JP7257551B2 - Complaint prediction system and complaint prediction method - Google Patents

Description

The present invention relates to a complaint prediction system and a complaint prediction method.

Odor is a sensory thing, and the impression and degree that humans receive from odor varies from person to person, so it is difficult to recognize it objectively. Therefore, the next user, etc. will be uncomfortable with the smell, especially the bad smell, caused by the previous user or user (referred to as "user, etc.") in cars, buses, trains, etc., indoors in buildings such as office buildings and hotels, etc. Feelings and complaints may occur.

Therefore, in order to remove odors from the interior of the vehicle or the space in the room in advance so that the next user of the vehicle or the room in the building will not be uncomfortable, various odor detection devices have been studied. .

As a detection device for such odors, for example, a plurality of odor sensors having different odor response characteristics are provided, and the odor components contained in the gas to be measured and their concentrations are specified based on the output values of the plurality of odor sensors. , an odor detection device that discriminates the type of odor based on the specified odor component and its concentration is disclosed (see, for example, Patent Document 1).

Japanese Patent No. 6508440

However, with the odor detection device of Patent Document 1, it is difficult to accurately detect the concentration of a specific odor component from a gas containing various odor components. In addition, each user has a different odor that they find unpleasant, and there is a tendency that the concentration of a specific odor component is not necessarily proportional to the proportion of complaints. Therefore, it is difficult to determine the ratio of occurrence of complaints in relation to the odor component, and there is a problem that the ratio of occurrence of complaints cannot be accurately predicted for the odor.

An object of one aspect of the present invention is to provide a complaint prediction system capable of predicting the rate of occurrence of complaints about odors with high accuracy.

One aspect of the complaint prediction system according to the present invention is a complaint prediction system for predicting the degree of complaint occurrence risk regarding the odor contained in the detection target gas in a partitioned space, wherein the odor component contained in the detection target gas A storage unit that stores related data in which a plurality of odor sensors with different responsive detection characteristics, information on past output values of the plurality of odor sensors, and information on past subjective judgments of odors by users are associated with each other. and a calculation unit for calculating the degree of risk of complaints from the users who plan to use the space, based on the current output values of the plurality of odor sensors and the related data.

One aspect of the complaint prediction system according to the present invention can predict the rate of occurrence of complaints about odors with high accuracy.

BRIEF DESCRIPTION OF THE DRAWINGS It is a system block diagram which shows the structure of the complaint prediction system which concerns on embodiment of this invention. 3 is a block diagram showing functions of a control device; FIG. It is a figure which shows an example of the data for learning. It is a block diagram which shows the hardware constitutions of a complaint prediction control apparatus. It is a flow chart explaining a complaint prediction method concerning this embodiment.

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of the present invention will be described in detail. In addition, in order to facilitate understanding of the description, the same components are denoted by the same reference numerals in each drawing, and overlapping descriptions are omitted. Also, the scale of each member in the drawings may differ from the actual scale. In this specification, the tilde "~" indicating a numerical range means that the numerical values before and after it are included as lower and upper limits unless otherwise specified.

<Complaint prediction system>
A complaint prediction system (hereinafter simply referred to as a prediction system) according to this embodiment will be described. The prediction system according to the present embodiment measures the odor components contained in the detection target gas existing in the space, and measures the risk of complaints about odors from users who plan to use the space (complaint occurrence risk). ). In this embodiment, a case where the gas to be detected is the air in the interior space (space) of an automobile will be described.

FIG. 1 is a system configuration diagram showing the configuration of a prediction system according to this embodiment. As shown in FIG. 1, the prediction system 1 includes a complaint prediction control device (hereinafter simply referred to as a control device) 10, and a plurality of odor sensors 201 having different detection characteristics that respond to odor components contained in the air. 20N (N is an integer equal to or greater than 1) and a communication device 30 . In the prediction system 1, the output values of the odor sensors 201 . . . 20N are transmitted from the communication device 30 to the control device 10 via the communication network 40.

Based on the current output values of the plurality of odor sensors 201 . Calculate the occurrence risk. A hardware configuration of the control device 10 will be described later.

The plurality of odor sensors 201 . . . 20N are sensors with different detection characteristics that respond to odor components contained in the gas to be detected. The odor component (odor component) is a chemical substance that constitutes an odor, and nonenal, diacetyl, isovaleric acid, and the like can be mentioned.

As the smell sensors 201 . . . 20N, a semiconductor type sensor or the like having a semiconductor element can be used. In the semiconductor sensor, oxygen adsorbed on the surface of the semiconductor element reacts (surface reaction) with the odor component that causes the odor and leaves the semiconductor element, thereby changing the resistance value of the semiconductor element. From this change in resistance value, the concentration of the odor component in the air present in the space is measured. Then, the measured concentration of the odor component is converted into an electric quantity, and an electric signal corresponding to the concentration of the odor component is output.

The odor sensors 201 . A gas sensor, a gas sensor for detecting cigarettes, and the like are used. Also, the smell sensors 201 to 20N may be MEMS (Micro Electro Mechanical Systems) type sensors.

The odor sensors 201 . . . 20N may react to a plurality of odor components, or may react to only one odor component.

The communication device 30 transmits the detection values of the odor sensors 201 . . . 20N to the communication network 40 .

A configuration of the control device 10 will be described. FIG. 2 is a block diagram showing functions of the control device 10. As shown in FIG. As shown in FIG. 2 , the control device 10 includes a learning model 11 , a learning data creation unit 12 , a learning unit 13 , a storage unit 14 , a calculation unit 15 , an input unit 16 , an acquisition unit 17 and a display unit 18 .

The learning model 11 includes input information including information on related data in which information on past output values of a plurality of odor sensors 201 . , based on the current output values and related data from the plurality of odor sensors 201 . It is obtained and formulated.

The learning model 11 is obtained by performing machine learning in the learning unit 13 using learning data stored in the learning data creation unit 12, learning results of the correspondence between input information and output information, That is, the learning result of the input/output relationship is applied. The learning model 11 is a program for using input information as input data, output information as output data, and modeling and calculating the input/output relationship between the input information and the output information. Note that the learning model 11 may be represented by a formula such as a function.

The learning model 11 preferably applies a supervised learning algorithm among machine learning. As supervised learning, for example, linear regression, logistic regression, random forest, boosting, support vector machine (SVM), neural network ) and the like. A neural network can use deep learning with a neural network having more than three layers. Types of neural networks include, for example, convolutional neural networks (CNN), recurrent neural networks (Recurrent Neural Networks, RNN), and general regression neural networks. can be done.

The input information consists of information on the user present in the space, information on the output values of the plurality of odor sensors 201 . information related to related data, information related to the type of odor sensed by the user and the cause of complaints caused by odor components, types of odor components detected by the plurality of odor sensors 201 . . . 20N and respective odor components can include information about the concentration of These pieces of information are prepared for each user present in the space. Also, these pieces of information may be based on measurements in the same space or may be based on measurements in different spaces. In addition, the input information may include necessary information as appropriate in addition to the above information.

Information about users existing in the space includes names, membership numbers, telephone numbers, e-mail addresses, addresses, and the like.

For example, when the output values of the plurality of odor sensors 201 . "Yes", "6 levels", "10 levels", and the like.

Examples of information relating to the user's subjective judgment of odor include "smell is stinky", "smell is very stinky", "smell of cigarettes", "smell of alcohol", and "smell of perfume".

As information related to the related data, for example, "When the output value of the odor sensor 201 is in 4 levels, there is no odor." When the output value is in two stages and the output value of the odor sensor 202 is in one stage, there is no odor."

Examples of information related to the type of odor sensed by the user include cigarette, perfume, and alcohol.

Information about the cause of complaints caused by odor components includes, for example, "cigarette stinks", "strong perfume", "body stinks", and "sweaty".

Information about the types of odor components detected by the plurality of odor sensors 201 . "light smell", "no smell of cigarettes", "strong smell of perfume", "smell of perfume", "light smell of perfume", "no smell of perfume", etc.

The output information can include information related to the degree of risk of complaints from users of the space, and may include necessary information as appropriate.

The degree of risk of complaints from users of the space is based on current information on the output values of the plurality of odor sensors 201 . . . 20N, information on past output values of the plurality of odor sensors 201 . It is calculated on the basis of relevant data associated with information relating to subjective judgment of a person's odor.

Examples of information on the degree of risk of complaints from space users include "complaint rate of 0%", "complaint rate of 6%", "complaint rate of 60%", and "complaint rate of 60%". is 90%” and the like.

The learning data creating unit 12 creates learning data for the learning model 11 . The learning data includes input information and output information.

FIG. 3 is a diagram showing an example of learning data. As shown in FIG. 3, the learning data includes, as input information, information on past output values of the plurality of odor sensors 201 . . . 20N and information on past user subjective judgments. The information includes information on the degree of risk of user complaints. In addition, in FIG. 3, black circles indicate odor levels.

The learning data creation unit 12 stores input information used for prediction (prediction input information) in the learning data, and output information predicted from the prediction input information (prediction output information) or from the prediction input information. The obtained actual output information can be input as input information and output information to update the learning data.

The prediction input information includes information about the user who is about to use the car. The input information for prediction may also include information about the user who is currently using the car.

The learning unit 13 can learn the input information for prediction and the output information for prediction input to the learning data by the learning data creation unit 12 as input information and output information, and update the learning model 11 . That is, the learning unit 13 uses the learning data created by the learning data creation unit 12 to learn the learning model 11 representing the correspondence between the input information and the output information by machine learning. For example, the learning unit 13 preferably learns the learning model 11 such that the input/output relationship of the learning model 11 approaches the input/output relationship of the learning data. Since the details of machine learning are the same as those of the learning model 11, description thereof is omitted.

The storage unit 14 stores information about the user, related data in which information about past output values of the plurality of odor sensors 201 . Remember. It should be noted that the information relating to past user's subjective judgments on odors may be based on measurements in the same space or may be based on measurements in different spaces.

In addition, the storage unit 14 can store, for each user, the relationship between the type of odor perceived by the user and the cause of complaint caused by the odor component in the related data.

The calculation unit 15 outputs prediction output information based on the prediction input information input to the learning model 11 .

The predictive output information can include information similar to the output information described above. As output information for prediction, based on the current output values of the plurality of odor sensors 201 . Since it can include the same information as the output information including information about, etc., the details of the information are omitted.

Further, the calculation unit 15 outputs a coping method based on the types of odor components detected by the odor sensors 201 . . . 20N and the concentrations of the respective odor components. As a coping method, there is a method of deodorizing using ozone or the like. Note that the coping method may include a case where nothing is done.

The input unit 16 inputs the output values of the odor sensors 201 to 20N acquired by the acquisition unit 17 to the calculation unit 15 as prediction input information.

The predictive input information can include information similar to the input information described above. The input information for prediction includes information about the user existing in the space, information about past output values of the plurality of odor sensors 201 . . . Information on related data in which information on subjective judgment is correlated, information on the type of odor sensed by the user and the cause of complaint caused by the odor component, and information detected by the plurality of odor sensors 201 . . . 20N. Since it can include the same information as the information about the types of odor components and the concentration of each odor component, the details of the information are omitted.

The acquisition unit 17 acquires the output values of the odor sensors 201 . . . 20N sent via the communication device 20 .

The display unit 18 displays the prediction output information output by the calculation unit 15 . In addition, the display unit 18 can display the optimum coping method calculated from the types of odor components output by the calculation unit 15 and the concentrations of the respective odor components.

(Hardware configuration of control device 10)
Next, an example of the hardware configuration of the control device 10 will be described. FIG. 4 is a block diagram showing the hardware configuration of the control device 10. As shown in FIG. As shown in FIG. 4, the control device 10 is configured by an information processing device (computer), and physically includes a CPU (Central Processing Unit: processor) 101 that is an arithmetic processing unit, and a RAM (Random Access Memory) 102 and ROM (Read Only Memory) 103, an input device 104 as an input device, an output device 105, a communication module 106, an auxiliary storage device 107 such as a hard disk, and the like. These are interconnected by a bus 108 . Note that the output device 105 and the auxiliary storage device 107 may be provided outside.

The CPU 101 controls the overall operation of the prediction system 1 and performs various types of information processing. The CPU 101 executes a complaint prediction program (hereinafter simply referred to as a prediction program) stored in the ROM 103 or the auxiliary storage device 107 to control display operations of the measurement recording screen and the analysis screen.

The RAM 102 is used as a work area for the CPU 101 and may include a non-volatile RAM that stores main control parameters and information.

The ROM 103 stores basic input/output programs and the like. The prediction program may be stored in ROM 103 .

The input device 104 is a keyboard, mouse, operation buttons, touch panel, or the like.

The output device 105 is a monitor display or the like. The output device 105 displays prediction results and the like, and the screen is updated according to input/output operations via the input device 104 and the communication module 106 .

The communication module 106 is a data transmission/reception device such as a network card, and functions as a communication interface that takes in information from an external data recording server or the like and outputs analysis information to other electronic equipment.

The auxiliary storage device 107 is a storage device such as an SSD (Solid State Drive) and a HDD (Hard Disk Drive), and stores, for example, a prediction program and various data and files necessary for the operation of the prediction system 1 .

Each function of the control device 10 shown in FIG. The CPU 101 executes the predicted program and the like. Each function of the control device 10 is realized by operating the input device 104, the output device 105, and the communication module 106, and reading and writing data in the RAM 102, ROM 103, auxiliary storage device 107, and the like. That is, by executing the prediction program according to the present embodiment on a computer, the control device 10 includes the learning model 11, the learning data creation unit 12, the learning unit 13, the storage unit 14, the calculation unit 15, and the It functions as an input unit 16 , an acquisition unit 17 and a display unit 18 .

The prediction program is stored, for example, in a storage device included in the computer. Part or all of the prediction program may be transmitted via a transmission medium such as a communication line, received by the communication module 106 or the like provided in the computer, and recorded (including installation). In addition, the prediction program is partly or entirely stored in a portable storage medium such as a CD-ROM, DVD-ROM, flash memory, etc., and is recorded (including installation) in the computer. good too.

The prediction system 1 includes a control device 10 and a plurality of odor sensors 201 . . . 20N. The prediction system 1 stores, in the storage unit 14, related data in which information about past output values of the plurality of odor sensors 201 . ing. Then, the prediction system 1 uses the calculation unit 15 to calculate the degree of risk of complaints from users who plan to use the space based on the current output values of the plurality of smell sensors 201 . . . 20N and related data. . Thereby, the prediction system 1 does not measure all the concentrations of specific odor components, but rather calculates the current output values of the plurality of odor sensors 201 . . . It is possible to calculate the degree of risk of complaints by a person. Therefore, the prediction system 1 can highly accurately predict the rate of occurrence of complaints about odors, regardless of the concentration of specific odor components.

As a result, the prediction system 1 can easily determine in advance whether the air inside the vehicle needs to be exhausted, deodorized, maintained, etc., before lending the vehicle to the next user.

The prediction system 1 stores, for each user, in the storage unit 14, the relationship between the type of odor sensed by the user and the cause of the complaint caused by the odor component as related data, and the calculation unit 15 stores the relationship between the type of odor sensed by the user and the cause of the complaint caused by the odor component. The cause of the complaint can be identified from the types of odor components detected in 201 . . . 20N. As a result, the prediction system 1 can specifically identify the cause of complaints for each user, so that the occurrence rate of complaints about odors for each user can be increased according to the types of odors present in the space. It can be predicted with high accuracy.

The prediction system 1 uses the plurality of odor sensors 201 . . . 20N to detect the type of odor component and the concentration of each odor component. A coping method can be output from the type of component and the concentration of each odor component. As a result, the prediction system 1 can propose a more appropriate coping method for the smell in the space, so that it is possible to reduce the rate of occurrence of complaints about the smell from users who plan to use the automobile in advance.

Prediction system 1 may comprise a learning model 11 . The learning model 11 is a learning model generated by machine-learning the correspondence relationship between the input information and the output information using the learning data created by the learning data creating unit 12 in the learning unit 13 . The prediction system 1 includes, in the learning model 11, information about the user, information about the output values of the plurality of odor sensors 201 . By inputting the input information, the calculation unit 15 infers information on the degree of risk of complaints from users who plan to use the space based on the input information for prediction input to the learning model, and output information for prediction. can be calculated as Therefore, the prediction system 1 can more accurately calculate the complaint occurrence risk by the user who plans to use the automobile, based on the results of the prediction output information obtained using the learning model 11 .

The prediction system 1 can include a learning data creation unit 12 and a learning unit 13 . The prediction system 1 can learn a learning model representing the correspondence relationship between the input information and the output information by using the learning data created by the learning data creating unit 12 in the learning unit 13 . Thereby, the prediction system 1 can apply the learning model learned by the learning unit 13 as the learning model 11 . Therefore, since the prediction system 1 can output the prediction output information from the prediction input information with higher accuracy by the learning model 11, the degree of complaint occurrence risk by the user who is planning to use the automobile can be calculated with higher accuracy. be able to.

The prediction system 1 can update the learning model 11 by causing the learning unit 13 to learn the prediction input information and the prediction output information input to the learning data of the learning data creation unit 12 as input information and output information. can. The prediction system 1 can update the learning model 11 by having the learning unit 13 learn input information and output information newly obtained in the learning data. Therefore, since the prediction system 1 can make the learning model 11 learn including the latest input information and output information, the prediction output information can be output from the prediction input information in consideration of the latest data. Therefore, since the prediction system 1 can further improve the accuracy of the prediction output information, it is possible to stably calculate the degree of complaint occurrence risk by the user who plans to use the automobile with higher accuracy.

As described above, the prediction system 1 can predict with high accuracy the rate of occurrence of complaints about the smell contained in the gas to be detected. Complaints from users and other users due to odor components in closed spaces such as cabins of aircraft, rooms in buildings such as office buildings and hotels, guest rooms, changing rooms, toilets, etc. It can be suitably used as a system that predicts that

In addition, in this embodiment, the prediction system 1 may be used for the current user.

In this embodiment, the prediction system 1 does not have to include the learning model 11 , the learning data creation unit 12 and the learning unit 13 .

In the present embodiment, the learning data creating unit 12 does not have to update the learning data by learning the prediction input information and the prediction output information input to the learning data as input information and output information.

<Complaint prediction method>
Next, the complaint prediction method according to this embodiment will be described using the prediction system 1 according to this embodiment. The complaint prediction method according to the present embodiment measures the smell component contained in the detection target gas present in the space in the prediction system 1 having the configuration shown in FIG. Predict the risk of complaints about odors by people.

FIG. 5 is a flowchart for explaining the complaint prediction method according to this embodiment. As shown in FIG. 5, the complaint prediction method according to the present embodiment includes a learning data creation step (step S11), a learning model learning step (step S12), an odor detection step (step S13), an odor sensor 201 . . . Input step of output value of 20N (step S14), calculation step of complaint occurrence risk (step S15), display step of complaint occurrence risk (step S16) and update step of learning data (step S18) .

The prediction system 1 creates learning data for the learning model 11 by the learning data creation unit 12 (learning data creating step: step S11). The learning data creation unit 12 learns the correspondence relationship between the input information and the output information, and creates learning data as shown in FIG. 3 as related data.

Next, the prediction system 1 causes the learning unit 13 to learn the learning model 11 using the learning data created in step S11 (learning model learning step: step S12).

The learning unit 13 uses the learning data created by the learning data creation unit 12 to learn the learning model 11 representing the correspondence relationship between the input information and the output information using machine learning such as deep learning. do. The learning unit 13 learns the learning model 11 according to the contents of the input information of the learning data so that the output matches the output information related to this input information. As described above, the learning unit 13 uses linear regression, logistic regression, random forest, boosting, support vector machine (SVM), and neural Algorithms such as Neural Networks can be applied as supervised learning models.

Next, the prediction system 1 acquires current output values of the plurality of odor sensors 201 .

Next, the prediction system 1 uses the input unit 16 to input information about users who are planning to use the space and information about the output values of the odor sensors 201 . . . 20N as input information for prediction (odor sensor 201 . . . 20N output value input step: step S14).

Next, the prediction system 1 uses the learning model 11 to calculate information regarding the degree of complaint occurrence risk by the user who is scheduled to use the space by the calculation unit 15 (complaint occurrence risk prediction step: step S15). . The calculation unit 15 inputs the prediction input information input in step S13 to the learning model 11 that has undergone machine learning in step S12, and outputs from the learning model 11, Acquire the result of predicting the degree of complaint occurrence risk as output information for prediction.

Next, the prediction system 1 causes the display unit 18 to display the prediction result of the complaint occurrence risk output by the calculation unit 15 as prediction output information (process for displaying the prediction result of the complaint occurrence risk: step S16 ).

In addition, the prediction system 1 displays coping methods on the display unit 18 based on the types of detected odor components and the concentrations of the respective odor components.

Next, the prediction system 1 inputs the prediction input information and the prediction output information to the learning data as input information and output information by the learning data creating unit 12, and updates the learning data (learning data update step: step S17).

The complaint prediction method according to this embodiment includes an odor detection step (step S13) and a calculation step (step S15). In the complaint prediction method according to the present embodiment, in the smell detection step (step S13), a plurality of smell sensors detect the smell component contained in the gas to be detected, and in the calculation step (step S15), the current plural smell sensors 201 . It is possible to calculate the degree of risk of complaints from users who are planning to do so. Therefore, the complaint prediction method according to the present embodiment can highly accurately predict the occurrence rate of complaints about odors without depending on the concentration of a specific odor component.

In addition, in this embodiment, the complaint prediction method according to this embodiment may be used for the current user.

In this embodiment, the step of creating learning data (step S11) and the step of learning a learning model (step S12) may not be performed if they are unnecessary.

In the present embodiment, the step of displaying the degree of risk of complaints (step S16) may not be performed if display of the degree of risk of complaints is unnecessary.

In this embodiment, the step of updating the learning data (step S17) may not be performed if the learning data need not be updated.

As described above, the embodiment has been described, but the above embodiment is presented as an example, and the present invention is not limited by the above embodiment. The above embodiments can be implemented in various other forms, and various combinations, omissions, replacements, changes, etc. can be made without departing from the scope of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the scope of the invention described in the claims and equivalents thereof.

This application claims priority based on Japanese Patent Application No. 2020-005397 filed with the Japan Patent Office on January 16, 2020, and the entire contents of Japanese Patent Application No. 2020-005397 are incorporated into this application. .

1 complaint prediction system 10 complaint prediction control device 11 learning model 12 learning data creation unit 13 learning unit 14 storage unit 15 calculation unit 16 input unit 17 acquisition unit 18 display unit 201...20N smell sensor 30 communication device 40 communication network

Claims (7)

A complaint prediction system for predicting the degree of complaint occurrence risk regarding odors contained in detection target gas in a partitioned space,
a plurality of odor sensors with different detection characteristics that respond to odor components contained in the detection target gas;
a storage unit for storing related data in which information about past output values of the plurality of odor sensors and information about past user's subjective judgments on odors are associated;
a calculation unit that calculates the degree of risk of complaints by the users who plan to use the space based on the current output values of the plurality of odor sensors and the related data;
complaint prediction system. The storage unit stores, for each user, the relationship between the type of odor and the cause of complaint caused by the odor component in the related data,
2. The complaint prediction system according to claim 1, wherein the calculation unit identifies the cause of the complaint from the type of the odor component detected by the odor sensor. The odor sensor detects the type of the odor component and the concentration of each of the odor components,
3. The complaint prediction system according to claim 1, wherein the calculation unit outputs a coping method based on the types of the odor components detected by the odor sensor and the concentrations of the respective odor components. For each user, input information including information on output values of the plurality of odor sensors and information on subjective judgment of the odor of the user of the space, and risk of complaints by the user of the space. Equipped with a learning model that has learned the correspondence relationship with output information including information about degrees,
The calculation unit is configured to calculate the use of the space that is scheduled to be used based on prediction input information including information about the user and information about the output values of the plurality of odor sensors, which are input to the learning model. 4. The complaint prediction system according to any one of claims 1 to 3, which calculates output information for prediction including information on the degree of risk of complaints by a person. a learning data creation unit that creates learning data including the input information and the output information;
a learning unit that learns the learning model using the learning data;
The complaint prediction system according to claim 4, comprising: wherein the learning unit learns the input information for prediction and the output information for prediction input to the learning data by the learning data creation unit as the input information and the output information, and updates the learning model. The complaint prediction system according to item 5. A complaint prediction method for predicting a complaint occurrence risk regarding an odor contained in a gas to be detected in a partitioned space,
an odor detection step of detecting odors with a plurality of odor sensors having different detection characteristics that respond to odor components contained in the gas to be detected;
Based on related data in which current output values of the plurality of odor sensors, information about past output values of the plurality of odor sensors, and information about past user's subjective judgments on odors are associated with each other, a calculation step of calculating the degree of risk of complaints by the user who plans to use the space;
Complaint prediction methods, including;

Images