Information processing apparatus

Abstract

An information processing apparatus including a control unit configured to perform a proposal of information to a user, set, after the proposal of information, a response period for detecting that the user has taken a responsive action to the proposal of the information, acquire feedback data representing a behavior of the user within the response period, and determine, based on the feedback data, whether the user has taken the responsive action. The control unit is configured to further perform, in the setting of the response period, adjustment of a length of the response period in accordance with content of the proposal of the information.

Description

Technical Field

[0001] This disclosure relates to information processing devices. Background Technology

[0002] When information is offered to a user, detecting the user's response to the offer is useful from the perspective of improving the accuracy of the information offered. Regarding this, for example, Japanese Unexamined Patent Application Publication No. 2022-144312 (JP 2022-144312 A) discloses a technique for inferring whether a user exposed to an advertisement is interested in the advertisement. In this technique, when the user performs an action such as searching for relevant keywords within a predetermined time period after being exposed to the advertisement, it is determined that the user has responded to the advertisement; in other words, the user is interested in the advertisement. Summary of the Invention

[0003] In order to properly detect user responses, the setting of the time period used for detection (hereinafter referred to as the "response period") becomes important. When the response period is too short, there is a risk of ignoring user responses, and when the response period is unnecessarily long, unnecessary user responses are detected.

[0004] The purpose of this disclosure is to properly detect a user's response to an information proposal made to the user.

[0005] One aspect of this disclosure is an information processing apparatus comprising a control unit configured to propose information to a user, and after the proposal, to set a response period for detecting whether the user has taken a response action to the proposal, acquire feedback data representing the user's behavior within the response period, and determine whether the user has taken the response action based on the feedback data and output a determination result. In this information processing apparatus, the control unit is configured to further adjust the length of the response period according to the content of the proposal in the information.

[0006] Another option is to have a computer execute a program of the method performed by the aforementioned information processing device, or to use a computer-readable storage medium to non-temporarily store the program.

[0007] According to this disclosure, a user's response to an information proposal made to the user can be appropriately detected. Attached Figure Description

[0008] The features, advantages, and technical and industrial significance of exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, wherein like symbols denote like elements, and wherein:

[0009] Figure 1This is a diagram illustrating an overview of the information proposal system of this disclosure; Figure 2 This is a diagram illustrating the hardware configuration of the vehicle-mounted device; Figure 3 This is a diagram illustrating the software configuration of the in-vehicle device; Figure 4 This is a first flowchart of the processing for information proposal performed by the onboard device; Figure 5 This diagram illustrates the coordination between software modules included in the in-vehicle device during the processing of information proposals; and Figure 6 This is the second flowchart concerning the processing of information proposals performed by the onboard device. Detailed Implementation

[0010] In recent years, with the development of machine learning, products incorporating language models are increasing. For example, natural language conversational capabilities can be added to applicable products by combining machine learning with large-scale datasets, the accuracy of which is enhanced by a large language model (hereinafter referred to as "LLM") within the product. One area where natural language conversation is useful is the automotive industry. For example, by installing an LLM in an in-vehicle device, it becomes possible to obtain information without operating a touchscreen, etc. This capability is particularly useful when hands are unavailable, such as while driving. For example, natural language conversational capabilities can be installed in integrated devices (e.g., in-vehicle devices) within a vehicle. However, regarding trained LLMs, from the perspective of data size and cost, methods that access LLMs via a network can be adopted instead of the aforementioned approach. By accessing LLMs via a network, it becomes possible to use large-scale language models that are difficult to install in local storage.

[0011] With the improvements in natural language dialogue capabilities, or even beyond, it becomes possible to propose various types of information to users. From the perspective of appropriate information proposal, understanding how users respond to information proposals is arguably important. However, it is difficult to ensure that response detection is performed satisfactorily. For example, when the time period used to detect a user's response becomes too long, the connection between the response and the user's behavior becomes unclear, and there is a risk of detecting user behavior other than responses to the proposal. Conversely, when the time period used to detect a user's response becomes too short, user movement may not be detected even when the user has attempted to respond to the proposal.

[0012] When information is presented to a user, the user may be in various situations, and the user may not always exhibit a certain response. Therefore, the information processing apparatus according to this disclosure solves the problems described above.

[0013] An information processing apparatus according to one embodiment of this disclosure includes a control unit configured to propose information to a user, set a response period after the proposal of the information for detecting whether the user has responded to the proposal of the information, acquire feedback data indicating the user's behavior during the response period, and determine whether the user has responded based on the feedback data. The control unit is further configured to adjust the length of the response period according to the content of the proposed information within the set response period.

[0014] Various forms of suggestions regarding information to users can be adopted. For example, an external agent deployed outside the information processing device can be used. For instance, the external agent could be a system capable of dialogue via natural language and providing suggestion services using language models, each language model dedicated to a specific domain (specialty). The language model can be a large language model. For example, a large language model is one trained to enable dialogue tasks via natural language. Examples of domains handled by the external agent include "route guidance," "regional information guidance," "vehicle handling guidance," "tourism guidance," and "leisure conversation." Typically, the external agent described above can be accessed remotely via a network.

[0015] As another approach, a local agent included in the information processing device can be used to perform information proposals to the user. For example, the local agent included in the information processing device is a language model capable of performing dialogue tasks in natural language, but it can be a language model that has not yet undergone domain-specific training and can be generated at a relatively low cost, unlike an external agent.

[0016] Feedback data is information that indicates a user’s behavior, and examples of it include information indicating the content of a user’s speech, information indicating gestures, and information about a user’s actions on an information processing device or peripheral devices associated with the information processing device.

[0017] After making an information suggestion to the user, the control unit sets a response period for detecting the user's response to the suggestion and adjusts the length of the response period according to the content of the suggestion. In other words, the length of the response period is adjusted, and then the response period is set to detect the response behavior. The content of the suggestion may encourage the user to respond quickly or allow a response over a relatively long period of time. Examples of the former include suggesting driving to a facility near the user's location at the time of the suggestion. Examples of the latter include suggesting the user's behavior several months later. The control unit performs the setting after adjusting the length of the response period, taking into account the relationship between the content of the suggestion as described above and the expected response behavior from the user. By adopting this configuration, the information processing device can appropriately acquire feedback data that may include the user's response behavior to the suggestion.

[0018] The control unit then determines, based on the acquired feedback data, whether the user has responded to the suggestion; in other words, it determines whether user behavior information that can be identified as a response is included in the acquired feedback data. Therefore, the user's response to a suggestion of information to be delivered to the user can be appropriately detected. For example, the determination results obtained by the control unit can be appropriately used in the output to improve the information suggestions to the user.

[0019] Specific embodiments of this disclosure will now be described with reference to the accompanying drawings. Unless otherwise stated, the hardware configurations, module configurations, functional configurations, etc., described in the various embodiments are not intended to limit the scope of this disclosure.

[0020] First Embodiment System Overview Reference Figure 1 An illustrative configuration of a proposal system according to a first embodiment is described. The proposal system according to this embodiment is configured to include an on-board unit 10 installed in a vehicle 1. The on-board unit 10 can access an agent (external agent 30) that provides information proposal services via natural language through a network (e.g., a mobile communication network) 20.

[0021] The vehicle-mounted device 10 is installed in a connected vehicle capable of communicating wirelessly with freely chosen devices. The vehicle-mounted device 10 may include a data communication module (DCM) for connecting components included in the vehicle 1 (e.g., ECUs and vehicle-mounted devices) and the network 20 to each other. In this embodiment, the vehicle-mounted device 10 can access the Internet wirelessly via the network 20 and connect to external agents such as 30 that provide proposed services.

[0022] Vehicle 1 (or components installed in the vehicle) can provide various services by communicating with external devices via onboard unit 10. Examples of various services include navigation services, remote control (e.g., remote air conditioning) services, onboard Wi-Fi(R) services, and emergency call services.

[0023] The in-vehicle device 10 has voice input / output capabilities and can converse with vehicle occupants via natural language. The in-vehicle device 10 is configured to have a control unit 11 for performing voice input / output and voice recognition, and a local agent. The local agent includes a language model trained to enable dialogue via natural language. For example, the local agent can provide predetermined functions via dialogue, such as route search and vehicle operation (air conditioning, etc.). Like the external agent 30, the local agent is configured to provide information suggestion services via natural language. The language model used by the local agent is stored in a storage device included in the in-vehicle device 10.

[0024] Here, the size of the language model used in the information proposal service via natural language dialogue varies greatly depending on its function. For example, there are various categories of dialogue, such as local information and tourist guidance, information about vehicles (operator manuals), and casual conversation, but a language model trained with large-scale training data is required to cover all these categories. The size of such a language model can range from several gigabytes to several hundred gigabytes, making it difficult to install in the vehicle-mounted device 10 with limited capacity. Therefore, the proposal service function using a large language model is set up in the external agent 30. At the same time, a relatively small language model is installed in the vehicle-mounted device 10, and, for example, an information proposal service via natural language corresponding to requests from a limited number of users is implemented by using a relatively small language model.

[0025] In the description of this embodiment, terms such as accessing an external agent and connecting to an external agent mean accessing and connecting to an external device for which an external agent provides proposal services. In this embodiment, in each of a plurality of external devices, multiple proposal services of a large language model operate as an “external agent,” and the vehicle device 10 can engage in dialogue by connecting to a freely chosen external agent.

[0026] Hardware configuration Next, the hardware configuration of each device in the configuration proposal system will be described. Figure 2 This is a diagram schematically illustrating an example of the configuration of the hardware included in the vehicle-mounted device 10 according to this embodiment.

[0027] The vehicle-mounted device 10 can be configured as a computer with a processor (CPU, GPU, etc.), main storage (RAM, ROM, etc.), and auxiliary storage (EPROM, hard disk drive, removable media, etc.). The auxiliary storage stores the operating system (OS), various programs, various tables, etc., and various functions (software modules) matching a predetermined purpose can be implemented by executing the programs stored therein, as described below. Note that some or all of these functions can be implemented as hardware modules using hardware circuitry such as ASICs and FPGAs.

[0028] The vehicle-mounted device 10 is configured to have a control unit 11, a storage unit 12, a wireless communication module 13, and an input / output unit 14 as hardware.

[0029] The control unit 11 is a computing unit that executes predetermined programs to implement various functions of the vehicle-mounted device 10. For example, the control unit 11 can be implemented by a hardware processor such as a CPU. The control unit 11 can be configured to include RAM, read-only memory (ROM), cache memory, etc.

[0030] Storage unit 12 is a device for storing information and is configured with storage media such as RAM, disk, and flash memory. Storage unit 12 stores programs to be executed by control unit 11, data to be used by the programs, and so on.

[0031] The wireless communication module 13 is a communication device that performs wireless communication with a predetermined network. In this embodiment, the wireless communication module 13 is configured to communicate with the network 20, which is a mobile communication network. The wireless communication module 13 may be configured to have an eUICC (e.g., a SIM card). The SIM card is configured as a microcomputer including a CPU and a storage device. The SIM card stores information therein for connecting to and authenticating with the network 20.

[0032] The input / output unit 14 is a unit that receives input from the user of the device and presents information to the user. The input / output unit 14 is typically configured to include means for inputting and outputting voice, such as a microphone and a speaker. The input / output unit 14 may also include means for providing visual information (such as a display).

[0033] Software Configuration Next, the software configuration of each device in the configuration system will be described. Figure 3This diagram schematically illustrates the software configuration of the vehicle-mounted device 10 according to this embodiment. In this embodiment, the control unit 11 included in the vehicle-mounted device 10 is configured to have four software modules: a dialogue receiving unit 111, an agent unit 112, a route guidance unit 113, and a processing unit 114. Each software module can be implemented by the control unit 11 (CPU, etc.) executing a program stored in the storage unit 12. Information processing performed by the software modules is synonymous with information processing performed by the control unit 11 (CPU, etc.).

[0034] The dialogue receiving unit 111 acquires speech uttered by a vehicle occupant (hereinafter also referred to as "user") via the input / output unit 14. The dialogue receiving unit 111 performs predetermined processing on the acquired speech data and performs speech recognition. As a result, the content of the speech is converted into text. The dialogue receiving unit 111 sends the obtained text, as the result of speech recognition, to the agent unit 112. The dialogue receiving unit 111 outputs the response (hereinafter referred to as "response statement") sent from the language model by the agent unit 112 in the form of speech and display on a screen.

[0035] Agent unit 112 provides information proposal services. Specifically, agent unit 112 uses a language model (local language model 121 described later) stored in its own device to provide information proposal services. Agent unit 112 may act as a virtual agent (local agent). The local agent can provide proposal services (e.g., casual conversation) performed, for example, within its own device. When expertise is required in a conversation, agent unit 112 provides information proposal services by sending spoken statements via network 20 to one or more external agents 30 that can be used, obtaining the results, and providing the results to the user. For example, when it is determined that the user is requesting information about vehicle 1, agent unit 112 selects an external agent 30 that can provide processing guidance for vehicle 1. When it is determined that the user is requesting information about a facility or store, agent unit 112 selects an external agent 30 that can provide that information. The selection of external agents 30 can be based on the results obtained by analyzing the content of the utterances. The agent unit 112 can obtain the fit of each of the multiple external agents 30 based on the words included in the spoken statement and the context, and can send the spoken statement to the external agent 30 that has obtained a fit of, for example, a predetermined value.

[0036] The route guidance unit 113 receives the user's specified origin and destination or receives instructions (e.g., instructions for setting location information such as destinations to be recommended to the user) from the agent unit 112, and generates a route connecting the origin and destination based on road map data, etc. The route guidance unit 113 outputs information about the generated route via the input / output unit 14.

[0037] Processing unit 114 detects the user's response to the information proposal service executed by agent unit 112. Specifically, after setting the information proposal service from agent unit 112, a response period for detecting the user's response behavior is set. Regarding the response period, in order to appropriately obtain the user's response behavior, the length of the response period is adjusted according to the information content, taking into account the relationship between the proposed information content and the user's expected response behavior. Processing unit 114 obtains feedback data indicating the user's behavior within the set response period and determines whether there is a response to the information proposal based on the obtained feedback data. The feedback data includes user behavior information obtained through input / output unit 14 (information about the user's speech through the microphone and information about the operation of predetermined buttons set in the vehicle device 10, etc.), information from sensors (not shown) (imaging information from cameras that image the user's behavior, expressions, etc.), and information about the user's operation of vehicle 1. Details of the processing by processing unit 114 will be described later.

[0038] The storage unit 12 included in the vehicle-mounted device 10 stores a local language model 121, agent information 122, and attribute data 123. The local language model 121 is a language model trained to enable dialogue tasks via natural language. For example, the local language model 121 is a language model generated at a relatively low cost and only needs to be a language model for general conversation. The local language model 121 is a more lightweight language model than the large language models included in external agents that can be accessed via a network. As a result of the agent unit 112 using the local language model 121, dialogues with satisfactory responses become possible. For example, when specialized conversation is required, spoken statements can be sent to an external agent, and the local agent can process spoken statements for conversations requiring rapid responses, appropriate for the situation, making it possible to use the appropriate methods.

[0039] Agent information 122 is a set of data associated with multiple external agents that can be used by the vehicle-mounted device 10. Examples of agent information 122 may include identifiers, names, and domain information about the external agents, and information about the destination (e.g., the network address of the external device providing the external agent). Agent unit 112 can determine the external agent used as the destination for the spoken statement by referring to agent information 122.

[0040] Attribute data 123 is a set of data related to the attributes of a user interacting with the in-vehicle device 10. Examples of attribute data 123 may include personal information such as the user's gender, age, height, and weight. When there are multiple users of the vehicle, attribute data 123 may also include data for multiple individuals.

[0041] The process of proposing information to users and their response behavior here, Figure 4 It is a flowchart illustrating the process of processing user information suggestions, and Figure 5 This diagram illustrates the collaboration between the various software modules of the control unit 11 of the on-board unit 10 in the processing of information proposals. The flow of the processing performed by the control unit 11 is described based on these diagrams. As an example, Figure 4 The process shown in the flowchart begins from the user's request to the vehicle-mounted device 10 (a request for information proposal).

[0042] First, in step S101, a request for information proposal from a user in vehicle 1 is received. This process is performed by the dialogue receiving unit 111. Specifically, the dialogue receiving unit 111 acquires the utterance related to the request from the user via the input / output unit 14. For example, the input / output unit 14 converts the utterance acquired via a microphone, etc., into speech data, and the dialogue receiving unit 111 acquires the speech data. The dialogue receiving unit 111 performs predetermined speech recognition processing on the acquired speech data and converts the speech data into text. While retaining the response to the utterance, the dialogue receiving unit 111 sends the obtained text as a result of speech recognition to the agent unit 112. This text is referred to as the "spoken statement".

[0043] Next, in step S102, the agent unit 112 performs information proposal processing based on the spoken statement sent by the dialogue receiving unit 111. Specifically, having received the spoken statement, the agent unit 112 understands the user's request based on the content of the utterance, retrieves agent information 122 about the external agent from the storage unit 12, and uses the agent information 122 to determine the external agent 30 as the destination for the spoken statement. The intent of the utterance can be determined using the local language model 121 or by using another machine learning model. This determination can be performed in a rule-based manner. The agent unit 112 retrieves information about the external agent (agent information 122) from the storage unit 12 and determines the external agent to which the spoken statement is sent based on the agent information 122 and the determined intent. The agent unit 112 may determine that it is unnecessary to send the spoken statement to the external agent. For example, this applies to situations requiring a rapid response or where the user's request can be fulfilled by their own device, such as when the request is for route guidance. In this case, the spoken statement can be processed using only the agent unit 112 (and the local language model 121).

[0044] In this example, the following three proxies are exemplified as external proxy 30.

[0045] (1) Vehicle agency An external agent capable of monitoring the vehicle's interior or setting up in-vehicle equipment. The vehicle agent is trained based on the vehicle's owner's manual and can also provide information about the functions included in the vehicle.

[0046] (2) Leisure conversation agent External proxies are specifically designed for non-task-oriented chat.

[0047] (3) Guiding Agent External agents can provide users with information on driving guidance, including store guidance and tour guidance.

[0048] In this example, the bootstrapping agent is identified as the external agent that handles the information proposal.

[0049] When agent unit 112 sends the spoken statement to the determined external agent 30, agent unit 112 adds information about the user. Examples of user information may include personal information such as the user's gender, age, height, and weight. This information can be obtained from attribute data 123 stored in storage unit 12. User information may also include information about the user's travel. Such information may include details about the vehicle 1's origin, destination, route, transfer points, etc. This information can be obtained from route guidance unit 113. The determined external agent 30 can then generate a response to the user's request based on this information.

[0050] The response generated by the external agent 30 is sent as a reply statement to the agent unit 112, and the agent unit 112 proposes information to the user as a response to the request via the dialogue receiving unit 111. Specifically, the dialogue receiving unit 111 generates voice data based on the reply statement and outputs the voice data via the input / output unit 14. The dialogue receiving unit 111 may generate only the voice data that reads out the reply statement, or it may generate information accompanying the voice data. Examples of information accompanying the voice data include user interface screens. The reply statement, written as text, may be included in the user interface screen.

[0051] Next, in step S103, the processing unit 114 sets a response period. The response period is a time interval set to detect whether there is a user response to the information proposal processing performed in step S102, and is a predetermined time interval immediately following the proposal processing. In this disclosure, the length of the response period is not fixed and is adjusted according to the content of the information proposal performed in step S102. For example, when a guidance information agent is determined to be an external agent processing the information proposal, the length of the response period can be adjusted according to the type of the proposed information. As an example, the processing unit 114 may adjust the response period to six months when proposing information about a trip to the user, to one month when proposing information about a store that provides food, and to one week when proposing information about a retail store.

[0052] As another approach, when information about a specific time is included in the proposed information, the response period can be set considering that specific time. For example, when a user's request is "I want to go somewhere during next year's Golden Week" and the information proposal in response to that request presents a region to visit "during next year's Golden Week," the response period can be adjusted to the time period immediately following the processing in step S102 up to "next year's Golden Week." Other forms than those described above can be used to adjust the response period. After processing unit 114 adjusts the response period as described above, processing unit 114 sets the response period and prepares to obtain feedback data in step S104.

[0053] Next, in step S104, processing unit 114 acquires feedback information about the user's behavior. Examples of user behavior include speech and movement. Examples of feedback data include the content of the user's speech, the analysis results of the speech, and travel records (e.g., places the user has visited after receiving a response statement). For example, feedback data may be text representing the user's speech after the information proposal or may be the result obtained by analyzing the speech (e.g., a numerical value indicating the degree of affirmation). Feedback data may be data representing the user's reaction after the information proposal. For example, feedback data may be data representing the content of the user's gestures (nodding, shaking, etc.). Feedback data may be data related to the user's travel after the information proposal (e.g., changes in location information and identifiers of visited locations).

[0054] The processing unit 114 acquires the user's speech via the input / output unit 14 and obtains the results obtained by analyzing the speech as feedback data. The processing unit 114 can acquire operation information regarding the setting of the vehicle 1's destination (driving destination) set in the vehicle device 10, user reaction data captured by a camera (not shown), etc., as feedback data. Of course, the processing unit 114 can also acquire user behaviors other than those mentioned above as feedback data.

[0055] Next, in step S105, it is determined whether the response period set in step S103 has ended. When the set response period is a relatively long period (e.g., a week), there is a possibility that the user may stop riding in vehicle 1 within the response period, potentially causing vehicle 1 to stop. In this case, the length of the response period and the time at which the response period was set are stored in the storage unit 12, and when the user subsequently rides in vehicle 1, the length and time are read again, and the process restarts. Figure 4 The process is as shown. When step S105 is determined to be affirmative, the process proceeds to step S106, and when step S105 is determined to be negative, the process starting from step S104 is repeated again.

[0056] In step S106, it is determined whether the user has taken a response action based on the feedback data obtained in step S104; in other words, it is determined whether there is information about the user's response action in the feedback data. As an example, imagine that the guidance information agent is determined to be an external agent handling information proposals, and the proposed information is about a store that provides food. In this case, for example, it can be determined that the user has taken a response action when information about the user setting the store's location as the destination of vehicle 1 in the vehicle device 10 (driving destination) is included in the feedback data, or when text information about the user's intention to drive to the store is included in the text representing the utterance. Even if the user has not set the destination of vehicle 1 in the vehicle device 10, it can be determined that the user has taken a response action when the vehicle 1 is detected to be near the store from the vehicle 1's location information used as feedback data.

[0057] As mentioned above, according to Figure 4 The process described involves adjusting and setting the content of information suggestions to users based on the response period, and acquiring feedback data within that response period. By determining whether user response behavior exists based on the feedback data, it is possible to appropriately detect the user's response to the information suggestions offered to them.

[0058] Second Embodiment based on Figure 6 A second embodiment of this disclosure is described. Figure 6This is a flowchart illustrating the process of proposing information to the user in this embodiment. Figure 6 In the processing shown, with Figure 4 Processes that are substantially the same as those shown are indicated by the same reference numerals; therefore, their detailed description is omitted. Figure 6 In the process shown, when the process of step S104 ends, the process of step S201 is then executed.

[0059] In step S201, it is determined whether the predetermined information regarding the user's affirmative action to the information proposed in step S102 is included in the feedback data acquired in step S104. An affirmative action means an action by the user that, rather than indicating a response to the information proposal, suggests a relatively high likelihood of a response. For example, consider a scenario where a guidance information agent is identified as an external agent handling information proposals, and the proposed information pertains to a store that provides food. As described above, actions such as indicating the store's location as the destination of vehicle 1 in the vehicle-mounted device 10 are considered response actions. However, if the user, after receiving the store proposal, again inquires about details of the store via the dialogue receiving unit 111 with the agent unit 112, this is processed as an affirmative action. In addition to inquiring about store details, inquiring about stores offering similar food can also be processed as an affirmative action. This is because it is inferred that the user will compare multiple stores, including the proposed store, and determine their final destination. Other actions besides those described above can also be used for affirmative actions. When step S201 is determined to be affirmative, the process proceeds to step S202, and when step S201 is determined to be negative, the process proceeds to step S105.

[0060] In step S202, in response to the determination of affirmation in step S201, the process of extending the response period set in step S103 is executed. An affirmative action is an action from which the user's response behavior is expected; therefore, the process is executed to definitively detect the behavior. For example, when an affirmative action exists, the response period can be extended by 20%. Alternatively, the degree of extension of the response period can be varied based on the degree of affirmation of the affirmative action. In other words, as the degree of affirmation of the affirmative action becomes stronger, the response period can be extended further. For example, when comparing making an inquiry about a proposed store as an affirmative action with making an inquiry about a store offering food similar to the proposed store as an affirmative action as described above, the former is assumed to be more affirmative. Therefore, in the former case, the response period can be extended by 20%, and in the latter case, the response period can be extended by 10%. When the process in step S202 ends, the process proceeds to step S105.

[0061] As mentioned above, according to Figure 6 The process described involves adjusting and setting the response timeframe based on the content of a user's information suggestion, and acquiring feedback data within that timeframe. The response timeframe can be extended based on whether positive user behavior is observed. By determining the presence of user response behavior based on feedback data, it is possible to appropriately detect the user's response to the information suggestion offered to them.

[0062] Third Embodiment In a third embodiment of this disclosure, the information processing apparatus is not configured as an in-vehicle device installed in a vehicle, but rather as a server device arranged in a non-driving manner. Specifically, the server device is configured to offer information to a user for business support. For example, it may offer task information related to the user's business based on a request from the user. As an example, the server device may offer information about a user's business trip application or offer a draft reply to an email received by the user. The user's response to the information offer from the server device as described above is the user's actual performance of a task related to the offered information. The disclosures described in the first and second embodiments can be applied to this embodiment to detect the user's response behavior as described above.

[0063] Variation Example The above embodiments are merely examples, and this disclosure can be implemented by appropriate modifications without departing from its spirit. For example, the processes and apparatus described in this disclosure can be implemented in any combination without resulting in technical inconsistencies.

[0064] In this embodiment, an external agent is illustrated as being deployed in an external device connected to the Internet, but the external agent can also be deployed in devices other than those described above. For example, the external agent can be deployed in an edge server accessible from the vehicle. The external agent can be deployed across multiple edge servers or distributed in the cloud. In this embodiment, the in-vehicle device 10 has been illustrated as an information processing apparatus according to this disclosure, but the information processing apparatus can be implemented as a device or equipment not installed in the vehicle.

[0065] When an external agent is deployed across multiple edge servers, the vehicle-mounted device 10 can obtain its own vehicle location information and determine the edge server where the target external agent is deployed based on the location information. For example, there may be a case where an external agent providing regional information is deployed across multiple edge servers, each edge server being deployed for a corresponding region. In this case, for example, the vehicle-mounted device 10 can determine the external agent deployed in the geographically nearest edge server based on the vehicle's location information. The regional information processed by the external agent may differ for each edge server. For example, an external agent providing regional information for region A may be deployed in an edge server deployed in region A, and an external agent providing regional information for region B may be deployed in an edge server deployed in region B. The vehicle-mounted device 10 determines the edge server corresponding to the region where the vehicle is located and accesses the external agent deployed in the edge server. As a result, the vehicle-mounted device 10 can obtain the regional information for that region.

[0066] Processes that have been described as being performed by a single device can be distributed and performed by multiple devices. Alternatively, processes that have been described as being performed by different devices can be performed by a single device. In computer systems, the hardware configuration (server configuration) used to implement various functions can be flexibly changed.

[0067] This disclosure can also be implemented by providing a computer program equipped with the functions described in the above embodiments to a computer and having one or more processors belonging to the computer read and execute the program. Such a computer program can be provided to the computer via a non-transitory computer-readable storage medium that can be connected to the computer's system bus, or it can be provided to the computer via a network. Examples of non-transitory computer-readable storage media include any type of disk, such as magnetic disks (floppy disks (R), hard disk drives (HDDs) etc.) and optical disks (CD-ROMs, DVDs, Blu-ray discs, etc.), read-only memory (ROM), random access memory (RAM), EPROM, EEPROM, magnetic cards, flash memory, optical cards, and any type of medium suitable for storing electronic instructions.

Claims

1. An information processing apparatus comprising a control unit configured to perform: Suggest information to users; Following the proposal in the information, a response period is set for detecting whether the user has taken a response action to the proposal in the information; Obtain feedback data representing the user's behavior during the response period; and Based on the feedback data, it is determined whether the user has taken the response action, wherein the control unit is configured to further adjust the length of the response period according to the content of the suggestion in the information within the setting of the response period.

2. The information processing apparatus according to claim 1, wherein, The control unit is configured to extend the set response period when the feedback data includes predetermined information indicating that the user's behavior is positive for the suggestion in the information.

3. The information processing apparatus according to claim 2, wherein, The control unit is configured to adjust the degree of extension of the response period based on the degree of affirmation of the proposal in the predetermined information.

4. The information processing apparatus according to claim 1, wherein, The control unit is configured to perform the following further action: The information is proposed based on a request from the user; and The length of the response period is adjusted based on the content of the proposal in the information and the information about the time related to the proposal included in the request.

5. The information processing apparatus according to any one of claims 1 to 4, wherein: The information processing device is an in-vehicle device installed in the vehicle; and The feedback data includes at least one of the following: information about the user's conversation in the vehicle, information about the user's operation of the vehicle, and information about the location of the vehicle operated by the user.

Images