Information processing apparatus and information processing method

Abstract

The purpose of this invention is to provide appropriate services corresponding to the user's current situation. An information processing apparatus includes a control unit that performs the following processing: determining the user's current situation based on acquired information; selecting user profile data corresponding to the determined situation from multiple user profile data representing user personas generated according to multiple possible situations the user may be in, based on the user's dialogue history or user attribute information; acquiring target user profile data representing the personas to which the service is provided from multiple devices providing services to the user; calculating the fit rate between each of the selected user profile data and the target user profile data for the service; and issuing an instruction to the device providing the service with the highest fit rate to provide the service to the user.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, etc., that provides information through dialogue with a user. Background Technology

[0002] There is a technology that uses natural language processing to conduct dialogues with users and to provide information to users based on these dialogues. For example, Patent Document 1 discloses a dialogue device that, based on the extracted strings of the user's preferred objects and the polarity of the user's preference for those objects, extracts strings of the user's preferred objects that are highly likely to be preferred, extracts the most typical words related to the semantic attributes of those strings, and uses them as preference extension information to generate speech.

[0003] Patent Document 1: Japanese Patent Application Publication No. 2015-225414 Summary of the Invention

[0004] The purpose of this invention is to use machine learning to provide appropriate services that correspond to the user's situation.

[0005] One aspect of the present invention is an information processing device.

[0006] The information processing device has user attribute information and is capable of natural language-based dialogue. The information processing device includes a control unit that performs the following processing: determining the user's current state based on acquired information; selecting one user profile data corresponding to the determined state from multiple user profile data representing user personas generated according to multiple possible states, based on the user's dialogue history or the user's attribute information; acquiring target user profile data representing the persona to which the service is provided from each of multiple devices providing services to the user; calculating the fit rate between the selected user profile data and each of the target user profile data for the service; and issuing an instruction to the device providing the service with the highest fit rate to provide the user with the service set with the target user profile data having the highest fit rate.

[0007] Furthermore, another aspect of the present invention is an information processing method.

[0008] The information processing method is executed by an information processing device that has user attribute information and is capable of natural language-based dialogue. The information processing method includes the following steps: determining the current state of the user based on the acquired information; selecting one user profile data corresponding to the determined state from multiple user profile data that represent the user's persona generated according to multiple states the user may be in, based on the user's dialogue history or the user's attribute information.

[0009] The system acquires target user profile data, representing the persona to which the service is intended, from each of a plurality of devices providing the service; calculates the fit rate between the selected user profile data and each of the target user profile data of the service; and issues an instruction to the device providing the service with the highest fit rate to provide the user with the service set with the target user profile data having the highest fit rate.

[0010] Furthermore, as another approach, examples include programs for causing a computer to perform the aforementioned information processing methods, or computer-readable storage media that non-temporarily stores such programs.

[0011] Invention Effects

[0012] The information processing apparatus involved in this invention can provide appropriate services corresponding to the user's situation. Attached Figure Description

[0013] Figure 1 This is a diagram illustrating the network structure including the server apparatus involved in the implementation.

[0014] Figure 2 This is a diagram illustrating the constituent elements of the server device according to the embodiments.

[0015] Figure 3 This is a flowchart of the process for generating user profile data performed by the server device involved in the implementation method.

[0016] Figure 4 This is a flowchart of the process performed by the server device involved in the implementation to provide a service with a high suitability rate for user profile data. Detailed Implementation

[0017] (summary)

[0018] There is a need for services that provide users with appropriate information based on natural language-based dialogue with them.

[0019] Relatedly, there are technologies that extract user preferences from conversations with users and generate their own messages.

[0020] For example, existing dialogue devices can analyze input strings to analyze user preferences and generate speech that includes information corresponding to the user's preferences.

[0021] Specifically, existing dialogue devices extract strings representing the user's preferred objects and the polarity of the user's preference for those objects. Then, the device extracts the subject of the preference representing the superordinate concept of the preferred object, and extracts strings representing preferred objects that are also highly likely to be preferred. Next, the device extracts the most representative words related to semantic attributes and uses these extracted elements as preference extension information to generate utterances based on that preference extension information.

[0022] However, existing dialogue devices have room for improvement. For example, even if a dialogue device can determine a user's preferences once, those preferences can change depending on the situation. Specifically, consider the following example: when a user is at work, they prefer business-related information, but when they are spending their day off with family, they prefer childcare-related information. Thus, the user persona (here, called the user profile) that the information processing device should envision for the user during the dialogue can differ depending on the user's situation. If the information processing device provides information or services that do not match the user's situation, it cannot adequately meet the user's needs in that scenario. Therefore, it is preferable for the information processing device to be able to provide information or services that match the user's situation.

[0023] In an information processing apparatus according to one aspect of the present invention,

[0024] The information processing device has user attribute information and is capable of natural language-based dialogue. The information processing device includes a control unit that performs the following processing: determining the user's current state based on acquired information; selecting one user profile data corresponding to the determined state from multiple user profile data representing user personas generated according to multiple possible states, based on the user's dialogue history or the user's attribute information; acquiring target user profile data representing the persona to which the service is provided from each of multiple devices providing services to the user; calculating the fit rate between the selected user profile data and each of the target user profile data for the service; and issuing an instruction to the device providing the service with the highest fit rate to provide the user with the service set with the target user profile data having the highest fit rate.

[0025] Attribute information refers to information that represents attributes such as a user's age, gender, and affiliation.

[0026] A dialogue history refers to a record of the content of a natural language-based dialogue between an information processing device and a user.

[0027] User profile data refers to data that represents the persona of a user corresponding to their current situation. Multiple user profiles can be created for a single user. For example, during the daytime on a weekday, the user's profile might represent a business professional, while during the daytime on a weekend, the user's profile might represent a father caring for his child.

[0028] Target user profile data refers to data representing the image of a person who is the recipient of a service, as defined by the device providing the service. For example, the target user profile data for a device providing economic newspaper content is men and women in their 20s to 60s, while the target user profile data for a device providing educational animated videos is elementary school boys and girls.

[0029] The control unit calculates the fit rate between the user profile data corresponding to the determined user's condition and the target user profile data set by each device providing the service, and issues an instruction to the device providing the service to provide the target user profile data set with the highest fit rate.

[0030] Thus, the information processing apparatus of the present invention can determine the user profile of the user corresponding to the current situation and provide the service of the determined user profile with the highest suitability.

[0031] According to this structure, the information processing device involved in the present invention can provide appropriate services according to the user's situation.

[0032] Furthermore, the multiple user profile data may include at least one of the following: user profile data representing the image of a person when the user is alone, user profile data representing the image of a person when the user is with family, and user profile data representing the image of a person when the user is at work or school.

[0033] Therefore, the information processing device involved in this invention can set appropriate user profile data corresponding to the specific situation that the user may be in.

[0034] The information obtained may include at least one of the following: conversation history with the user and itself; sound acquired by multiple sensors located around the user; images captured by cameras located around the user; the user's location information; and the user's schedule information acquired from external services used by the user. The control unit determines the situation based on the first information.

[0035] Therefore, the information processing device involved in this invention can accurately determine the user's status based on various data resources.

[0036] Furthermore, the control unit can update the user profile data of the user corresponding to the determined situation based on the first information under the determined situation.

[0037] Therefore, the information processing device involved in this invention can identify user profiles of appropriate users that correspond to the actual situation.

[0038] Hereinafter, specific embodiments of the present invention will be described with reference to the accompanying drawings. Unless otherwise specified, the hardware structures, module structures, functional structures, etc., described in each embodiment are not intended to limit the scope of the invention to these.

[0039] (Implementation Method)

[0040] [Summary of the processing performed by the server device]

[0041] refer to Figure 1 The outline of the processes performed by the server device according to the embodiments will be described. Figure 1 This is a diagram illustrating the network structure including the server device 100 involved in the embodiments. The information processing apparatus according to one aspect of the present invention is implemented by the server device 100.

[0042] Server device 100 is an information processing device that provides appropriate information to user 30 based on a dialogue with user 30 conducted using natural language processing employing generative artificial intelligence (AI). Typically, user 30, while riding in vehicle 10, speaks to an in-vehicle terminal that communicates with server device 100. Server device 100 analyzes the user 30's spoken voice, etc., acquired via the in-vehicle terminal, and generates a response corresponding to the meaning of the spoken voice. Then, when generating a response corresponding to the meaning of the spoken voice, if server device 100 determines that the information requested by user 30 exists in an external device, it issues an instruction to the external device to provide service to user 30. Alternatively, the natural language processing for generating the dialogue with user 30 can also be performed by the in-vehicle terminal. In this case, the in-vehicle terminal is equipped with artificial intelligence such as generative AI.

[0043] For example, server device 100 receives a voice message from user 30 asking, "Where are some restaurants nearby where I can have lunch?", analyzes the meaning of the voice message, and issues an instruction to the device providing information about restaurants where lunch can be served, instructing it to provide services to user 30. At this time, for example, the device providing information about restaurants where lunch can be served might respond by providing the user with the specific name and location of the restaurant. Alternatively, the vehicle terminal can also output the information provided by the device providing information about restaurants where lunch can be served as voice output generated by server device 100.

[0044] When the server device 100 receives and analyzes the user 30's voice messages to provide information, it needs to accurately grasp the user 30's needs. For example, if the user 30 is at work, providing information about rest days will not fully meet the user 30's needs.

[0045] Therefore, the server device 100, the vehicle 10, and the devices 200a to 200c are configured such that the server device 100 can provide appropriate information corresponding to the situation of the user 30, thereby fully meeting the needs of the user 30.

[0046] The server device 100 acquires information detected by various sensors, such as the camera 16, installed in the vehicle 10. Specifically, the camera 16 transmits the information via the vehicle 10's communication unit (described later) connected to the vehicle network, and the vehicle 10's communication unit transmits the information to the server device 100 via a wide area network.

[0047] Server device 100 stores table 1000 containing user profile data. Furthermore, the user profile data can include attributes representing the target user such as gender, age, keywords indicating interests, and family structure. Keywords indicating interests can be appropriately set from the user profile data, including the user's occupation, role within the family, interests, and leisure time habits.

[0048] Furthermore, devices 200a-200c store target user profile data representing the image of the person who becomes the object of the service provided by each device. The target user profile data may include the target user's gender, age, occupation, interests, annual income, leisure time spending habits, family structure, etc.

[0049] Server device 100 sends an instruction to the device among devices 200a-200c that has the highest fit rate between the user profile data of user 30 and the target user profile data of that device, to provide the services offered by that device to user 30. For example, server device 100 sends an instruction to device 200c that has the target user profile C with the highest fit rate with the user profile data of user 30. Then, device 200c that receives the instruction provides services to user 30.

[0050] [Structure of the server device]

[0051] Next, the hardware and software structures of the system including the server device 100 will be described. Figure 2 This is a diagram illustrating the constituent elements of the server device 100 according to the embodiment.

[0052] Server device 100 can be configured as a computer having a processor (CPU, GPU, etc.), main storage (RAM, ROM, etc.), and auxiliary storage (EPROM, hard disk drive, removable media, etc.). The auxiliary storage stores an operating system (OS), various programs, various tables, etc., and by executing the programs stored therein, various functions (software modules) matching the specified purpose can be achieved, as described later. However, some or all of the functions can also be implemented as hardware modules, for example, using hardware circuits such as ASICs or FPGAs.

[0053] The server device 100 comprises a control unit 110, a storage unit 120, a communication unit 130, and a dialogue unit 140.

[0054] The control unit 110 is a computing unit that executes a predetermined program to implement various functions of the server device 100. The control unit 110 can be implemented, for example, by a hardware processor such as a CPU. Furthermore, the control unit 110 may be configured with RAM, read-only memory (ROM), cache memory, etc.

[0055] In this embodiment, the control unit 110 of the server device 100 is configured with seven software modules: a first acquisition unit 111, a generation unit 112, a determination unit 113, a selection unit 114, a second acquisition unit 115, a calculation unit 116, and an instruction unit 117. Each software module can also be implemented by the control unit 110 (CPU, etc.) executing a program stored in the storage unit 120 (described later). Furthermore, the information processing performed by the software modules has the same meaning as the information processing performed by the control unit 110 (CPU, etc.).

[0056] The first acquisition unit 111 acquires data detected by the sensor 15 or the camera 16. The data acquired by the first acquisition unit 111 is not limited to the above, as long as it is used to determine the status of the user 30. The first acquisition unit 111 can acquire the dialogue history between the user 30 and the dialogue unit 140, the sound acquired by the sensor 15, the images captured by the camera 16, and the location information of the user 30. Furthermore, the first acquisition unit 111 can also acquire the user 30's schedule information from external devices different from devices 200a-200c. This information is referred to as "first information." Additionally, the user 30's location information can be the location information of a terminal associated with the user 30, detected by a Global Navigation Satellite System (GNSS).

[0057] Furthermore, during the generation stage of user profile data of user 30, the first acquisition unit 111 acquires the attribute information of user 30 and the dialogue history between user 30 and dialogue unit 140.

[0058] The generation unit 112 generates user profile data, representing the persona of user 30, based on the attribute information of user 30 and the dialogue history between user 30 and the dialogue unit 140, according to the multiple states that user 30 may be in.

[0059] Figure 3 This is a flowchart illustrating the process of generating user profile data performed by the server device 100 according to the implementation method. Figure 3 The process of processing the user profile data of user 30 pre-generated by the generation unit 112 is explained.

[0060] The server device 100 begins processing step S10 after a predetermined operation has been performed. For example, the server device 100 may begin processing step S10 when the setting update button is pressed on the vehicle terminal 17. Alternatively, the server device 100 may execute the processing step S10 at predetermined time intervals.

[0061] First, in step S10, the first acquisition unit 111 acquires the attribute information of the user 30. The first acquisition unit 111 can acquire information representing each item of the user 30's attribute information input by the user 30 into the vehicle terminal 17 or the like, or it can acquire data representing the user 30's attributes from a terminal associated with the user 30. Here, the user 30's attribute information may include, for example, data representing the user 30's name, age, gender, address, occupation, body type, family composition, annual income, etc.

[0062] Next, in step S11, the first acquisition unit 111 acquires the dialogue history between user 30 and dialogue unit 140. The first acquisition unit 111 acquires the dialogue history including content automatically classified or annotated by the AI ​​of dialogue unit 140 based on user 30's spoken text.

[0063] Next, in step S12, the generation unit 112 generates user profile data based on the attribute information of user 30 and the dialogue history between user 30 and dialogue unit 140, according to the possible states that user 30 may be in. The generation unit 112 analyzes the attribute information and dialogue history of user 30 to extract the possible states that user 30 may be in. Then, the generation unit 112 sets user profile data corresponding to each possible state that user 30 may be in.

[0064] In addition, the user profile data may include at least one of the following: user profile data representing the image of the person corresponding to the user 30 when spending time alone, user profile data representing the image of the person corresponding to the user 30 when spending time with family, and user profile data representing the image of the person corresponding to the user 30 when spending time at the workplace or school.

[0065] Thus, the generation unit 112 extracts the possible states of multiple users 30 by analyzing dialogue history, etc., and sets user profile data that matches each state by comparing these states with the attribute information of users 30.

[0066] The determination unit 113 determines the current state of the user 30 based on the data acquired by the first acquisition unit 111. The determination unit 113 can combine various types of data acquired by the first acquisition unit 111 to determine the current state of the user 30.

[0067] Based on the determined situation, the selection unit 114 selects user profile data that matches the current situation of user 30 from the multiple user profile data generated by the generation unit 112. The selection unit 114 may select only one user profile data that matches the current situation of user 30, or it may select two or more.

[0068] The second acquisition unit 115 acquires target user profile data, representing the image of a person who is the recipient of the service provided by that device, from each of the plurality of devices providing services to the user. The second acquisition unit 115 communicates with each of the devices 200a to 200c providing services to the user via the communication unit 130.

[0069] The calculation unit 116 calculates the fit rate between the user profile data of the user 30 selected by the determination unit 113 and each of the multiple target user profile data acquired by the second acquisition unit 115.

[0070] The instruction unit 117 issues an instruction to the device that has the target user profile data with the highest suitability calculated by the calculation unit 116, so as to provide the service provided by the device to the user 30. The instruction unit 117 sends the instruction to the device via the communication unit 130.

[0071] The storage unit 120 is a unit for storing information and is composed of storage media such as RAM, disk, or flash memory. The storage unit 120 stores programs executed by the control unit 110, data used by those programs, etc.

[0072] The communication unit 130 is a wireless communication interface for connecting the server device 100 to an external network. The communication unit 130 is configured, for example, to communicate with external devices via a wireless LAN or a cellular communication network such as 3G, 4G or 5G.

[0073] The dialogue unit 140 is a processing unit that conducts natural language-based dialogues with the user 30. The dialogue unit 140, as software, incorporates generative AI to analyze the user 30's voice or input text recognized by the microphone, and generates a response corresponding to the meaning expressed by the voice or text. The dialogue unit 140 can communicate with a wide area network via the communication unit 130 to obtain information. The dialogue unit 140 outputs responses in the form of voice or text.

[0074] Vehicle 10 is a vehicle capable of communicating with a wide area network. Vehicle 10 can be a passenger car, or a large vehicle such as a bus or truck. Vehicle 10 includes a control unit 11, a storage unit 12, a communication unit 13, a drive unit 14, sensors 15, a camera 16, and an on-board terminal 17.

[0075] The control unit 11 is a computing unit that executes prescribed programs to implement various functions of the vehicle 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. The control unit 11 executes various software programs to control the driving of the vehicle 10, etc.

[0076] The storage unit 12 is a unit for storing information and is composed of storage media such as RAM, disk, or flash memory. The storage unit 12 stores programs executed by the control unit 11, data used by those programs, and so on.

[0077] The communication unit 13 is a wireless communication interface for connecting the vehicle 10 to an external network. The communication unit 13 is configured, for example, to communicate with external devices via a wireless LAN or a cellular communication network such as 3G, 4G or 5G.

[0078] The drive unit 14 is a mechanism for driving the vehicle 10. The drive unit 14 can be configured to include, for example, an electric motor for driving the wheels, an inverter, a brake, and a steering mechanism. The drive unit 14 can be operated by power supplied from a battery.

[0079] Sensor 15 is a type of sensor installed in vehicle 10. Sensor 15 can be, for example, a temperature sensor, a radio wave ranging sensor, an infrared sensor, a touch sensor, a microphone, etc.

[0080] Camera 16 is an in-vehicle camera installed in vehicle 10. Camera 16 is configured to at least capture images inside the vehicle interior. Camera 16 is a camera with an imaging element such as a charge-coupled device (CCD) or complementary metal-oxide-semiconductor (CMOS).

[0081] The vehicle-mounted terminal 17 is a terminal that receives operations from the user 30 of the vehicle 10 regarding various devices equipped in the vehicle or provides information to the user 30. In the event of a dialogue between the server device 100 and the user 30 using natural language processing, the vehicle-mounted terminal 17 receives input from the user 30 and sends the input to the server device 100. The server device 100 then generates a response to the input and sends it to the vehicle-mounted terminal 17. The vehicle-mounted terminal 17 then outputs text or audio representing the received response.

[0082] in addition, Figure 2 The structure shown is an example; specially designed circuitry can be used to perform all or part of the illustrated function. Furthermore, programs can also be stored or executed using a combination of main and auxiliary storage devices, other than those shown in the diagram.

[0083] [Server device processing]

[0084] Next, the specific details of the processing performed by the server device 100 according to one aspect of the present invention will be described.

[0085] Figure 4 This is a flowchart of a process executed by the server device 100 according to the implementation method, which issues instructions to provide a service with a high suitability rate for user profile data.

[0086] When the server device 100 receives a specified operation from the user, it begins the processing of step S20. For example, when the server device 100 receives a voice message from the user 30 requesting service, it may begin the processing of step S20.

[0087] First, in step S20, the first acquisition unit 111 acquires data detected by the sensor 15. For example, the first acquisition unit 111 acquires the result detected by the sensor 15 or sound detected by the microphone. In step S20, an image captured by the camera 16 may be acquired. The first acquisition unit 111 may acquire first information.

[0088] Next, in step S21, the determination unit 113 determines the current situation of the user 30 based on the data acquired by the first acquisition unit 111. For example, the determination unit 113 determines, based on the images of the user 30 and the vehicle interior captured by the camera 16, that the user 30 is on vacation and riding in the vehicle 10 with his family.

[0089] Next, in step S22, the selection unit 114 selects user profile data of user 30 corresponding to the determined situation. For example, the selection unit 114 selects user profile data representing a father who is taking care of his child as the user profile data corresponding to the situation determined in step S21 where the user is on vacation and riding in vehicle 10 with his family.

[0090] Next, in step S23, the second acquisition unit 115 acquires target user profile data representing the target audience of the service provided by each of the plurality of devices providing the service requested by the user 30. For example, the second acquisition unit 115 acquires target user profile data set for each service from each of the three external devices 200a to 200c that provide the service. The second acquisition unit 115 can acquire target user profile data set individually by the device providing each service, or it can set target user profile data for each service by analyzing arbitrary information acquired from the devices providing each service.

[0091] For example, server device 100 obtains target user profile A from device 200a, target user profile B from device 200b, and target user profile C from device 200c. For example, device 200a is a device providing an online shopping website for a company selling outdoor products, and target user profile A is women in their 20s to 50s who enjoy the outdoors. And, for example, device 200b is a device providing a news website offering economic news, and target user profile B is a businessperson. And, for example, device 200c is a device distributing videos with parenting information for fathers with children, and target user profile C is a father raising children.

[0092] Next, in step S24, the calculation unit 116 calculates the fit rate of each of the user profile data of the user 30 selected in step S22 and the target user profile data obtained in step S23.

[0093] For example, the calculation unit 116 can determine whether the information represented by the items included in the user profile data of user 30 is consistent with the information represented by the items included in the target user profile data. Then, the calculation unit 116 can calculate the proportion of items in all items included in the user profile data of user 30 that are consistent with the items included in the target user profile data as the fit rate.

[0094] Alternatively, the calculation unit 116 can assign weights to the items included in the user profile data of user 30 in order of importance. Then, the calculation unit 116 can multiply the weights of the items included in the user profile data of user 30 that are consistent with the items included in the target user profile data, and then calculate their proportion among all items in the user profile data of user 30 as the fit rate.

[0095] For example, consider the following situation: Target user profile C, which is the target user profile data for device 200c, includes the items "30+ years old, 40+ years old, male, female, has children," while user profile data for user 30 includes the items "30+ years old, male, has children." In this case, the calculation unit 116 can calculate that all items included in user profile data for user 30 are included in target user profile C, and therefore calculate the fit rate as 100%.

[0096] Furthermore, consider, for example, the following situation: Target user profile A, which is the target user profile data for device 200a, includes the item "20s, 30s, 40s, 50s, female, likes the outdoors," while user profile data for user 30 includes the item "30s, male, has children." In this case, the calculation unit 116 can calculate that only one item included in user profile data for user 30 is included in target user profile A, and therefore calculate the fit rate as 33%.

[0097] Furthermore, consider the following scenario: Target user profile B, which serves as the target user profile data for device 200b, includes the categories of "20s, 30s, 40s, 50s, 60s, and business professionals." User profile data for user 30 includes the categories of "30s, male, and has children." As for user profile data for user 30, the category of "30s, male, and has children" was selected, therefore the fitness rate is calculated to be 33%. User 30 also has the category of "business professional," but this was not selected under the current circumstances and is therefore not considered in the fitness rate calculation.

[0098] Next, in step S25, the instruction unit 117 sends an instruction to the device that provides the target user profile data with the highest suitability rate to provide the service to the user 30. For example, the instruction unit 117 sends an instruction to the device 200c, which has a suitability rate of 100% and displays the highest suitability rate among the three devices, to provide the service provided by the device 200c to the user 30.

[0099] Additionally, the instruction unit 117 can send instructions to multiple devices among those devices that have target user profile data with a suitability rate of a predetermined value or higher, to provide the user 30 with the services offered by those devices. When the user 30 receives notifications of service provision from multiple devices, they can select the device from which they wish to receive the service.

[0100] As described above, in this embodiment, the server device 100 selects user profile data of user 30 that matches the current situation of user 30, and sends an instruction to the device that provides the service most suitable for the user profile data. Thus, the server device 100 is able to provide appropriate services according to the user's current situation.

[0101] (Modifications of the implementation method)

[0102] In this implementation, user profile data for user 30 is pre-generated. However, user profile data for user 30 is not fixed and can change at any time. Therefore, in a variation of this implementation, when determining the current state of user 30 and selecting user profile data for user 30, the user profile data for user 30 is also updated appropriately.

[0103] Generation section 112 in Figure 4 After step S21 as described above and before the processing in step S22, the following processing is performed.

[0104] The generation unit 112 updates the user profile data of user 30 corresponding to the determined situation based on data (first information) acquired by the sensor 15 or camera 16, etc., under the situation determined in step S21. For example, consider the following situation: As user profile data for user 30, only user profile data for a male businessman in his 30s and a male in his 30s who is raising children is set. In this case, if the generation unit 112 can detect from the first information that user 30 is engaged in outdoor activities, the generation unit 112 can add user profile data for a male in his 30s who likes the outdoors to user profile data for user 30.

[0105] As described above, the server device 100 in the modified embodiment can appropriately update the user profile data set for the user 30 in response to changes in the user 30's situation. Therefore, the server device 100 in the modified embodiment can provide services that better meet the needs of users in a realistic way.

[0106] (Other variations)

[0107] The above-described embodiments are merely examples, and the present invention can be implemented with appropriate modifications without departing from its spirit. For example, the processes and apparatus described in the present invention can be freely combined and implemented without causing technical conflicts.

[0108] In addition, when a device provides multiple services, the instruction unit 117 can send an instruction to the device to provide the user 30 with the service with the highest suitability rate among the multiple services provided by the device.

[0109] Furthermore, the calculation unit 116 will calculate a higher suitability rate for target user profile data that includes more items than those included in user profile data of user 30, but the calculation method for suitability rate is not limited to this. The more items in the target user profile data that are not completely identical to those in user profile data of user 30 but have high affinity (or highly relevant keywords), the higher the suitability rate of the target user profile data can be calculated. Moreover, the calculation unit 116 can calculate a higher suitability rate for target user profile data that includes a larger number of items, where the domain of these items is suitable for the items included in user profile data of user 30.

[0110] Furthermore, in this embodiment, an example of the information processing device according to the present invention being a server device 100 has been described. However, the information processing device according to the present invention can also be implemented as a vehicle-mounted terminal. When the information processing device according to the present invention is implemented as a vehicle-mounted terminal, the following are all performed by the vehicle-mounted terminal mounted on the vehicle 10: determining the state of the user 30, selecting user profile data corresponding to the state of the user 30, acquiring target user profile data, calculating the fit rate between the selected user profile data and the target user profile data, and sending an instruction to any one of the devices 200a to 200c.

[0111] When the information processing device involved in this invention is implemented as a vehicle-mounted terminal, the vehicle-mounted terminal obtains data from sensors 15 or cameras 16 provided in the vehicle 10 to determine the status of the user 30. Then, the vehicle-mounted terminal obtains multiple user profile data corresponding to the user 30 from the server device, and selects the user profile data corresponding to the status of the user 30 from the obtained user profile data.

[0112] Then, the vehicle-mounted terminal communicates with devices 200a-200c via a server device, obtaining target user profile data from each device. Next, the vehicle-mounted terminal calculates the fit rate between the selected user profile data and each target user profile data, and sends an instruction via the server device to the device holding the user profile data with the highest fit rate, instructing it to provide service to user 30. Alternatively, the vehicle-mounted terminal can also send this instruction via the server device to multiple devices with fit rates above a predetermined value. In this case, user 30 receives service notifications from multiple devices. Then, user 30 can select the desired device from the devices that received the notifications.

[0113] In addition, the vehicle terminal can also communicate directly with devices 200a to 200c to obtain target user profile data from devices 200a to 200c, or send an instruction to any of devices 200a to 200c to provide services to user 30.

[0114] The present invention can also be implemented by supplying a computer program with the functions described in the above embodiments to a computer, and having the computer read and execute the program by one or more processors. 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 via a network. Non-transitory computer-readable storage media include, for example, any type of disk such as a hard disk (floppy disk, hard disk drive (HDD), etc.), an optical disk (CD-ROM, DVD, Blu-ray disc, 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.

[0115] Symbol Explanation

[0116] 100 - Server device, 110 - Control unit, 111 - First acquisition unit, 112 - Generation unit, 113 - Judgment unit, 114 - Selection unit, 115 - Second acquisition unit, 116 - Calculation unit, 117 - Instruction unit, 120 - Storage unit, 130 - Communication unit.

Claims

1. An information processing device having user attribute information and capable of engaging in natural language-based dialogue, characterized in that it comprises: The control unit performs the following processing: Based on the information obtained, determine the user's current situation; Based on the user's conversation history or the user's attribute information, select one user profile data corresponding to the determined situation from multiple user profile data that represent the user's persona generated according to multiple situations the user may be in. Information representing the person to whom the service is provided, i.e., target user profile data, is obtained from each of the multiple devices providing services to the user; Calculate the fit rate between the selected user profile data and each of the target user profile data of the service; and Instructions are sent to the device that provides the service with the highest suitability rate to provide the user with the target user profile data that has the highest suitability rate.

2. The information processing device according to claim 1, characterized in that, The multiple user profile data include at least one of the following: User profile data representing the image of a person when the user is alone, user profile data representing the image of a person when the user is with family, and user profile data representing the image of a person when the user is at work or school.

3. The information processing apparatus according to claim 1 or 2, characterized in that, As part of the acquired information, the first information includes at least one of the following: the user's conversation history with themselves, sound acquired by multiple sensors placed around the user, images captured by cameras placed around the user, the user's location information, and the user's schedule information acquired from external services used by the user. The control unit performs the following processing: The situation is determined based on the first piece of information.

4. The information processing apparatus according to claim 3, characterized in that, The control unit performs the following processing: Based on the first information under the determined situation, update the user profile data of the user corresponding to the determined situation.

5. An information processing method, executed by an information processing device having user attribute information and capable of natural language-based dialogue, the information processing method being characterized by comprising the following steps: Based on the information obtained, determine the user's current situation; Based on the user's conversation history or the user's attribute information, select one user profile data corresponding to the determined situation from multiple user profile data that represent the user's persona generated according to multiple situations the user may be in. Information representing the person to whom the service is provided, i.e., target user profile data, is obtained from each of the multiple devices providing services to the user; Calculate the fit rate between the selected user profile data and each of the target user profile data of the service; and Instructions are sent to the device that provides the service with the highest suitability rate to provide the user with the target user profile data that has the highest suitability rate.

Images