JP2020170434A - Information processing method and device at place such as child consultation office - Google Patents

Abstract

To support decision making of the staff of places such as child consultation offices.SOLUTION: An information processing method includes the steps of: (A) storing data in a storage device when receiving the data input regarding at least any of a plurality of items related to information on a child involved in an abuse notice and risk assessment information on the child from a terminal device; (B) inputting data of already entered items among the plurality of items into a learned model of past abuse cases and identifying the number of days expected to be required for dealing with the child for each type of dealing with the child; and transmitting data on the number of days to the terminal device.SELECTED DRAWING: Figure 2

Description

The present invention relates to an information processing technique used in a child guidance center or the like.

In recent years, child abuse has come to be recognized as a major social problem, and the amount of work has increased significantly at welfare sites such as child guidance centers. Therefore, staff members such as child guidance centers are overwhelmed by work, it is difficult to improve their expertise, they cannot effectively collaborate with other institutions, and they have to make decisions based only on their experience and intuition. I was in a situation where I couldn't get it.

Until now, there have been systems that mainly systematize paper-based operations and have a function to judge the degree of urgency by answering predetermined questions. , Child guidance centers and other staff are not able to provide sufficient support for decision-making.

"FUJITSU Local Government Solution Welfare Comprehensive Child Counseling System", [Online] [Search on March 14, 2019] Internet <URL: http://www.fujitsu.com/jp/group/fip/solutions/industry-solutions/ public-sector-solution / childconsul />

Therefore, an object of the present invention is, as one aspect, to provide a novel technique for supporting the decision-making of staff such as child guidance centers.

The information processing method according to the present invention stores when (A) data input for at least one of a plurality of items related to the information about the child related to the notification of abuse and the risk assessment information of the child is received from the terminal device. The steps to be stored in the device and (B) the data of the already input items among the above multiple items are input to the trained model of the past abuse case, and the child can be dealt with for each type of child care. It includes a step of specifying the number of days expected to be required and (C) a transmission step of transmitting data regarding the number of days to the terminal device.

According to one aspect, it will be possible to appropriately support the decision-making of staff such as child guidance centers.

FIG. 1 is a diagram showing an outline of a system according to an embodiment of the present invention. FIG. 2 is a diagram showing a processing flow according to the present embodiment. FIG. 3 is a diagram showing an example of a data input screen. FIG. 4 is a diagram showing an example of a decision-making screen. FIG. 5 is a block configuration diagram of a computer device.

FIG. 1 shows an outline of the system according to the embodiment of the present invention. In the present embodiment, each staff member such as a child guidance center performs work using a terminal device 2000 such as a tablet. As a result, it will be possible to work not only at business establishments such as child guidance centers, but also at various places such as the homes of children who have been notified of abuse.

The terminal device 2000 performs processing while communicating with the information processing device 1000 via various communication media. For example, a dedicated application program may be installed in the terminal device 2000, and processing may be executed in cooperation with the information processing device 1000 by executing the dedicated application program, or a general-purpose web browser. May execute the process in cooperation with the information processing apparatus 1000. The information processing device 1000 may be one computer or an information processing system including a plurality of computers. It may also be a virtual one or more servers realized in the cloud or the like.

In order to realize the function according to the present embodiment, the information processing apparatus 1000 includes a processing unit 1010, a database 1020, a corresponding number of days prediction unit 1030, and a learning unit 1040.

The processing unit 1010 serves as an interface with the terminal device 2000, registers received data in the database 1020, reads data from the database 1020 and sends it to the terminal device 2000, and responds based on the data stored in the database 1020. The prediction unit 1030 is made to perform the prediction processing.

Database 1020 stores various data about children who have been notified of abuse. In some cases, data on staff such as child guidance centers who are in charge of children who have been notified of abuse may be stored.

The correspondence day prediction unit 1030 according to the present embodiment is a trained model by machine learning, and is a module that outputs the number of days predicted to be required for a child's correspondence from the data of the items described below. That is, it predicts the number of days from the date of receipt of notification to the end of the notification based on past abuse case patterns.

More specifically, the corresponding days prediction unit 1030 is a trained model based on gradient boosting. Boosting is one of the modeling techniques of machine learning that attempts to build a strong new learning device that is as versatile as possible by using multiple weak learning devices. In many cases, a combination of multiple conditional branching algorithms called decision trees is used. More precisely, when creating a new decision tree as boosting, the result of the previous decision tree is used, and the decision tree algorithm that minimizes the error between the measured value and the predicted value is adopted. ing. That is, gradient boosting is a method that uses the gradient descent method to minimize the error between the actual correct answer and the prediction as a loss function. More specifically, in this embodiment, Extreme Gradient Boosting (Tianqi Chen and Carlos Guestrin. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pages 785-794. . ACM, 2016) is used. Since the specific processing contents are well known, detailed description thereof will be omitted.

The learning unit 1040 reads out the data of the abuse cases sequentially accumulated in the database 1020, and executes a process for updating the corresponding number of days prediction unit 1030 at an arbitrary timing (for example, periodically). Since the algorithm for such learning is also as shown in the above papers and the like, detailed description thereof will be omitted here.

Next, the processing contents of the system in the present embodiment will be described with reference to FIGS. 2 to 4.

First, the processing unit 1010 of the information processing device 1000 receives the basic information of the child from the terminal device 2000 and stores it in the database 1020 (FIG. 2: step S1).

Basic information about a child is information about the child that is recorded when the notification of abuse is received, and the child's name, gender, relationship, nationality, date of birth, age, information about the brother, and the mother is a specific pregnant woman (child welfare). Includes whether or not a pregnant woman is in an environment that requires public support for childcare based on the law during pregnancy), her place of residence, and so on. Of these, for example, gender, age, and whether or not the mother is a specific pregnant woman are used as inputs for the corresponding number of days prediction unit 1030.

Further, the processing unit 1010 receives the information of the notification acceptance / emergency acceptance meeting from the terminal device 2000 and stores it in the database 1020 (step S3).

FIG. 3 shows an example of a screen for inputting information on the notification acceptance / emergency acceptance meeting displayed on the terminal device 2000.

The information of the notification acceptance / emergency acceptance meeting is the information about the case that is input when the abuse notification is accepted or when the information is collected from the related organizations, and the status (new / re-acceptance / re-notification), notification date and time, notification. Includes acceptance process (acceptance route type), main abuser, abuse type, date and time of emergency acceptance meeting, etc. Of these, for example, the status, the date and time of notification, the process of receiving the notification, the main abuser, and the type of abuse are used as inputs for the response days prediction unit 1030.

As shown in the upper part of FIG. 3, the following 2. Emergency dispatch, 3. Temporary protection consideration items, 4. Limit rule items, 5. Information such as decision-making and safety responsibility will continue to be entered.

In addition, for example, the data received in steps S1 and S3 is information about the child related to the notification of abuse.

Next, the processing unit 1020 receives the emergency dispatch information from the terminal device 2000 and stores it in the database 1020 (step S5).

Emergency dispatch information is a check item when considering emergency dispatch for the purpose of confirming the safety of the child. For example, whether or not there was a history of affairs related to abuse in the past (or unknown), and when the child returns home. Includes items such as whether the child is anxious or scared (or unknown) and whether the child has bruising (or unknown) at this time. The wound bruise may include information such as an image taken by a camera or the like of the terminal device 2000 and a wound type. For example, these data are used as input of the corresponding number of days prediction unit 1030.

Further, the processing unit 1010 receives the information of the temporary protection examination item from the terminal device 2000 and stores it in the database 1020 (step S7).

The information on the temporary protection study item is a check item for considering temporary protection, which is a compulsory intervention that temporarily separates the child from the abusive environment. For example, the presence or absence (or unknown) of scratches on the head, face, and abdomen. ), Fractures, burns, SBS (head trauma), MSBP (including suspicion) (or unknown), sexual abuse (including suspicion) (or unknown), protection of the child himself Includes items such as whether or not (or unknown) is suing, and whether or not there is medical abuse (or unknown) such as medical (healthcare) neglect or MSBP. For example, these data are used as input of the corresponding number of days prediction unit 1030.

Further, the processing unit 1020 receives the limit rule information from the terminal device 2000 and stores it in the database 1020 (step S9).

The limit rule information is information for considering the setting of a limit rule that makes a pledge with a guardian and promises forced intervention in case of breaking the pledge. For example, a situation in which the safety of a child cannot be confirmed, such as canceling a designated interview without permission or refusing to visit a home, even though the parents were informed in advance of the need for guidance and support during legal measures. Items such as the presence or absence of are included. For example, these data are used as input of the corresponding number of days prediction unit 1030.

The data received in steps S5 to S9 is the child's risk assessment information.

After that, the processing unit 1020 reads data of a plurality of predetermined items from the database 1020, causes the corresponding days prediction unit 1030 to execute processing so as to predict the corresponding days for each corresponding type, and each corresponding type. The prediction result of the number of corresponding days is specified (step S11).

Correspondence types are, for example, home, home with limit rule, and temporary protection. Merely at home represents a situation where the risk is extremely low or the case is not applicable to abuse (for example, when it is just a crying notification and not abuse), and there is no legal action without any guidance or support. There is. At home with limit rules refers to a situation in which it is judged that there is a risk of abuse again in the future, but it is not a risk of protection. Therefore, like probation, a framework requiring support is presented, and guidance measures such as regular interviews and home visits are legally obligatory. If this is violated (limit rule), the risk judgment will be reviewed again and temporary protection will be reconsidered. Temporary protection represents a situation in which a child is temporarily forced to move into a shelter or the like.

The plurality of predetermined items are a plurality of predetermined items among the plurality of items relating to the information regarding the child related to the notification of abuse and the risk assessment information of the child.

In addition, since there is information that cannot be investigated or is unknown in the first place, it may not be possible to input all of a plurality of predetermined items. Therefore, the input data may be used for the item for which the data has been input, and the predetermined default data may be used for the item for which the data has not been input or the content is unknown.

The correspondence day number prediction unit 1030 predicts the correspondence day number in the case of "at home" from, for example, the instruction input of "at home" and the data of a plurality of predetermined items. In addition, the number of corresponding days in the case of "at home with limit rule" is predicted from the instruction input of "at home with limit rule" and the data of a plurality of predetermined items. Further, the number of corresponding days in the case of "temporary protection" is predicted from the instruction input of "temporary protection" and the data of a plurality of predetermined items.

The corresponding number of days prediction unit 1030 according to the present embodiment predicts a specific number of days (integer) of 0 days or more. In the terminal device 2000, the specific number of days may be presented as it is, but there is a problem of how the specific number of days should be grasped. That is, there is a problem that it is difficult to grasp the level of labor required only by the number of days. Therefore, in the present embodiment, for example, category A of less than 14 days, category B of 14 days or more and less than 30 days, category C of 30 days or more and less than 90 days, category D of 90 days or more and less than 180 days, 180 days or more. It shall be divided into 6 categories, Category E with less than 365 days and Category F with 365 days or more. The number of categories is arbitrary.

Therefore, the corresponding number of days prediction unit 1030 determines the category corresponding to the predicted corresponding number of days for each corresponding type (step S13). The corresponding number of days prediction unit 1030 outputs at least one of the predicted corresponding number of days and the category to the processing unit 1010. In addition, the processing unit 1010 stores at least one of the predicted correspondence days and the category in the database 1020. The processing unit 1010 may execute this step.

Then, the processing unit 1010 generates data for decision display including the category of the predicted correspondence days for each correspondence type, and transmits it to the terminal device 2000 (step S15).

The terminal device 2000 displays a screen as shown in FIG. 4, for example. In the example of FIG. 4, a home-based selection unit, a home-based selection unit with a limit rule, and a temporary protection selection unit are included, and each of them is defined as a category of predicted response days (for example, 90 to 180 days). ) Is shown.

In this way, staff members such as child guidance centers can easily identify the type of response that is expected to shorten the number of response days. In other words, decision-making support for staff such as child guidance centers will be provided appropriately. It should be noted that the staff of the child guidance center or the like may determine the response type in consideration of not only such response days but also other factors.

When the staff inputs a decision to the terminal device 2000, the content of the decision is transmitted from the terminal device 2000 to the information processing device 1000. When the processing unit 1010 of the information processing device 1000 receives the content of the position determination from the terminal device 2000, it stores it in the database 1020 (step S17).

By performing the above processing, the predicted response days based on the past abuse case pattern will be presented to the staff of the child guidance center, etc. for the new abuse case, so the child consultation will be based on the predicted response days. Staff such as places will be able to make appropriate decisions.

Although the embodiments of the present invention have been described above, the present invention is not limited thereto. For example, the functional block configuration or module configuration described above is an example, and different configurations may be adopted. Specifically, one functional block or module may be divided into a plurality of parts, or a plurality of functional blocks or modules may be integrated into one.

Further, as for the processing flow, the order of processing may be changed or a plurality of steps may be executed in parallel as long as the processing result does not change. For example, a staff member such as a child guidance center may change the order of the inputs related to steps S3 to S9 in the terminal device 2000.

For example, an example of using Xgboost is shown in the corresponding number of days prediction unit 1030, but if a more preferable method is found, the corresponding number of days may be predicted by that method. In addition, the category may be directly predicted instead of predicting the number of corresponding days. Further, the data to be input to the corresponding number of days prediction unit 1030 and the data to be input to the terminal device 2000 should be changed to more items, more limited items, or in some cases, more appropriate items. In some cases.

The information processing device 1000 described above is a computer device, and as shown in FIG. 5, a memory 2501, a CPU (Central Processing Unit) 2503, a hard disk drive (HDD) 2505, and a display device. The display control unit 2507 connected to the 2509, the drive device 2513 for the removable disk 2511, the input device 2515, and the communication control unit 2517 for connecting to the network are connected by a bus 2519. The HDD may be a storage device such as a solid state drive (SSD). The operating system (OS) and the application program for carrying out the processing according to the embodiment of the present invention are stored in the HDD 2505 and read from the HDD 2505 to the memory 2501 when executed by the CPU 2503. .. The CPU 2503 controls the display control unit 2507, the communication control unit 2517, and the drive device 2513 according to the processing contents of the application program to perform a predetermined operation. Further, although the data in the process of processing is mainly stored in the memory 2501, it may be stored in the HDD 2505. In an embodiment of the present technology, the application program for performing the above-described processing is stored and distributed on a computer-readable removable disk 2511 and installed from the drive device 2513 to the HDD 2505. It may be installed on the HDD 2505 via a network such as the Internet and a communication control unit 2517. Such a computer device realizes various functions as described above by organically collaborating with the hardware such as the CPU 2503 and the memory 2501 described above and the program such as the OS and the application program. ..

The data used by executing the processing as described above is stored in a storage device such as a memory 2501 or an HDD 2505 regardless of whether the data is in the middle of processing or is the processing result.

The above-described embodiments can be summarized as follows.

The information processing method according to the present embodiment receives data input from the terminal device for (A) at least one of a plurality of items related to the information about the child related to the notification of abuse and the risk assessment information of the child. , The step to store in the storage device (for example, database), and (B) the data of the already input items among the above multiple items are input to the learned model of the past abuse case, and the child is dealt with (also called coping). ) Includes a step of specifying the number of days expected to be required for dealing with children, and (C) a transmission step of transmitting data on the number of days to the terminal device.

In this way, if data on the number of days expected to be required for dealing with children can be presented to staff members such as child guidance centers, it is possible to make appropriate decisions regarding the type of response, considering the length of the number of days as one factor. become able to. The data regarding the number of days may be the number of days itself.

In addition, the data regarding the number of days described above may be a category including the specified number of days among a plurality of categories for which the number of days range is defined. It is easier to recognize the degree of length of days than a concrete numerical value.

In addition, in the transmission step described above, data on the number of days is presented for each type of correspondence to children, and data for displaying for selecting the type of correspondence to children is transmitted. You may. This makes it easier for staff such as child guidance centers to directly grasp the data on the number of days for each type of response to children.

In addition, the learned model described above includes the data of the above-mentioned multiple items regarding the information on the child related to the notification of abuse in the past abuse cases and the risk assessment information of the child, and the number of days required to deal with the child. It may be a trained model based on gradient boosting, trained using. It will be possible to predict the above number of days more accurately.

A program for causing a computer to execute the information processing method described above can be created, and the program is stored in various storage media.

Further, the information processing device that executes the information processing method as described above may be realized by one computer or a plurality of computers, and information processing may be performed by combining them. It shall be referred to as a system or simply a system.

1000 Information processing device 1010 Processing unit 1020 Database 1030 Corresponding days prediction unit 1040 Learning unit

Claims (6)

When data entered from the terminal device for at least one of multiple items related to the child's abuse notification information and the child's risk assessment information is received, the step of storing it in the storage device and
The data of the already entered items among the plurality of items is input to the learned model of the past abuse case, and the number of days expected to be required for the child is specified for each type of the child's response. Steps to do and
A transmission step of transmitting data related to the number of days to the terminal device, and
Information processing methods performed by a computer, including. The information processing method according to claim 1, wherein the data regarding the number of days is a category including the specified number of days among a plurality of categories for which the number of days range is defined. In the transmission step
Claim 1 or 2 characterized in that data relating to the number of days is presented for each type of correspondence to the child, and data for displaying data for selecting the type of correspondence to the child is transmitted. The described information processing method. The trained model
Learned using the data of the plurality of items related to the information about the child related to the notification of abuse in the past abuse case and the risk assessment information of the child and the number of days required to deal with the child, and for gradient boosting. The information processing method according to any one of claims 1 to 3, which is a learned model based on the method. When data entered from the terminal device for at least one of multiple items related to the child's abuse notification information and the child's risk assessment information is received, the step of storing it in the storage device and
The data of the already entered items among the plurality of items is input to the learned model of the past abuse case, and the number of days expected to be required for the child is specified for each type of the child's response. Steps to do and
A step of transmitting data regarding the number of days to the terminal device,
A program that allows a computer to execute. When data entered from the terminal device is received from the terminal device for at least one of a plurality of items related to the information about the child related to the abuse notification and the risk assessment information of the child, the means for storing the information in the storage device and
The data of the already entered items among the plurality of items is input to the learned model of the past abuse case, and the number of days expected to be required for the child is specified for each type of the child's response. Means to do and
A means for transmitting data on the number of days to the terminal device, and
Information processing system with.

Images