enabling the physical acquisition of environmental, behavioral, and spatial parameters related to each performance area stored in the memory unit.

[0041] In one embodiment, the proximity sensor is mounted on a mechanically rotatable bracket and configured to physically adjust its orientation during movement to avoid collisions with desks, furniture, equipment, or groups of students. Furthermore, the physical displacement of the sensing assembly during proximity detection contributes to measurements used to evaluate facility layout efficiency and infrastructure adaptability as components of educational quality monitoring.

[0042] In one embodiment, the chassis (102a) has a docking interface equipped with alignment rails, locking pins, and mechanical latching elements for securing the device to a fixed base installed in the educational environment. This docking interface enables continuous stationary sensing of physical parameters related to academic engagement, collaboration patterns, and environmental stability, and is utilized for multidimensional educational quality monitoring.

[0043] In an exemplary embodiment, the adaptive robotic evaluation system functions as a cyber-physical analysis platform that generates multidimensional educational quality metrics, with mechanical subsystems, sensing assemblies, and computing units working together under a unified technical framework. The system is initialized by executing configuration routines in the processing unit, which loads a set of institutional classifications, performance categories, metric definitions, and governance constraints from the memory unit. These definitions specify how to map physical and organizational raw data streams to the dimensions of academic performance, financial performance, community engagement performance, and research performance, in accordance with the institution's standardized data dictionary and metric protocols. During initialization, the control unit also acquires a digital floor plan, logical zoning definitions, and a list of preferred locations such as lecture halls, laboratories, administrative offices, research centers, and community engagement facilities. Each zoning is associated with a performance category and metric weighting, allowing the system to calculate the expected data contribution from each location related to institutional objectives.

[0044] After initialization, the system enters a continuous monitoring loop driven by monitoring techniques performed by the processing unit. At a high level, this loop consists of four tightly coupled stages: data acquisition, data fusion and classification, sufficiency analysis, and robot motion planning. In the data acquisition stage, a mechanically adjustable sensing assembly is actively controlled to capture physical measurements as the moving support structure moves through the environment. The motion control interface receives low-level speed and steering commands from the control unit to drive the differential drive wheels or steerable axles along a preset or dynamically updated path. Meanwhile, encoders and inertial sensors provide odometry feedback for position estimation. While the device moves, the control unit continuously calculates the optimal azimuth and elevation angles of the sensing assembly based on the current zone type, expected occupancy, and sensor field of view model. Rotary joints and elevation linkage actuators are instructed to orient the image sensors toward focal areas such as podiums, group seating areas, and laboratory benches, and the telescopic mast extends and retracts to minimize obstruction by furniture or people.

[0045] The acquisition techniques associated with each sensor modality are designed to generate structured feature vectors rather than raw signal archives, optimizing storage and transmission. For example, image processing routines performed by the processing unit can use one or more vision models to detect and track human silhouettes, estimate spatial density, and infer posture categories (e.g., attentive, cooperative, indifferent). Speech analysis routines calculate acoustic energy levels and perform basic classifications of sound environments such as lectures, group discussions, and distracting noise, as well as speech activity detection. Environmental sensors measure temperature, humidity, illuminance, and air quality to generate normalized environmental comfort scores. Proximity sensors and collision avoidance techniques estimate available space and pedestrian congestion around the device. These modality-specific routines output feature vectors tagged with timestamps, spatial coordinates, zone identification, and anonymized context labels, which are stored in the memory unit, associated with relevant performance categories defined during initialization.

[0046] In parallel, the data interface unit maintains synchronous connections with institutional systems such as the academic affairs management system, financial system, regional collaboration platform, research registration system, and external data sources. Regular transactional data such as course registration, grades, retention statistics, budget expenditure, project count, outreach activities, and research outcomes are delivered via application programming interfaces, schedule extraction, and pull or push mechanisms through message queues. This institutional data is ingested into the staging area of ​​the memory unit and transformed into standardized metric components compliant with the institutional data warehouse schema and metadata catalog. The processing unit then implements data fusion techniques to align physical feature vectors with institutional records in both temporal and spatial dimensions. For example, physical density measurements and acoustic activity detected at a specific time in a particular classroom are linked to timetable information, course identifiers, student cohorts, and faculty data stored in the academic system. Similarly, laboratory environmental comfort indicators are associated with safety compliance records, equipment usage, and research project metadata.

[0047] The fusion technology computes multidimensional groupings, with each group corresponding to a composite observation aggregating heterogeneous signals associated with one or more performance categories. Each group is represented as a high-dimensional vector containing physical features, institutional indicators, and descriptive metadata. The classification subroutine maps each group to institutionally defined quality indicators such as "educational engagement index," "appropriateness of learning environment," "laboratory utilization efficiency," "strength of community collaboration," and "level of research environment support." For each indicator, the processing unit uses a predefined formula incorporating a weighted combination of constituent features, threshold parameters, and normalization coefficients. Threshold parameters are not embedded as fixed absolute values, but rather expressed as configurable lower and upper limits that vary depending on the zone, time of day, or institutional policy. For example, the appropriateness of the learning environment score is calculated from environmental comfort features, spatial density, and acoustic noise, and a technique is used to map the feature range between the lower and upper comfort thresholds to the normalized score.

[0048] After calculating metric values ​​for each multidimensional grouping, the system proceeds to the adequacy analysis phase. Here, the processing unit evaluates whether each performance category and each metric has sufficiently up-to-date and complete coverage within a specified time window and spatial domain. To achieve this, the memory unit maintains a coverage map that records the date, time, and location where valid groupings were collected, and the metrics they support. The adequacy analysis method iterates through all monitored zones and time frames, comparing the actual data coverage to a target coverage level expressed as minimum sampling frequency or minimum confidence score. When areas or metrics with coverage below the target threshold are identified, a quantitative deficiency index is generated. For example, an auditorium might be flagged as under-observed regarding environmental comfort during nighttime sessions, or a community center might show insufficient observation of usage patterns during public hours.

[0049] The deficiency indicators are then passed to the robot's motion planning phase, where the control unit determines how to physically reposition the device to maximize the reduction of information gaps. For candidate trajectories and observation sequences, a cost function is defined that combines elements such as travel time, battery consumption, collision risk, and expected information gain, measured as the rate of increase in predicted coverage of the deficiency indicators. The control unit uses this cost function within its path optimization techniques, which can be implemented as a graph search procedure, a model predictive control strategy, or a heuristic scheduler tailored to the facility topology. Taking into account constraints such as access permissions, operating hours, and safety regulations, the control unit generates a priority list of target locations and an ordered set of observation tasks. The motion control interface receives corresponding commands, and the device physically moves to the region with the highest marginal value of new data.

[0050] As the device moves along a planned path, the sensing assembly continuously runs acquisition routines, and the processing unit periodically recalculates the deficiency measurements using the newly acquired data. This enables closed-loop adaptive operation, where sensing and motion are continuously informed by updated analysis results. During stationary phases, such as when the chassis is docked to a base station or when stabilization supports are deployed, the technology may switch to high-precision acquisition mode. This may increase the sampling rate or activate additional vibration-sensitive sensing modes, such as high-resolution video. The telescopic mast and stabilization supports ensure that mechanical vibrations do not degrade the measurements of the visual and acoustic sensors, maintaining signal quality for detailed analysis of engagement and coordination patterns.

[0051] In addition to local processing, the communication unit executes protocols for transmitting multidimensional grouped data, calculated metrics, coverage maps, and system status information to a central repository or institutional data warehouse. The transmission scheduler technology works in conjunction with the adequacy analysis module and the action planning module. When the device detects a network connection or enters a docking station, the scheduler prioritizes uploading aggregated metrics and metadata over large amounts of raw data, reducing bandwidth consumption and ensuring decision-makers receive actionable information in near real-time. All transmitted data is accompanied by metadata that conforms to the institutional metadata framework and governance rules outlined in institutional documentation, specifying the source, timestamp, zone identification, sensing configuration, and transformation history. This allows the central repository to integrate the robotic data stream with other institutional systems, enabling the generation of dashboards, predictive models, and regulatory reports.

[0052] The technical framework also includes diagnostic and self-monitoring routines. The processing unit continuously evaluates sensor health, data quality, and abnormal conditions. If the data stream shows out-of-range values, excessive noise, or inconsistencies with expected patterns, the system can mark the affected group with a reduced confidence score or initiate a recalibration routine for the sensing assembly. The control unit may periodically guide the device to a calibration zone with a known reference pattern or environmental baseline to verify sensor accuracy. The self-diagnostic function also impacts the satisfaction analysis by distinguishing between insufficient coverage due to unvisited zones and insufficient valid data due to sensor degradation.

[0053] The described technical process transforms the device into an autonomous agent for multidimensional educational quality monitoring through the collaborative execution of the mobile subsystem, sensing assembly, processing unit, control unit, memory unit, data interface unit, and communication unit. By continuously acquiring physical measurements, integrating them with institutional records, evaluating coverage gaps, and adaptively readjusting positions to maximize information gain, the system overcomes the static, passive, and fragmented nature of existing software-centric solutions. It provides a continuously updated, contextually rich, and governance-compliant representation of institutional performance that is available to decision-makers, certification bodies, and regulators without relying on manual data collection or ad-hoc reporting workflows.

[0054] This invention includes a mobile support structure having a chassis equipped with wheels, an electric motor, and motion control elements for moving through educational, administrative, and research spaces. The chassis mechanically supports a sensing assembly mounted on a movable platform equipped with rotary joints and lifting linkage mechanisms driven by actuators. The assembly allows for the mechanical repositioning of image sensors, sound sensors, environmental sensors, and proximity sensors, and adjusts the field of view, orientation, and height in response to dynamic occupancy, physical obstacles, and environmental conditions. The chassis may be provided with vibration damping structures, telescopic mast extensions, and deployable stabilizing supports to ensure measurement accuracy during movement and stationary operation.

[0055] The data interface unit retrieves institutional information from distributed academic, financial, regional collaboration, research, and external systems. This interface integrates multi-domain institutional records that comply with the organization's established governance framework, metadata standards, and data access policies. The memory unit stores both physical measurements and institutional data, maintaining their relationships with performance categories and metadata attributes. The processing unit aggregates the stored information into multidimensional groups and classifies physical and institutional data into a standardized performance classification system.

[0056] The control unit continuously evaluates stored data and, upon detecting missing, insufficient, or outdated physical measurements, issues commands to the movement mechanism and robot joints to reposition the device. For example, the device autonomously moves to a designated space that is of high academic significance but lacks recent physical measurements. Movement is supported by a differential drive system, path selection logic, and collision avoidance functions based on proximity sensing.

[0057] The communication unit transmits aggregated performance metrics, physical measurements, metadata genealogy, and quality attributes to a central repository, data warehouse, or analytics platform, enabling their subsequent use in dashboards, predictive analytics, certification processes, and strategic planning. Data transmission supports security, access control, traceability, auditability, and compliance, ensuring alignment with the General Data Protection Regulation, INTERNATIONAL 27001, and national regulatory frameworks as described in the organization's governance model.

[0058] This invention relates to an adaptive computer-implemented cyber-physical system designed for multidimensional monitoring and evaluation of educational quality across the entire educational institution environment. More specifically, it relates to a robotic device capable of autonomous navigation, repositioning of mechanical sensors, real-time acquisition of physical data, integration of heterogeneous educational institution datasets, and technique generation of performance indicators related to academic management, financial efficiency, community engagement, and research productivity. Furthermore, this invention relates to a technical architecture that controls data fusion, sufficiency analysis, dynamic motion planning, metadata traceability, and transmission of standardized analytical results to a centralized repository, enabling compliance with data governance frameworks, regulatory requirements, and institutional certification protocols. Positioned at the intersection of robotic sensing, institutional data management, cyber-physical analysis, and educational performance engineering, this invention provides an infrastructure that transcends the limitations of conventional software-based systems by incorporating dynamic and physical evidence obtained from real-world interactions in learning spaces, laboratories, administrative facilities, and community areas.

[0059] The drawings and the preceding description illustrate examples of embodiments. Those skilled in the art will understand that one or more of the described elements may be integrated into a single functional element. Alternatively, certain elements may be divided into multiple functional elements. It is also possible to add elements of one embodiment to another. For example, the order of processes described herein is modifiable and is not limited to the methods described herein. Furthermore, the operations in the flowchart do not necessarily have to be implemented in the order shown, nor do all operations necessarily have to be performed. Operations that do not depend on other operations may be performed in parallel with other operations. The scope of embodiments is by no means limited by these specific examples. Numerous variations are possible, including differences in structure, dimensions, and use of materials, whether or not they are expressly described in the specification. The scope of embodiments is at least as broad as or broader than the scope given by the following claims.

[0060] The advantages, other benefits, and solutions to problems have been described above with respect to specific embodiments. However, these advantages, benefits, solutions to problems, and any components that may result from the occurrence or enhancement of any advantages, benefits, or solutions should not be construed as essential, necessary, or intrinsic features or components in any or all of the claims.

Claims

1. An adaptive robot evaluation system for multidimensional educational quality monitoring, A mobile support structure comprising a chassis, multiple drive wheels, an electric drive motor, and a motion control interface arranged for moving equipment in the educational, administrative, and research environment of an educational facility; A mechanically adjustable sensing assembly mounted on a mobile support structure, the sensing assembly comprising an image sensor, an audio sensor, an environmental sensor, and a proximity sensor, is supported on a movable platform assembly having a rotational and lifting linkage mechanism driven by actuators, the movable platform assembly being positioned to change the orientation, height, and field of view of the sensing assembly and to acquire physical measurements related to occupancy, movement, acoustic activity, and environmental conditions in an area for monitoring educational performance; A data interface unit mounted on a chassis and electrically connected to a sensing assembly, the data interface unit being configured to receive institutional information originating from a distributed academic system, financial system, community collaboration system, and research system of an educational institution; A memory unit mounted on the chassis and electrically connected to a data interface unit and a sensing assembly, the memory unit is configured to store physical measurements acquired by the sensing assembly together with institutional information received by the data interface unit, and to maintain the relationship between the stored information and each performance category used by the educational institution to assess the quality of education; A processing unit mounted on a chassis and electrically connected to a memory unit, the processing unit is configured to combine stored physical measurements and stored institutional information to perform multidimensional grouping corresponding to the facility's academic performance, financial performance, community contributions, and research achievements; A control unit mounted on a chassis and electrically connected to a processing unit and an operation control interface, the control unit is configured to direct the operation of a mobile support structure and to actuate the rotation and lifting link mechanisms of a movable platform assembly based on the absence or lack of stored physical measurements related to at least one performance category; and A communication unit mounted on a chassis and electrically connected to a memory unit, the communication unit being configured to transmit multidimensional grouped data and associated stored physical measurements to a central repository of an educational institution; Here, the mobile support structure, the sensing assembly, the data interface unit, the memory unit, the processing unit, the control unit, and the communication unit are mechanically supported by a chassis, interconnected by electrical conductors, and cooperate to physically move through the facility environment, mechanically position the sensing components, and acquire physical measurements related to multidimensional educational quality monitoring. Here, the mechanically adjustable sensing assembly includes a motor-driven rotary joint and an actuator-driven lifting linkage, and the sensing assembly is physically directed towards user gathering areas, educational focus points, laboratory benches, and administrative interaction spaces. Here, the control unit includes a driven lifting linkage that operates a rotary joint and a lifting linkage to mechanically reposition the sensing assembly, which physically guides the sensing assembly toward the user gathering area, educational focus point, laboratory bench, and administrative interaction space. Herein, the control unit mechanically rearranges the sensing assembly by operating a rotary joint and a lifting linkage when the accumulated information indicates that the physical measurements related to research activities related to academic involvement or educational quality monitoring are insufficient; this is a feature of the adaptive robotic evaluation system for multidimensional educational quality monitoring.

2. Furthermore, it is equipped with a mobile unit, The mobile unit is equipped with a differential drive mechanism including independent drive wheels and rotary encoders, which are arranged to physically control the linear and rotational movement of the device. Here, the control unit includes a differential drive mechanism including independent drive wheels and rotary encoders arranged to physically control the linear and rotational displacement of the device when the processing unit indicates that stored physical measurements related to academic performance, financial resource utilization, or participation in community activities are missing or incomplete. The adaptive robot evaluation system for multidimensional educational quality monitoring according to claim 1, wherein the chassis comprises a vibration damping structure including an elastomer isolator, a mechanical suspension element, or a compliant mount, arranged to isolate the sensing assembly from the movement of the chassis.

3. The aforementioned detection assembly is mounted on a telescopic mast structure and can be mechanically extended and retracted from the chassis by a linear actuator, allowing its height from the floor to be changed. Here, the telescopic mast structure is positioned to extend above seats and laboratory furniture, and to obtain unobstructed physical measurements of student distribution, instructional gestures, and collaborative movement patterns related to academic performance indicators recognized by the educational facility. Hereinafter, the mobile support structure is characterized in that it has a compact wheelbase and a steerable front axle and is configured to traverse narrow spaces between desks, workbenches and facility furniture, thus enabling the adaptive robot evaluation system for multidimensional educational quality monitoring according to claim 1.

Images