KR20220036135A - System for evaluating business capability of smart office based on user’s behavior analysis - Google Patents

Abstract

The present invention relates to a smart office work productivity evaluation system based on human behavior analysis. More specifically, it measures the cause index that can affect work productivity in real time and analyzes the correlation and relationship with the derived evaluation index. It is a smart office work productivity evaluation system based on human behavior analysis that can identify and adjust the cause index that can improve work productivity. It measures the detailed cause index related to work productivity in real time and calculates the cause index from the detailed cause index. Cause index calculation unit; An evaluation index calculation unit that inputs and measures detailed indicators of work productivity and calculates work productivity evaluation indicators from the detailed indicators; And a big data AI analysis engine that analyzes the correlation and relationship between the evaluation index and the causal index and derives a causal index that influenced the evaluation index. Smart office work productivity based on human behavior analysis, comprising a. It's about the evaluation system.

Description

Smart office work productivity evaluation system based on human behavior analysis {System for evaluating business capability of smart office based on user’s behavior analysis}

The present invention relates to a smart office work productivity evaluation system based on human behavior analysis.

The performance evaluation system (BSC; Balanced Score Card) developed by Kaplan and Norton in the early 1990s has become so popular that it is said to be taking the United States and the world by storm. In the case of Korea, leading domestic conglomerates such as KT, POSCO, Hankook Tire, and Daelim Group, led by E-Land in 1998, rushed to introduce BSC. Additionally, the BSC system was rapidly introduced in the public sector, including the government sector.

The rapid spread of the performance evaluation system (BSC) to each government department is due to the fact that since 2005, the President has been reporting government departments' annual reports in the form of a strategic planning and performance indicator system like the U.S. Government Performance and Results Act (GPRA). It can be said that it originates from the demand, but above all, in the public sector where vision, strategy, and goals are ambiguous, there is no tool as effective as the performance evaluation system as a tool to clearly define it and evaluate and manage performance based on it. It could be said that it is because of this.

However, recently the concepts of smart buildings and smart offices are being introduced. In other words, future technologies are evolving into technologies that enable humans and smart devices to communicate as one, and are showing a change from simple smart devices to spatial smartization. In other words, for the next generation of communication between humans and devices, there are limits to the combination of individual products and the sequential operation of each service, and the creation of an active spatial medium in which sensors/actuators/circuit systems/network functions are all customized and combined is required. there is.

In particular, through emotional ICT technology, the trend is evolving beyond the manufacturing of IT-based smart devices to high-functioning, high-performance, and artificial intelligence that can deliver information and provide services necessary for emotional stimulation and health maintenance by considering the user's biological signals and movements. there is.

Therefore, within a smart office environment suitable for this artificial intelligence AI era, we provide a platform that can measure and evaluate the work productivity of executives and employees, analyze the causes of productivity decline, and derive improvements, optimal guides, and improvement plans. development was required.

Republic of Korea Public Patent No. 10-2010-0108065 Republic of Korea registered patent 10-1908431 Republic of Korea registered patent 10-1748399 Republic of Korea registered patent 10-199445 Republic of Korea Public Patent No. 10-2010-0102772 Republic of Korea registered patent 10-1058183

Therefore, the present invention was devised to solve the above-described conventional problems. According to the embodiment of the present invention, various data and factors that determine work satisfaction and productivity in the current work environment of people (executives and employees) The purpose is to provide a smart office work productivity evaluation system based on human behavior analysis that can increase the productivity of executives and employees by measuring the data and using and analyzing the data to adjust and change the cause values.

According to an embodiment of the present invention, data values from hardware such as IoT sensors are collected and analyzed, correlations between indicators are analyzed, and factors/indexes that reduce work productivity in the current situation are found and modified/changed to ultimately The purpose is to provide a smart office work productivity evaluation system based on human behavior analysis that can guide executives and employees to continuously perform work in an optimal work environment (circumstance).

According to an embodiment of the present invention, data collected through IoT sensors and hardware figures using big data and machine learning methodologies are calculated, analyzed, and accumulated into each composite index, and are divided into individual executives and employees, or certain zones and floors. A smart system based on human behavior analysis that can judge/respond to the right environment and, if necessary, recommend conditions necessary to increase work productivity based on the collected DB when the office environment needs to be rebuilt. The purpose is to provide an office work productivity evaluation system.

According to an embodiment of the present invention, the data collected in real time displays the relationship between indicators affecting current productivity through a situation board/dashboard, etc., and when the productivity indicator falls, the cause index that causes the indicator decrease is systematically calculated. We provide a smart office work productivity evaluation system based on human behavior analysis that can be controlled by the system to return to the normal level of productivity index value by immediately identifying and adjusting the value of the detailed index to increase the index. There is a purpose.

Meanwhile, the technical problems to be achieved in the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly apparent to those skilled in the art from the description below. It will be understandable.

The purpose of the present invention is to measure the cause index that can affect work productivity in real time and analyze the correlation and relationship with the derived evaluation index to identify and adjust the cause index that can improve work productivity. A smart office work productivity evaluation system based on human behavior analysis, comprising: a cause index calculation unit that measures a detailed cause index related to work productivity in real time and calculates a cause index from the detailed cause index; An evaluation index calculation unit that inputs and measures detailed indicators of work productivity and calculates work productivity evaluation indicators from the detailed indicators; And a big data AI analysis engine that analyzes the correlation and relationship between the evaluation index and the causal index and derives a causal index that influenced the evaluation index. Smart office work productivity based on human behavior analysis, comprising a. This can be achieved with an evaluation system.

And the big data AI analysis engine includes an evaluation unit that generates work productivity evaluation data from the evaluation indicators, and regression analysis and cross-analysis of the correlation and relationship between the evaluation indicators and the causal index through artificial intelligence and machine learning. , comprising a cause index derivation unit that performs factor analysis to derive a cause index that affected the evaluation index that is below the normal level index, and an analysis section that generates adjustment data of the detailed cause index of the cause index that affected the evaluation index. It can be characterized.

In addition, it may further include a system control unit that controls IoT devices installed in the smart office based on the adjustment data generated by the analysis unit.

The causal index calculation unit may include a spatial index calculation unit, an environmental index calculation unit, a digital environment index calculation unit, and a safety index calculation unit.

In addition, the spatial index calculation unit includes a spatial data measurement unit that measures spatial detailed cause data, and a spatial index DB in which the measured or input spatial detailed cause data is stored, and calculates an indoor space index from the space detailed cause data. , The space detailed cause data includes chair height, color, number of entrance gates, desk height, desk area, restaurant area per person, office area per person, distance between seats, storage space per person, lounge space, OA room area per person, number of bathrooms per person, and movement. At least one of the following: movement path, average floor height, restroom area per person, number of conference rooms per person, conference room area per person, average distance between seats and conference rooms, density per unit area, green space area per person, and compatibility with human expectations related to space user interface behavioral affordances and constraints. The environmental index calculation unit includes an environmental data measurement unit that measures environmental detailed cause data, and an environmental index DB in which the measured or input environmental detailed cause data is stored, and calculates an environmental space index from the environmental detailed cause data. The environmental detailed cause data includes temperature, air flow volume, air flow speed, indoor air quality, humidity, background noise level, reverberation time, sound insulation between seats, conference room sound insulation, conversation intelligibility, illuminance, lighting color temperature, and surface light reflectance. , fine dust, vibration, odor, type of wall paper, and CO2 concentration.

In addition, the digital environment index calculation unit includes a tool index DB in which the measured or input tool detailed cause data is stored, and the digital environment index is calculated from the tool detailed cause data, and the tool detailed cause data includes laptop information, desktop information, Monitor information, groupware information, mobile terminal information, video conference tool information, wireless network environment, tablet board, messenger information, kiosk, non-face-to-face telework environment and system, conference room reservation and data sharing, easy usability, digital user interface interaction and At least one of the business convenience service information, the safety index calculation unit includes a safety index DB in which measured or input safety detailed cause data is stored, calculates a safety index from the safety detailed cause data, and the safety detailed cause data Horizontal average evacuation distance, vertical average evacuation distance, number of evacuation exits, weight of the highest building, evacuation time, number of evacuation elevators, number of fire extinguishers per unit area, presence/absence of detection of remaining personnel, number of sprinklers per unit area, number of gas masks per person. , it may be characterized by at least one of the air conditioning range, the number of detection sensors per person, and the number of untact heat detections.

In addition, the evaluation indicator calculation unit may be characterized as including a work satisfaction indicator calculation unit, a human convenience indicator calculation unit, a user experience indicator calculation unit, a work efficiency indicator calculation unit, a social collaboration indicator calculation unit, and a safety indicator calculation unit.

In addition, the job satisfaction index calculation unit includes a job satisfaction DB where the detailed work satisfaction index data measured or input is stored, and calculates the work satisfaction index from the detailed work satisfaction index data, and the detailed work satisfaction index data includes turnover rate, average It is at least one of the number of years of service, work satisfaction survey results, organizational evaluation score, and business NIS index, and the human convenience index calculation unit includes a convenience index measurement unit that measures convenience detailed index data, and the convenience detailed index data measured or input. It includes a business convenience DB where is stored, and calculates business convenience indicators from the convenience detailed indicator data, and the convenience detailed indicator data includes heart rate, body temperature, eye blinks, sitting frequency, medical expense expenditure, vacation frequency, and employee emotional index. It may be characterized as being at least one of the following.

And the user experience (UX) indicator calculation unit includes a user experience DB in which detailed user experience indicator data measured or input is stored, and calculates a user experience indicator from the user experience detailed indicator data, and the user experience detailed indicator data is It is at least one of convenience space utilization, office experience satisfaction, and web/mobile system utilization, and the work efficiency index calculation unit includes a detailed efficiency index measurement unit that measures detailed work efficiency index data, and the detailed work efficiency index data measured or entered. It includes a work efficiency DB where is stored, and calculates work efficiency indicators from the work efficiency detailed index data, and the work efficiency detailed index data includes average meeting time, commuting/leaving time, KPI achievement rate, sales and operating profit ratio, and orders. It may be characterized as being at least one of the number of cases.

In addition, the social collaboration indicator calculation unit includes a collaboration detailed indicator measurement unit that measures collaboration detailed indicator data, and a collaboration DB in which the measured or input collaboration detailed indicator data is stored, and calculates a social experience indicator from the collaboration detailed indicator data. , the collaboration detailed indicator data is at least one of face-to-face communication frequency, telephone frequency, groupware frequency, email sending/receiving frequency, meeting room reservation/use frequency, and communication account corporate card spending amount, and the safety indicator calculation unit calculates the safety detailed indicator data. It includes a safety indicator measuring unit that measures the detailed safety indicator, and a safety indicator DB in which the measured or input safety detailed indicator data is stored, and calculates a safety indicator from the safety detailed indicator data, and the safety detailed indicator data includes the seat frequency and average. It may be characterized as at least one of the moving distance, stress index, frequency of safety accidents, frequency of human errors, numerical value of employee fever measurement, and employee safety survey results.

According to the smart office work productivity evaluation system based on human behavior analysis according to an embodiment of the present invention, various data and factors that determine work satisfaction and productivity in the current work environment of people (executives and employees) are measured and the corresponding data is collected. It has the effect of increasing the productivity of executives and employees by utilizing and analyzing it to adjust and change the cause value.

According to the smart office work productivity evaluation system based on human behavior analysis according to an embodiment of the present invention, data values from hardware such as IoT sensors are collected and analyzed, and correlations between indicators are analyzed to determine factors that reduce work productivity in the current situation. By finding and modifying/changing the factor, it ultimately has the effect of guiding executives and employees so that they can continue to perform their work in an optimal work environment (circumstance).

And according to the smart office work productivity evaluation system based on human behavior analysis according to an embodiment of the present invention, data collected through IoT sensors and hardware figures using big data and machine learning methodologies are calculated, analyzed, and accumulated into each comprehensive index. It is possible to judge/respond to the environment suitable for each employee, certain zone, or floor. If necessary, if the office environment needs to be rebuilt, suggestions for conditions necessary to increase work productivity based on the collected DB ( Recommand) has the effect of being able to do so.

And according to the smart office work productivity evaluation system based on human behavior analysis according to an embodiment of the present invention, the data collected in real time displays the relationship between indicators affecting current productivity through a situation board/dashboard, etc., and the productivity indicators are If it falls, it has the effect of systematically immediately identifying the cause index that causes the index decrease and controlling it through the system to return to the normal level of the productivity index value by adjusting the value of the detailed index to increase the index. .

Meanwhile, the effects that can be obtained from the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below. You will be able to.

The following drawings attached to this specification illustrate preferred embodiments of the present invention, and serve to further understand the technical idea of the present invention along with the detailed description of the invention, so the present invention is limited only to the matters described in such drawings. It should not be interpreted as such.
1 is a block diagram of a smart office work productivity evaluation system based on human behavior analysis according to an embodiment of the present invention;
Figure 2 is a schematic diagram of a smart office work productivity evaluation system based on human behavior analysis according to an embodiment of the present invention;
Figure 3 is a configuration diagram of a causal index calculation unit according to an embodiment of the present invention;
Figure 4 is a schematic diagram of a causal index calculation unit according to an embodiment of the present invention;
Figure 5 is a configuration diagram of an evaluation index calculation unit according to an embodiment of the present invention;
Figure 6 is a schematic diagram of an evaluation indicator calculation unit according to an embodiment of the present invention;
Figure 7 shows a detailed configuration diagram of a smart office work productivity evaluation system based on human behavior analysis according to an embodiment of the present invention.

The above objects, other objects, features and advantages of the present invention will be easily understood through the following preferred embodiments related to the attached drawings. However, the present invention is not limited to the embodiments described herein and may be embodied in other forms. Rather, the embodiments introduced herein are provided so that the disclosed content will be thorough and complete and so that the spirit of the present invention can be sufficiently conveyed to those skilled in the art.

In this specification, when an element is referred to as being on another element, it means that it may be formed directly on the other element or that a third element may be interposed between them. Also, in the drawings, the thickness of components is exaggerated for effective explanation of technical content.

Embodiments described herein will be explained with reference to cross-sectional views and/or plan views, which are ideal illustrations of the present invention. In the drawings, the thicknesses of films and regions are exaggerated for effective explanation of technical content. Therefore, the form of the illustration may be modified depending on manufacturing technology and/or tolerances. Although terms such as first and second are used in various embodiments of the present specification to describe various components, these components should not be limited by these terms. These terms are merely used to distinguish one component from another. Embodiments described and illustrated herein also include complementary embodiments thereof.

The terminology used herein is for describing embodiments and is not intended to limit the invention. As used herein, singular forms also include plural forms, unless specifically stated otherwise in the context. As used in the specification, 'comprises' and/or 'comprising' does not exclude the presence or addition of one or more other elements.

In describing specific embodiments below, various specific details have been written to explain the invention in more detail and to aid understanding. However, a reader with sufficient knowledge in the field to understand the present invention can recognize that it can be used without these various specific details. In some cases, it is mentioned in advance that when describing the invention, parts that are commonly known but are not significantly related to the invention are not described in order to prevent confusion without any reason in explaining the invention.

Hereinafter, the configuration and functions of the human behavior analysis-based smart office work productivity evaluation system 100 according to an embodiment of the present invention will be described.

First, Figure 1 shows a block diagram of a smart office work productivity evaluation system 100 based on human behavior analysis according to an embodiment of the present invention. And Figure 2 shows a schematic diagram of a smart office work productivity evaluation system 100 based on human behavior analysis according to an embodiment of the present invention.

Basically, the human behavior analysis-based smart office work productivity evaluation system 100 according to an embodiment of the present invention measures cause indices that can affect work productivity in real time and creates a database, and calculates the cause index and the derived evaluation index. The purpose is to identify cause indices that can improve work productivity by analyzing correlations and relationships, and to be able to adjust and guide them.

According to the smart office work productivity evaluation system 100 based on human behavior analysis according to an embodiment of the present invention, various data and factors that determine work satisfaction and productivity in the current work environment of people (executives and employees) are used as cause indices. By measuring and using and analyzing the data, it is possible to adjust and change the cause value to increase the productivity of employees.

In addition, according to the human behavior analysis-based smart office work productivity evaluation system 100 according to an embodiment of the present invention, data values (causal index) of hardware such as IoT sensors are collected and analyzed, and the correlation between evaluation indicators is analyzed. By finding and correcting/changing the factors/factors that reduce work productivity in the current situation, we can ultimately guide executives and employees to continuously perform their work in an optimal work environment (Circumstance).

And according to the human behavior analysis-based smart office work productivity evaluation system 100 according to an embodiment of the present invention, data collected through IoT sensors and hardware figures using big data and machine learning methodology are converted into each comprehensive causal index. By accumulating calculations and analysis, it is possible to judge/respond to the environment suitable for individual employees, certain zones, or floors. If necessary, when the office environment needs to be rebuilt, the condition values required to increase work productivity are based on the collected DB. You can make a recommendation.

And according to the human behavior analysis-based smart office work productivity evaluation system 100 according to an embodiment of the present invention, data collected in real time (cause index) is an evaluation index that affects current productivity through a situation board/dashboard, etc. It expresses the relationship between the two, and when the productivity index falls, the cause index that causes the decrease in the evaluation index is systematically and immediately identified, and the value of the detailed cause index is adjusted to increase the corresponding evaluation index, thereby returning the productivity evaluation index value to the normal level. It can be controlled by the system so that it can return.

The cause index calculation unit 10 is configured to measure the detailed cause index related to work productivity in real time and calculate the cause index from the detailed cause index. These detailed cause indices can be measured in real time from various IoT sensors.

In addition, the evaluation indicator calculation unit 60 is configured to input and measure detailed indicators of work productivity for executives and employees, and calculate work productivity evaluation indicators from these detailed indicators.

And the big data AI analysis engine 200 is configured to analyze the correlation and relationship between these evaluation indicators and the causal index to derive the causal index that influenced the evaluation index. That is, as shown in FIGS. 1 and 2, the big data AI analysis engine 200 may be comprised of an evaluation unit 210, a causal index derivation unit 220, and an analysis unit 230. You can see that there is.

First, the evaluation unit 210 analyzes the evaluation index calculated by the evaluation index calculation unit 60 and generates work productivity evaluation data. For example, by comparing the calculated evaluation indicators and qualitative level indicators, it is possible to derive detailed evaluation indicators that require improvement and supplementation.

And the cause index derivation unit 220 performs regression analysis, cross analysis, and factor analysis on the correlation and relationship between the evaluation index and the cause index through artificial intelligence and machine learning to determine the cause index that affected the evaluation index below the normal level index. It is designed to derive

And the analysis unit 230 generates adjustment data of the detailed cause index of the cause index that influenced these evaluation indicators. In other words, it is designed to derive adjustment data for the optimal guide and improvement plan that can normalize the factors that have declined.

And based on the adjustment data generated by the analysis unit, the system control unit 300 controls the IoT devices 2 installed in the smart office to change the cause index to match the adjustment data.

Figure 3 shows the configuration of the cause index calculation unit 10 according to an embodiment of the present invention. And Figure 4 shows a schematic diagram of the cause index calculation unit 10 according to an embodiment of the present invention.

As shown in FIG. 3, the causal index calculation unit 10 includes a spatial index calculation unit 20, an environmental index calculation unit 30, a digital environment index calculation unit 40, and a safety index calculation unit 50. It can be seen that it can be configured including.

And the spatial index calculation unit 20 according to an embodiment of the present invention includes a spatial data measurement unit 21 that measures spatial detailed cause data, and this spatial data measurement unit 21 measures spatial detailed cause data in real time. It can be composed of various IoT sensors (1) that can measure.

In addition, the space index DB 22 is configured to store measured or input space detailed cause data, and the space index calculation unit 20 calculates the indoor space index based on such space detailed cause data.

Spatial detailed cause data according to an embodiment of the present invention consists of element values that affect the bodies or movement lines of executives and employees within the office. There are factors such as the ergonomic configuration of office furniture used by executives and employees (height values of chairs and desks), office color values, seating distance between executives and employees, obstacles in people's movement lines, space area per person, and density.

Specifically, chair height, color, number of entrance gates, desk height, desk area, restaurant area per person, office area per person, distance between seats, storage space per person, lounge space, OA room area per person, number of bathrooms per person, movement line, average floor height. , bathroom area per capita, number of conference rooms per capita, conference room area per capita, average seat-conference room distance, density per unit area, and green space area per capita, spatial user interface affordances and compatibility with human expectations related to constraints, etc.

And the environmental index calculation unit 30 according to an embodiment of the present invention includes an environmental data measurement unit 31 that measures environmental detailed cause data, and this environmental data measurement unit 31 measures environmental detailed cause data in real time. It can be composed of various IoT sensors (1) that can measure.

Additionally, measured or input environmental detailed cause data is stored in the environmental index DB 32, and the environmental index calculation unit 30 calculates the environmental spatial index from these environmental detailed cause data.

These environmental indices have detailed environmental cause data related to the physical environment within the office. For example, temperature/humidity/air quality/fine dust/Co2 concentration/noise/vibration/scent/illuminance… It consists of etc. The environmental detailed cause data are values measured by IoT sensors or H/W, such as temperature (℃) of the environment surrounding employees, humidity level, air quality in the office, CO² density, noise level according to the distance from people around, and fine details. Depending on the vibration, scent or smell, and the illuminance value of lighting, humans are affected in various ways in the work environment. These detailed indicators are ultimately represented by an integrated master index called the indoor environment index.

Specifically, as shown in Figure 4, the environmental detailed cause data includes temperature, air flow amount, air flow speed, indoor air quality, humidity, background noise level, reverberation time, sound insulation between seats, conference room sound insulation, conversation clarity, and illuminance. , lighting color temperature, surface light reflectance, fine dust, vibration, odor, type of wall covering, and CO2 concentration.

In addition, the digital environment index calculation unit 40 includes a tool index DB 41 in which measured or input detailed tool cause data is stored, and calculates the digital environment index from the tool detailed cause data.

In other words, the digital environment index (tool index) is not only the H/W of the devices used (PC, tablet, monitor), but also the groupware, messenger (communication tool), video conferencing equipment, kiosk, and wireless N/W used within the company. It can be used to measure improved work productivity through tools such as W environment, non-face-to-face telework environment/system, and work convenience services (robot, RPA, chatbot S/W).

Specifically, as shown in Figure 4, the tool detailed cause data includes laptop information, desktop information, monitor information, groupware information, mobile terminal information, video conference tool information, wireless network environment, tablet board, messenger information, kiosk, and conference room. This could be easy usability for reservations and data sharing, digital user interface interaction, and business convenience service information.

In addition, as the importance of employee safety, especially within the office, increases, the safety index can be separately measured and indexed for employees' work productivity and work continuity.

The safety index calculation unit 50 includes a safety index DB 51 in which measured or input safety detailed cause data is stored, and calculates the safety index from the safety detailed cause data.

Specifically, as shown in Figure 4, the safety detailed cause data includes horizontal average evacuation distance, vertical average evacuation distance, number of evacuation exits, weight of the highest building, evacuation time, number of evacuation elevators, number of fire extinguishers per unit area, and detection of remaining personnel. This may include presence/absence, number of sprinklers per unit area, number of gas masks per person, air conditioning range, and number of detection sensors per person.

In other words, when a disaster situation occurs, the safety level of employees can be quantified and expressed by the average evacuation distance for employees to evacuate and move, the number of evacuation exits, and the number of safety equipment (sprinklers, fire extinguishers, gas masks, etc.) per unit area. This ultimately affects evaluation indicators such as employee attendance rate, movement frequency, stress, and work safety in the evaluation indicators that will be explained later.

The above indices are interrelated/connected and combined into indicators related to work productivity, and the indices are used as secondary indices that can determine the improvement or decline in work productivity.

Using big data and machine learning methodologies, the data collected through IoT sensors and hardware figures are calculated, analyzed, and accumulated into each index to judge/respond to the environment appropriate for each employee, certain zone, or floor. And, if necessary, if the office environment needs to be rebuilt, a recommendation can be made on the conditions necessary to increase work productivity based on the collected DB.

In addition, the data collected in real time displays the relationship between indicators that affect current productivity through dashboards/dashboards, etc., and when productivity indicators drop, the cause index that causes the indicator decrease is systematically immediately identified and the relevant indicators are adjusted. By adjusting the value of the detailed cause index to increase, the system can be controlled to return to the normal level of productivity index value.

Figure 5 shows a configuration diagram of the evaluation indicator calculation unit 60 according to an embodiment of the present invention, and Figure 6 shows a schematic diagram of the evaluation indicator calculation unit 60 according to an embodiment of the present invention. In addition, Figure 7 shows a detailed configuration diagram of a smart office work productivity evaluation system 100 based on human behavior analysis according to an embodiment of the present invention.

As shown in Figure 5, the evaluation indicator calculation unit 60 according to an embodiment of the present invention includes a work satisfaction indicator calculation unit 70, a human convenience indicator calculation unit 80, a user experience indicator calculation unit 90, It can be seen that it may be configured to include a work efficiency indicator calculation unit 110, a social collaboration indicator calculation unit 120, and a safety indicator calculation unit 130.

The work satisfaction index calculation unit 70 includes a work satisfaction DB 71 in which the detailed work satisfaction index data measured or input is stored, and calculates the work satisfaction index from the detailed work satisfaction index data.

As shown in Figure 6, detailed work satisfaction indicator data may be turnover rate, average years of service, work satisfaction survey results, organizational evaluation score, work NIS index, etc.

And the human convenience index calculation unit 80 includes a convenience index measurement unit 81 that measures convenience detailed index data, and a business convenience DB 82 in which the measured or input convenience detailed index data is stored, and the convenience detailed index data is stored. It is configured to calculate work convenience indicators from indicator data. The convenience indicator measurement unit 81 may be composed of an IoT sensor 1 that can measure detailed convenience indicator data of executives and employees in real time.

As shown in FIG. 6, such convenience detailed indicator data may include heart rate, body temperature, eye blinking, frequency of sitting or sitting, medical expenses, frequency of vacation, and employee emotional index.

In addition, the user experience (UX) index calculation unit 90 includes a user experience DB 91 in which detailed user experience index data that is measured or input is stored, and calculates a user experience index from this detailed user experience index data.

Specifically, detailed user experience indicator data may include convenience space utilization, office experience satisfaction, and web/mobile system utilization.

In addition, the work efficiency indicator calculation unit 110 includes a detailed efficiency indicator measurement unit 111 that measures detailed work efficiency indicator data, and a work efficiency DB 112 in which the measured or input detailed work efficiency indicator data is stored, Work efficiency indicators are calculated from these detailed work efficiency indicator data. The detailed efficiency indicator measurement unit 111 may be composed of an IoT sensor (1) that can measure detailed efficiency indicator data of executives and employees in real time.

Specifically, work efficiency detailed indicator data may correspond to average meeting time, commuting/leaving time, KPI achievement rate, sales and operating profit ratio, and number of orders.

In addition, the social collaboration indicator calculation unit 120 includes a collaboration detailed indicator measurement unit 121 that measures collaboration detailed indicator data, and a collaboration DB 122 in which the measured or input collaboration detailed indicator data is stored, and the collaboration detailed indicator data is stored in the social collaboration indicator calculation unit 120. Social experience indicators are calculated from indicator data.

Specifically, detailed collaboration indicator data may include face-to-face communication frequency, phone frequency, groupware frequency, email sending/receiving frequency, meeting room reservation/use frequency, and communication account corporate card spending amount.

And the safety indicator calculation unit 130 includes a safety indicator measurement unit 131 that measures safety detailed indicator data, and a safety indicator DB 132 in which the measured or input safety detailed indicator data is stored. Safety indicators are calculated from detailed indicator data.

Specifically, detailed safety indicator data may include seating frequency, average moving distance, stress index, employee fever level measurement, safety accident and human error occurrence susceptibility, and employee safety survey results. In addition, the frequency of safety accidents that occur in the office is extracted as the result, the frequency of human error is extracted as the frequency of safety problems that occur due to judgment errors of executives and employees in the office, and the numerical value of employee fever measurements, etc. You can. If the fever measurements of executives and employees are observed to be high at a certain time and place, environmental values can be adjusted for that floor and time.

As mentioned earlier, the big data AI analysis engine 200 is configured to analyze the correlation and relationship between these evaluation indicators and the causal index to derive the causal index that influenced the evaluation index.

The evaluation unit 210 of the big data AI analysis engine 200 analyzes the evaluation indicators calculated by the evaluation indicator calculation unit 60 and generates work productivity evaluation data. For example, by comparing the calculated evaluation indicators and qualitative level indicators, it is possible to derive detailed evaluation indicators that require improvement and supplementation.

And the cause index derivation unit 220 performs regression analysis, cross analysis, and factor analysis on the correlation and relationship between the evaluation index and the cause index through artificial intelligence and machine learning to determine the cause index that affected the evaluation index below the normal level index. It is designed to derive

In other words, if the work efficiency index falls below the normal level index, the cause of the decline in the work efficiency index is derived by analyzing detailed cause data within the indoor environment index and digital environment index that are correlated and related to the work efficiency index. .

And the analysis unit 230 generates adjustment data of the detailed cause index of the cause index that influenced these evaluation indicators. In other words, it is designed to derive adjustment data for the optimal guide and improvement plan that can normalize the factors that have declined.

And based on the adjustment data generated by the analysis unit 230, the system control unit 300 controls the IoT devices 2 installed in the smart office to change the cause index to match the adjustment data.

In addition, the apparatus and method described above are not limited to the configuration and method of the above-described embodiments, but all or part of each embodiment can be selectively combined so that various modifications can be made. It may be composed.

1:IoT sensor
2:IoT devices
10: Calculation of cause index
20: Spatial index calculation department
21: Spatial data measurement unit
22: Spatial index DB
30:Environmental Index Calculation Department
31: Environmental data measurement department
32:Environmental Index DB
40:Digital Environment Index Calculation Department
41: Tool Index DB
50: Safety index calculation department
51:Safety Index DB
60: Evaluation index calculation unit
70: Work satisfaction index calculation unit
71:Job Satisfaction DB
80: Human convenience index calculation unit
81: Convenience indicator measurement unit
82:Work convenience DB
90: User experience indicator calculation unit
91:User experience DB
100: Smart office work productivity evaluation system based on human behavior analysis
110: Work efficiency indicator calculation department
111: Detailed efficiency indicator measurement unit
112:Work efficiency DB
120:Social collaboration indicator calculation department
121: Collaborative detailed indicator measurement department
122:Collaboration DB
130: Safety indicator calculation department
131: Safety detailed indicator measurement unit
132:Safety indicator DB
200:Big data AI analysis engine
210: Evaluation Department
220: Derivation of causal index
230:Analysis Department
300: System control unit

Claims (10)

A human behavior analysis-based smart device that measures the cause index that can affect work productivity in real time and analyzes the correlation and relationship with the derived evaluation index to identify and adjust the cause index that can improve work productivity. As an office work productivity evaluation system,
a cause index calculation unit that measures a detailed cause index related to work productivity in real time and calculates a cause index from the detailed cause index;
An evaluation index calculation unit that inputs and measures detailed indicators of work productivity and calculates work productivity evaluation indicators from the detailed indicators; and
Smart office work productivity evaluation based on human behavior analysis, comprising a big data AI analysis engine that analyzes the correlation and relationship between the evaluation index and the causal index and derives a causal index that influenced the evaluation index. system.
According to clause 1,
The big data AI analysis engine is,
An evaluation unit that generates work productivity evaluation data from the evaluation index, and the correlation and relationship between the evaluation index and the cause index are analyzed through regression analysis, cross analysis, and factor analysis through artificial intelligence and machine learning to determine if the evaluation index is below the normal level index. A smart office based on human behavior analysis, comprising a cause index derivation unit that derives a cause index that influenced the evaluation index, and an analysis unit that generates adjustment data of the detailed cause index of the cause index that affected the evaluation index. Work productivity evaluation system.
According to clause 2,
A smart office work productivity evaluation system based on human behavior analysis, further comprising a system control unit that controls IoT devices installed in the smart office based on the adjustment data generated by the analysis unit.
According to clause 1,
The causal index calculation unit is a smart office work productivity evaluation system based on human behavior analysis, characterized in that it includes a spatial index calculation unit, an environmental index calculation unit, a digital environment index calculation unit, and a safety index calculation unit.
According to clause 4,
The spatial index calculation unit includes a spatial data measurement unit that measures spatial detailed cause data, and a spatial index DB in which the measured or input spatial detailed cause data is stored, and calculates an indoor space index from the space detailed cause data,
The space detailed cause data includes chair height, color, number of entrance gates, desk height, desk area, restaurant area per person, office area per person, distance between seats, storage space per person, lounge space, OA room area per person, number of restrooms per person, and movement line. , average floor height, bathroom area per person, number of conference rooms per person, conference room area per person, average seat-meeting room distance, density per unit area, green space area per person, and compatibility with human expectations related to space user interface affordances and constraints, and ,
The environmental index calculation unit includes an environmental data measurement unit that measures environmental detailed cause data, and an environmental index DB in which the measured or input environmental detailed cause data is stored, and calculates an environmental space index from the environmental detailed cause data,
The environmental detailed cause data includes temperature, air flow volume, air flow speed, indoor air quality, humidity, background noise level, reverberation time, sound insulation between seats, conference room sound insulation, conversation intelligibility, illuminance, lighting color temperature, surface light reflectance, and fine A smart office work productivity evaluation system based on human behavior analysis, characterized by at least one of dust, vibration, odor, wall type, and CO2 concentration.
According to clause 5,
The digital environment index calculation unit includes a tool index DB in which measured or entered tool detailed cause data is stored, and calculates a digital environment index from the tool detailed cause data,
The above tool detailed cause data includes laptop information, desktop information, monitor information, groupware information, mobile terminal information, video conference tool information, wireless network environment, tablet board, messenger information, kiosk, non-face-to-face telework environment/system, and conference room reservation. , at least one of digital user interface interaction and business convenience service information,
The safety index calculation unit includes a safety index DB in which measured or input safety detailed cause data is stored, and calculates a safety index from the safety detailed cause data,
The safety detailed cause data includes horizontal average evacuation distance, vertical average evacuation distance, number of evacuation exits, weight of the highest building, evacuation time, number of evacuation elevators, number of fire extinguishers per unit area, presence/absence of detection of remaining personnel, number of sprinklers per unit area. , A smart office work productivity evaluation system based on human behavior analysis, characterized by at least one of the number of gas masks per person, air conditioning range, number of detection sensors per person, and number of untact fever detections.
According to clause 6,
The evaluation indicator calculation unit is based on human behavior analysis, characterized in that it includes a work satisfaction indicator calculation unit, a human convenience indicator calculation unit, a user experience indicator calculation unit, a work efficiency indicator calculation unit, a social collaboration indicator calculation unit, and a safety indicator calculation unit. Smart office work productivity evaluation system.
According to clause 7,
The work satisfaction index calculation unit includes a work satisfaction DB in which detailed work satisfaction index data measured or input is stored, and calculates a work satisfaction index from the detailed work satisfaction index data,
The detailed work satisfaction indicator data is at least one of turnover rate, average years of service, work satisfaction survey results, organizational evaluation score, and work NIS index,
The human convenience indicator calculation unit includes a convenience indicator measurement unit that measures convenience detailed indicator data, a business convenience DB in which the measured or input convenience detailed indicator data is stored, and calculates a business convenience indicator from the convenience detailed indicator data. ,
The convenience detailed indicator data is a smart office work productivity evaluation system based on human behavior analysis, characterized in that at least one of heart rate, body temperature, eye blinking, frequency of sitting, medical expenses, vacation frequency, and employee emotional index.
According to clause 8,
The user experience (UX) indicator calculation unit includes a user experience DB in which detailed user experience indicator data measured or input is stored, and calculates a user experience indicator from the user experience detailed indicator data,
The detailed user experience indicator data is at least one of convenience space utilization, office experience satisfaction, and web/mobile system utilization,
The work efficiency indicator calculation unit includes a detailed efficiency indicator measurement unit that measures detailed work efficiency indicator data, and a work efficiency DB in which the measured or input detailed work efficiency indicator data is stored, and the work efficiency indicator data is calculated from the detailed work efficiency indicator data. Calculate indicators,
The detailed work efficiency indicator data is a smart office work productivity evaluation system based on human behavior analysis, characterized in that at least one of average meeting time, commuting/leaving time, KPI achievement rate, sales and operating profit ratio, and number of orders.
According to clause 9,
The social collaboration indicator calculation unit includes a collaboration detailed indicator measurement unit that measures collaboration detailed indicator data, and a collaboration DB in which the measured or input collaboration detailed indicator data is stored, and calculates a social experience indicator from the collaboration detailed indicator data,
The collaboration detailed indicator data is at least one of face-to-face communication frequency, phone frequency, groupware frequency, email sending/receiving frequency, meeting room reservation/use frequency, and communication account corporate card spending amount,
The safety indicator calculation unit includes a safety indicator measurement unit that measures safety detailed indicator data, a safety indicator DB in which the measured or input safety detailed indicator data is stored, and calculates a safety indicator from the safety detailed indicator data,
The safety detailed indicator data is a human behavior analysis-based smart smart device characterized in that it is at least one of the following: seating frequency, average moving distance, stress index, safety accident, human error frequency, employee fever measurement numerical value, and employee safety survey results. Office work productivity evaluation system.

Images