Business support methods, programs, and information processing systems for supporting child consultation services.

Abstract

To provide a method for achieving improvement of the quality of decision making regarding a child consultation.SOLUTION: In an operation support system in which a server terminal, a plurality of user terminals, and a child record consultation system are connected together by a network, the server terminal 100 includes a communication terminal 110, a recording unit 120, and a control unit 130. The control unit receives registration of child information regarding a child from the user terminals, receives registration of provision information for providing consultations regarding a chile related to the child information from the user terminals, receives registration of risk access information related to the reception, which is for supporting decision of protecting child, from the user terminals, inputs the received child information, reception information, and risk access information to a learned model based on an inclination boosting, executes a risk access evaluation including calculating the degree that the input information contributes to prediction on a scale of probability, and sends the result of the risk access evaluation to the user terminals.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to a business support method for supporting child consultation services. , programs, and information processing systems It relates thereto.

Background Art

[0002] Conventionally, in order to evaluate the risk related to child abuse and protect children from abuse, various efforts have been made in various places concerned. However, problems such as a shortage of on-site staff and an increase in the number of cases of dealing with child abuse have been cited.

[0003] Under such a background, as an automation technology for determining abuse risks, for example, in Patent Document 1, a technology for predicting risks by inputting data on information related to children and risk assessment information into a learned model is disclosed.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, Patent Document 1 predicts the number of days required for dealing with children based on a learned model based on gradient boosting such as Extreme Gradient Boosting (XGBoost). However, usually, when making a prediction based on a learned model based on gradient boosting, regarding each piece of information input into the learned model, since the degree to which they contribute to the prediction is obtained on a logarithmic odds scale, there is a problem that the calculated numerical value is difficult to interpret.

[0006] Therefore, the present invention aims to solve these problems and provide a method for improving the quality of decision-making regarding child counseling. [Means for solving the problem]

[0007] In one aspect of the present invention, a business support method for supporting child consultation work is provided by a server terminal connected via a network to a user terminal related to a user of a child consultation center, wherein the control unit of the server terminal receives registration of child information relating to a child from the user terminal, receives registration of reception information for receiving consultations relating to the child associated with the child information from the user terminal, receives registration of risk assessment information for supporting decisions on the protection of the child associated with the reception from the user terminal, inputs the received child information, reception information and risk assessment information into a trained model based on gradient boosting, performs a risk assessment evaluation which includes calculating the degree to which the input information contributed to the prediction on a probability scale, and transmits the results of the risk assessment evaluation to the user terminal. [Effects of the Invention]

[0008] According to the present invention, it is possible to provide a method for improving the quality of decision-making regarding child counseling. [Brief explanation of the drawing]

[0009] [Figure 1] This is a block diagram showing a business support system according to the first embodiment of the present invention. [Figure 2] Figure 1 is a functional block diagram showing the server terminal 100. [Figure 3] Figure 1 is a functional block diagram showing the user terminal 200. [Figure 4] This figure shows an example of user data stored on server 100. [Figure 5] This figure shows an example of reception data stored in server 100. [Figure 6]This is an example of a flowchart relating to a business support method according to the first embodiment of the present invention. [Figure 7] This figure illustrates a method for calculating a prediction score according to a first embodiment of the present invention. [Figure 8] This figure illustrates a method for calculating the probability contribution to the recurrence probability according to the first embodiment of the present invention. [Figure 9] This is an example of displaying risk assessment evaluation results according to the first embodiment of the present invention. [Figure 10] This is another example of displaying risk assessment evaluation results according to the first embodiment of the present invention. [Modes for carrying out the invention]

[0010] Embodiments of the present invention will be described below with reference to the drawings. The embodiments described below are not intended to unduly limit the scope of the claims of this disclosure. Furthermore, not all components shown in the embodiments are necessarily essential components of this disclosure.

[0011] (Embodiment 1) <Structure> Figure 1 is a block diagram showing a business support system according to the first embodiment of the present invention. This system 1 consists of a user terminal 200 used by users such as staff of a child consultation center, a child consultation record system 300 that records and manages information related to child consultations, and a server terminal 100 that mediates between them. Here, all or some of the functions of the child consultation record system 300 may be provided in the server terminal 100, and if all functions are provided in the server terminal 100, the child consultation record system 300 may be unnecessary in this system 1.

[0012] The server terminal 100 and the user terminal 200 are connected via a network NW. The network NW consists of the Internet, intranet, wireless LAN (Local Area Network), WAN (Wide Area Network), etc.

[0013] The server terminal 100 provides applications to support the efficiency of operations to multiple user terminals 200A and 200B related to users such as staff of child welfare centers. It manages information registered from each of the user terminals 200A and 200B, and based on the registered information, it performs a risk assessment evaluation regarding the possibility of child abuse and provides the evaluation results. For example, it may be a general-purpose computer such as a workstation or personal computer, or it may be logically implemented by cloud computing. In this embodiment, for the sake of explanation, one server terminal is shown as an example, but it is not limited to this and there may be multiple terminals.

[0014] As described above, user terminals 200A and 200B are information processing devices such as personal computers and tablet terminals owned by users, such as staff of child guidance centers, who use applications provided by server terminal 100. However, they may also consist of smartphones, mobile phones, PDAs, etc. For the sake of explanation, user terminals 200A and 200B will be collectively referred to as user terminal 200 below.

[0015] In addition, this system is connected to the child consultation record system 300 via the network NW. Users who use the user terminal 200 can register various types of information related to children, including child information, with the server terminal 100 or the child consultation record system. The server terminal 100 can send and receive information to and from the child consultation record system 300, enabling data linkage. Here, the child consultation record system 300 is a system mainly for recording child consultations and issuing administrative documents. For example, it issues child numbers and reception numbers related to children, issues reception tickets and temporary protection decision notices, manages family information and burden amounts in cooperation with administrative information, and manages the progress of procedures. On the other hand, this system is a system mainly for supporting communication and decision-making with users, enabling input, viewing, and sharing of records inside and outside the child guidance center, conducting chat communication among child guidance center staff, registering and sharing photos of children, and simulating past temporary protection trends. As described above, the server terminal 100 and the child consultation record system 300 are connected via the network NW, and data linkage is performed with each other using, for example, a QR code, a child number, or a reception number as a key. Therefore, users do not need to input and register information for both the server terminal 100 and the child consultation record system 300. By registering information in one system, synchronization with the other system is possible. As described above, if all or some of the functions of the child consultation record system 300 are provided in the server terminal and the processing can be completed in the server terminal 100, it may be possible to eliminate data linkage using a QR code or the like.

[0016] In this embodiment, the system 1 includes a server terminal 100, a user terminal 200, and a child consultation record system 300. Although it will be described as a configuration in which a user or an applicant operates on the server terminal 100 using the user terminal 200 and the child consultation record system 300 respectively, the server terminal 100 may be configured as a stand-alone device and may have functions for a user or an applicant to operate on the server terminal itself.

[0017] FIG. 2 is a functional block configuration diagram of the server terminal 100 in FIG. 1. The server terminal 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

[0018] The communication unit 110 is a communication interface for communicating with the user terminal 200 and the child consultation record system 300 via the network NW. For example, communication is performed according to a communication protocol such as TCP / IP (Transmission Control Protocol / Internet Protocol) or a closed network.

[0019] The storage unit 120 stores programs for executing various control processes and each function in the control unit 130, input data, etc., and is composed of a RAM (Random Access Memory), a ROM (Read Only Memory), etc. Further, the storage unit 120 has a user data storage unit 121 for storing various data related to the user, a reception data storage unit 122 for storing various data related to reception, etc. Furthermore, the storage unit 120 can also temporarily store data communicated with the user terminal 200 and the child consultation record system 300. Note that a database (not shown) storing various data may be constructed outside the storage unit 120 or the server terminal 100.

[0020] The control unit 130 controls the overall operation of the server terminal 100 by executing programs stored in the memory unit 120, and is composed of a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), etc. The functions of the control unit 130 include an instruction reception unit 131 that receives input from the user terminal 200 or the child consultation record system 300, a user data management unit 132 that refers to and processes various data related to the user, a reception data management unit 133 that refers to and processes various data related to reception, and a risk assessment unit 134 that analyzes and performs an evaluation of the information entered by the user. The instruction reception unit 131, user data management unit 132, recruiter data management unit 133, and risk assessment unit 134 are started by programs stored in the memory unit 120 and executed by the server terminal 100, which is a computer (electronic computer).

[0021] The instruction receiving unit 131 receives instructions from the user terminal 200 via the communication unit 110 when the user makes a predetermined input via a user interface such as a screen displayed on the user terminal 200 through a web browser or application, which is provided by the server terminal 100. Alternatively, it receives information from the child consultation record system 300 via the communication unit 110 in response to a request from the server terminal 100 or the user terminal 200.

[0022] The user data management unit 132 manages and processes various data related to users (for example, child information, parent information, related party information, family group information, and related organization information, etc.).

[0023] The reception data management unit 133 manages and processes various data related to reception (for example, reception information, risk assessment information, survey information, photo information, simulation information, recommendation information, etc.).

[0024] The risk assessment unit 134 performs a process to assess the risk of child abuse based on information registered from the user terminal 200 (or the child consultation record system 300).

[0025] Figure 3 is a functional block diagram showing the user terminal 200 in Figure 1. The user terminal 200 comprises a communication unit 210, a display and operation unit 220, a storage unit 230, a camera 240, and a control unit 250.

[0026] The communication unit 210 is a communication interface for communicating with the server terminal 100 via the network NW, and communication is performed using a communication protocol such as TCP / IP.

[0027] The display operation unit 220 is a user interface used to display text, images, etc., in response to input data from the control unit 240, based on the user's input instructions. If the user terminal 200 is a personal computer, the display operation unit 220 consists of a display and a keyboard or mouse. If the user terminal 200 is a smartphone or tablet, the display operation unit 220 consists of a touch panel, etc. This display operation unit 220 is activated by a control program stored in the memory unit 230 and executed by the user terminal 200, which is a computer (electronic calculator). Through the display operation unit, the user can perform actions such as pressing keys on the keyboard, moving the cursor with a mouse, or tapping, swiping, and pinching on a touch panel in response to the aptitude test provided.

[0028] The memory unit 230 stores programs for executing various control processes and functions within the control unit 240, input data, etc., and is composed of RAM, ROM, etc. The memory unit 230 also temporarily stores the contents of communications with the server terminal 100.

[0029] Camera 240, for example, has the function of imaging parts of a child's body.

[0030] The control unit 250 controls the overall operation of the user terminal 200 by executing programs stored in the memory unit 230, and is composed of a CPU, GPU, etc.

[0031] Furthermore, the server terminal 100 may be configured to include display and operation functions, in which case the user terminal 200 may not be included.

[0032] Furthermore, since the functional configuration of the child consultation record system 300 is essentially the same as that of the server terminal 100 or the user terminal 200, we will omit the explanation.

[0033] Figure 4 shows an example of user data stored in server 100.

[0034] The user data 1000 shown in Figure 4 stores various data related to the user. In Figure 4, for the sake of explanation, an example of one user (a user identified by user ID "10001") is shown, but information for multiple users can be stored. Various data related to the user may include, for example, child information (child's name, ID, address, contact information such as email address, gender, age, school name, grade, homeroom teacher's name, attendance status, tag information, etc.), guardian information (guardian's name, ID, address, contact information, gender, etc.), related party information (related party's name, ID, address, contact information, gender, etc.), family group information (family group name, ID, description of the group name, group members (including guardians based on past marital relationships, common-law marriages, etc.)), related organization information (related organization name, ID, type (medical institution, police, educational institution, etc.), address, contact information), etc.

[0035] Figure 5 shows an example of reception data stored in server 100.

[0036] The reception data 2000 shown in Figure 5 stores various data related to reception. In Figure 5, for the sake of explanation, an example of one reception (a reception identified by reception ID "20001") is shown, but information for multiple receptions can be stored. Typically, receptions are registered in association with child information, etc., concerning the registered child. Various data related to reception include, for example, basic reception information (type of abuse (physical abuse, neglect, etc.), start date and time of response, etc.), risk assessment information (date and time of reception, person who entered the information, information at the time of notification receipt, items for considering emergency dispatch, whether or not it falls under limit rules (for example, whether or not the safety of the child cannot be confirmed, such as canceling a designated interview without notice or refusing a home visit, even though the need for guidance or support was communicated to the guardian in advance during legal action), attached images and / or wounds, information on psychological diagnosis and home conditions, decision-making results and / or safety confirmation results, items related to the implemented response, approver of the investigation record, etc.), investigation information (date and time of response, investigation title, minutes (investigation results (facts)), assessment, future The system can store information such as responses, risk assessment information (checklist registration (information obtained through the survey), attached images and / or information on injuries, psychological diagnosis and home conditions, next interview date and time, status in the survey completion dictionary, safety scale at the time of survey completion (input result as a subjective numerical value regarding the child's safety), response details, person who approved the survey record, etc.), photographic information (attached images and / or information on injuries, psychological diagnosis and home conditions), simulation information (overall risk (an indicator showing the tendency to be temporarily protected), past similar cases (information on 36 types of abuse), radar chart (a chart showing the balance of the degree of need for action, recurrence rate, number of days of action, etc.)), and recommendation information (recommendations and reference information for future responses).

[0037] <Processing flow> Referring to Figure 6, the processing flow of the business support method executed by System 1 of this embodiment will be described. This is an example of a flowchart relating to the business support method according to the first embodiment of the present invention.

[0038] To use this system 1, users (for example, staff at a child welfare center) access the server terminal 100 using their respective web browsers or applications on the user terminal 200. If it is the first time using the service, they register as a new user. If they already have a user account, they log in after undergoing the prescribed authentication, such as entering their ID and password, to make the service available. After this authentication, a predetermined user interface screen is provided via a website or application, and the user proceeds to step S101 shown in Figure 6. Figure 9 shows an example of the home screen of the application displayed on the user terminal 200. On this screen, users can perform the registration described below by selecting the registration menu.

[0039] First, as part of step S101, the instruction receiving unit 131 of the control unit 130 of the server terminal 100 receives registration of basic information such as child information from the user terminal 200 via the communication unit 110. The user data management unit 132 of the control unit 130 of the server terminal 100 stores the received basic information as user data 1000 in the user data storage unit 121 of the storage unit 120, associating it with the user ID. Here, if the user has registered the above basic information in the child consultation record system 300, they can also import the basic information registered in the child consultation record system 300 into the application provided by the server terminal 100 by reading a QR code with the camera built into the user terminal 200 and entering numbers such as the child number on the displayed screen.

[0040] Next, as part of step S102, the instruction receiving unit 131 receives registration of reception information from the user terminal 200. Here, reception refers to the reception of a child who requires a specific response. First, the user inputs basic information about the reception (type of abuse (physical abuse, neglect, etc.), start date and time of response, etc.) on the application screen displayed on the user terminal 200. The reception data management unit 133 of the control unit 130 of the server terminal 100 stores the received basic information as reception data 2000 in the reception data storage unit 122 of the storage unit 120, associating it with the reception ID. Here, if the user has registered the above reception information in the child consultation record system 300, they can also import the reception information registered in the child consultation record system 300 into the application provided by the server terminal 100 by reading a QR code with the camera built into the user terminal 200 and entering a number such as the child number on the displayed screen.

[0041] In conjunction with the reception information, the instruction reception unit 131 accepts registration of survey information from the user terminal 200, in no particular order, such as the date and time of response, survey title, minutes (survey results (facts)), assessment, and future actions; registration of photographic information such as attached images and / or information regarding wounds, psychological diagnosis, and home conditions; and subsequently, registration of risk assessment information such as checklist registration (information obtained through the survey), attached images and / or information regarding wounds, psychological diagnosis, and home conditions, next interview date and time, status in the survey completion dictionary, safety scale at the time of survey completion (input result as a subjective numerical value regarding the child's safety), response details, and the person who approved the survey record (for example, the date of reception). The system accepts information such as the time, the person who entered the information, information at the time of notification receipt, items for considering emergency work, items for considering temporary protection, whether or not the limit rules apply (for example, whether or not the safety of the child cannot be confirmed, such as the unauthorized cancellation of a designated interview or refusal of a home visit despite the need for guidance or support being communicated to the guardian in advance during legal action), attached images and / or information on injuries, psychological diagnosis and home conditions, decision-making results and / or safety confirmation results, items related to the implementation of the response, and the person who approved the investigation record). It can also accept input information entered by multiple users via a chat application. The reception data management unit 133 of the control unit 130 of the server terminal 100 stores the received basic information as reception data 2000 associated with the reception ID in the reception data storage unit 122 of the storage unit 120. Here, if the user has registered information associated with the above reception information in the child consultation record system 300, they can also import the information registered in the child consultation record system 300 into the application provided by the server terminal 100 by reading the QR code with the camera built into the user terminal 200 and entering numbers such as the child number on the displayed screen.

[0042] Here, the registration of the above-mentioned survey information is assumed to be an operation performed by staff within the child guidance center based on information obtained from staff members who are out on assignment outside the center; the registration of the above-mentioned photographic information and the above-mentioned risk assessment information is assumed to be an operation performed by staff members who are out on assignment outside the center to confirm the safety of children; and the above-mentioned chat communication is assumed to be an operation in which staff members who are out on assignment report the survey results and confirm the response methods sent by staff members inside the center. In this way, the series of registration information may be entered and accepted by multiple staff members both inside and outside the center.

[0043] Next, as part of the process in step S103, the risk assessment unit 134 of the control unit 130 performs a risk assessment evaluation regarding the possibility of child abuse based on the registered child's basic information, reception information, and risk assessment information associated with the reception information. Here, the server terminal 100 stores in the storage unit 130, input information (not shown), including past child basic information (age, gender, address (city / town)), reception information (type of abuse, reception time, reception category (new, re-report, re-reception)), and risk assessment information associated with the reception information (reception route, primary abuser, applicability to each item of the risk assessment), and output information, including past protection rates (an indicator showing the tendency to be temporarily protected), past similar cases (abuse is classified into 36 types, and the characteristics of the pattern closest to the current case are displayed; if there are past cases belonging to the same pattern, past case records are displayed), and a learning model generated by predicting information such as the degree of need for action, recurrence rate, and number of days of action using machine learning. Based on the learning model, output information is generated for the current input information.

[0044] In this embodiment, a learning model based on gradient boosting can be used. Boosting is a machine learning modeling technique that aims to build a new, highly general-purpose learner by using multiple weak learners. It is often used by combining multiple conditional branching algorithms called decision trees. More precisely, when creating a new decision tree as a boosting method, the results of the previous decision trees are used, and a decision tree algorithm is adopted that minimizes the error between the actual value and the predicted value. In other words, gradient boosting is a method that uses gradient descent to minimize the error between the actual correct answer and the prediction as a loss function. More specifically, a method called XGBoost can be used.

[0045] In XGBoost, a numerical value indicating the degree to which the input information contributed to the generation of the output information can be calculated on a log-odds scale based on the applicability / non-applicability of the items included in the input basic information and the reception information (for example, child's age, injuries / bruises on the head, face, and abdomen, number of items requiring temporary protection, fear / anxiety of returning home, complaint of child protection, details unknown in the initial investigation, signs of continued abuse, number of items requiring emergency dispatch, injuries / bruises on the child at the present time, etc.). However, when the numerical value generated on a log-odds scale is displayed as a risk assessment result, it has low intuitive interpretability for the user. Therefore, in this embodiment, in the conditional branching, a numerical value converted to a probability scale is calculated as the contribution, indicating the degree to which the input information contributed to the generation of the output information based on the applicability / non-applicability of the above items. In the log-odds space, the contribution can be calculated in any order because it is represented linearly, whereas in the probability space, the contribution is represented non-linearly, so the value of the contribution depends on the order of calculation, and the numerical value calculated in the probability space changes according to the calculation order. However, in this embodiment, calculating the contribution in a probability space makes the calculation process easier, and since the calculated value is expressed as a probability, it is easier for the user to interpret intuitively.

[0046] As shown in Figure 7, the method for calculating the contribution in the probability space involves starting from a baseline value and increasing or decreasing the numerical value according to whether the child's age, injuries / bruises on the head, face, or abdomen, the number of items requiring temporary protection, fear / anxiety of returning home, complaints for child protection, details unknown in the initial investigation, signs of continued abuse, the number of items requiring emergency dispatch, and whether the child currently has injuries / bruises, etc., are applicable or not, to calculate the final predicted score. In this example, the baseline value is 47.3%, and the numerical value is increased or decreased according to whether each item is applicable or not, ultimately resulting in a value of 3.4%.

[0047] Furthermore, the contribution calculated in the above probability space can be converted into an implementation rate. The numerical values ​​calculated in the above probability space do not necessarily represent the proportion of events that occur. For example, the predicted score calculated as the contribution (e.g., "1.0") may differ from the "implementation rate of temporary protection in the relevant score case" (e.g., 0.85). Therefore, in order to convert the predicted score from this machine learning method into an "implementation rate," an approximation transformation using the sigmoid function can be applied to the contribution in the probability space.

[0048] As shown in Figure 8, when the contribution value calculated in the probability space is converted to a probability contribution in terms of recurrence probability, for example, against a baseline value of 39.6%, the impact on the final recurrence probability is calculated to be 4% by adding or subtracting values ​​based on factors such as the child's age of 12, the presence of injuries / bruises on the head, face, and abdomen, the number of items requiring temporary protection being 3, the absence of fear / anxiety about returning home, the absence of a complaint for child protection, the lack of details in the initial investigation, the absence of signs of continued abuse, the number of emergency dispatches being 0, and the absence of injuries / bruises on the child at the present time.

[0049] Next, as part of step S104, the risk assessment unit 134 transmits the output information generated in the above step to the user terminal 200, and the output information is displayed in a predetermined format on the user interface screen of the application on the user terminal 200.

[0050] Figure 9 shows an example screen for outputting risk assessment evaluation results of a business support application, as displayed on the user's terminal. By selecting the "Simulation" tab on the application's personal page screen displayed on user terminal 200, the user is shown a radar chart illustrating the characteristics of the case using three indicators: overall risk (an indicator representing the tendency to require temporary protection), recurrence probability, response days, and degree of need for action, as well as a visualized screen of similar past cases, as shown in Figure 9. Here, a high value for overall risk indicates that similar cases have tended to require temporary protection in the past, supporting the user in judging the urgency from the perspective of whether or not to provide temporary protection. The radar chart also shows the balance of indicators such as degree of need for action (the probability of falling into a classification defined as a case requiring action by a specialized agency such as a child welfare center (e.g., 24 patterns) out of multiple abuse classifications (e.g., 36 patterns)), recurrence rate (the probability of recurrence in the relevant group of similar cases), and response days (the number of days required to conclude the case in the relevant group of cases). A large area on the radar chart indicates a high degree of need for action, a high recurrence rate, and a tendency for the case to take a long time to conclude. Past similar cases are classified into multiple types (e.g., 36 types), and the characteristics of the pattern that most closely matches the current case are displayed. If there are past cases belonging to the same pattern, the past case records are displayed. In this example, case 49, "Repeated physical abuse of a boy," is displayed, and it is understood that in this case, approximately half were reported by the municipality, and signs of continued abuse were observed in 44%. By checking past case records, users can get hints on how the case may change. In this embodiment, as an example of the risk assessment evaluation results, the reason for the predicted response period as a result of machine learning is described, and in this example screen, it is understood that the reason for predicting the response period as "243 days" is that, from the "standard value" of 363 days, 88 days were subtracted because the "decision regarding safety" was "at home," and 52 days were subtracted for "other reasons," resulting in the calculation of "243 days."Thus, according to this embodiment, users can specifically understand the basis for calculating items displayed as risk assessment results, including the number of days to respond. Furthermore, as shown in Figure 10, the basis for calculating the recurrence probability can also be shown as a risk assessment result. In this example screen, users can specifically understand that the recurrence probability was calculated as "69%" because, from the "standard value" of 36.3%, 10% was deducted because the child's age is "10 years old," and another 8% was deducted for "other reasons."

[0051] As described above, users can make a decision on whether or not temporary protection of a child is necessary by referring to the risk assessment evaluation results, as well as other registered survey information, photographic information, and information entered via chat communication.

[0052] As described above, according to this embodiment, users can access information about the child's situation in a timely manner from both inside and outside the child guidance center, and by referring to the results of risk assessment evaluations, etc., they can quickly and appropriately determine whether or not temporary protection of the child is necessary.

[0053] Although embodiments relating to the disclosure have been described above, these can be implemented in various other forms and can be carried out by various omissions, substitutions, and modifications. These embodiments and variations, as well as those with omissions, substitutions, and modifications, are included within the technical scope of the claims and their equivalents. [Explanation of symbols]

[0054] 1. Business support system: 100 server terminals, 110 communication unit, 120 storage unit, 130 control unit, 200 user terminals, 300 child consultation record system, NW network

Claims

1. A business support method for assisting child consultation work, provided by a server terminal that connects via a network to user terminals related to users of child consultation centers, The control unit of the server terminal is: The user terminal accepts registration of information about children. From the user terminal, registration of reception information for receiving consultations regarding the child, which is associated with the child's information, is received. From the user terminal, registration of risk assessment information for supporting the decision to protect the child, which is associated with the reception information, is received. The child information, registration information, and risk assessment information received are input into a trained model based on gradient boosting, and a risk assessment evaluation is performed, which includes calculating the degree to which the input information contributed to the prediction on a probability scale. The results of the risk assessment evaluation are transmitted to the user terminal. A method for performing the risk assessment assessment, comprising generating the results of the risk assessment assessment in such a way that a reference value expressed on a probability scale and a numerical value representing the degree to which each of the multiple factor items indicated in the input information contributed to the prediction, calculated based on the applicability / non-applicability of each of the multiple factor items, can be displayed in association with each other.

2. The method according to claim 1, wherein the reception information includes any one of the following: type of abuse, reception time, reception category, or a combination thereof.

3. The method according to claim 1, wherein the risk assessment information includes any or a combination of the following: date and time of receipt, person who entered the information, information at the time of notification receipt, items for considering emergency call-out, items for considering investigation protection, whether or not it falls under limit rules, attached images and / or wounds, information on psychological diagnosis and home conditions, decision-making results and / or safety confirmation results, items related to the corresponding implementation and the person who approves the investigation record.

4. The method according to claim 1, wherein the user terminal receives, in association with the reception information, images of the child and / or information regarding injuries, psychological diagnosis and home conditions.

5. The method according to claim 1, wherein performing the risk assessment evaluation includes increasing or decreasing a numerical value expressed on a probability scale relative to a reference value expressed on a probability scale, based on the applicability / non-applicability of each of the multiple factor items included in the input child information, reception information, and risk assessment information, and generating final output information.

6. The method according to claim 1, wherein performing the risk assessment includes calculating the degree of impact on the probability of recurrence based on a numerical value expressed on the probability scale.

7. The method according to claim 1, wherein performing the risk assessment assessment includes generating the results of the risk assessment assessment so that, in response to an increase or decrease in a numerical value expressed on a probability scale, at least one of the plurality of factor items and the increase or decrease value attributable to that item can be displayed as the reason for the increase or decrease.

8. A program that enables the execution of a business support method for assisting child consultation work on a server terminal that connects via a network to a user terminal related to a user of a child consultation center, In the control unit of the server terminal, The user terminal accepts registration of information about children. From the user terminal, registration of reception information for receiving consultations regarding the child, which is associated with the child's information, is received. From the user terminal, registration of risk assessment information for supporting the decision to protect the child, which is associated with the reception information, is received. The child information, registration information, and risk assessment information received are input into a trained model based on gradient boosting, and a risk assessment evaluation is performed, which includes calculating the degree to which the input information contributed to the prediction on a probability scale. The results of the risk assessment evaluation are transmitted to the user terminal. A program that performs the aforementioned risk assessment assessment, including generating the results of the risk assessment assessment in such a way that a reference value expressed on a probability scale and a numerical value representing the degree to which each of the multiple factor items indicated in the input information contributed to the prediction, calculated based on the applicability / non-applicability of each of the multiple factor items, can be displayed in association with each other.

9. An information processing system that supports child consultation work, provided by a server terminal connected via a network to user terminals related to users of child consultation centers, The control unit of the server terminal is: The user terminal accepts registration of information about children. From the user terminal, registration of reception information for receiving consultations regarding the child, which is associated with the child's information, is received. From the user terminal, registration of risk assessment information for supporting the decision to protect the child, which is associated with the reception information, is received. The child information, registration information, and risk assessment information received are input into a trained model based on gradient boosting, and a risk assessment evaluation is performed, which includes calculating the degree to which the input information contributed to the prediction on a probability scale. The results of the risk assessment evaluation are transmitted to the user terminal. An information processing system that performs the risk assessment assessment, including generating the results of the risk assessment assessment so that a reference value expressed on a probability scale and a numerical value representing the degree to which each of the multiple factor items indicated in the input information contributed to the prediction, calculated based on the applicability / non-applicability of each of the multiple factor items, can be displayed in association with each other.

Images