Information processing apparatus

Abstract

The present disclosure relates to an information processing apparatus. Including a control unit that performs: suggesting information about a place of visit to a user, about which visit the user is recommended, acquiring position information of the user after the suggestion, and when it is determined based on the acquired position information that the user visited the place of visit and the user's stay at the place of visit is longer than a first threshold value of duration, determining that the user exhibited a reactive behavior in response to the suggestion of information about the place of visit.

Description

Technical Field

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

[0002] When providing information to users, detecting their reaction behavior to the suggestions is useful for improving the accuracy of the recommendations. In this regard, for example, Japanese Unexamined Patent Application Publication No. 2022-144312 (JP2022-144312 A) discloses a technique for estimating whether a user who has been exposed to an advertisement is interested in it. In this technique, when a user performs an action such as searching for related keywords within a predetermined time period after being exposed to the advertisement, it is determined that the user has shown a reaction behavior to the advertisement, i.e., the user is interested in the advertisement. Summary of the Invention

[0003] It is not easy to detect a user's reaction to suggestions regarding information about a location the user visited; that is, to detect whether the user actually visited the location. Furthermore, it is not easy to detect whether the user's reaction is relevant to that location.

[0004] The purpose of this disclosure is to appropriately detect a user's response to suggestions regarding information about the user's access locations.

[0005] One aspect of this disclosure is

[0006] An information processing device including a control unit, the control unit performing: suggesting information about a location to a user, recommending a visit to the location; acquiring the user's location information after the suggestion; and determining that the user has exhibited reactive behavior in response to the suggestion about the location when it is determined based on the acquired location information that the user has visited the location and the user's stay at the location exceeds a duration of a first threshold.

[0007] Other aspects include programs that enable a computer to execute the methods performed by the aforementioned information processing apparatus, and computer-readable storage media that store programs in a non-transitory manner.

[0008] According to this disclosure, a user's response to suggestions regarding information about the user's access location can be appropriately detected. Attached Figure Description

[0009] 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: Figure 1 This is a diagram illustrating an overview of the information recommendation system according to this disclosure; Figure 2This is a diagram showing the hardware configuration of the vehicle-mounted device; Figure 3 This is a diagram showing the software configuration of the vehicle-mounted device; Figure 4 This is the first flowchart of the information suggestion processing performed by the on-board unit; and Figure 5 This diagram illustrates the collaboration between software modules included in the in-vehicle device during the processing of information recommendations. Detailed Implementation

[0010] In recent years, advancements in machine learning have increased the number of products equipped with language models. For example, natural language dialogue capabilities can be added to a product by integrating a large language model (LLM) into it; the accuracy of this large language model has been improved through machine learning using large datasets. One area where natural language dialogue is useful is the automotive industry. For instance, equipping in-vehicle systems with LLMs allows information to be obtained without operating touch panels. This functionality is particularly useful when the user's hands are occupied, such as while driving. For example, built-in devices within vehicles (e.g., in-vehicle systems) can be equipped with natural language dialogue capabilities. However, from the perspective of the data size and cost of training LLMs, technologies that access LLMs via the network can be used as an alternative. Accessing LLMs via the network makes it possible to use large-scale language models that are difficult to install on local storage.

[0011] Even when not limited to natural language dialogue functions, improvements to such dialogue capabilities can suggest various types of information to users. Currently, from the perspective of providing appropriate information suggestions to users, understanding how users react to the information suggestions offered is considered important, but it is difficult to say that positive detection of such responses is being achieved. In particular, when suggestions prompt users to actually visit a location—that is, when information about a recommended location is suggested—it is not easy to detect whether the user actually visits that location. Furthermore, even when a user visits the location, it is not easy to detect whether the user exhibits a positive response to the location.

[0012] User behavior after being provided with information suggestions about a location to visit varies from user to user, and even when users exhibit behavior indicating interest in the information suggestions (e.g., making further inquiries about the location to visit), it is uncertain whether they will actually take action to visit the location. Therefore, the information processing apparatus according to this disclosure solves these problems.

[0013] The information processing apparatus according to a first aspect of this disclosure includes a control unit that performs the following actions: suggesting information about a location to be visited to a user, wherein a visit to the location is recommended; acquiring the user's location information after the suggestion; and determining, based on the acquired location information, that the user has visited the location and that the user's stay at the location exceeds a duration of a first threshold, that the user has exhibited a reactive behavior in response to the suggestion about the location.

[0014] Providing users with information about places to visit can take various forms. For example, an external agent deployed outside the information processing device can be used. This external agent could be a system capable of conversing in natural language and providing suggestion services using language models specialized for each of multiple categories (domains). The language model could be a large language model (LLM). A large language model is, for example, a language model trained to perform conversational tasks in natural language. Examples of categories that an external agent can handle include "direction directions," "area information guidance," "sightseeing guidance," and "shopping guidance." These external agents are typically configured to enable remote access via a network.

[0015] Alternatively, a local agent equipped in the information processing device can be used to suggest information to the user. The language model of the local agent is a language model capable of performing dialogue tasks in natural language, but unlike external agents, it can be a language model that has not been specifically trained for a particular category and, for example, generated at a relatively low cost.

[0016] A user's location information is information that detects changes in location while the user is moving. This location information can be obtained using the Global Positioning System (GPS) function set on the user's own mobile device (such as a smartphone), or using the GPS function provided to a moving object (such as the vehicle the user is riding in). The location information detected by these GPS functions is then passed to an information processing device, enabling the acquisition of the user's location information. In other words, the information processing device acquires the user's location information using the detection results from a device capable of detecting the user's movement.

[0017] After providing the user with the suggested information, the control unit then determines whether the user has already visited the suggested location based on the acquired user location information. This determination is made, for example, when the user's location information overlaps with the location information of the suggested location, or when the user's location information is currently within a nearby area centered on the suggested location. On the other hand, when a user visits a suggested location, it is conceivable that the visit is based on the user's request, which is a prerequisite for the suggestion, and therefore it is assumed that the visit is a result of the user's response to the suggestion regarding the location. It is reasonably expected that the user will stay at the location for a certain duration to achieve the purpose of the visit. Therefore, when the control unit determines that the user has visited the suggested location and the user's stay at the location exceeds a first threshold, the control unit determines that the user's visit behavior is a response to the suggestion regarding the location. This configuration allows the information processing device to appropriately detect the user's response to the suggestion. Note that the first threshold can be set based on statistical values ​​related to the stay time of people who have previously visited the location, or it can be a value set using some other technique.

[0018] Furthermore, when the suggested location is a user's preferred location, the user's dwell time will typically tend to be longer. Therefore, in the aforementioned information processing apparatus, when it is determined that a user has visited a location and the user's dwell time at the location exceeds a second threshold duration (the duration of the second threshold is greater than the duration of the first threshold), the control unit can also determine that the user has shown a positive response to the suggestion regarding the location. The second threshold has a value greater than the first threshold and is preferably set based on statistical values ​​of the dwell time of people who have previously visited the location and their evaluations of the location. This configuration allows the information processing apparatus to appropriately detect the user's response to the suggestion.

[0019] Furthermore, by detecting that a user has already demonstrated a response to a suggestion regarding a location to visit, and further detecting that the user has already demonstrated a positive response to the suggestion, the control unit can accumulate the detection results and use these results in the processing for suggesting future locations to visit, thereby improving the suggestion processing.

[0020] In the following description, specific embodiments of the present disclosure will be illustrated with reference to the accompanying drawings. Unless otherwise stated, the hardware configurations, module configurations, functional configurations, etc., described in each embodiment are not intended to limit the scope of the present disclosure to these configurations.

[0021] First Embodiment System Overview Reference Figure 1A general configuration of the recommendation system according to the first embodiment is described. The recommendation 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 recommendation services in natural language via a network (e.g., a mobile communication network) 20.

[0022] The vehicle-mounted device 10 is installed in a networked vehicle capable of communicating with various devices wirelessly. The vehicle-mounted device 10 may include a data communication module (DCM) for connecting components of the vehicle 1 (e.g., electronic control unit (ECU), vehicle terminal, etc.) to the network 20. In this embodiment, the vehicle-mounted device 10 can access the Internet via the network 20 wirelessly and connect to external agents such as 30 that provide advisory services.

[0023] Vehicle 1 (or components installed in the vehicle) can also provide various services by communicating with external devices via onboard unit 10. Examples of such services include navigation services, remote control (e.g., remote air conditioning, etc.) services, onboard Wi-Fi (registered trademark) services, emergency call services, etc.

[0024] The in-vehicle device 10 also features voice input and output capabilities and is capable of engaging in natural language dialogue with vehicle occupants. The in-vehicle device 10 is configured to include a control unit 11 that performs voice input and output and voice recognition, as well as a local agent. The local agent includes a language model trained to enable natural language dialogue. For example, the local agent can provide pre-defined functions through dialogue, such as route search, vehicle operation (air conditioning, etc.). Furthermore, the local agent is configured to provide information suggestion services in natural language, similar to the external agent 30. Note that the language model used by the local agent is stored in the storage device of the in-vehicle device 10.

[0025] Currently, the size of language models used in information suggestion services via natural language dialogue varies greatly depending on their function. For example, there are various dialogue categories, such as regional information, sightseeing guidance, shopping guidance, etc., and to cover all these categories, it becomes necessary to prepare language models trained with large-scale training data. The size of such language models can range from several gigabytes to hundreds of gigabytes, making it difficult to install them in the vehicle device 10 with limited storage capacity. Therefore, suggestion service functions using large-scale language models are set up in the external agent 30. On the other hand, the vehicle device 10 is equipped with a relatively small language model, which the local agent uses to implement natural language information suggestion services, for example, in response to requests from a limited number of users.

[0026] Note that in the description of this embodiment, the expressions "accessing an external agent" and "connecting to an external agent" refer to accessing or connecting to an external device that provides advice services via an external agent. In this embodiment, each of the multiple advice services using a large language model operates as a "foreign agent" on a corresponding one of the multiple external devices, and the vehicle device 10 can participate in the dialogue by connecting to any of these external agents.

[0027] Hardware configuration Next, the hardware configuration of each device that constitutes the recommended system will be described. Figure 2 An example of the hardware configuration of the vehicle-mounted device 10 according to this embodiment is illustrated schematically.

[0028] The vehicle-mounted device 10 can be configured as a computer including a processor (central processing unit (CPU), graphics processing unit (GPU), etc.), main storage devices (random access memory (RAM), read-only memory (ROM), etc.) and auxiliary storage devices (erasable programmable read-only memory (EPROM), hard disk drive, removable media, etc.). The operating system (OS), various types of programs, various types of tables, etc., are stored in the auxiliary storage devices, and the programs stored therein are executed, thereby enabling various functions (software modules) to meet predetermined purposes, which will be described later. However, some or all of the functions can alternatively be implemented as hardware modules using hardware circuitry (e.g., application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), etc.).

[0029] The vehicle-mounted device 10 is configured to include a control unit 11, a storage unit 12, a wireless communication module 13, an input / output unit 14, and a GPS device 15 as hardware.

[0030] The control unit 11 is a computing unit that executes predetermined programs to implement various functions of the vehicle-mounted device 10. The control unit 11 can be implemented using a hardware processor such as a CPU. Furthermore, the control unit 11 can be configured to include RAM, ROM, cache memory, etc.

[0031] Storage unit 12 is a device for storing information and is composed of storage media such as RAM, disk, and flash memory. Storage unit 12 stores programs executed by control unit 11, data used by the programs, etc.

[0032] The wireless communication module 13 is a communication device for wirelessly communicating with a predetermined network. In this embodiment, the wireless communication module 13 is configured to communicate with network 20, which is a mobile communication network. The wireless communication module 13 may be configured to have an embedded universal integrated circuit card (eUICC) (e.g., a Subscriber Identity Module (SIM) card). The SIM card is configured as a microcomputer including a CPU and storage devices. The SIM card stores information for connecting to network 20 and receiving authentication.

[0033] 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 typically includes means for inputting and outputting audio, such as a microphone and a speaker. The input / output unit 14 may also include means for providing visual information (such as a display).

[0034] GPS device 15 is a unit that uses GPS functionality to obtain the location information of vehicle 1. It should be noted that the location information of vehicle 1 detected by GPS device 15 regarding the user riding in vehicle 1 is considered equivalent to the user's location information.

[0035] Software Configuration Next, the software configuration of the devices that constitute the system will be described. Figure 3 This diagram schematically illustrates the software configuration of the vehicle-mounted device 10 according to this embodiment. In this embodiment, the control unit 11 of the vehicle-mounted device 10 is configured to have five software modules: a dialogue processing unit 111, an agent unit 112, a route guidance unit 113, a location acquisition unit 114, and a processing unit 115. Each software module can be implemented by the control unit 11 (CPU, etc.) that executes a program stored in the storage unit 12. Note that the information processing performed by the software module is equivalent to the information processing (CPU, etc.) performed by the control unit 11.

[0036] The dialogue processing unit 111 acquires speech uttered by a vehicle occupant (hereinafter also referred to as "user") via the input / output unit 14. The dialogue processing unit 111 performs predetermined processing on the acquired speech data and performs speech recognition. The content of the speech is thus converted into text. The dialogue processing unit 111 then sends the text obtained as a result of speech recognition to the agent unit 112. The dialogue processing unit 111 also outputs, in speech or display form, a response (hereinafter referred to as "response statement") from the language model sent from the agent unit 112.

[0037] Agent unit 112 provides information suggestion services. Specifically, in this embodiment, agent unit 112 performs processing to suggest information about recommended places to visit. Specifically, agent unit 112 uses a language model stored in the device itself (local language model 121, described later) to provide information suggestion services. Agent unit 112 can act as a virtual agent (local agent). The local agent can provide suggestion services (e.g., temporary dialogues, etc.) that can be completed within the device itself. Furthermore, when expertise is required in the dialogue, agent unit 112 sends the utterance sentence to one or more available external agents 30 via network 20, obtains the results, and provides the results to the user, thereby realizing the information suggestion service. For example, when it is determined that the user is looking for information about recommended places to visit for sightseeing of vehicle 1, agent unit 112 selects an external agent 30 that can provide sightseeing guidance. Furthermore, when it is determined that the user is looking for information about facilities or shops, agent unit 112 selects an external agent 30 that can provide information about such facilities, etc. The selection of external agents 30 can be based on the results of analyzing the content of the utterance. For example, agent unit 112 can calculate the relevance score of each external agent 30 based on the words or context included in the utterance, and send the utterance with the obtained relevance score above a predetermined value to the external agent 30.

[0038] The route guidance unit 113 receives the user's specified starting point and destination, or receives instructions from the agent unit 112 (e.g., instructions to set location information such as recommended destinations for the user), and generates a route connecting the starting point and destination based on road map data, etc. Information about the generated route is also output via the input / output unit 14.

[0039] The location acquisition unit 114 acquires location information related to the user's movement via the GPS device 15. As described above, the user is riding in the vehicle 1, and the GPS device 15 is located in the vehicle 1. Therefore, in this embodiment, the location information detected by the GPS device 15 is considered equivalent to the user's location information. Alternatively, when the user's mobile device (e.g., a smartphone, etc.) is equipped with GPS functionality, the location acquisition unit 114 can acquire location information about the user's movement via that mobile device.

[0040] Processing unit 115 determines whether the user has actually visited the suggested location by agent unit 112 based on the user's location information obtained by location acquisition unit 114. When it is determined that the user has visited the suggested location, it then determines whether the user has exhibited a responsive behavior towards the suggestion based on the user's dwell time at that location. The dwell time at the location can be calculated using changes in the user's location information. For example, the time the user spends in the vicinity of the location can be considered as dwell time, or other methods of calculating dwell time can be used. Furthermore, the processing unit determines whether the user's responsive behavior towards the suggestion is positive based on the dwell time and evaluates the suggested service. The processing of processing unit 115 will be described in detail later.

[0041] Furthermore, the storage unit 12 of 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 perform dialogue tasks in natural language. The local language model 121 is a language model that can be generated at a relatively low cost, and for example, a language model for general conversation is sufficient. Compared to large language models that provide external agents accessible via a network, the local language model 121 is a lightweight language model. The use of the local language model 121 by the agent unit 112 enables vivid and responsive dialogue. This allows for differentiation in usage; for example, when a specialized conversation is needed, utterances can be sent to an external agent, while when a rapid response is required, the local agent can perform the processing of the utterances.

[0042] Agent information 122 is a set of data about multiple external agents available to the vehicle-mounted device 10. Agent information 122 may include, for example, identifiers and names of external agents, information about the scope specific to the external agent, information about the destination (e.g., the network address of the external device providing the external agent, etc.). Agent unit 112 may refer to agent information 122 to determine which external agent a statement will be sent to.

[0043] Attribute data 123 is a set of data related to the attributes of users participating in dialogue with the in-vehicle device 10. Attribute data 123 may include personal information, such as the user's gender, age, height, and weight. Furthermore, when multiple users exist in the vehicle, attribute data 123 may also include data for each user.

[0044] The process of providing information suggestions to users and the detection of user response behavior. Now, Figure 4 This is a flowchart illustrating the process of suggesting information about visit locations to users, and Figure 5This is a diagram illustrating the collaboration of various software modules in the control unit 11 of the in-vehicle device 10 during the information suggestion process. The processing flow performed by the control unit 11 will be described with reference to these diagrams. Note that in one example, when a user makes a request to the in-vehicle device 10 (requesting information suggestions about a visit location), Figure 4 The process begins as shown in the flowchart.

[0045] First, in S101, a request for information suggestions regarding a destination from a user riding in vehicle 1 is received. This processing is performed by the dialogue processing unit 111. Specifically, the dialogue processing unit 111 obtains the request-related utterance from the user via the input / output unit 14. For example, the input / output unit 14 converts the utterance obtained through a microphone, etc., into speech data, and the dialogue processing unit 111 obtains the speech data. The dialogue processing unit 111 performs predetermined speech recognition processing on the obtained speech data to convert the speech data into text. When the response to the utterance is paused, the dialogue processing unit 111 sends the text obtained as a result of speech recognition to the agent unit 112. This text is referred to as a "utterance statement".

[0046] Next, in S102, the agent unit 112 performs processing based on the suggestion information of the utterance sent by the dialogue processing unit 111. Specifically, the agent unit 112 receives the utterance and understands the user's request (such as the type of location the user wants to visit) based on the content of the utterance, and also retrieves agent information 122 related to the external agent from the storage unit 12, and then uses the agent information 122 to determine which external agent 30 to send the utterance to. The intent of the utterance can be determined using the local language model 121, or it can be determined using another machine learning model. Alternatively, a rule-based method can be used to determine the intent of the utterance. The agent unit 112 retrieves information about the external agent (agent information 122) from the storage unit 12, and determines which external agent to send the utterance to based on the agent information 122 and the determined intent. Furthermore, the agent unit 112 can also determine that it is not necessary to send the utterance to the external agent. In this case, the processing of the utterance can be performed solely by the agent unit 112 (and the local language model 121).

[0047] In this example, the following two examples illustrate external agent 30.

[0048] (1) Tourist guidance agency These are external agents that can provide users with information about driving directions (including sightseeing guidance).

[0049] (2) Shopping guidance agent These are external agents that can provide users with information about driving directions (including store directions).

[0050] In this example, we will consider the case where the sightseeing guide agent is determined to be an external agent corresponding to the information suggestion.

[0051] Note that when the utterance is sent to the designated external agent 30, agent unit 112 adds information about the user. This user information may include personal details such as the user's gender, age, height, and weight. Such information can be obtained from attribute data 123 stored in storage unit 12. Furthermore, the user information may also include travel information. Examples of this information include information about the vehicle 1's starting point, destination, route, waypoints, etc. Such information can be obtained from route guidance unit 113. The designated external agent 30 can then generate a response to the user's request based on this information. For example, external agent 30 might generate a response recommending that the user visit a tourist attraction X located near the destination of vehicle 1. In this case, the destination is "tourist attraction X".

[0052] The response generated by external agent 30 is sent as a reply statement to agent unit 112, which uses it as a response to the request and performs processing to suggest information about the access location to the user via dialogue processing unit 111. Specifically, dialogue processing unit 111 generates voice data based on the reply statement and executes its output via input / output unit 14. Note that dialogue processing unit 111 may generate only the voice data for reading out the reply statement, or it may additionally generate information accompanying the voice data. An example of information accompanying the voice data is a user interface screen. This user interface screen may include the reply statement in written form.

[0053] Next, in S103, the processing unit 115 sets a response period. This response period is a predetermined time period set to detect whether the user has exhibited a reaction behavior to the processing performed in S102 regarding the suggested information about the access location, and it begins immediately after the suggested processing. For example, the response period can be set to one week, or it can be set to any other time period.

[0054] Next, in S104, a determination is made regarding whether the reaction period set in S103 has ended. Note that the starting point of the reaction period is the time when the suggested processing in S102 is executed, and in S104, a determination is made regarding whether the reaction period has elapsed since that point. When the determination in S104 is affirmative, Figure 4 The processing of the suggested information regarding the location to be visited ends, and if the result is negative, the process proceeds to S105.

[0055] In S105, the location acquisition unit 114 acquires the user's location information. As described above, in this embodiment, the location information of vehicle 1 is considered as the location information of the user riding in the vehicle. This user's location information is transmitted from the location acquisition unit 114 to the processing unit 115. When the processing in S105 ends, the process proceeds to S106.

[0056] In S106, processing unit 115 determines whether the user has visited the location suggested by agent unit 112 (e.g., the aforementioned tourist attraction X) based on the user's location information obtained in S105. Specifically, when it can be determined that the user's location information indicates that the user is located within a predetermined radius centered on tourist attraction X, it can be determined that the user has visited the location. Note that the predetermined radius can be appropriately adjusted according to the characteristics of the location. For example, when the location is a building in an urban environment, the predetermined radius can be set to be relatively small, while when the location is a park in the suburbs, the predetermined radius can be set to be larger considering the size of the park, and so on. When the determination in S106 is affirmative, the process proceeds to S107, and when the determination is negative, S104 and subsequent processes are repeated.

[0057] In S107, processing unit 115 measures the user's dwell time at the visited location. Specifically, based on the user's location information, it measures the duration for which the user continuously stays within the aforementioned area (e.g., an area within a predetermined radius centered on the tourist attraction). In principle, it is reasonable to interpret the user's dwell time as ending when the user leaves the area; however, if the departure time is relatively short (e.g., shorter than a predetermined threshold duration), the departure can be ignored, and the user's dwell time can be measured as if the dwell time were continuous. This takes into account the accuracy of the location information acquisition and the appropriateness of the designated area. When processing in S107 ends, processing proceeds to S108.

[0058] In S108, processing unit 115 performs a determination process regarding the user's reaction to the suggested information about the location, based on the dwell time measured in S107. Specifically, when the user's dwell time exceeds a duration indicated by a first threshold, processing unit 115 determines that the user has exhibited a reaction to the suggested information. The first threshold is set based on statistical values ​​regarding the dwell time of people who have previously visited the location at the suggested location. For example, when the location is tourist attraction X, the first threshold can be set to 50% of the average dwell time of past visitors at tourist attraction X. When a response from external agent 30 includes information about such a location, such statistical values ​​(e.g., average values) about the location can be included along with the information about the location and information related to the statistical values ​​regarding the dwell time there. Agent unit 112, having received a response from external agent 30, suggests information about the location to the user via dialogue processing unit 111 and provides the statistical value information to processing unit 115 in preparation for processing in S108. Alternatively, the processing unit 115 may access external devices other than the external agent 30 via the network 20 to search for information about the visited locations and collect information about the length of stay at those locations.

[0059] In the example above, a first threshold is set for each suggested visit location; however, alternatively, a first threshold can be set for each type of visit location (e.g., outdoor facilities, indoor facilities, etc.).

[0060] Furthermore, when a user's dwell time exceeds a second threshold (greater than the first threshold), the processing unit 115 determines that the user has demonstrated a positive response to the suggested information. This determination is based on the concept that the longer the user's dwell time, the more positive the user's response to the location. The second threshold is set based on statistics regarding the dwell time of people who have previously visited the location and their evaluations of the location. The statistics regarding dwell time are as described above. Information about the location and the statistics regarding dwell time, along with information about the evaluations, can also be included in the response from the external agent 30 regarding the location. The second threshold can then be set based on the correlation between dwell time and the evaluation results. For example, when a large amount of dwell time can be extracted, a determination can be made based on this dwell time to indicate a positive response in the correlation between dwell time and evaluation results; the lower limit of this dwell time can be set as the second threshold. Alternatively, when accessing an external device other than the external agent 30 via the network 20, the processing unit 115 may search for information about the access location, collect information about the stay time and evaluation, and set a second threshold based on the collected results.

[0061] Note that when a user's dwell time exceeds the second threshold duration, but the suggested location belongs to a predetermined category where it is difficult to find a correlation between dwell time and the user's positive evaluation, processing unit 115 does not need to determine that the user has exhibited a positive response to the information suggestion. For example, when the suggested location is a place such as a restaurant or beauty salon, where user reviews tend to be based on the quality of service provided, it is conceivable that finding a correlation between dwell time and the user's positive evaluation would be difficult. When suggesting such locations, the second threshold is not used to determine whether the user has exhibited a positive response.

[0062] In this way, according to Figure 4 The processing shown can appropriately detect the user's response to suggestions regarding the location of the visit. Furthermore, the processing results of processing unit 115 (i.e., information about whether the user has shown a response to the suggestion regarding the location of the visit and whether the user has shown a positive response to the suggestion) can be accumulated in the vehicle-mounted device 10. Agent unit 112 then uses the processing results when making suggestions regarding future locations of the visit, thereby enabling even more appropriate information suggestions.

[0063] Furthermore, despite Figure 4 The process shown includes a set response time period, but it is not always necessary to set a response time period. In this case, after performing the suggestion process regarding the accessed location, the processes S107 and S108 are executed starting from the time point when it is detected that the user has accessed the accessed location.

[0064] Variation Example The above embodiments are merely examples, and this disclosure can be appropriately modified and implemented without departing from its scope. For example, the processes and means described in this disclosure can be freely combined and implemented, provided there is no technical inconsistency. For example, the information processing apparatus according to this disclosure can be configured as a server device arranged in a non-movable form, rather than as an in-vehicle device installed in a vehicle. In this case, the disclosure described in the first embodiment can be applied to this variant.

[0065] Furthermore, while the deployment of an external agent on an internet-connected external device has been illustrated in the embodiments, the external agent can alternatively be deployed on other types of devices. For example, the external agent can be deployed on an edge server accessible from the vehicle. Alternatively, the external agent can be deployed distributed across multiple edge servers or deployed in the cloud. Additionally, in this embodiment, the in-vehicle device 10 is illustrated as an information processing apparatus according to this disclosure; however, the information processing apparatus can also be implemented as a device or equipment not installed in a vehicle.

[0066] Note that when an external agent is deployed across multiple edge servers, the vehicle-mounted device 10 can obtain the vehicle's location information and identify the edge server on which the desired external agent is deployed based on that location information. For example, an external agent providing regional information may be deployed on multiple edge servers, each deployed in a different region. In this case, the vehicle-mounted device 10 can, for example, identify the external agent deployed on the geographically nearest edge server based on the vehicle's location information. The regional information processed by the external agent may vary depending on the edge server. For example, an external agent providing regional information for region A may be deployed on an edge server located in region A, and an external agent providing regional information for region B may be deployed on an edge server located in region B. The vehicle-mounted device 10 can identify the edge server corresponding to the region where the vehicle is located and obtain the regional information (information related to the access location) for that region by accessing the external agent provided by that edge server.

[0067] Furthermore, a process described as being performed by one device can be distributed among multiple devices and performed by multiple devices. Alternatively, a process described as being performed by different devices can be performed by one device. In a computer system, the hardware configuration (server configuration) used to implement various functions can be flexibly changed.

[0068] This disclosure can also be implemented by providing a computer with a computer program that performs the functions described in the above embodiments, and enabling one or more processors of the computer to read and execute the program. Such a computer program can be provided to the computer via a non-transitory computer-readable storage medium connectable 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 a magnetic disk (floppy disk, hard disk drive (HDD) etc.), an optical disk (CD-ROM, DVD, Blu-ray disc, etc.), ROM, RAM, EPROM, electrically erasable programmable read-only memory (EEPROM), magnetic cards, flash memory, optical cards, and any type of medium suitable for storing electronic commands.

Claims

1. An information processing apparatus, comprising: Control unit, which executes The system suggests information about visiting locations to users, and visits to those locations are recommended. After making the suggestion, obtain the user's location information, and When it is determined based on the acquired location information that the user has visited the access location and the user's stay at the access location exceeds a first threshold duration, it is determined that the user has exhibited reactive behavior in response to the suggestion regarding the access location information.

2. The information processing apparatus according to claim 1, wherein, When it is determined that the user has visited the location and the user's stay at the location is longer than the duration of a second threshold, the control unit further determines that the user has shown a positive response to the suggestion regarding the location, and the duration of the second threshold is greater than the duration of the first threshold.

3. The information processing apparatus according to claim 2, wherein, When the user's stay at the access location exceeds the duration of the second threshold, but the access location belongs to a predetermined category, the control unit does not determine that the user is exhibiting positive responsive behavior.

4. The information processing apparatus according to any one of claims 1 to 3, wherein, The first threshold is set based on statistics about the length of stay of people who have visited the location in the past.

5. The information processing apparatus according to claim 2 or 3, wherein, The second threshold is set based on statistics about the length of stay of people who have visited the site in the past and evaluations made by people who have visited the site related to the site.

Images