Information processing device, control method, and control program

Abstract

This information processing device (100) is a device capable of chatting with a plurality of users. The information processing device (100) comprises: a communication unit (130) that receives chat data transmitted by a terminal used by a first user among a plurality of users; and a reply determination unit (150) that determines not to reply when an end degree, which is a degree at which the conversation ends and which is based on the chat data, is a predetermined threshold value or greater, and determines to reply when the end degree is less than the threshold value.

Description

Information processing device, control method, and control program

[0001] The present disclosure relates to an information processing device, a control method, and a control program.

[0002] For example, a technology has been proposed in which a user chats with a chat robot (see Patent Document 1).

[0003] Patent No. 6431993

[0004] Incidentally, there are cases where multiple users chat with an automatic reply device (e.g., a chat robot). When the above technology is used, the automatic reply device replies every time each of the multiple users chats. In other words, the automatic reply device always replies. If the automatic reply device always replies, the conversation becomes chaotic.

[0005] The purpose of this disclosure is to bring order to the conversation.

[0006] According to one aspect of the present disclosure, there is provided an information processing device capable of chatting with a plurality of users. The information processing device includes a communication unit that receives chat data transmitted from a terminal used by a first user of the plurality of users, and a response determination unit that determines not to make a response if a degree of completion, which indicates a degree to which a conversation has ended based on the chat data, is equal to or greater than a predetermined threshold, and determines to make a response if the degree of completion is less than the threshold.

[0007] According to the present disclosure, conversations can be organized.

[0008] FIG. 1 is a diagram showing a chat control system according to a first embodiment; FIG. 2 is a diagram showing hardware included in an information processing device according to the first embodiment; FIG. 3 is a block diagram showing functions of the information processing device according to the first embodiment; FIG. 4 is a flowchart showing an example of processing executed by the information processing device according to the first embodiment; FIG. 5 is a diagram showing a specific example of a chat screen according to the first embodiment; FIG. 6 is a block diagram showing functions of an information processing device according to a second embodiment; FIG. 7 is a flowchart showing an example of processing executed by the information processing device according to the second embodiment; FIG. 8 is a flowchart showing an example of processing executed by an information processing device according to a sixth embodiment; FIG. 9 is a diagram showing a specific example of a chat screen according to the sixth embodiment.

[0009] Hereinafter, an embodiment will be described with reference to the drawings.

[0010] Embodiment 1. Fig. 1 is a diagram showing a chat control system according to embodiment 1. The chat control system includes an information processing device 100 and terminals 200 to 202. The information processing device 100 and the terminals 200 to 202 communicate via a network. Note that Fig. 1 shows three terminals. The number of terminals is not limited to three.

[0011] The information processing device 100 is a device that executes the control method. The information processing device 100 provides a chat environment. The information processing device 100 may also be called an automatic reply device. The information processing device 100 has the function of a chat robot. The chat robot may also be called a chatbot.

[0012] Terminal 200 is a terminal used by user 1. Terminal 201 is a terminal used by user 2. Terminal 202 is a terminal used by user 3. Note that any one of users 1 to 3 is also referred to as a first user.

[0013] The terminals 200 to 202 are PCs (Personal Computers), smartphones, tablet terminals, etc. The terminals 200 to 202 can chat in a chat environment provided by the information processing device 100. In this way, multiple terminals can chat in the chat environment. Furthermore, the information processing device 100 can participate in chats as a chat robot.

[0014] Furthermore, the information processing device 100 may provide a chat service in the metaverse to the terminals 200 to 202. For example, in the metaverse, each user logs in to each avatar. Then, each user chats via each avatar. For example, when the information processing device 100 participates in a chat, the information processing device 100 (i.e., a chat robot) logs in to an avatar. The chat robot chats via the avatar. The metaverse is also called a virtual space.

[0015] Next, the hardware of the information processing device 100 will be described. Fig. 2 is a diagram showing the hardware of the information processing device of embodiment 1. The information processing device 100 is also called a computer. The information processing device 100 has a processor 101, a volatile storage device 102, and a non-volatile storage device 103.

[0016] The processor 101 controls the entire information processing device 100. For example, the processor 101 is a central processing unit (CPU) or a field programmable gate array (FPGA). The processor 101 may be a multiprocessor. The information processing device 100 may also include a processing circuit.

[0017] The volatile storage device 102 is a main storage device of the information processing device 100. For example, the volatile storage device 102 is a random access memory (RAM). The nonvolatile storage device 103 is an auxiliary storage device of the information processing device 100. For example, the nonvolatile storage device 103 is a hard disk drive (HDD) or a solid state drive (SSD).

[0018] Next, a description will be given of the functions of the information processing device 100. Fig. 3 is a block diagram showing the functions of the information processing device of embodiment 1. The information processing device 100 has a storage unit 110, a management unit 120, a communication unit 130, a reading time calculation unit 140, a response determination unit 150, a sentence generation unit 160, and an input time calculation unit 170.

[0019] The storage unit 110 may be realized as a storage area secured in the volatile storage device 102 or the non-volatile storage device 103. The storage unit 110 may also be called a memory. Some or all of the management unit 120, communication unit 130, reading time calculation unit 140, reply determination unit 150, sentence generation unit 160, and input time calculation unit 170 may be realized by a processing circuit. Furthermore, some or all of the management unit 120, communication unit 130, reading time calculation unit 140, reply determination unit 150, sentence generation unit 160, and input time calculation unit 170 may be realized as program modules executed by the processor 101. For example, the program executed by the processor 101 is also called a control program or a control program product. For example, the control program is recorded on a recording medium.

[0020] The storage unit 110 stores various information, such as chat history.

[0021] The management unit 120 manages chat data for each thread. When determining the thread to which the chat data belongs, the management unit 120 may perform text analysis on the chat data. The management unit 120 may inquire of a generating AI (Artificial Intelligence) about the thread to which the chat data belongs. The management unit 120 may also determine the thread to which the chat data belongs using latent dirichlet allocation, probabilistic latent semantic indexing, or the like. The management unit 120 may manage the relationship between the chat data and the chat data of replies to the chat data.

[0022] The communication unit 130 receives chat data. For example, the communication unit 130 receives chat data from the terminal 200.

[0023] The reading time calculation unit 140 calculates the reading time based on the chat data. The reading time is calculated so that the information processing device 100 behaves like a person. In other words, assuming that the information processing device 100 is a person, the reading time is the time it takes for the information processing device 100 to read the chat data. For example, the reading time calculation unit 140 calculates the reading time using equation (1). Note that the constant is, for example, 3 seconds.

[0024] Reading time = number of characters in chat data / constant ... (1)

[0025] The reading time calculation unit 140 may calculate the reading time based on Shannon's information entropy, the number of new characters in the chat data, the difficulty of the meaning of the chat content, or the like. Furthermore, the reading time calculation unit 140 may vary the reading time even if the number of characters remains the same. For example, the reading time calculation unit 140 may further add a random number to equation (1). This changes the reading time even if the number of characters remains the same. In this way, varying the reading time expresses human-likeness.

[0026] The reply determination unit 150 waits for the reading time. The reply determination unit 150 determines whether to make a reply based on the chat data. For example, the reply determination unit 150 analyzes the chat data. The reply determination unit 150 evaluates the degree of completion, which is the degree to which the conversation is completed, based on the analysis results. For example, if the chat data is "Let's stop talking about this topic," the reply determination unit 150 evaluates the degree of completion as high. The reply determination unit 150 may also evaluate the degree of completion as high if the chat data contains words used when a conversation is completed. The reply determination unit 150 may also have an AI evaluate the degree of completion of the conversation. For example, if the reply determination unit 150 inputs the chat data to the AI, the AI ​​outputs the degree of completion. The reply determination unit 150 may evaluate the degree of completion using the chat history. For example, the reply determination unit 150 evaluates the degree of completion from the content of the chat data, taking the chat history into consideration. The reply determination unit 150 may also evaluate the degree of completion using a summary of the chat history.

[0027] The reply determination unit 150 determines not to reply if the degree of completion based on the chat data is equal to or greater than a predetermined threshold. The reply determination unit 150 determines to reply if the degree of completion is less than the threshold. Note that the threshold may be changed as appropriate. The reply determination unit 150 may also perform reply determination for each thread.

[0028] When it is determined that a reply should be made, the sentence generation unit 160 generates a reply content for the chat data. For example, the sentence generation unit 160 generates a reply content for the chat data based on the analysis result of the chat data. The sentence generation unit 160 may also generate a reply content for the chat data using a database. The sentence generation unit 160 may request a generation AI to generate a reply content for the chat data. For example, the sentence generation unit 160 requests the generation AI to generate a reply content based on the chat history or a summary of the chat history and the chat data.

[0029] The sentence generation unit 160 may generate a reply content for chat data taking into consideration the role, situation, or constraint. For example, assume that a chat is taking place in the metaverse and the information processing device 100 (i.e., a chat robot) is logged in as a spectator avatar. That is, assume that the chat robot plays the role of the spectator. The sentence generation unit 160 generates a reply content so that the spectator would reply. Also, for example, if the metaverse space is a stadium, the sentence generation unit 160 generates a reply content taking into consideration the situation of the stadium or the progress of a game being played in the stadium. Furthermore, the constraints include prohibiting prohibited phrases, content that offends people, etc. When requesting the generation AI to generate a reply content, the sentence generation unit 160 may request the generation AI to generate a reply content taking into consideration the role, situation, or constraint.

[0030] The input time calculation unit 170 calculates the input time based on the response content. The input time is calculated so that the information processing device 100 behaves like a person. In other words, assuming that the information processing device 100 is a person, the input time is the time it takes for the information processing device 100 to write the response content. For example, the input time calculation unit 170 calculates the input time using equation (2). Note that the constant is, for example, 2 seconds.

[0031] Input time = number of characters in response content / constant ... (2)

[0032] The input time calculation unit 170 may calculate the input time based on Shannon's information entropy, the number of new characters in the response content, the difficulty of the meaning of the response content, or the like. Furthermore, the input time calculation unit 170 may vary the input time even if the number of characters remains the same. For example, the input time calculation unit 170 further adds a random number to equation (2). This changes the input time even if the number of characters remains the same. In this way, varying the input time allows for a more human-like appearance.

[0033] The communication unit 130 waits for the input time. The communication unit 130 outputs the reply content. For example, the communication unit 130 transmits the reply content to multiple terminals corresponding to multiple users participating in the chat. As a result, each of the multiple terminals adds the reply content to a chat screen. If the information processing device 100 manages the chat screen, the communication unit 130 adds the reply content to the chat screen. If a chat is taking place in the metaverse, the communication unit 130 adds the reply content to the chat screen displayed in the metaverse space.

[0034] Next, the processing executed by the information processing device 100 will be described using a flowchart. FIG. 4 is a flowchart showing an example of the processing executed by the information processing device of embodiment 1. (Step S11) The communication unit 130 receives chat data. (Step S12) The reading time calculation unit 140 calculates the reading time based on the chat data. (Step S13) The reply determination unit 150 waits for the reading time. (Step S14) The reply determination unit 150 determines whether or not to reply based on the chat data. If a reply will be made, the processing proceeds to step S15. If a reply will not be made, the processing ends. (Step S15) The sentence generation unit 160 generates reply content from the chat data. (Step S16) The input time calculation unit 170 calculates the input time based on the reply content. (Step S17) The communication unit 130 waits for the input time. (Step S18) The communication unit 130 outputs the reply content.

[0035] Next, a specific example of a chat screen is shown. FIG. 5 is a diagram showing a specific example of a chat screen in embodiment 1. For example, the communication unit 130 receives chat data "I'm worried. Are there any shops that can repair my air conditioner?" from the terminal 202. The reply determination unit 150 evaluates the degree of completion as low based on the chat data. Therefore, the reply determination unit 150 determines that a reply should be made. The sentence generation unit 160 generates the reply content based on the chat data. The communication unit 130 waits for the input time, and then transmits the reply content to the terminals 200 to 202. As a result, the terminals 200 to 202 add the reply content to the chat screen.

[0036] If the chat robot always replies, the conversation will become disorganized. For example, after User 1 chats, the chat robot replies. After User 2 chats, the chat robot replies. In this way, if the chat robot always replies, the conversation will become disorganized.

[0037] According to the first embodiment, the information processing device 100 determines whether or not to make a reply. Therefore, there are cases where the information processing device 100 does not make a reply. Therefore, the information processing device 100 can keep the conversation in order.

[0038] If the chat robot receives chat data and immediately replies, the conversation will not sound human-like. Therefore, the information processing device 100 waits for the reading time and the input time. As a result, the information processing device 100 can realize a human-like conversation.

[0039] Variation of the First Embodiment The information processing device 100 waits for the reading time. The communication unit 130 may receive new chat data before the reading time ends. In this case, the reading time is updated. The update process will be described below.

[0040] When new chat data is received, the reading time calculation unit 140 calculates a new reading time based on the new chat data. The calculation method is as described above. The reading time calculation unit 140 updates the reading time to the sum of the remaining reading time calculated previously and the new reading time. For example, the reading time calculated previously is 20 seconds. 15 seconds later, the communication unit 130 receives new chat data. The reading time calculation unit 140 calculates a new reading time of "10 seconds." The reading time calculation unit 140 updates the reading time to the sum (15 seconds) of the remaining reading time calculated previously (5 seconds = 20 seconds - 15 seconds) and the new reading time (10 seconds). The response determination unit 150 waits for the reading time (15 seconds).

[0041] In this way, when new chat data is received, the information processing device 100 waits while taking the new chat data into consideration, thereby enabling the information processing device 100 to behave like a human.

[0042] Furthermore, when new chat data is received, the reply determination unit 150 determines whether or not to reply based on the new chat data. Specifically, if the degree of completion based on the new chat data is equal to or greater than the threshold, the reply determination unit 150 determines not to reply. If the degree of completion is less than the threshold, the reply determination unit 150 determines to reply. If a reply is to be made, the sentence generation unit 160 generates the content of the reply. The sentence generation unit 160 may generate the content of the reply based on the previous chat data, or may generate the content of the reply based on the new chat data.

[0043] Second Embodiment Next, a second embodiment will be described. In the second embodiment, differences from the first embodiment will be mainly described. In the second embodiment, descriptions of commonalities with the first embodiment will be omitted. In the second embodiment, a case where the input time is adjusted will be described.

[0044] 6 is a block diagram showing the functions of the information processing device of embodiment 2. The information processing device 100 further includes an adjustment unit 180. Part or all of the adjustment unit 180 may be realized by a processing circuit. Alternatively, part or all of the adjustment unit 180 may be realized as a program module executed by the processor 101.

[0045] It is said that the normal response time for a person in a chat is about 20 seconds. If the waiting time is long (i.e., if a user participating in a chat waits for 20 seconds or more), the user will feel stressed. Therefore, the information processing device 100 executes the following process.

[0046] First, the adjustment unit 180 calculates the discomfort level using formula (3). Note that "20" in formula (3) is the person's normal chat response time. "20" in formula (3) may be changed. Note that the person's normal chat response time is acquired by the adjustment unit 180. For example, the adjustment unit 180 acquires the person's normal chat response time from the storage unit 110. The adjustment unit 180 may acquire the person's normal chat response time from an external device. The external device is a device that exists outside the information processing device 100. For example, the external device is a cloud server, an external memory, etc. Illustration of the external device is omitted.

[0047] Discomfort level = input time + reading time - 20 ... (3)

[0048] The adjustment unit 180 may calculate the discomfort level using equation (4). Note that the constant is 3, for example.

[0049] Discomfort level = input time + reading time - (1200 / completion level) + number of new chat data received before the reading time has elapsed × constant ... (4)

[0050] If the discomfort level is greater than a predetermined threshold, the adjustment unit 180 adjusts the input time to a value obtained by subtracting the reading time from the normal chat response time for a person. For example, the normal chat response time for a person is 20 seconds. The reading time is 10 seconds. The adjustment unit 180 adjusts the input time to 10 seconds (= 20 seconds - 10 seconds). If the discomfort level is equal to or less than the threshold, the adjustment unit 180 does not adjust the input time. Note that the discomfort level may be calculated for each thread.

[0051] According to the second embodiment, the information processing device 100 can prevent users participating in a chat from feeling stressed.

[0052] Variation of Embodiment 2 The adjustment unit 180 acquires the personality or current emotion of the user of the terminal that sent the received chat data. For example, the adjustment unit 180 acquires the personality of the user from the storage unit 110 or an external device. For example, the personality of the user may be an angry personality, a calm personality, or the like. The current emotion of the user is analyzed by the information processing device 100 or an external device. For example, the information processing device 100 or the external device acquires an image, video, or chat data of the user, and analyzes the current emotion of the user based on the image, video, or chat data of the user. The adjustment unit 180 acquires the current emotion of the user, which is the analysis result. For example, the current emotion may be anger, bad mood, or the like.

[0053] If the user's personality is one that feels unpleasant, or if the current emotion is an unpleasant emotion, the adjustment unit 180 subtracts a predetermined value from the adjusted input time. For example, assume that the user's personality is one that feels angry easily. The normal chat response time for a person is 20 seconds. The reading time is 10 seconds. The predetermined value is 3 seconds. The adjustment unit 180 adjusts the input time to 10 seconds (= 20 seconds - 10 seconds). The adjustment unit 180 subtracts the value "3 seconds" from the adjusted input time of "10 seconds." As a result, the input time becomes 7 seconds. The communication unit 130 waits for 7 seconds.

[0054] The adjustment unit 180 may also calculate the emotion level based on the current emotion. The adjustment unit 180 may also calculate the discomfort level using equation (5). Note that the constant is 3, for example.

[0055] Displeasure level = input time + reading time - (1200 / completion level + emotional level) + number of new chat data received before the reading time has elapsed × constant ... (5)

[0056] Here, if the user has a personality that makes them feel uncomfortable or if the user's current emotion is an unpleasant emotion, it is desirable that the input time be short. Therefore, the information processing device 100 shortens the input time. Thus, the information processing device 100 can reduce the discomfort felt by the user.

[0057] Embodiment 3 Next, embodiment 3 will be described. In embodiment 3, differences from embodiments 1 and 2 will be mainly described. Furthermore, in embodiment 3, descriptions of matters common to embodiments 1 and 2 will be omitted.

[0058] After the reply content is generated, the reply determination unit 150 acquires the chat history. For example, the reply determination unit 150 acquires the chat history from the storage unit 110. The chat history may be stored in an external device. If the chat history is stored in an external device, the reply determination unit 150 acquires the chat history from the external device.

[0059] The reply determination unit 150 uses the chat history to determine whether the reply content or content similar to the reply content has already been output. If the reply content or content similar to the reply content has already been output, the reply determination unit 150 determines not to make a reply.

[0060] The process of detecting content similar to the reply content will be described. The reply determination unit 150 searches the chat history for chat content containing the words contained in the reply content. The reply determination unit 150 compares the reply content with the searched chat content and calculates the similarity. The reply determination unit 150 may have AI perform the calculation of the similarity. If the similarity is equal to or greater than a threshold, the reply determination unit 150 detects the chat content as similar to the reply content. Alternatively, if the similarity is equal to or greater than a threshold, the reply determination unit 150 may generate a random number, and if the random number is equal to or greater than the threshold, detect the chat content as similar to the reply content. The reply determination unit 150 may calculate the similarity for each thread.

[0061] Next, the processing executed by the information processing device 100 will be described using a flowchart. Fig. 7 is a flowchart showing an example of the processing executed by the information processing device of embodiment 2. The processing in Fig. 7 differs from the processing in Fig. 4 in that step S15a is executed. Therefore, step S15a will be described in Fig. 7. Further, description of the processing other than step S15a will be omitted.

[0062] (Step S15a) The reply determination unit 150 acquires the chat history. The reply determination unit 150 uses the chat history to determine whether the reply content or content similar to the reply content has already been output. If the reply content or content similar to the reply content has already been output, the process ends. If the reply content or content similar to the reply content has not been output, the process proceeds to step S16.

[0063] According to the third embodiment, the information processing device 100 can prevent similar content from being output.

[0064] If a reply content or content similar to the reply content has already been output, the sentence generation unit 160 may generate chat content for the new topic. For example, the sentence generation unit 160 may refer to the chat history to generate chat content for the new topic. The sentence generation unit 160 may also request a generation AI to generate chat content for the new topic. The sentence generation unit 160 may generate chat content for the new topic for each thread. The input time calculation unit 170 calculates the input time based on the chat content for the new topic. The communication unit 130 waits for the input time. The communication unit 130 outputs the chat content.

[0065] Embodiment 4 Next, embodiment 4 will be described. In embodiment 4, differences from embodiments 1 to 3 will be mainly described. Furthermore, in embodiment 4, descriptions of matters common to embodiments 1 to 3 will be omitted.

[0066] After the reply determination unit 150 determines based on the chat data that a reply will not be made (e.g., No in step S14 of FIG. 4 ), the sentence generation unit 160 generates chat content on a new topic if no new chat data is received for a predetermined time. After the communication unit 130 outputs the reply content (i.e., after a reply is made), the sentence generation unit 160 may generate chat content on a new topic if no new chat data is received for a predetermined time. For example, the sentence generation unit 160 references the chat history to generate chat content on a new topic. The sentence generation unit 160 may also generate chat content on a new topic using a database. The sentence generation unit 160 may also request a generation AI to generate chat content on a new topic. The sentence generation unit 160 may generate chat content on a new topic for each thread. The communication unit 130 outputs the chat content. For example, the communication unit 130 transmits the chat content to multiple terminals corresponding to multiple users participating in the chat. When the information processing device 100 manages a chat screen, the communication unit 130 adds the chat content to the chat screen. When a chat is taking place in the metaverse, the communication unit 130 adds the chat content to the chat screen displayed in the metaverse space.

[0067] According to the fourth embodiment, the information processing device 100 can make the conversation more lively.

[0068] Fifth Embodiment Next, a fifth embodiment will be described. In the fifth embodiment, differences from the fourth embodiment will be mainly described. Furthermore, in the fifth embodiment, descriptions of the commonalities between the fourth embodiment and the fifth embodiment will be omitted.

[0069] When generating chat content on a new topic, the sentence generation unit 160 generates the chat content on the new topic taking into account the situation or constraints of the metaverse space. For example, if a chat is taking place in the metaverse and the metaverse space is a stadium, the sentence generation unit 160 generates the chat content on the new topic taking into account the situation of the stadium or the sport being played in the stadium. In addition, the constraints include prohibitions on prohibited words, content that offends people, etc. When requesting the generation AI to generate chat content on a new topic, the sentence generation unit 160 may request the generation AI to generate the chat content on the new topic taking into account the situation or constraints of the metaverse space.

[0070] According to the fifth embodiment, the information processing device 100 can provide chat content that takes into account the situation or constraints of the metaverse space.

[0071] Sixth Embodiment Next, a sixth embodiment will be described. In the sixth embodiment, differences from the first to fifth embodiments will be mainly described. In the sixth embodiment, descriptions of the commonalities between the first to fifth embodiments will be omitted.

[0072] Fig. 8 is a flowchart showing an example of processing executed by the information processing device of embodiment 6. The processing in Fig. 8 differs from the processing in Fig. 4 in that step S16a is executed. Therefore, step S16a will be described in Fig. 8. Description of processing other than step S16a will be omitted.

[0073] (Step S16a) The communication unit 130 outputs information indicating that writing is in progress and the input time. For example, the communication unit 130 transmits the information indicating that writing is in progress and the input time to multiple terminals corresponding to multiple users participating in the chat. If the information processing device 100 manages the chat screen, the communication unit 130 adds the information indicating that writing is in progress and the input time to the chat screen. If a chat is taking place in the metaverse, the communication unit 130 adds the information indicating that writing is in progress and the input time to the chat screen displayed in the metaverse space.

[0074] Next, an example of a chat screen is shown. FIG. 9 is a diagram showing a specific example of a chat screen according to the sixth embodiment. FIG. 9 shows a case where the information processing device 100 replies after user 3. For example, in step S16, the input time is calculated to be 10 seconds. For example, the communication unit 130 transmits information indicating that writing is in progress and the input time of "10 seconds" to multiple terminals corresponding to multiple users participating in the chat. As a result, the information indicating that writing is in progress and the input time of "10 seconds" are displayed on the chat screen.

[0075] In some cases, the chat screen does not display the waiting time and only displays that a message is being posted. In such cases, the user feels stressed because they do not know how long they have to wait.

[0076] According to the sixth embodiment, the waiting time (10 seconds in the case of FIG. 9) is displayed on the chat screen. This allows users participating in the chat to know the time it will take to post. Therefore, the information processing device 100 can prevent users from feeling stressed.

[0077] The embodiments and modifications thereof are merely examples, and various modifications are possible within the scope of the present disclosure. Furthermore, the features of the embodiments and modifications thereof can be combined with each other as appropriate.

[0078] 100 Information processing device, 101 Processor, 102 Volatile storage device, 103 Non-volatile storage device, 110 Storage unit, 120 Management unit, 130 Communication unit, 140 Reading time calculation unit, 150 Response determination unit, 160 Sentence generation unit, 170 Input time calculation unit, 180 Adjustment unit, 200 to 202 Terminals.

Claims

1. An information processing device capable of chatting with multiple users, comprising: a communication unit that receives chat data sent by a terminal used by a first user of the multiple users; and a response determination unit that determines not to reply if a degree of completion, which indicates the degree to which a conversation has ended based on the chat data, is equal to or greater than a predetermined threshold, and determines to reply if the degree of completion is less than the threshold.

2. An information processing device as described in claim 1, further comprising: a reading time calculation unit that calculates a reading time based on the chat data; a sentence generation unit that, when it is determined that a reply will be made, executes a process of generating a reply content of the chat data or a process of requesting a generation AI (Artificial Intelligence) to generate the reply content; and an input time calculation unit that calculates an input time based on the reply content, wherein the reply determination unit waits for the reading time and makes the determination, and the communication unit waits for the input time and outputs the reply content.

3. The information processing device according to claim 2, wherein the sentence generation unit executes a process of generating the reply content taking into consideration the role of the information processing device in the virtual space in which the chat is taking place, the situation of the virtual space, or constraints, or a process of requesting the generation AI to generate the reply content taking into consideration the role, the situation, or the constraints.

4. An information processing device as described in claim 2 or 3, wherein the communication unit receives new chat data before the reading time ends, and the reading time calculation unit calculates a new reading time based on the new chat data and updates the reading time to the sum of the remaining reading time calculated last time and the new reading time.

5. The information processing device according to claim 4, wherein the reply determination unit, when the new chat data is received, determines not to reply if the degree of completion based on the new chat data is equal to or greater than the threshold, and determines to reply if the degree of completion is less than the threshold.

6. An information processing device according to any one of claims 2 to 5, further comprising an adjustment unit that acquires a normal response time for a chat, calculates a degree of discomfort based on the normal response time, the input time, and the reading time, and, if the degree of discomfort is greater than a predetermined threshold, adjusts the input time to a value obtained by subtracting the reading time from the normal response time.

7. The information processing device according to claim 6, wherein the adjustment unit acquires the personality of the first user or the current emotion of the first user, and if the personality of the first user is an unpleasant personality or the emotion is an unpleasant emotion, subtracts a predetermined value from the adjusted input time.

8. The information processing device according to any one of claims 2 to 7, wherein the communication unit outputs information indicating that writing is in progress and the input time.

9. An information processing device according to any one of claims 2 to 8, wherein the reply determination unit acquires a chat history after the reply content is generated, and determines using the chat history whether the reply content or content similar to the reply content has already been output, and determines not to make a reply if the reply content or content similar to the reply content has already been output.

10. An information processing device as described in claim 1, further comprising a sentence generation unit that executes a process of generating chat content on a new topic or a process of requesting a generation AI to generate chat content on the new topic if no new chat data is received for a predetermined time after it is determined that no reply will be made or after a reply has been made, and the communication unit outputs the chat content on the new topic.

11. The information processing device according to claim 10, wherein the sentence generation unit executes a process of generating chat content for the new topic taking into account the situation or constraints of the virtual space in which the chat is taking place, or a process of requesting the generation AI to generate chat content for the new topic taking into account the situation or constraints.

12. A control method in which an information processing device capable of chatting with multiple users receives chat data sent by a terminal used by a first user of the multiple users, and determines not to reply if the degree of completion, which indicates the degree to which the conversation has ended based on the chat data, is equal to or greater than a predetermined threshold, and determines to reply if the degree of completion is less than the threshold.

13. A control program that causes an information processing device capable of chatting with multiple users to execute the following process: receive chat data sent by a terminal used by a first user among the multiple users; determine not to reply if the degree of completion, which indicates the degree to which the conversation has ended based on the chat data, is equal to or greater than a predetermined threshold; and determine to reply if the degree of completion is less than the threshold.

Images