JP2020087338A - Information processing system, information processing method, information processing program, and information processing device - Google Patents

Abstract

To provide an information processing system capable of displaying information on the degree of dependence on gambling or the like in an easy-to-understand manner.SOLUTION: An output part is configured to acquire a risk score calculated by a prediction model application part and calculate the contribution level on the basis of a Z-score of explanatory variable and importance stored in the importance table. The output part displays an explanatory variable in descending order of contribution level on a detailed screen. With this, explanatory variables that affect the magnitude of the risk score of each user can be displayed in an easy-to-understand manner.SELECTED DRAWING: Figure 21

Description

The present invention relates to an information processing system, an information processing method, an information processing program, and an information processing device.

Gambling addiction has become a social issue, and if casinos are realized in Japan in the future, the number of gambling addiction patients may increase. Also, in recent years, addiction to online games and the Internet has become a major social problem. Hereinafter, these behavioral addictions will be collectively referred to as gambling addiction.

For gambling addiction, it is necessary to take measures depending on the severity, like alcohol addiction and drug addiction. For example, if you are a healthy person or a person with mild risk, instruction by an educational institution or counseling is effective. In addition, counseling and treatment by medical institutions are effective for people with moderate risk and severe risk. Furthermore, for those with severe risk and addiction, it is effective to continuously participate in recovery facilities and self-help groups in addition to medical institutions such as hospitals.

Conventionally, there is known a technique in which a gambling machine or the like monitors the behavior of the identified person such as gambling and determines the category of the behavior of the monitored person such as gambling (see, for example, Patent Document 1).

Japanese Patent Publication No. 2007-503631

However, in the above-mentioned Patent Document 1 and the like, there is no study on displaying information regarding the degree of dependence on gambling and the like in an easy-to-understand manner.

In one aspect, an object of the present invention is to provide an information processing system, an information processing method, an information processing program, and an information processing device capable of easily displaying information regarding the degree of dependence on a certain object.

In one aspect, the information processing system stores in an acquisition unit that acquires information about an action corresponding to each of a plurality of items detected for a person, and information about the action acquired by the acquisition unit and a storage unit. Based on the weight information of each of the plurality of items, a value relating to the degree of dependence of the certain person on a certain object, and each of the plurality of items for determining the degree of dependence on the certain object contribute to the magnitude of the value. And a display control for displaying some or all of the items included in the plurality of items in an order corresponding to the magnitude of the contribution calculated by the calculation unit. And a section.

Information about the degree of dependence on a certain object can be displayed in an easy-to-understand manner.

It is a figure which shows roughly the structure of the information processing system which concerns on one Embodiment. It is a figure which shows the hardware constitutions of the server which the ICT infrastructure management organization of FIG. 1 has. FIG. 2 is a functional block diagram of a server included in the ICT infrastructure operating institution of FIG. 1. It is a flowchart which shows the process of an explanatory variable preparation part, an objective variable preparation part, and a prediction model preparation part. FIG. 5A is a diagram showing entrance/exit information to and from the casino facility, FIG. 5B is a diagram showing gaming information, and FIG. 5C is a diagram showing wide area action information. FIG. 6A is a diagram showing monthly explanatory variables (entrance/exit information) for each individual, and FIG. 6B is a diagram showing monthly explanatory variables (gaming information) for each individual. 6C is a diagram showing monthly explanatory variables (wide area action information) for each individual. FIG. 7A is a diagram showing demographic information, and FIG. 7B is a diagram showing monthly explanatory variables (demographic information) for each individual. It is a figure which shows the monthly explanatory variable (merge version) for every individual. FIG. 9A is a diagram showing the person/family application information, FIG. 9B is a diagram showing visit restriction information, and FIG. 9C is a diagram showing event information. 9(d) is a diagram showing a monthly objective variable for each individual. It is a figure which shows the data for learning. It is a figure which shows an importance level table. It is a flow chart which shows processing of a prediction model application part. It is a figure which shows an example of the explanatory variable created from the newly acquired data. FIG. 14A is a diagram showing a prediction result, and FIG. 14B is a diagram showing a type table of explanatory variables. It is a flow chart which shows processing (the 1) of an output part. 16 is a flowchart showing a specific process of step S120 of FIG. FIG. 17A is a diagram showing a z-score table created based on the explanatory variables of FIG. 13, and FIG. 17B is a diagram showing a contribution degree table. It is a figure (the 1) which shows a list screen. It is a figure (the 2) which shows a list screen. 16 is a flowchart showing a specific process of step S130 of FIG. It is a figure (the 1) which shows a detailed screen. It is a figure (the 2) which shows a detailed screen. It is a flowchart which shows the process (the 2) of an output part. FIG. 24A is a diagram showing an emphasis method table according to a risk score, and FIG. 24B is a diagram showing an emphasis method table according to a risk level. It is a figure which shows an example of the screen displayed in step S208 of FIG. It is a figure which shows the modification of the screen of FIG.

Hereinafter, an embodiment of the information processing system will be described in detail with reference to FIGS.

FIG. 1 schematically shows the configuration of an information processing system 100 according to an embodiment. As shown in FIG. 1, the information processing system 100 includes public institutions such as national and local governments, gambling addiction countermeasure institutions, IR (Integrated Resort) business operators, external institutions (medical institutions, counselors, and external organizations). Etc.), the ICT infrastructure management organization collects and analyzes various information (big data) from the device installed in the commercial facility business operator via the network N to provide information regarding dependence on gambling, etc. ..

As shown in FIG. 1, the IR business operator has a server 20, a plurality of devices 22 connected to the server 20, and a terminal 24. The device 22 is an entrance/exit gate provided at an entrance/exit of a casino facility operated by an IR business, an electronic gaming device such as a slot machine, a table game, or the like. The terminal 24 is a terminal used by the IR business staff at work. The server 20 transmits the information obtained from the device 22 to the server 80 included in the ICT infrastructure operating organization. At the same time, the server 20 transmits the information obtained from the device 22 to the server 10 managed by a public institution or the server 30 managed by a gambling addiction countermeasures institution. Further, the server 20 uses the ICT-based server 80 to store information applied to the casino facility by the user himself/herself who uses the casino facility or his/her family, and information input from the terminal 24 and grasped by the staff in the casino facility. Send. At the same time, the server 20 transmits these pieces of information to the server 10 managed by a public institution and the server 30 managed by a gambling addiction countermeasure institution. Here, the information obtained from the device 22 includes an entry/exit log recording the entry/exit time of each user, gaming information recording the game play time, bet amount, winning amount, etc. of each user. .. Further, the information applied to the casino facility by the user himself or his/her family includes the regulation information regarding the user (the upper limit of the number of monthly usage, the upper limit of the monthly usage amount, etc.). Further, the information input by the staff in the casino facility from the terminal 24 includes information that the visit is restricted for the user, information about the attitude and behavior of the user that should be noted (Responsible Gambling (RG) application information), etc. Is included.

The public institution has a server 10 and a terminal 12. The server 10 acquires entry/exit logs transmitted from the servers 20 of IR companies at multiple locations throughout the country, and creates entry/exit information for the casino facility as shown in FIG. 5A. The entry/exit information includes visit information of each user (information about who entered the casino facility, when, and exited). The information input to the terminal 12 includes information that the visit restriction has been implemented for the user, information on the attitude/verbal behavior of the user that should be noted (Responsible Gambling (RG) application information), and the like. The server 10 transmits the entry/exit information and the information obtained from the terminal 12 to the ICT-based server 80. At the same time, the server 10 transmits the entrance/exit information and the information obtained from the terminal 12 to the server 30 managed by the gambling addiction countermeasure organization.

The external institution has a server 40 and a terminal 42. Information relating to patients with addiction such as gambling is input to the terminal 42 from doctors and counselors belonging to external organizations. The information about the patient and the like includes counseling results, diagnosis and treatment results, contents of recovery support support, and the like. The server 40 transmits the information obtained from the terminal 42 to the ICT-based server 80. At the same time, the server 40 transmits the information obtained from the terminal 42 to the server 10 managed by the public institution and the server 30 managed by the gambling addiction countermeasures institution.

The gambling addiction countermeasure organization has a server 30 and a terminal 32. Application information (individual/family application information as shown in FIG. 9(a)) and personal attribute information (demographic information as shown in FIG. 7(a)) are input to the terminal 32. To be done. In addition, information (visit restriction information in FIG. 9B) indicating that the gambling addiction countermeasure organization has performed early intervention work (implementation of visit restriction) for the residents is input to the terminal 32. The terminal 32 transmits the input information to the server 30. The server 30 transmits the information obtained from the terminal 32 to the ICT-based server 80.

The commercial facility business operator has a server 70. The commercial facility business operator collects wide area behavior information (see FIG. 5C) obtained at a store such as a supermarket operated by the commercial facility business in the server 70. The server 70 transmits the collected information to the ICT-based server 80.

The ICT infrastructure operation organization has a server 80 and a terminal 82. The server 80 is ICT-based, and collects and analyzes information from the servers of the above-mentioned organizations to generate and output a screen displaying information regarding addiction such as gambling.

FIG. 2 shows the hardware configuration of the ICT-based server 80. As shown in FIG. 2, the server 80 includes a CPU (Central Processing Unit) 90, a ROM (Read Only Memory) 92, a RAM (Random Access Memory) 94, a storage unit (here, an HDD (Hard Disk Drive)) 96, a network. An interface 97, a display unit 93, an input unit 95, a portable storage medium drive 99, and the like are provided. Each component of these servers 80 is connected to a bus 98. In the server 80, the CPU 90 executes a program (including an information processing program) stored in the ROM 92 or the HDD 96, or a program (including an information processing program) read from the portable storage medium 91 by the portable storage medium drive 99. By doing so, the function of each unit shown in FIG. 3 is realized. Note that the functions of the respective units in FIG. 3 may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). Devices (servers and terminals) other than the server 80 included in the information processing system 100 of FIG. 1 also have the same hardware configuration as that of FIG.

FIG. 3 shows a functional block diagram of the ICT-based server 80. As shown in FIG. 3, in the server 80, the CPU 90 executes the program, whereby the information acquisition unit 50, the explanatory variable creation unit 51, the objective variable creation unit 52, the prediction model creation unit 53, the prediction model application unit 54, It functions as an acquisition unit, a calculation unit, and an output unit 55 as a display control unit.

The information acquisition unit 50 acquires information from the servers 10, 20, 30, 40, 70 via the network N. The information acquisition unit 50 transmits the acquired information to the explanatory variable creation unit 51, the objective variable creation unit 52, and the prediction model application unit 54.

The explanatory variable creation unit 51 creates an explanatory variable used for machine learning using the information acquired by the information acquisition unit 50.

The target variable creation unit 52 creates a target variable used for machine learning using the information acquired by the information acquisition unit 50.

The prediction model creation unit 53 creates a prediction model using the explanatory variable created by the explanatory variable creation unit 51 and the objective variable created by the objective variable creation unit 52. The prediction model creation unit 53 stores the created prediction model in the prediction model DB 60. In addition, the prediction model creation unit 53 stores the importance as weight information of each explanatory variable calculated when creating the prediction model in the importance table 62 as a storage unit. Note that in FIG. 3, the prediction model DB 60 is described as having the server 80, but the prediction model DB 60 is held by a device other than the server 80 (for example, a data server capable of communicating with the server 80). Good. Similarly, the importance degree table 62 may be held by a device other than the server 80.

The prediction model application unit 54 creates an explanatory variable from the information newly acquired by the information acquisition unit 50, and applies the prediction model to the created explanatory variable to perform prediction regarding the risk of addiction such as gambling. The prediction model application unit 54 transmits the prediction result and the explanatory variable to the output unit 55.

The output unit 55 generates a screen for displaying the prediction result of the prediction model application unit 54 and displays (outputs) it on the display unit 93 or outputs it to the terminal 82 to display it on the display unit of the terminal 82. The output unit 55 uses the prediction result of the prediction model application unit 54, the explanatory variables, and the importance table 62 created by the prediction model creation unit 53 when creating the screen.

(Regarding the processing of the explanatory variable creation unit 51, the objective variable creation unit 52, and the prediction model creation unit 53)
Next, the processes of the explanatory variable creation unit 51, the objective variable creation unit 52, and the prediction model creation unit 53 will be described in detail along the flowchart of FIG. 4 and with reference to other drawings as appropriate.

The process of FIG. 4 is, for example, a process of generating (updating) a prediction model using the acquired information when the information acquisition unit 50 acquires a certain amount of information. The fixed amount of information can be information obtained during a predetermined period (for example, 3 months or 6 months). That is, the process of FIG. 4 is performed each time a predetermined period elapses. Alternatively, the user can specify an arbitrary period and timing and generate (update) the prediction model based on the specified period and timing.

In the process of FIG. 4, first, in step S10, the explanatory variable creating unit 51 creates an explanatory variable. Specifically, the explanatory variable creation unit 51 processes and aggregates individual behavior information and individual attribute information to create an explanatory variable used for generating a prediction model. The personal behavior information is time-series event information that records when and what was done for each individual, and the explanatory variable creation unit 51 sequentially aggregates information for a predetermined fixed period for each individual to explain variables. To create. For example, when the fixed period is 6 months, the totaling process is sequentially performed by shifting the 6-month totaling period by 1 month, such as January 2017 to June 2017 and February 2017 to July. ..

The personal behavior information includes, for example, entrance/exit information to and from a casino facility as shown in FIG. 5A, gaming information as shown in FIG. 5B, and wide area behavior information as shown in FIG. 5C. Etc. are included. In addition, the personal attribute information includes demographic information as shown in FIG.

The entry/exit information to/from the casino facility of FIG. 5A includes information on the entry time and the exit time of each user from the casino facility. The explanatory variable creation unit 51 creates monthly explanatory variables (entry and exit information) for each individual as shown in FIG. 6A by totaling entry and exit information to and from the casino facility. The monthly explanatory variable (entrance/exit information) for each individual includes the number of days that the user has visited the casino facility and the total amount during a certain period (for example, January-June 2017 or February-July 2017). Includes time spent, average time spent per day and maximum time spent per day.

The gaming information of FIG. 5B includes information on the game machine used by each user, the play time, the bet amount, and the winning amount. The explanatory variable creation unit 51 creates a monthly explanatory variable (gaming information) for each individual as shown in FIG. 6B by totaling gaming information. The monthly explanatory variable (gaming information) for each individual includes a total bet count, a total bet amount, and a total bet amount of each user in a certain period (for example, January to June 2017 or February to July 2017). Includes winnings, average bets per day, and maximum bets per one time.

The wide area action information of FIG. 5C includes information on the store used by each user, the type of use (purchase of goods or eating and drinking), the date and time of use, and the amount of money. The explanatory variable creation unit 51 creates a monthly explanatory variable (wide area action information) for each individual as shown in FIG. 6C by collecting the wide area action information. The monthly explanatory variable (wide area action information) includes the total number of purchases, the total purchase price, and the total number of food and drinks of each user in a certain period (for example, January to June 2017 or February to July 2017). , The average amount of food and drink for one meal is included. In addition, among the monthly explanatory variables for each individual shown in FIGS. 6A to 6C, the result of aggregation in the period from January 2017 to June 2017 is used for the prediction as of July 2017. It becomes a variable. In addition, the totalized result in the period from February to July 2017 becomes an explanatory variable used for the prediction as of August 2017.

In the demographic information of FIG. 7A, as the attribute information of each user, information that may change over time (married/unmarried, residence type, etc.) and static information that does not change over time (gender, birth year). The date is included). The explanatory variable creation unit 51 creates the monthly explanatory variable (demographic information) for each individual as shown in FIG. 7B by processing the demographic information. In the monthly explanatory variable (demographic information) for each individual in FIG. 7B, flag information of each user in a certain period (for example, January to June 2017 or February to July 2017). Or age information is included. The flag information includes a male flag indicating whether or not a man is present, a married flag indicating whether or not a person is married, a single house flag indicating whether or not a single house, a condominium flag indicating whether or not a condominium, and a rental flag indicating whether or not to rent. Is included. The flag information is created by converting the demographic information into dummy variables (multivalued category values are decomposed into a plurality of flag information). The age information is calculated from the date of birth information. Of the monthly explanatory variables (demographic information) for each individual in FIG. 7B, the information for the period from January 2017 to June 2017 is an explanatory variable used for the prediction as of July 2017. .. The information in the period from February to July 2017 becomes an explanatory variable used for the prediction as of August 2017. When the information changes within the period of 6 months, the information of the final state is used, but when it does not change, the past information may be used as it is.

The explanatory variable creation unit 51 merges the monthly explanatory variables (FIGS. 6A to 6C and FIG. 7B) for each individual created as described above, as shown in FIG. Create monthly explanatory variables (merged version) for each individual. The explanatory variable creation unit 51 transmits the created monthly explanatory variable (merged version) for each individual to the prediction model creation unit 53.

Returning to FIG. 4, in step S12, the objective variable creating unit 52 creates an objective variable. Here, in predicting the risk of addiction such as gambling, how to define the addiction risk is important. The present embodiment aims at early detection of addiction such as gambling. Therefore, instead of the onset of addiction, it is considered that the event that is a predictor of addiction such as personal declaration, family declaration, visit refusal information occurs as a risk state, and an event that is a predictor of addiction within a certain period Performs binary classification (prediction) of whether or not it occurs.

Specifically, the objective variable creating unit 52 displays the information shown in FIG. 9C on the basis of the principal/family application information as shown in FIG. 9A and the visit restriction information as shown in FIG. 9B. Generate event information as shown. Then, the objective variable creating unit 52 creates a monthly objective variable for each individual as shown in FIG. 9D based on the event information of FIG. 9C.

Here, the person/family application information in FIG. 9(a) indicates that there is a risk of addiction, and the person or family has filed restrictions on admission to the casino facility to the casino facility or gambling addiction countermeasures organization. Which includes a user ID, an applicant, and an application date. In addition, the visit restriction information of FIG. 9( b) monitors the behaviors with suspicion of addiction such that the number of visits exceeds a threshold, and implements preventive measures for imposing entry restrictions and frequency restrictions on visitors to casino facilities and gambling. This is information indicating that the independence measures agency has taken action. The visit restriction information includes information on the type of visit restriction and visit restriction date in association with the user ID. The event information of FIG. 9C is information obtained by merging the principal/family application information of FIG. 9A and the visit restriction information of FIG. 9B.

The monthly objective variable for each individual in FIG. 9D includes a user ID, a predicted implementation month, and a correct answer flag. In the present embodiment, the objective variable creation unit 52 extracts the event occurrence date from the individual regulation application information, “positive example” when the event occurs within a certain period from the predicted implementation month, and “negative” when the event does not occur. Create the correct answer flag (objective variable) so that it becomes "example". For example, when the fixed period (“prediction period”) is two months, the correct answer flag when the forecast execution month is July 2017 is that the event occurs in August or September 2017. If so, it is determined as a positive example (correct answer flag=1), and otherwise, it is determined as a negative example (correct answer flag=0). Further, the correct answer flag when August 2017 is the predicted implementation month is a correct example (correct answer flag=1) when an event occurs in September or October 2017, and is not the case. In the negative example (correct answer flag=0).

In addition, in the case of predicting the occurrence of the first event, neither the explanatory variable nor the objective variable after the event has occurred is used.

Returning to FIG. 4, in the next step S14, the prediction model creation unit 53 creates learning data. In this case, the prediction model creation unit 53 creates learning data by column-combining the explanatory variables created by the explanatory variable creation unit 51 and the objective variables created by the objective variable creation unit 52. For example, the prediction model creation unit 53 internally joins the monthly explanatory variable (merged version) for each individual shown in FIG. 8 and the monthly objective variable for each individual shown in FIG. Create learning data as shown. More specifically, for example, the prediction model creation unit 53 may perform column combination of the explanatory variables of January to June 2017 of the same user and the objective variable of which the prediction implementation month is July 2017. , Creates learning data for which the predicted implementation month is July 2017. In addition, for example, by combining the explanatory variables of February to July 2017 of the same user and the objective variable of the predicted implementation month of August 2017, the training data of the predicted implementation month of August 2017 is column-combined. To create. In the learning data shown in FIG. 10, the information of the user ID and the prediction execution month is used in the above-mentioned column combination, and is not used in generating the prediction model.

Next, in step S16 of FIG. 4, the prediction model creation unit 53 creates a prediction model using the learning data and stores the created prediction model in the prediction model DB 60. Specifically, the prediction model creation unit 53 creates a prediction model for predicting an objective variable from an explanatory variable group using machine learning (binary classification method) with learning data as an input. As the machine learning method, for example, logistic regression, decision tree, random forest, SVM (Support Vector Machine), etc. can be used. The prediction model creation unit 53 stores the created prediction model in the prediction model DB 60. Note that the format of the prediction model created by the machine learning method used differs, but in most machine learning, the degree of importance that indicates how much each explanatory variable contributes to prediction from the internal parameters of the model. Can be calculated. The prediction model creation unit 53 stores the calculated importance levels of the explanatory variables in the importance level table 62 as shown in FIG. The prediction model created by the prediction model creation unit 53 is used by the prediction model application unit 54 to calculate the prediction result, and the importance is used to visualize the prediction basis when the output unit 55 outputs the prediction result. used.

(Regarding the processing of the prediction model application unit 54)
Next, the processing of the prediction model application unit 54 will be described in detail with reference to the flowchart of FIG. It is assumed that the process of FIG. 12 is a process at which a new data is obtained (for example, once a month) or a user specifies an arbitrary period and timing and is executed.

In step S110, the prediction model application unit 54 creates an explanatory variable using the newly obtained data. FIG. 13 shows an example of explanatory variables created from newly obtained data. The explanatory variable in FIG. 13 is for calculating the risk score for October 2018, and the monthly explanatory variable for each individual is obtained by collecting the data of each user from April to September 2018. It is created in the same manner as (Merge version) (FIG. 8).

Next, in step S112, the prediction model application unit 54 applies the prediction model to the created explanatory variable and calculates the risk score. Specifically, the prediction model application unit 54 reads the prediction model created by the prediction model creation unit 53 in step S16 of FIG. 4 from the prediction model DB 60. The prediction model application unit 54 then applies the read prediction model to the newly created explanatory variable to calculate a risk score indicating the possibility that each user will fall into a problem situation. FIG. 14A shows the risk score of each user, which is the prediction result of the prediction model application unit 54. The prediction model application unit 54 transmits the prediction result of FIG. 14A to the output unit 55. The prediction model application unit 54 also transmits the explanatory variable of FIG. 13 to the output unit 55 together with the prediction result.

(Processing of output unit 55 (part 1))
Next, the processing (No. 1) of the output unit 55 will be described in detail with reference to the flowchart of FIG. The process of FIG. 15 is a process executed by the output unit 55 when a display request for a list screen regarding gambling dependence is input by a staff member of a gambling addiction countermeasures organization.

In the process of FIG. 15, first, in step S120, the output unit 55 creates screen creation data. Specifically, the output unit 55 executes processing according to the flowchart of FIG. In step S140 of FIG. 16, the output unit 55 calculates a z-score for each explanatory variable of each user acquired from the prediction model application unit 54, and creates a z-score table. The z-score means a value when normalized for one explanatory variable so that the average of all users is 0 and the variance is 1. The z-score is an index showing how much the explanatory variables of each user differ from the standard. FIG. 17A shows a z-score table created based on the explanatory variables of FIG. It can be said that the z-score of each explanatory variable is information about a gambling action corresponding to each of a plurality of items (explanatory variables) detected for each user.

Next, in step S142, the output unit 55 calculates z score×importance (=contribution) and creates a contribution table. Specifically, the output unit 55 multiplies the z-score of each explanatory variable of each user of FIG. 17A by the importance of each explanatory variable stored in the importance table 62 of FIG. The contribution of the explanatory variables is calculated, and a contribution table as shown in FIG. 17B is created. In the contribution table, the explanatory variables that deviate from the standard and the explanatory variables with higher importance have higher contributions. That is, the degree of contribution is the degree to which each of a plurality of items (explanatory variables) for determining the degree of dependence on gambling or the like contributes to the magnitude of the value (risk score) regarding the degree of dependence on the user's gambling. It can be said that there is. After step S142, the process proceeds to step S122 in FIG.

When proceeding to step S122 in FIG. 15, the output unit 55 creates a list screen using the prediction result of the prediction model application unit 54 (FIG. 14A) and the contribution degree table (FIG. 17B). The list screen is displayed on the display unit 93 or the created list screen is output to the terminal 12 and is displayed on the display unit of the terminal 12. The list screen is a screen as shown in FIG. The output unit 55 displays the information on the gambling dependence of each user on the list screen of FIG. 18 in order from the user with the highest risk score. Here, information of "RANK", "ID", "score", and "simple analysis result" is displayed on the list screen. “RANK” means the rank of the risk score, “ID” means the user ID, and “score” means the value of the risk score. In the column of “simple analysis result”, a predetermined number (for example, four) of explanatory variables and their contributions are displayed for each user from the one having the largest contribution.

In the present embodiment, by displaying a list screen as shown in FIG. 18, it is possible to display information (risk score and reason for prediction) regarding the latest prediction result for a plurality of users.

Next, in step S124, the output unit 55 waits until the user is selected on the list screen of FIG. FIG. 19 shows an example in which a user with RANK=5 and ID=04946392 is selected. When the user is selected as shown in FIG. 19, the process proceeds to step S126.

After shifting to step S126, the output unit 55 displays the information of the selected user on the list screen. In this case, the output unit 55, as shown in the upper part of the list screen of FIG. 19, is predetermined information (risk score, RANK, age, total stay time) as the information of the selected user (ID=04943692). , Gambling carrier, gaming information) are extracted from FIG. 13 and displayed. In the list screen of FIG. 19, the color indicating the risk score (=0.74) of the user is changed according to the numerical value of the risk score (see the hatched portion in FIG. 19). This makes it possible to easily display whether the risk score is high or low.

Returning to FIG. 15, in the next step S128, the output unit 55 waits until the detail button corresponding to the selected user is pressed. That is, in the example of FIG. 19, the output unit 55 waits until the button indicated by the symbol A is pressed. When the detail button is pressed, the output unit 55 moves to step S130.

When the process proceeds to step S130, the output unit 55 executes the process of identifying the countermeasure against the gambling dependence of the selected user. In step S130, the process according to the flowchart of FIG. 20 is executed.

In the process of FIG. 20, first, in step S150, the output unit 55 determines whether the risk score is higher than a predetermined threshold value. If the determination in step S150 is negative, that is, if the risk score of the selected user is smaller than the threshold, it is not necessary to present a countermeasure, so the process proceeds to step S164, and the output unit 55 Decide not to present any countermeasures. After that, all the processes in FIG. 20 are ended, and the process proceeds to step S132 in FIG.

On the other hand, if the determination in step S150 is affirmative, the process moves to step S152, and the output unit 55 selects an explanatory variable satisfying a predetermined condition from the explanatory variables of the selected user. In this case, the output unit 55 selects, for example, an explanatory variable in which z score×importance (=contribution) is equal to or more than a threshold value, or a predetermined number of explanatory variables higher in the ranking of z score×importance (=contribution). Or select.

Next, in step S154, the output unit 55 determines whether or not the selected explanatory variable includes an explanatory variable that can be controlled by a person's will. Specifically, the output unit 55 refers to the explanatory variable type table shown in FIG. 14B, and the explanatory variables selected in step S152 include explanatory variables that can be controlled by a person's will. Determine whether or not. Here, in the table of FIG. 14B, the explanatory variables that can be controlled by the intention of the person include the number of visits and the bet amount, and the explanatory variables that cannot be controlled by the intention of the person include gender. Is described.

If the determination in step S154 is negative, that is, if the selected explanatory variables do not include any explanatory variable that can be controlled by a person's will, the process proceeds to step S164. When the process moves to step S164, the output unit 55 determines not to present the countermeasure, and then ends all the processes in FIG. 20 and moves to step S132 in FIG.

On the other hand, when the determination in step S154 is affirmative, the process proceeds to step S156, and the output unit 55 selects one explanatory variable that can be controlled by the will of the person. Next, in step S158, the output unit 55 sets the reduction target value based on the average value of the persons in which no event has occurred or the like. Next, in step S160, the output unit 55 creates the text of the countermeasure plan using the preset rule and the set reduction target value. For example, the output unit 55 is the text, "If you reduce the number of days to play by 30% and limit it to 3 times a week, you can reduce the risk of addiction by 40%" and "the bet amount per time is 30%." If you reduce the cost to JPY 000, you can reduce the risk of addiction by 20%."

Next, in step S162, the output unit 55 determines whether or not all the explanatory variables (the explanatory variables that can be controlled by the will of the person) have been selected. When the determination in step S162 is negative, the process returns to step S156, and the processes and determinations in steps S156 to S162 are repeatedly executed until the determination in step S162 is affirmed. Then, when the determination in step S162 is affirmed, the output unit 55 ends all the processing in FIG. 20, and proceeds to step S132 in FIG.

When proceeding to step S132 in FIG. 15, the output unit 55 displays a detailed screen. Specifically, the output unit 55 displays a detailed screen as shown in FIG.

The output unit 55, for example, as shown in FIG. 21, in the range B of the detailed screen, as in the case of FIG. 19, predetermined information (risk score, RANK) as information of the selected user (ID=04943692). , Age, total time spent, gambling carrier, gaming information).

Further, the output unit 55 displays "score transition" in the range C of the detailed screen. In the score transition column, a transition of past risk scores of the selected user in time series is displayed.

Further, the output unit 55 displays, in the range D of the detailed screen, information (score basis) regarding the explanatory variable that was the basis for calculating the risk score. In this case, as shown in FIG. 21, the output unit 55 displays the explanatory variables in order of increasing contribution (=z score×importance). The output unit 55 also displays a graph indicating the actual value itself and the size of the value in the actual value column. Further, the output unit 55 represents the maximum value of the actual values by the position of the right end of the graph, the white circle (◯) represents the average of healthy persons, and the black circle (●) represents the average of gambling-dependent persons. The output unit 55 also displays a graph showing the importance value itself and the magnitude of the value in the importance field, and z score x importance (=contribution) in the z score x importance field. Display the value itself.

Further, the output unit 55 displays the "Countermeasure" button in the range D of the detailed screen in association with the explanatory variable for which the text of the countermeasure is created in step S130 (the process of FIG. 20) described above. When the button of this countermeasure is pressed, as shown in FIG. 22, the output unit 55 pops up the text of the countermeasure corresponding to the pressed button.

In this embodiment, since the detailed screens as shown in FIGS. 21 and 22 are displayed on the display unit 93 or the display unit of the terminal 12, it is possible to confirm detailed information regarding the gambling dependence of the selected user. Becomes Further, since the score transition (range C) is displayed on the detailed screen, it is possible to easily confirm whether or not the risk of gambling dependence is increasing for the user. Further, it is possible to easily confirm the position of the selected user in the overall distribution of the actual values, the importance of each explanatory variable, and the degree of influence of each explanatory variable on the risk score.

Further, by pressing the countermeasure button, the countermeasure based on the rule is displayed, so that it is possible to confirm what countermeasure should be taken to reduce the risk of addiction such as gambling.

Therefore, a user such as a staff member of a gambling addiction countermeasure organization identifies a user who is at risk of gambling addiction by referring to the screens of FIGS. 18, 19, 21, and 22, and The reason why the risk score is high and appropriate countermeasures can be notified to external organizations.

In the process of FIG. 15, the case has been described in which the countermeasure is specified before displaying the detailed screen (S130) and the countermeasure button is displayed on the detailed screen (S132). However, the present invention is not limited to this. For example, when a certain explanatory variable is selected from the detailed screen, a countermeasure related to the selected explanatory variable is specified, and when the countermeasure can be specified, the countermeasure is specified. May be displayed.

21 and 22, a case has been described in which the explanatory variables are displayed in descending order of contribution, but the present invention is not limited to this, and may be displayed in descending order of contribution. Further, the display order of the explanatory variables may be switched between the order of increasing contribution and the order of decreasing contribution. In addition, in FIG. 21 and FIG. 22, all explanatory variables may be displayed, or some of the explanatory variables (a predetermined number from the largest contribution degree) may be displayed.

(Regarding the processing (part 2) of the output unit 55)
Next, the processing (No. 2) of the output unit 55 will be described according to the flowchart of FIG. 23 and appropriately referring to other drawings. The process of FIG. 23 is a process executed by the output unit 55 when the display request of the score transition screen (screen of FIG. 25) of a plurality of users is input by the staff of the gambling addiction countermeasures organization.

In the process of FIG. 23, first, in step S200, the output unit 55 acquires the risk score of each user for each predetermined period. Here, as an example, the output unit 55 acquires the risk score of each user for each week. That is, the prediction model application unit 54 performs the prediction process (FIG. 12) every week.

Next, in step S202, the output unit 55 identifies the method of emphasizing the background color in the display frame when the acquired risk scores are displayed in chronological order for each user as shown in FIG. In this case, the output unit 55 specifies the background color emphasis method, for example, based on the emphasis method table according to the risk score as illustrated in FIG. Here, in the table of FIG. 24A, the emphasis method (background color) is defined for each risk score range. Therefore, the output unit 55 specifies the background color of each risk score acquired in step S200 by referring to the table in FIG.

Next, in step S204 of FIG. 23, the output unit 55 identifies the event occurrence date of each user. In this case, the output unit 55 identifies the event occurrence date of each user from the event information of FIG. In addition, when creating the machine learning objective variable in step S12 described above, if it is included in the period from the event occurrence date to a certain period before the event occurrence date, it is treated as a “positive example” to predict the event occurrence in advance. Has been realized. Therefore, for the purpose of confirming the certainty of the advance prediction, in the following description, a day before a certain period of the event occurrence date may be used instead of the event occurrence date.

Next, in step S206, the output unit 55 identifies the emphasis method based on the risk degree determined from the event occurrence date of each user and the change trend (or stability) of the risk score. In this case, the output unit 55 specifies the emphasis method based on, for example, the emphasis method table according to the degree of risk as shown in FIG. Here, the risk level is determined for each combination of the change trend (slope) of the risk score and the event occurrence status, as shown in FIG. For example, the output unit 55 sets the moving window period to 4 weeks, specifies the risk degree of each week included in the moving window period based on the change trend (slope) of the risk score and the event occurrence state within the moving window period, and specifies the risk level. The emphasis method corresponding to the determined risk level is specified from the table in FIG. As the slope, a slope obtained by regression analysis or the like can be used, or a moving average of slopes in a moving window period can be used. For example, when the slope of the score increase in the moving window period is 2.0 or more and the certain week included in the moving window period is the week after the event occurs, the output unit 55 encloses the week in a square. , Make the risk score characters pink and bold. In the present embodiment, the event occurrence date of each user specified by the output unit 55 in step S204 is information associated with each user, and the risk degree determined in step S206 is a risk related to gambling dependence of each user. It can be said that it is degree.

Next, in step S208, the output unit 55 generates a screen displaying the risk score of each user for each predetermined period acquired in step S200, based on the emphasis method identified in steps S202 and S206, and the display unit 93 and It is displayed on the display unit of the terminal 12.

FIG. 25 shows an example of the screen displayed in step S208. In the screen of FIG. 25, weekly risk scores (values) of each user are displayed in chronological order. Further, in the screen of FIG. 25, the background color is color-coded according to the risk score. Further, in the screen of FIG. 25, a portion where the risk score changes rapidly is surrounded by a square. In FIG. 25, when two or more adjacent risk scores are enclosed by a square, the two or more adjacent risk scores are enclosed by one square. Further, on the screen of FIG. 25, the risk score (value) in the period after the event has occurred is shown in bold type (in FIG. 25, the characters are enlarged for convenience of illustration). Although not shown in the screen of FIG. 25, it is assumed that the character colors are also color-coded based on the table of FIG. 24(b).

According to the screen of FIG. 25, focusing on the row of arrow E, it can be seen that there is a portion where the risk score is displayed in bold type even though there is no portion surrounded by a square. In this case, there is a user in which an event has occurred even though the risk score does not tend to increase. In such a case, the staff member of the gambling addiction countermeasures organization can determine that the prediction is missing and that the prediction model needs to be improved. Further, focusing on the line of arrow F, it can be seen that the risk score of the portion surrounded by the square is displayed in bold type. In this case, since the risk score has risen and an event has occurred, the staff of the gambling addiction countermeasures organization can judge that the prediction is appropriate. Further, focusing on the row of the arrow G, it can be seen that there is a portion where the risk score is not displayed in bold in the portion surrounded by the square. In this way, when there is a user who does not have an event even though the risk score has risen, staff of the gambling addiction countermeasures organization should pay particular attention to the user in the future. It can be determined that the user. Further, the staff member of the gambling addiction countermeasures organization can determine that there is a lack of correspondence to the target user, and that it is necessary to improve the business process such as the reference value of event occurrence.

As described above, in the present embodiment, it is possible to easily display the change of the risk score of each user and the presence/absence of an event on the screen. Also, by referring to the screen, it becomes possible to discover the need for improvement of the prediction model.

Here, in the present embodiment, display control is performed so that the background color and the character color do not match. Thereby, the risk score can be displayed in an easy-to-see manner.

In addition, in the present embodiment, the range surrounded by a square may be a range in which the increase in the risk score as compared with the previous week is continuous for a threshold value or more (for example, three times or more). Further, the range surrounded by a square may be a range in which the score is increased at a rate equal to or higher than a threshold value (for example, 75% or higher) compared with the previous time.

In the present embodiment, the case where the background color is controlled based on the value of the risk score and the color and thickness of the character are controlled based on the degree of risk has been described, but the present invention is not limited to this. That is, the display mode of either the background color or the character may be changed based on the value of the risk score, and the display mode of the other of the background color and the character may be changed based on the risk. When changing the display mode of characters, the size of characters may be changed.

In the present embodiment, as shown in FIG. 26, the output unit 55 changes the background color based on the range of the risk score and displays the characters of the risk score of the week in which the event occurs and the week after that. The display mode may be different (for example, bold). Even in this case, it is possible to make it easy to discover that there is a discrepancy between the forecast and the actual result and the period when the discrepancy occurs. This will make it easier for staff of gambling addiction control agencies to judge the need for improvement of the prediction model. Further, the staff of the gambling addiction countermeasures organization can easily find an exceptional user such as a high-income earner who frequently and expensively plays but does not fall under addiction.

The output unit 55 displays the user detailed screen as shown in FIG. 21 when the user (user ID) is selected on the screen after displaying the screens shown in FIGS. 25 and 26. May be.

As described above in detail, according to the present embodiment, the output unit 55 acquires the risk score calculated by the prediction model application unit 54, and the z score of the explanatory variable and the importance level stored in the importance level table 62. The contribution degree is calculated based on and. Then, the output unit 55 displays the explanatory variables on the detailed screen (FIGS. 21 and 22) in order from the largest contribution. As a result, the explanatory variables that influence the magnitude of the risk score value of each user can be displayed in an easy-to-understand manner.

Further, according to the present embodiment, the output unit 55 displays the risk score and the transition of the risk score in time series on the detail screen (FIGS. 21 and 22). Thereby, the value of the risk score of the user and the transition of the risk score can be displayed in an easy-to-understand manner.

Further, in the present embodiment, the output unit 55 creates and displays a countermeasure for dependence on gambling based on the risk score and the degree of contribution. This makes it possible to automatically create and display an appropriate countermeasure based on the risk score and the degree of contribution.

In addition, the output unit 55 of the present embodiment determines whether or not to create a countermeasure based on the type of the explanatory variable (whether or not the explanatory variable is controllable by the will of the person) (S154). This makes it possible to properly select an explanatory variable for which a countermeasure is required to be created.

Further, in the present embodiment, the output unit 55 controls the background color of the area displaying the risk score according to the risk score when displaying the screens of FIGS. 25 and 26. In addition, the output unit 55 controls the color and thickness of the characters of the risk score according to the risk level determined based on the risk score and the occurrence or non-occurrence of an event. As a result, the relationship between the magnitude of the risk score and the magnitude of the risk can be displayed in an easy-to-understand manner. In this case, the staff of the gambling addiction countermeasures organization determines the need for improvement of the prediction model based on the relationship between the magnitude of the risk score and the magnitude of the risk, and identifies the users who should be noted. You can

In addition, although the said embodiment demonstrated the case where the server 80 functions as an ICT base and performs the above-mentioned process, it is not restricted to this. Other servers and devices such as the server 30 managed by the gambling addiction countermeasures organization and the server 10 managed by public institutions may function as the ICT base to execute the above-described processing.

In the above embodiment, the functions other than the output unit 55 of the server 80 (see FIG. 3) may be included in devices other than the server 80 included in the information processing system 100. Further, a part of the function of the output unit 55 in the above-described embodiment (for example, the function of executing the process of step S120 of FIG. 15) is included in a device other than the server 80 included in the information processing system 100. Good.

The above processing functions can be realized by a computer. In that case, a program describing the processing contents of the functions that the processing device should have is provided. By executing the program on a computer, the above processing functions are realized on the computer. The program describing the processing content can be recorded in a computer-readable storage medium (excluding carrier waves).

When the program is distributed, it is sold in the form of a portable storage medium such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory) in which the program is recorded. It is also possible to store the program in the storage device of the server computer and transfer the program from the server computer to another computer via the network.

The computer executing the program stores, for example, the program recorded in the portable storage medium or the program transferred from the server computer in its own storage device. Then, the computer reads the program from its own storage device and executes processing according to the program. The computer can also read the program directly from the portable storage medium and execute processing according to the program. In addition, the computer can also sequentially execute processing according to the received program each time the program is transferred from the server computer.

The above-described embodiment is a preferred embodiment of the present invention. However, the present invention is not limited to this, and various modifications can be made without departing from the scope of the present invention.

Note that the following supplementary notes will be disclosed with respect to the above description of the embodiment.
(Supplementary Note 1) An acquisition unit that acquires information about an action corresponding to each of a plurality of items detected for a person,
Based on the information on the behavior acquired by the acquisition unit and the weight information of each of the plurality of items stored in the storage unit, a value regarding the degree of dependency of the certain person on a certain target and the degree of dependency on the certain target are determined. A calculating unit that calculates a contribution degree indicating the degree to which each of the plurality of items for doing contributes to the magnitude of the value,
A display control unit that displays some or all of the items included in the plurality of items in an order according to the magnitude of the contribution calculated by the calculation unit;
An information processing system comprising:
(Supplementary Note 2) The information processing system according to Supplementary Note 1, wherein the display control unit also displays information on the value and/or the transition of the value in time series.
(Supplementary note 3) The information processing system according to Supplementary note 1 or 2, wherein the display control unit further determines and displays a countermeasure for dependency on the certain object based on the value and the contribution degree. .
(Supplementary note 4) The information processing program according to supplementary note 1 or 2, wherein the display control unit further determines and displays a countermeasure for a certain item for which designation has been accepted.
(Supplementary Note 5) The display control unit determines, among the plurality of items, an item for which a countermeasure is displayed, in accordance with information of a type associated with each of the plurality of items. 5. The information processing program according to any one of 4 to 4.
(Supplementary Note 6) Information regarding an action corresponding to each of a plurality of items detected for a certain person is acquired,
Based on the acquired information about the behavior and the weight information of each of the plurality of items stored in the storage unit, the value regarding the degree of dependence of the certain person on a certain object, and the value for determining the degree of dependence on the certain object A contribution degree indicating the degree to which each of a plurality of items contributes to the magnitude of the value is calculated,
Displaying some or all of the items included in the plurality of items in an order according to the magnitude of the calculated contribution degree,
An information processing method characterized in that a computer executes a process.
(Supplementary Note 7) Dependency of the certain person on a certain object calculated based on information about the action corresponding to each of the plurality of items detected for the certain person and the weight information of each of the plurality of items stored in the storage unit. And a contribution indicating the degree to which each of the plurality of items for determining the degree of dependence on the certain object contributes to the magnitude of the value,
An information processing program for causing a computer to execute a process of displaying some or all of the items included in the plurality of items in an order according to the magnitude of the acquired contribution value.
(Supplementary Note 8) The process of displaying some or all of the items included in the plurality of items in the order according to the magnitude of the contribution is performed by the information of the values and/or the transition of the values in time series The information processing program according to attachment 7, which also displays.
(Supplementary Note 9) The process of displaying a part or all of the items included in the plurality of items in an order according to the magnitude of the contribution is further dependent on the certain object based on the value and the contribution. 9. The information processing program according to appendix 7 or 8, which determines and displays a countermeasure for the above.
(Supplementary Note 10) In the process of displaying some or all of the items included in the plurality of items in the order according to the magnitude of the contribution degree, determining and displaying a countermeasure for a certain item for which designation is further received An information processing program according to supplementary note 7 or 8.
(Supplementary Note 11) The process of displaying some or all of the items included in the plurality of items in the order according to the degree of contribution is performed according to the information of the type associated with each of the plurality of items. The information processing program according to any one of appendices 7 to 10, characterized in that among the plurality of items, an item for which a countermeasure is displayed is determined.
(Supplementary Note 12) Dependency of the certain person on a certain object calculated based on information about the action corresponding to each of the plurality of items detected for the certain person and weight information of each of the plurality of items stored in the storage unit. An acquisition unit that acquires a value relating to a certain target, and a contribution degree indicating the degree to which each of the plurality of items for determining the degree of dependence on the certain object contributes to the magnitude of the value,
A display control unit that displays a part or all of the items included in the plurality of items in an order according to the magnitude of the value of the contribution degree acquired by the acquisition unit;
An information processing device comprising:

55 Output unit (acquisition unit, calculation unit, display control unit)
80 server (information processing device)
100 information processing system

Claims (8)

An acquisition unit that acquires information about an action corresponding to each of a plurality of items detected for a certain person,
A value regarding the degree of dependency of the certain person on a certain object and a degree of dependency on the certain object are determined based on the information regarding the behavior acquired by the acquisition unit and the weight information of each of the plurality of items stored in the storage unit. A calculation unit that calculates a contribution degree indicating the degree to which each of the plurality of items for doing contributes to the magnitude of the value,
A display control unit that displays some or all of the items included in the plurality of items in an order according to the magnitude of the contribution calculated by the calculation unit;
An information processing system comprising: Obtain information about the behavior corresponding to each of the multiple items detected for a person,
Based on the acquired information about the behavior and the weight information of each of the plurality of items stored in the storage unit, the value regarding the degree of dependence of the certain person on a certain object, and the value for determining the degree of dependence on the certain object A contribution degree indicating the degree to which each of a plurality of items contributes to the magnitude of the value is calculated,
Displaying some or all of the items included in the plurality of items in an order according to the calculated magnitude of the contribution,
An information processing method characterized in that a computer executes a process. A value regarding the degree of dependence of the certain person on a certain object, which is calculated based on the information regarding the action corresponding to each of the plurality of items detected for a certain person and the weight information of each of the plurality of items stored in the storage unit, Each of the plurality of items for determining the degree of dependence on the target is acquired with a contribution degree indicating the degree of contribution to the magnitude of the value,
An information processing program for causing a computer to execute a process of displaying some or all of the items included in the plurality of items in an order according to the magnitude of the acquired contribution value. The process of displaying a part or all of the items included in the plurality of items in an order according to the magnitude of the contribution degree, also displaying information of the value and/or a transition of the value in a time series. The information processing program according to claim 3, wherein The process of displaying a part or all of the items included in the plurality of items in an order according to the magnitude of the contribution, further, based on the value and the contribution, a countermeasure for dependence on the certain object is taken. The information processing program according to claim 3 or 4, which is determined and displayed. The process of displaying some or all of the items included in the plurality of items in an order according to the magnitude of the contribution degree is characterized in that a countermeasure for a certain item for which a designation is accepted is determined and displayed. The information processing program according to claim 3. The process of displaying a part or all of the items included in the plurality of items in an order according to the magnitude of the contribution is performed by the plurality of items according to the type information associated with each of the plurality of items. The information processing program according to any one of claims 3 to 6, characterized in that among the items, an item for which a countermeasure is displayed is determined. A value regarding the degree of dependence of the certain person on a certain object, which is calculated based on the information regarding the action corresponding to each of the plurality of items detected for a certain person and the weight information of each of the plurality of items stored in the storage unit, An acquisition unit that acquires a contribution degree indicating the degree to which each of the plurality of items for determining the degree of dependence on the certain object contributes to the magnitude of the value,
A display control unit that displays some or all of the items included in the plurality of items in an order in accordance with the magnitude of the contribution value acquired by the acquisition unit;
An information processing device comprising:

Images