Information processing device, information processing method and information processing program

Abstract

To provide a technology that enables easy acquisition of information related to harassment, thereby enabling smooth support for measures against the harassment.SOLUTION: An information processing device disclosed herein manages information related to harassment. The information processing device includes a control unit that executes: acquiring consultation information related to circumstances of a case in which the harassment is suspected from a first user who wishes to have online consultation about the harassment via a predetermined interface; acquiring first answer information in which a primary determination is made as to whether the circumstances of the case included in the consultation information match the harassment by inputting the consultation information into a first pre-learning model constructed by learning using predetermined case data related to the harassment; and providing the first answer information to the first user.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program for managing information related to harassment.

Background Art

[0002] In recent years, various types of harassment such as power harassment, sexual harassment, and maternity harassment have become problems in organizations such as companies. When such harassment occurs, it may induce stress disorders such as mental illnesses (mental diseases and depression, etc.), mental burdens, maladaptive behaviors, and cognitive problems in the person who has suffered from it, or it may deteriorate the organizational environment. Therefore, the management departments of organizations, etc. are required to take measures against it.

[0003] Here, in order to take measures against harassment by raising awareness through education and enlightenment, setting up consultation desks, etc., it will incur a large social cost. Therefore, technologies for preventing and assisting in dealing with harassment using an information processing system, etc. have been proposed.

[0004] For example, Patent Document 1 discloses a harmful act detection system including a computer that observes and detects power harassment, sexual harassment, and harmful acts including bullying among people in a workplace environment. In this harmful act detection system, based on voice data obtained by inputting the voice around the target person, a word included therein, the target person, the feelings of others, etc. are acquired, and an index value related to the harmful act is calculated.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] Conventionally, in the management departments of organizations and the like, measures against harassment have been taken through education, raising awareness, setting up consultation desks, etc., but this has imposed a significant social cost. Also, even if a consultation desk is set up in an organization, users may hesitate to consult about embarrassing problems that are difficult to talk to people about, or may not be able to easily use such a consultation desk, resulting in a situation where the discovery of harassment is delayed.

[0007] On the other hand, according to the technology described in Patent Document 1, it seems possible to detect harmful acts such as power harassment, sexual harassment, and bullying in the workplace environment using an information processing system, and thus discover harassment at an early stage. However, since the technology performs observations and detections related to harmful acts using at least one of the voice data obtained by inputting the voices around the target person and the vital data of the target person, it is necessary to obtain these data, and it is not possible to directly and easily obtain information related to harassment. And there is still room for improvement in technologies that enable smooth support for measures against harassment.

[0008] An object of the present disclosure is to provide a technology that can easily obtain information related to harassment, thereby enabling smooth support for measures against harassment.

Means for Solving the Problems

[0009] The information processing apparatus of the present disclosure is an information processing apparatus that manages information related to harassment. And this information processing apparatus acquires, from a first user who wishes to have an online consultation regarding the harassment, consultation information which is information regarding the situation of a case in which the harassment is suspected, via a predetermined interface, and acquires first response information which is response information that can be automatically generated based on the consultation information and which is information in which it is primarily determined whether or not the situation of the case included in the consultation information matches the harassment, by inputting the consultation information into a first pre-trained model constructed by performing learning using predetermined case data related to the harassment, and provides the first response information to the first user via the interface, and includes a control unit that executes this.

[0010] According to the information processing apparatus described above, since consultation information as information regarding the situation of a case in which harassment is suspected can be directly and automatically acquired from a first user, information related to harassment can be easily acquired. Note that the interface may be a portal website configured to be able to provide a chat service by a chatbot.

[0011] And in the information processing apparatus described above, when it is primarily determined in the first response information that the situation of the case included in the consultation information matches the harassment, the control unit acquires, from a second user who can be specified based on the situation of the case as the person who committed the harassment, hearing information which is information regarding the act in which the harassment is suspected, and acquires second response information which is response information that can be automatically generated based on the consultation information and the hearing information and which is information in which it is secondarily determined whether or not the situation of the case included in the consultation information matches the harassment, by inputting the consultation information and the hearing information into the first pre-trained model, and may further execute providing the second response information to the first user and the second user via the interface.

[0012] Also, in this case, when it is secondarily determined in the second response information that the situation of the case included in the consultation information matches the harassment, the control unit may further execute: obtaining, by inputting the consultation information and the hearing information into a second pre-learning model constructed by learning using predetermined countermeasure data regarding the harassment, countermeasure information that can be automatically generated based on the consultation information and the hearing information and that is information regarding countermeasures against the harassment; and providing the countermeasure information to the first user and the second user via the interface. According to this, not only is it determined whether the situation of the case included in the consultation information matches the harassment, but also a countermeasure policy against the harassment is automatically generated. As a result, the cost for countermeasures against harassment is reduced, and smooth support for countermeasures against harassment becomes possible.

[0013] Furthermore, the control unit further executes causing the second pre-learning model to learn using first data regarding a pair of employment rules in a predetermined organization and a classification label regarding countermeasures against the harassment, and second data regarding a pair of personal information about a predetermined user and a classification label regarding countermeasures against the harassment, and may acquire the countermeasure information by inputting the employment rules in the organization to which the second user belongs and the personal information about the second user into the second pre-learning model. At this time, the personal information may include information regarding the contribution of the user to the organization. Then, when causing the second pre-learning model to learn, the control unit may adjust the classification label so that the countermeasures against the harassment are reduced as the degree of contribution of the user to the organization in the second data is greater. According to this, a countermeasure policy specialized for the organization to which the second user belongs and the second user is generated. Furthermore, it is also possible to generate a countermeasure policy that emphasizes the contribution and necessity of the second user in the organization to which the second user belongs. In addition, the control unit may further execute automatically generating a prevention guideline against the harassment based on the situation of the case included in the consultation information and the countermeasure information therefor, and updating the employment rules by adding the prevention guideline to the employment rules used to acquire the countermeasure information. This makes it easier to establish prevention against harassment in the organization.

[0014] In addition, the information processing apparatus of the present disclosure obtains, from a first user who wishes to have an online consultation regarding the harassment, consultation information which is information regarding the situation of a case in which the harassment is suspected, via a predetermined interface; obtains first response information which is response information that can be automatically generated based on the consultation information and which is information in which it is primarily determined whether or not the situation of the case included in the consultation information matches the harassment, by inputting the consultation information into a first pre-trained model constructed by performing learning using predetermined case data regarding the harassment; and provides the first response information to a personnel user who is engaged in personnel-related work in the organization to which the first user belongs. Thereby, the personnel user can quickly and accurately respond to the consultation information from the first user based on the first response information, and thus, the personnel user can start problem-solving before the situation deteriorates without being confused about the next action. Further, the information processing apparatus of the present disclosure obtains article information generated by a predetermined user at a predetermined timing before or after the user transmits the article information; obtains third response information which is response information that can be automatically generated based on the article information and which is information in which it is determined whether or not a word included in the article information matches the harassment, by inputting the article information into a third pre-trained model constructed by performing learning using predetermined word data regarding the harassment; and, when it is determined in the third response information that the word matches the harassment, provides a suggestion for improving the word to the user via a predetermined interface.

[0015] Further, the present disclosure can be grasped from the aspect of an information processing method by a computer. That is, the information processing method of the present disclosure is an information processing method for managing information related to harassment, in which a computer obtains, from a first user who wishes to have an online consultation regarding the harassment, consultation information that is information regarding the situation of a case in which the harassment is suspected, via a predetermined interface, and obtains first response information that is response information that can be automatically generated based on the consultation information and in which it is primarily determined whether the situation of the case included in the consultation information matches the harassment, by inputting the consultation information into a first pre-trained model constructed by performing learning using predetermined case data related to the harassment, and provides the first response information to the first user via the interface.

[0016] Further, the present disclosure can be grasped from the aspect of an information processing program. That is, the information processing program of the present disclosure is an information processing program for managing information related to harassment, which causes a computer to obtain, from a first user who wishes to have an online consultation regarding the harassment, consultation information that is information regarding the situation of a case in which the harassment is suspected, via a predetermined interface, and obtain first response information that is response information that can be automatically generated based on the consultation information and in which it is primarily determined whether the situation of the case included in the consultation information matches the harassment, by inputting the consultation information into a first pre-trained model constructed by performing learning using predetermined case data related to the harassment, and cause the computer to provide the first response information to the first user via the interface.

Advantages of the Invention

[0017] According to the present disclosure, information related to harassment can be easily obtained, thereby enabling smooth support for measures against harassment.

Brief Description of the Drawings

[0018]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Embodiments for Carrying Out the Invention

[0019] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. The configurations of the following embodiments are examples, and the present disclosure is not limited to the configurations of the embodiments.

[0020] <First Embodiment> The outline of the information processing system according to the first embodiment will be described with reference to FIG. 1. FIG. 1 is a diagram showing the schematic configuration of the information processing system according to this embodiment. The information processing system 100 according to this embodiment includes a network 200, a server 300, and user terminals 400. Note that the information processing system of the present disclosure is a system for managing information related to harassment, and the management of the information related to harassment is executed by the server 300. In the following description, among the users who use the information processing system 100, a user who wishes to have an online consultation regarding harassment is referred to as a first user, and a user who can be identified as the other party who has committed the harassment is referred to as a second user. And each of the first user and the second user may possess a user terminal 400.

[0021] The network 200 is, for example, an IP network. As long as the network 200 is an IP network, it may be wireless, wired, or a combination of wireless and wired. For example, if it is wireless communication, the user terminal 400 may access a wireless LAN access point (not shown) and communicate with the server 300 via a LAN or a WAN. Also, the network 200 is not limited to these examples, and may be, for example, a public switched telephone network, an optical fiber line, an ADSL line, a satellite communication network, or the like.

[0022] The server 300 is connected to the user terminals 400 via the network 200. In FIG. 1, for the sake of simplicity of explanation, one server 300 and four user terminals 400 are shown, but it goes without saying that these are not limited thereto.

[0023] The server 300 can be any electronic device as long as it is a computer device with processing capabilities for operations such as data acquisition, generation, and update, and processing operations. For example, it can be a personal computer, a server, a mainframe, or other electronic devices. That is, the server 300 can be configured as a computer having a processor such as a CPU or GPU, a main storage device such as a RAM or ROM, and an auxiliary storage device such as an EPROM, a hard disk drive, or a removable media. The removable media can be, for example, a USB memory or a disk recording medium such as a CD or DVD. The auxiliary storage device stores an operating system (OS), various programs, various tables, and the like.

[0024] Further, the server 300 may appropriately use SaaS (Software as a Service), PaaS (Platform as a Service), or IaaS (Infrastructure as a Service) provided by a cloud server without providing software, hardware, an OS, etc. dedicated to the information processing system 100 according to the present embodiment.

[0025] The user terminal 400 can be any electronic device such as a portable terminal owned by a user (which is the first user and the second user) who uses the information processing system 100. For example, it can be a portable terminal, a tablet terminal, a smartphone, a wearable terminal, a personal computer, or other terminal devices.

[0026] Next, based on FIG. 2, the components of the server 300 will be mainly described in detail. FIG. 2 is a diagram showing in more detail the components of the server 300 included in the information processing system 100 in the first embodiment, and also showing the components of the user terminal 400 that communicates with the server 300.

[0027] Server 300 has a communication unit 301, a storage unit 302, and a control unit 303 as functional units. It loads the program stored in the auxiliary storage device into the working area of the main storage device and executes it. By controlling each functional unit through the execution of the program, it can realize each function that meets the predetermined purpose in each functional unit. However, some or all of the functions may be realized by a hardware circuit such as an ASIC or an FPGA.

[0028] Here, the communication unit 301 is a communication interface for connecting the server 300 to the network 200. The communication unit 301 includes, for example, a network interface board or a wireless communication circuit for wireless communication. The server 300 is communicably connected to the user terminal 400 and other external devices via the communication unit 301.

[0029] The storage unit 302 is composed of a main storage device and an auxiliary storage device. The main storage device is a memory in which the program executed by the control unit 303 and the data used by the control program are expanded. The auxiliary storage device is a device in which the program executed in the control unit 303 and the data used by the control program are stored. A pre-learning model described later is stored in the storage unit 302 in advance. In addition, the storage unit 302 stores the data transmitted from the user terminal 400 or the like, and the consultation information and hearing information described later may be stored in the storage unit 302. Note that the server 300 can acquire the data transmitted from the user terminal 400 or the like via the communication unit 301.

[0030] The control unit 303 is a functional unit that controls the operations performed by the server 300. The control unit 303 can be realized by an arithmetic processing device such as a CPU. The control unit 303 further includes three functional units: a first acquisition unit 3031, a second acquisition unit 3032, and a provision unit 3033. Each functional unit may be realized by executing the stored program by the CPU.

[0031] The first acquisition unit 3031 acquires consultation information from the first user via a predetermined interface. Here, the above-mentioned consultation information is information regarding the situation of a case where harassment is suspected. The first user can input consultation information by accessing the above-mentioned interface using the user terminal 400. Then, the first acquisition unit 3031 acquires the consultation information by acquiring the information transmitted from the user terminal 400 of the first user via the above-mentioned interface, and stores this in the storage unit 302 of the server 300.

[0032] In addition, when it is primarily determined in the first response information described later that the situation of the case included in the consultation information matches harassment, the first acquisition unit 3031 acquires hearing information from the second user. Here, the above-mentioned hearing information is information regarding the act where harassment is suspected. The first acquisition unit 3031 acquires the hearing information, for example, by acquiring the information transmitted from the user terminal 400 of the second user, and stores this in the storage unit 302 of the server 300.

[0033] Here, the user terminal 400 in the present embodiment has a communication unit 401, an input / output unit 402, and a storage unit 403 as functional units. The communication unit 401 is a communication interface for connecting the user terminal 400 to the network 200, and is configured to include, for example, a network interface board or a wireless communication circuit for wireless communication. The input / output unit 402 is a functional unit for displaying information such as information transmitted from the outside via the communication unit 401, or inputting the information when transmitting information to the outside via the communication unit 401. The storage unit 403 is configured to include a main storage device and an auxiliary storage device, similar to the storage unit 302 of the server 300.

[0034] The input / output unit 402 further includes a display unit 4021, an operation input unit 4022, and an image / audio input / output unit 4023. The display unit 4021 has a function of displaying various information, and is realized by, for example, an LCD (Liquid Crystal Display) display, an LED (Light Emitting Diode) display, an OLED (Organic Light Emitting Diode) display, etc. The operation input unit 4022 has a function of receiving operation inputs from the user, and is specifically realized by soft keys or hard keys such as a touch panel. The image / audio input / output unit 4023 has a function of receiving inputs of images such as still images and moving images, and is specifically realized by a camera using an image sensor such as Charged-Coupled Devices (CCD), Metal-oxide-semiconductor (MOS), or Complementary Metal-Oxide-Semiconductor (CMOS). Also, the image / audio input / output unit 4023 has a function of receiving inputs and outputs of audio, and is specifically realized by a microphone and a speaker.

[0035] Then, the first user can access the above interface using the user terminal 400 configured as described above. Here, the server 300 may provide information for accessing the above interface to the user terminal 400 of the first user.

[0036] The second acquisition unit 3032 acquires the first response information by inputting the above consultation information into a pre-learning model to be described later. Here, the first response information is information that can be automatically generated based on the consultation information, and is information obtained by a primary determination as to whether the situation of the case included in the consultation information matches harassment. That is, the second acquisition unit 3032 can automatically generate the first response information based on the above consultation information and the pre-learning model. As will be described later, the second acquisition unit 3032 also acquires the second response information by inputting the above consultation information and hearing information into the pre-learning model to be described later. Here, the second response information is information that can be automatically generated based on the consultation information and the hearing information, and is information obtained by a secondary determination as to whether the situation of the case included in the consultation information matches harassment.

[0037] Then, the providing unit 3033 provides the first user with the above first response information and second response information via the above interface.

[0038] Note that the above interface is, for example, a portal website configured to be able to provide a chat service by a chatbot.

[0039] In recent years, an AI chatbot that outputs output text data, which is an appropriate response to input text data input using artificial intelligence or the like, has been put into practical use, and the above interface is a website for guiding the first user to a chat service by such a chatbot.

[0040] And for such an AI chatbot, the above pre-trained model is constructed. Here, the pre-trained model uses, for example, a neural network model generated by deep learning, and includes an input layer that receives the input of the above consultation information and hearing information, an intermediate layer (hidden layer) that extracts feature quantities from these data input to the input layer, and an output layer that outputs an identification result based on the feature quantities as an answer. Such a pre-trained model is constructed, for example, by performing supervised learning using teacher data that is a pair of information regarding the situation of a predetermined case data related to harassment and a classification label indicating whether or not it matches harassment. Specifically, a pair of a feature quantity and a label is given to a neural network, and the weights of the connections between neurons are tuned so that the output of the neural network becomes the same as the label. In this way, the features of the teacher data are learned, and a pre-trained model for estimating the result from the input is inductively obtained.

[0041] And by using such a pre-trained model, the above first response information and second response information can be automatically generated.

[0042] In this case, the AI chatbot, for example, receives the input of consultation information from the first user, inputs the consultation information to the above pre-trained model to obtain the first response information, and provides this first response information as a response to the input from the first user.

[0043] Note that the control unit 303 functions as the control unit according to the present disclosure by executing the processes of the first acquisition unit 3031, the second acquisition unit 3032, and the provision unit 3033.

[0044] Here, the operation flow of the information processing system 100 in the present embodiment will be described. FIG. 3 is a diagram illustrating the operation flow of the information processing system 100 in the present embodiment. In FIG. 3, the operation flow between the server 300 and the user terminal 400 in the information processing system 100 in the present embodiment, and the processes executed by the server 300 and the user terminal 400 are described. Note that the flow illustrated in FIG. 3 describes the operation flow between the server 300 and the user terminals 400 of the first user and the second user, and the processes executed by the server 300 and the user terminals 400 of the first user and the second user.

[0045] In the present embodiment, first, access information is input to the user terminal 400 of the first user (S101). Here, the above access information is information regarding access to a website for guiding the first user to a chat service by an AI chatbot, and is, for example, a user ID, a password, or the like. Then, the access information is transmitted from the user terminal 400 of the first user to the server 300. Then, the server 300 acquires the information transmitted from the user terminal 400 of the first user (S102).

[0046] When the server 300 acquires the access information from the first user, next, it provides a chat service to the first user (S103). Here, the above chat service is a chat service by an AI chatbot, and the server 300 can provide the chat service to the first user by transmitting information regarding a portal website configured to be able to provide the chat service to the user terminal 400 of the first user. Then, the user terminal 400 of the first user acquires this information (S104).

[0047] Here, FIG. 4 is a first diagram illustrating a screen displayed on an interface used for a chat service by a chatbot. The screen SC1 illustrated in FIG. 4 is displayed on the display unit 4021 of the user terminal 400 of the first user. On the screen SC1, an input field SC11 for obtaining a consultation matter from the first user and an answer field SC12 of the AI chatbot for the input from the first user are shown. Then, the first user can input, in the input field SC11, the situation of the case and a reply to the answer of the AI chatbot.

[0048] In the example shown in FIG. 4, as the situation of the case, being scolded excessively by the boss is input (FIG. 4(a)). In this case, the AI chatbot generates additional questions about the situation of the case in order to obtain more information from the first user (FIG. 4(b)). Then, as shown in FIG. 4(c), a reply from the first user will be further input. In this way, the server 300 provides a chat service to the first user and obtains information about the input case situation as consultation information.

[0049] Then, returning to FIG. 3(a), when the server 300 obtains the consultation information (S105) input to the user terminal 400 of the first user via the above chat service (S106), the server 300 generates first answer information (S107).

[0050] Here, FIG. 5 is a second diagram illustrating a screen displayed on an interface used for a chat service by a chatbot. In the example shown in FIG. 5, as the first answer information, it is generated that the above case situation may correspond to power harassment. As described above, the server 300 can obtain the first answer information by inputting the above consultation information into the pre-trained model.

[0051] Then, returning to FIG. 3, the above first answer information is provided to the first user via the chat service, and the user terminal 400 of the first user obtains this (S108).

[0052] Next, the server 300 determines whether the result of the primary determination included in the first response information matches harassment (S109). If an affirmative determination is made in S109, the server 300 proceeds to the processing after S110. If a negative determination is made in S109, the server 300 ends the execution of this flow.

[0053] If an affirmative determination is made in S109, next, the server 300 acquires hearing information from the second user. Here, the server 300 can, for example, send an interface for inputting hearing information to the user terminal 400 of the second user. Then, hearing information is input to the user terminal 400 of the second user (S110). Here, as described above, the hearing information is information regarding an act suspected of harassment from the second user, and is information including the response from the second user to the hearing items (the acts and statements from the second user to the first user, the place where it was done, the surrounding environment, etc.) for confirming the situation of the case included in the consultation information from the first user. Then, the server 300 acquires the information transmitted from the user terminal 400 of the second user (S111).

[0054] Then, the server 300 generates second response information based on the consultation information acquired in the process of S106 and the hearing information acquired in the process of S111 (S112). Specifically, the server 300 inputs the consultation information and the hearing information into the above-mentioned pre-trained model to obtain second response information in which it is secondarily determined whether the situation of the case included in the consultation information matches harassment. Then, this second response information is provided to the first user and the second user via an interface such as a chatbot, and the user terminals 400 of the first user and the second user acquire this (S113).

[0055] According to the processing flow described above, since the first user can start a consultation with the AI chatbot, it is possible to suppress as much as possible the situation where the first user hesitates to consult about a trouble that is difficult to talk to people about, and the first user can easily use the AI chatbot as a consultation window. In addition, since consultation information as information about the situation of a case suspected of harassment can be automatically obtained directly from the first user and using the AI chatbot, information about harassment can be easily obtained. And, it becomes possible to smoothly support measures against harassment by using the second response information generated based on the consultation information from the first user and the hearing information from the second user.

[0056] And, according to the information processing system 100 described above, information about harassment can be easily obtained, and thus it becomes possible to smoothly support measures against harassment.

[0057] <Second Embodiment> The second embodiment will be described with reference to FIGS. 6 and 7. In this embodiment, when the result of the secondary determination included in the second response information described in the description of the first embodiment above matches harassment, the server 300 acquires countermeasure information, which is information regarding measures against harassment. Then, the server 300 provides the above-mentioned countermeasure information to the first user and the second user via an interface such as a chatbot.

[0058] Here, the countermeasure information can be obtained by inputting the consultation information, the hearing information, the employment rules in the organization to which the second user belongs, and the personal information about the second user into a pre-trained model constructed by performing learning using predetermined countermeasure data regarding harassment. At this time, the server 300 can construct a pre-trained model in advance as follows.

[0059] FIG. 6 is a first diagram for explaining the identification result obtained from the input to the pre-trained model in the present embodiment and the neural network constituting the pre-trained model. In the present embodiment, a neural network model generated by deep learning is used as the pre-trained model. The pre-trained model 30 in the present embodiment includes an input layer 31 that receives inputs of consultation information, hearing information, employment rules, and personnel information, an intermediate layer (hidden layer) 32 that extracts harassment-related feature amounts from these data input to the input layer 31, and an output layer 33 that outputs an identification result based on the feature amounts. In the example of FIG. 6, the pre-trained model 30 has one intermediate layer 32, the output of the input layer 31 is input to the intermediate layer 32, and the output of the intermediate layer 32 is input to the output layer 33. However, the number of intermediate layers 32 is not limited to one layer, and the pre-trained model 30 may have two or more intermediate layers 32.

[0060] Also, according to FIG. 6, each of the layers 31 to 33 includes one or more neurons. For example, the number of neurons in the input layer 31 can be set according to the input image data. Also, the number of neurons in the output layer 33 can be set according to the countermeasures against harassment that is the identification result.

[0061] And the neurons of adjacent layers are appropriately connected, and a weight (connection weight) is set for each connection based on the result of machine learning. In the example of FIG. 6, each neuron is connected to all the neurons of the adjacent layer, but the connection of neurons is not limited to such an example and can be set as appropriate.

[0062] Such a pre-trained model 30 is constructed by performing supervised learning using, as teacher data, in addition to predetermined countermeasure data related to harassment (a pair of information on the harassment act and a classification label for the countermeasure therefor), first data related to a pair of employment rules in an organization such as a company and a classification label for countermeasures against harassment, and second data related to a pair of personal information about a user belonging to an organization such as a company and a classification label for countermeasures against harassment. Specifically, a pair of a feature amount and a label is given to a neural network, and the weights of the connections between neurons are tuned so that the output of the neural network becomes the same as the label. In this way, a pre-trained model for learning the features of the teacher data and estimating the result from the input is inductively obtained.

[0063] That is, according to the information processing system 100 of the present embodiment, not only is it determined whether the situation of the case included in the consultation information matches harassment, but also a countermeasure policy against the harassment is automatically generated. As a result, the cost for countermeasures against harassment is reduced, and smooth support for countermeasures against harassment becomes possible. And at this time, by taking into account the employment rules in the organization to which the second user belongs and the personal information about the second user as input information for countermeasures against harassment, a countermeasure policy specialized for the organization and the user is generated. Note that the server 300 may automatically generate a preventive guideline against harassment based on the situation of the case included in the consultation information acquired in the process of S106 described in the description of FIG. 3 above and the countermeasure information therefor. Here, the above preventive guideline is, for example, information on a pair of the above-described situation of the case and the countermeasure taken therefor, summarized for each situation of the case, and the server 300 can execute an update to add such information to the employment rules used to acquire the countermeasure information, thereby adding the preventive guideline to the employment rules. This makes it easier to establish prevention against harassment in the organization.

[0064] In the information processing system 100 of the present embodiment, when the server 300 constructs the above-described pre-trained model, in the above-described second data, the classification label may be adjusted so that the higher the degree of contribution of the user to the organization, the more the countermeasure against harassment is reduced.

[0065] FIG. 7 is a second diagram for explaining the identification result obtained from the input to the pre-trained model in the present embodiment and the neural network constituting the pre-trained model. In the pre-trained model 30 shown in FIG. 7, when supervised learning is performed using the second data as teacher data, as personnel information, for example, in addition to the personnel evaluation, the sales contribution is taken into account. And when the personnel evaluation is the same, the classification label is adjusted so that the higher the sales contribution, the more the countermeasure against harassment is reduced. Thereby, a countermeasure policy that emphasizes the contribution and necessity of the second user in the organization to which the second user belongs is generated.

[0066] According to the information processing system 100 described above, it is possible to smoothly support countermeasures against harassment.

[0067] <Third Embodiment> The third embodiment will be described below.

[0068] In the present embodiment, the server 300 acquires the text information generated by the user belonging to an organization such as a company. Here, the above-described text information is, for example, the information of the text included in the e-mail, and the server 300 acquires the text information at a predetermined timing before or after the user sends the e-mail. Note that the server 300 can acquire the above-described text information using a well-known technique.

[0069] Then, the server 300 obtains the third response information by inputting the above text information into the pre-trained model. Here, the third response information is information on whether the words included in the above text information match harassment. The pre-trained model uses, for example, a neural network model generated by deep learning, and has an input layer that accepts the input of the above text information, an intermediate layer (hidden layer) that extracts features from the data input to the input layer, and an output layer that outputs the identification result based on the features as a response. Such a pre-trained model is constructed, for example, by performing supervised learning using teacher data that is a set of information about a predetermined word data related to harassment and a classification label indicating whether or not it matches harassment. Specifically, a set of features and labels is given to the neural network, and the weights of the connections between neurons are tuned so that the output of the neural network is the same as the label. In this way, the features of the teacher data are learned, and a pre-trained model for estimating the result from the input is inductively obtained.

[0070] If the server 300 determines in the above third response information that the words included in the text information match harassment, it provides the user with a proposal for improving the words via an interface such as a chatbot.

[0071] The information processing system 100 described above can also smoothly support countermeasures against harassment.

[0072] <Other Variations> The above embodiments are merely examples, and the present disclosure can be appropriately modified and implemented without departing from the gist thereof. For example, the processes and means described in the present disclosure can be freely combined and implemented as long as no technical contradiction occurs.

[0073] Regarding the first response information described in the above embodiment description, the server 300 may provide it to a personnel user who is engaged in personnel-related work in the organization to which the first user belongs. As a result, the personnel user can quickly and accurately respond to the consultation information from the first user based on the first response information. Thus, the personnel user can start problem-solving before the situation worsens without hesitation about the next action.

[0074] Furthermore, the server 300 may automatically generate and provide necessary actions to the personnel user regarding predetermined management items related to harassment. Here, the above management items are "clarification, dissemination, and enlightenment of the content, policy, etc. of harassment", "stipulation and dissemination, and enlightenment of strict countermeasure policies and content for the perpetrator", "establishment of a consultation window", "appropriate response to consultations", "prompt and accurate confirmation of the facts", "implementation of appropriate consideration measures for the victim", "implementation of appropriate measures for the perpetrator", "implementation of recurrence prevention measures", "implementation of necessary measures according to the actual situation of the employer, pregnant workers, etc., such as improvement of the business system (only for harassment related to pregnancy, childbirth, etc.)", "implementation and dissemination of measures for protecting the privacy of the parties, etc.", "stipulation and dissemination, and enlightenment that disadvantageous treatment should not be carried out for reasons such as consultation and cooperation".

[0075] Also, the processing described as being performed by one device may be shared and executed by a plurality of devices. For example, the second acquisition unit 3032 may be formed in another arithmetic processing device. At this time, these arithmetic processing devices are preferably configured to be able to cooperate well. Also, the processing described as being performed by different devices may be executed by one device. In a computer system, how each function is realized by what hardware configuration (server configuration) can be flexibly changed.

[0076] The present disclosure can also be realized by supplying a computer program that implements the functions described in the above embodiments to a computer and causing one or more processors included in the computer to read and execute the program. Such a computer program may be provided to the computer by a non-transitory computer-readable storage medium connectable to the system bus of the computer, or may be provided to the computer via a network. The non-transitory computer-readable storage medium includes, for example, any type of disk such as a magnetic disk (e.g., a floppy (registered trademark) disk, a hard disk drive (HDD), etc.), an optical disk (e.g., a CD-ROM, a DVD disk, a Blu-ray disk, etc.), a read-only memory (ROM), a random access memory (RAM), an EPROM, an EEPROM, a magnetic card, a flash memory, an optical card, and any type of medium suitable for storing electronic instructions.

Explanation of Signs

[0077] 100 ··· Information processing system 200 ··· Network 300 ··· Server 301 ··· Communication unit 302 ··· Storage unit 303 ··· Control unit 400 ··· User terminal

Claims

1. An information processing apparatus for managing information related to harassment, comprising: obtaining, from a first user who wishes to have an online consultation regarding the harassment, consultation information which is information regarding the situation of a case in which the harassment is suspected, via a predetermined interface; obtaining first response information which is response information that can be automatically generated based on the consultation information and which is information obtained by inputting the consultation information into a first pre-trained model constructed by performing learning using predetermined case data related to the harassment, the information being such that a primary determination has been made as to whether or not the situation of the case included in the consultation information matches the harassment; providing the first response information to the first user via the interface; An information processing apparatus comprising a control unit that executes the above.

2. The control unit: when it is primarily determined in the first response information that the situation of the case included in the consultation information matches the harassment, obtaining hearing information which is information regarding an act in which the harassment is suspected, from a second user who can be identified based on the situation of the case as the person who committed the harassment; obtaining second response information which is response information that can be automatically generated based on the consultation information and the hearing information and which is information obtained by inputting the consultation information and the hearing information into the first pre-trained model, the information being such that a secondary determination has been made as to whether or not the situation of the case included in the consultation information matches the harassment; further executing providing the second response information to the first user and the second user via the interface; The information processing apparatus according to Claim 1.

3. The interface is a portal website configured to be able to provide a chat service by a chatbot. The information processing apparatus according to Claim 1 or Claim 2.

4. The control unit When it is secondarily determined in the second response information that the situation of the case included in the consultation information matches the harassment, the countermeasure information that can be automatically generated based on the consultation information and the hearing information and that is information regarding countermeasures against the harassment is input to a second pre-learning model constructed by performing learning using predetermined countermeasure data regarding the harassment, and obtained thereby; and further provides the countermeasure information to the first user and the second user via the interface. The information processing apparatus according to claim 2.

5. The control unit further performs learning of the second pre-learning model using first data regarding a pair of employment rules in a predetermined organization and a classification label regarding countermeasures against the harassment, and second data regarding a pair of personal information about a predetermined user and a classification label regarding countermeasures against the harassment; and obtains the countermeasure information by inputting the employment rules in the organization to which the second user belongs and the personal information about the second user to the second pre-learning model. The information processing apparatus according to claim 4.

6. The personal information includes information regarding the user's contribution to the organization. The control unit when performing learning of the second pre-learning model, adjusts the classification label in the second data such that the countermeasures against the harassment are reduced as the degree of the user's contribution to the organization is greater. The information processing apparatus according to claim 5.

7. The control unit Based on the situation of the case included in the consultation information and the corresponding countermeasure information, automatically generate prevention guidelines for the harassment, and update the employment rules by adding the prevention guidelines to the employment rules used to obtain the countermeasure information. The information processing apparatus according to claim 5.

8. An information processing apparatus for managing information related to harassment, obtaining, via a predetermined interface, consultation information which is information about the situation of a case in which the harassment is suspected, from a first user who wishes to conduct an online consultation regarding the harassment; obtaining first response information which is response information that can be automatically generated based on the consultation information and is information in which it is primarily determined whether or not the situation of the case included in the consultation information matches the harassment, by inputting the consultation information into a first pre-trained model constructed by performing learning using predetermined case data related to the harassment; providing the first response information to a personnel user who is engaged in personnel-related work in the organization to which the first user belongs; An information processing apparatus comprising a control unit that executes the above.

9. An information processing apparatus for managing information related to harassment, obtaining the text information generated by a predetermined user at a predetermined timing before or after the user transmits the text information; obtaining third response information which is response information that can be automatically generated based on the text information and is information in which it is determined whether or not the words included in the text information match the harassment, by inputting the text information into a third pre-trained model constructed by performing learning using predetermined word data related to the harassment; When it is determined in the third response information that the word matches the harassment, provide the user with a proposal for improving the word via a predetermined interface. An information processing apparatus including a control unit that executes .

10. An information processing method for managing information related to harassment, comprising: a computer obtaining, via a predetermined interface, consultation information which is information about the situation of a case in which the harassment is suspected, from a first user who wishes to have an online consultation regarding the harassment; obtaining first response information which is response information that can be automatically generated based on the consultation information and in which it is primarily determined whether the situation of the case included in the consultation information matches the harassment, by inputting the consultation information into a first pre-trained model constructed by performing learning using predetermined case data related to the harassment; providing the first user with the first response information via the interface; and executing the method.

11. An information processing program for managing information related to harassment, comprising: causing a computer to obtain, via a predetermined interface, consultation information which is information about the situation of a case in which the harassment is suspected, from a first user who wishes to have an online consultation regarding the harassment; to obtain first response information which is response information that can be automatically generated based on the consultation information and in which it is primarily determined whether the situation of the case included in the consultation information matches the harassment, by inputting the consultation information into a first pre-trained model constructed by performing learning using predetermined case data related to the harassment; to provide the first user with the first response information via the interface; and causing the computer to execute the above operations.

Images