Search

KR-102961418-B1 - Apparatus for managing spatial orchestration based on artificial intelligence and method thereof

KR102961418B1KR 102961418 B1KR102961418 B1KR 102961418B1KR-102961418-B1

Abstract

The present invention discloses an artificial intelligence-based spatial orchestration management device and method. Specifically, the present invention collects spatial data according to spatial identifiers for a plurality of pre-set spaces, preprocesses the collected spatial data, generates a spatial state model based on the preprocessed spatial data, verifies a spatial normative constraint among a plurality of pre-set normative constraints for each space, generates one or more control signals by considering the priority according to the current state of each space among a plurality of rules and constraints included in the spatial normative constraints through artificial intelligence-based inference based on the verified spatial normative constraints and spatial state models, performs a control function by linking with one or more peripheral devices based on the generated one or more control signals, and updates the spatial state model and normative constraints based on the results of the control function execution, state changes, operation logs, etc. By defining and managing spaces as a relationship-based set of spaces rather than as individual units, the invention can provide continuous and consistent judgment and control functions among a plurality of spaces.

Inventors

  • 임가율

Assignees

  • 주식회사 아르티폭스

Dates

Publication Date
20260511
Application Date
20260116

Claims (7)

  1. In an artificial intelligence-based spatial orchestration management device, A preprocessing unit that performs preprocessing on multiple spatial data collected for each of the multiple preset spaces; A state modeling unit that generates a plurality of state models based on the above-mentioned preprocessed plurality of spatial data; A verification unit that checks, among the multiple normative constraints for each state model that are pre-stored in a storage unit, each of the multiple normative constraints corresponding to the generated multiple state models; An analysis unit that performs AI-based learning based on the generated plurality of state models and the identified plurality of normative constraints, and generates one or more control signals for each space based on the learning results; and It includes an external device control unit that, based on one or more control signals generated for each space, links with one or more devices located in each of the plurality of spaces to remotely control the operation of the corresponding devices for each of the plurality of spaces and collects the processing results for each space according to the remote control. The above space orchestration is, It represents the comprehensive design and coordination of people, technology, content, services, circulation, and environmental components to align with a single purpose and experience flow, and the management of what operates, when, and how within a space, and The above spatial data is, It includes environmental information related to the space, object state information related to an object located in the space, biometric information related to a person who is an object located in the space, device state information related to one or more devices located in the space, and one or more pre-set norm information related to the space, The above preprocessing unit is, Noise removal, distortion correction, scaling, and normalization functions are performed on the above spatial data, and The above state modeling unit is, Regarding a specific space among the plurality of spaces mentioned above, a state model is generated by integrating the specific space, one or more objects located within the specific space, one or more normative information related to the specific space, and one or more risk factors related to the specific space, based on the preprocessed space data. The above state model is, It includes spatial states, object states, relationship states, risk prediction states, and nested spatial states related to space, The above spatial conditions include temperature, population density, and risk level at the spatial unit level, and The above object state includes the states of people, devices, and robots, and The above relationship state includes the distance between objects, the possibility of collision, and dependencies, and The above risk prediction status includes future risk levels and abnormal behavior, The above-mentioned nested space state includes a state in which a single object belongs to multiple spaces, and The above verification unit is, One or more rules and one or more constraints are generated based on multiple normative information corresponding to a state model related to the space, the suitability and priority of an intervention are determined for each of the generated one or more rules and one or more constraints, and based on the determination result, at least one rule and at least one constraint are selected from among the generated one or more rules and one or more constraints such that the suitability of the intervention is greater than or equal to a preset standard suitability and the priority satisfies a preset standard priority, a normative constraint including the selected at least one rule and at least one constraint is generated, and the generated normative constraint related to the space is stored in the storage unit. The above analysis unit is, Learning is performed using the generated plurality of state models and the identified plurality of normative constraints as input values for a preset artificial intelligence model, and one or more control signals for each space are generated based on the learning results. The above control signal is, An artificial intelligence-based spatial orchestration management device characterized by including information on where, to whom, and with what priority a control function will be applied according to the result of a norm judgment, being generated for each of one or more spaces to which the control function will be applied, and each being generated for one or more spaces among the plurality of spaces to which the control function will be applied.
  2. delete
  3. In an artificial intelligence-based spatial orchestration management method, A step of performing preprocessing on each of the multiple spatial data collected for each of the multiple preset spaces by the preprocessing unit; A step of generating a plurality of state models based on the preprocessed plurality of spatial data by the state modeling unit; A step of confirming, by a verification unit, each of the multiple normative constraints corresponding to the generated multiple state models among the multiple normative constraints for each state model that are pre-stored in a storage unit; A step of performing AI-based learning based on the generated plurality of state models and the identified plurality of normative constraints by an analysis unit, and generating one or more control signals for each space based on the learning results; and The method includes the step of remotely controlling the operation of each device in each of the plurality of spaces based on one or more control signals generated for each space by an external device control unit, and collecting processing results for each space based on the remote control. The above spatial orchestration is, It represents the comprehensive design and coordination of people, technology, content, services, circulation, and environmental components to align with a single purpose and experience flow, and the management of what operates, when, and how within a space, and The above spatial data is, It includes environmental information related to the space, object state information related to an object located in the space, biometric information related to a person who is an object located in the space, device state information related to one or more devices located in the space, and one or more pre-set norm information related to the space, The step of performing preprocessing on the above plurality of spatial data is, Noise removal, distortion correction, scaling, and normalization functions are performed on the above spatial data, and The step of generating each of the above plurality of state models is, Regarding a specific space among the plurality of spaces mentioned above, a state model is generated by integrating the specific space, one or more objects located within the specific space, one or more normative information related to the specific space, and one or more risk factors related to the specific space, based on the preprocessed space data. The above state model is, It includes spatial states, object states, relationship states, risk prediction states, and nested spatial states related to space, The above spatial conditions include temperature, population density, and risk level at the spatial unit level, and The above object state includes the states of people, devices, and robots, and The above relationship state includes the distance between objects, the possibility of collision, and dependencies, and The above risk prediction status includes future risk levels and abnormal behavior, The above-mentioned nested space state includes a state in which a single object belongs to multiple spaces, and The above verification unit is, One or more rules and one or more constraints are generated based on multiple normative information corresponding to a state model related to the space, the suitability and priority of an intervention are determined for each of the generated one or more rules and one or more constraints, and based on the determination result, at least one rule and at least one constraint are selected from among the generated one or more rules and one or more constraints such that the suitability of the intervention is greater than or equal to a preset standard suitability and the priority satisfies a preset standard priority, a normative constraint including the selected at least one rule and at least one constraint is generated, and the generated normative constraint related to the space is stored in the storage unit. The step of generating one or more control signals for each space based on the above learning results is: Learning is performed using the generated plurality of state models and the identified plurality of normative constraints as input values for a preset artificial intelligence model, and one or more control signals for each space are generated based on the learning results. The above control signal is, An artificial intelligence-based spatial orchestration management method characterized by including information on where, to whom, and with what priority a control function will be applied according to the result of a norm judgment, being generated for each of one or more spaces to which the control function will be applied, and each being generated for one or more spaces among the plurality of spaces to which the control function will be applied.
  4. delete
  5. delete
  6. delete
  7. In Paragraph 3, A step of retraining an artificial intelligence model based on the collected spatial processing results, one or more risk patterns, and one or more norm conflict histories by the integrated management unit; and An artificial intelligence-based spatial orchestration management method characterized by further including the step of performing execution scheduling by the integrated management unit on the collected first spatial data and second spatial data when a state change of an object or device located within the first space and the second space is detected, the execution scheduling includes a preprocessing process through the preceding preprocessing unit, a state model generation process through the state modeling unit, a norm constraint verification process through the verification unit, a control signal generation process through the analysis unit, and an external device control process through the external device control unit.

Description

Apparatus for managing spatial orchestration based on artificial intelligence and method thereof The present invention relates to an artificial intelligence-based spatial orchestration management device and method, and more specifically, to an artificial intelligence-based spatial orchestration management device and method that collects spatial data according to spatial identifiers for a plurality of preset spaces, preprocesses the collected spatial data, generates a spatial state model based on the preprocessed spatial data, verifies a spatial normative constraint among a plurality of preset normative constraints for each space, generates one or more control signals by considering the priority according to the current state of each space among a plurality of rules and constraints included in the spatial normative constraints through artificial intelligence-based inference based on the verified spatial normative constraints and spatial state models, performs a control function by linking with one or more peripheral devices based on the generated one or more control signals, and updates the spatial state model and normative constraints based on the results of the control function execution, state changes, operation logs, etc. Recently, systems that collect environmental information and perform automation functions by utilizing sensors, IoT (Internet of Things) devices, and network devices are becoming widely adopted in various fields such as smart homes, smart buildings, mobility, healthcare, and manufacturing. Such IoT automation technology has primarily utilized a structure that controls the operation of lighting, HVAC, door locks, and home appliances based on pre-set rules or simple conditions, derived from environmental information such as temperature, humidity, illuminance, and air quality, or device status data. Furthermore, this automation is structured around the interconnection of a single device or equipment within a single space. In addition, with the proliferation of smartphones, wearable devices, and home gateways, device-centric operating systems or middleware technologies for controlling multiple devices on a single platform have been proposed. However, while these platforms provide functions such as sensor data collection, device state management, event processing, and application execution, they focus on managing individual devices or services rather than treating the entire space as a single operational unit. In the medical and healthcare fields, technologies are being researched to measure biometric information such as EEG, heart rate, respiration, and movement, and to analyze the user's condition. Some studies process environmental information and biometric information together to provide personalized notifications or automatic control functions, but most of these systems are also limited to specific environments (e.g., inside a hospital room, around a wearable, etc.) or specific service domains. Although sensor-based state analysis and device control technologies are being applied in the fields of robotics, autonomous vehicles, and industrial equipment, and structures in which multiple devices are interconnected via networks are being utilized, the focus is generally on state management and control at the robot, vehicle, or equipment level, without considering continuity between spaces or integrated operation of multiple spaces. As such, while various systems and platforms are provided for sensor data analysis, device integration, automated control, and state determination centered on specific domains or single spaces within individual spaces, there are limitations in modeling multiple, overlapping, and mobile spaces as a single set of spaces and in performing norm-based judgment and intervention at the spatial level by integrating biological, environmental, behavioral, device, and normative information. FIG. 1 is a block diagram showing the configuration of an artificial intelligence-based spatial orchestration management device according to an embodiment of the present invention. FIG. 2 is a flowchart illustrating an artificial intelligence-based spatial orchestration management method according to an embodiment of the present invention. It should be noted that the technical terms used in this invention are used merely to describe specific embodiments and are not intended to limit the invention. Furthermore, unless specifically defined otherwise in this invention, the technical terms used in this invention should be interpreted in the sense generally understood by those skilled in the art to which this invention pertains, and should not be interpreted in an overly broad or overly narrow sense. Additionally, if a technical term used in this invention is an incorrect technical term that fails to accurately express the concept of the invention, it should be replaced with a technical term that can be correctly understood by those skilled in the art. Moreover, general terms used in this inv