JP7018002B2 - Information processing equipment, information processing methods, and information processing programs - Google Patents

Description

The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

Conventionally, there is known an information processing device that sets an advertisement to be displayed in an advertisement space included in a page viewed by the user according to the environment in which the user is located (see Patent Document 1).

Japanese Unexamined Patent Publication No. 2014-109992

However, the above-mentioned information processing apparatus has room for improvement in providing service information related to a service for accepting an order spoken by a user.

The present application is made in view of the above, and provides an information processing device, an information processing method, and an information processing program that improve a method of providing service information related to a service that accepts an order by a user's utterance. The purpose.

The information processing apparatus according to the present application includes an acquisition unit, a determination unit, and a distribution unit. The acquisition unit acquires context information about the user. The determination unit determines the service information related to the service that accepts the order by the user's utterance based on the acquired context information of the current user. The distribution unit distributes the determined service information to the user's terminal device.

According to one embodiment, it is possible to provide an information processing device, an information processing method, and an information processing program that improve a method of providing service information related to a service that accepts an order spoken by a user.

FIG. 1A is a diagram (No. 1) for explaining information processing according to an embodiment. FIG. 1B is a diagram (No. 2) for explaining information processing according to the embodiment. FIG. 2 is a diagram showing a configuration example of an information processing system according to an embodiment. FIG. 3 is a block diagram showing a configuration example of the information providing device according to the embodiment. FIG. 4A is an example (No. 1) showing utterance request information displayed on the screen of the user's terminal device. FIG. 4B is an example (No. 2) showing utterance request information displayed on the screen of the user's terminal device. FIG. 4C is an example (No. 3) showing utterance request information displayed on the screen of the user's terminal device. FIG. 5 is an example of a table summarizing the scores for the product IDs. FIG. 6 is a flowchart illustrating a model generation process according to the embodiment. FIG. 7 is a flowchart illustrating the voice advertisement determination process according to the embodiment. FIG. 8 is a hardware configuration diagram showing an example of a computer that realizes the function of the information providing device.

Hereinafter, the information processing apparatus, the information processing method, and the embodiment for implementing the information processing program (hereinafter referred to as “the embodiment”) according to the present application will be described in detail with reference to the drawings. It should be noted that this embodiment does not limit the information processing apparatus, information processing method, and information processing program according to the present application.

[1. Information processing]
An example of information processing according to the embodiment will be described. FIG. 1A is a diagram (No. 1) for explaining information processing according to an embodiment. FIG. 1B is a diagram (No. 2) for explaining information processing according to the embodiment. Here, information processing is performed by the information providing device 2 (information processing device) capable of communicating with the terminal device 3.

The information providing device 2 and the terminal device 3 are connected to each other so as to be able to communicate with each other wirelessly or by wire via the network N. The network N is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network) such as the Internet, and is composed of one or more networks.

The terminal device 3 is, for example, a smart device (smartphone or tablet), a mobile phone, a personal computer, or the like, and can input voice. Here, the terminal device 3 will be described by taking a smart device as an example, but the terminal device 3 is not limited to the smart device. The terminal device 3 has, for example, a GPS (Global Positioning System) sensor that acquires information about the current position. The terminal device 3 can order a product by utterance, that is, an order of a product by a voice user interface.

Service information is distributed by installing a predetermined application on the terminal device 3. The predetermined application is, for example, an application in which music is distributed or an application in which radio can be listened to.

The service information is service information related to a service that accepts an order uttered by the user U. Specifically, the service information is service information that prompts an order (purchase) by the utterance of the user U, and is notification information including contents of introducing a product and inquiring about the purchase of the product. The service information is, for example, voice advertisement information or recommendation information. The recommendation information is information including the recommendation information by voice and the recommendation information by screen display. Here, voice advertisement information will be described as an example of service information, but the service information is not limited to voice advertisement information. The voice advertisement information is delivered by voice to the terminal device 3 of the user U in which the predetermined application is installed.

At the first predetermined timing, the information providing device 2 delivers voice advertisement information to the terminal device 3 of the user U in which the predetermined application is installed. The first predetermined timing is, for example, in an application in which music is distributed, a timing at which a preset predetermined time elapses and the music is switched. In the following, the terminal device 3 in which the predetermined application is installed, that is, the terminal device 3 to which the voice advertisement information is distributed may be referred to as "the terminal device 3 of the user U".

The information providing device 2 acquires the context information of the user U (S10).

The context information is information indicating the context regarding the user U. The context information includes surrounding information indicating the situation around the user.

The surrounding information includes the place where the user U exists (current position) and at _{least one} of the existence of other people P1 and P2 around the user U.

The information providing device 2 acquires the current position of the user U from, for example, the GPS sensor of the terminal device 3 of the user U. Further, the information providing device 2 acquires information for determining whether or not another person P ₁ or P ₂ exists around the terminal device 3 of the user U. The information providing device 2 acquires the current positions of the other person P ₁ and P ₂ from, for example, the GPS sensor of the terminal device 3 ₁ of the other person P ₁ and the terminal device 3 ₂ of the other person P ₂ . Then, the information providing device ₂ determines whether or not _other people P1 and P2 exist around the user U.

Whether or not another person P ₁ or P ₂ exists around the user U is determined by short-range wireless communication, for example, communication by a method such as FeliCa, ISO / IEC14443 (MIFARE), or Bluetooth (registered trademark). It may be detected and performed by the terminal device 3 of the user U.

Further, the determination as to whether or not another person P ₁ or P ₂ exists around the user U is not limited to the above method, and may be performed based on the current position of the user U. That is, for example, the information providing device 2 may determine the existence of the other person P ₁ and P ₂ without depending on the information from the terminal devices 3 ₁ and 3 ₂ of the other person P ₁ and P ₂ . The information providing device ₂ estimates that, for example, when the user U is at a specific station where people gather or at a specific place, there are _other people P1 and P2 around the user U, and the surroundings of the user U. It may be determined that another person P ₁ or P ₂ exists in the area.

The information providing device 2 determines the voice advertisement information to be delivered to the terminal device 3 of the user U based on the acquired context information (S11). For example, the information providing device 2 determines the voice advertisement information related to the service that accepts the order uttered by the user U based on the current context information of the user U.

Here, when there are other people P ₁ and P ₂ around the user U, it is difficult for the user U to order the frozen dumplings by utterance, and when the other people P ₁ and P ₂ exist around the user U. Even if there is, the user U can easily order the dry battery by utterance.

For example, as shown in FIG. 1A, when the user U is around (inside the alternate long and short dash line in FIG. _1A ), the information providing device ₂ places an order by the user U by speaking. The voice advertisement information about the dry battery, which is difficult for the user U to easily place an order by utterance, is determined as the voice advertisement information to be delivered to the terminal device 3 of the user U, instead of the voice advertisement information about the frozen dumplings.

When _other people P1 and P2 exist around the user U, the information providing device ₂ delivers, for example, voice advertisement information such as "Should I order a dry battery?" To the terminal device 3 of the user U. Determined as voice advertisement information to be performed.

On the other hand, for example, as shown in _FIG . _1B , when there are no other persons P1 and P2 around the user U (inside the alternate long and short dash line in FIG. _1B ), the utterance is heard by the _other persons P1 and P2. Will never be. Therefore, when the other person P ₁ and P ₂ do not exist around the user U, the information providing device 2 determines the voice advertisement information regarding the frozen dumplings as the voice advertisement information to be delivered to the terminal device 3 of the user U.

When there are no _other people P1 and P2 around the user U, the information providing device ₂ sends voice advertisement information such as "Should I order frozen dumplings?" To the terminal device 3 of the user U. Determined as voice advertisement information to be delivered.

Then, the information providing device 2 distributes the determined voice advertisement information to the terminal device 3 of the user U (S12).

In this way, the information providing device 2 determines the voice advertisement information (service information) related to the service that accepts the utterance of the user U based on the current context information of the user U, and the determined voice advertisement information is used by the user U. Deliver to terminal device 3. As a result, the information providing device 2 can deliver voice advertisement information that makes it easy for the user U to place an order by utterance according to the context of the current user U, and the voice advertisement related to the service that accepts the utterance of the user U. It is possible to improve the method of providing information.

[2. Information processing system]
Next, the information processing system 1 according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram showing a configuration example of the information processing system 1 according to the embodiment. The information processing system 1 according to the embodiment includes an information providing device 2, a terminal device 3, and a voice recognition server 4.

The terminal device 3, the voice recognition server 4, and the information providing device 2 are connected to each other so as to be able to communicate with each other wirelessly or by wire via the network N.

The voice recognition server 4 is a device that executes natural language processing on voice information and converts voice data into text data. When the voice recognition server 4 receives the voice data of the utterance from the terminal device 3, the voice recognition server 4 converts the voice data into text data. The voice recognition server 4 transmits the text data converted from the voice data to the information providing device 2. Further, the voice recognition server 4 detects the voice volume level in the utterance. The voice volume level may be detected by the terminal device 3.

Further, the voice recognition server 4 may be integrally configured with the information providing device 2. Further, when the terminal device 3 has a voice recognition function, the voice data and the text data may be converted by using these functions.

[3. Information provider]
Next, the information providing device 2 according to the embodiment will be described with reference to FIG. FIG. 3 is a block diagram showing a configuration example of the information providing device 2 according to the embodiment.

The information providing device 2 includes a communication unit 10, a control unit 11, and a storage unit 12. The communication unit 10 is a communication interface capable of communicating with the terminal device 3 via the network N (see FIGS. 1 and 2).

The control unit 11 is a controller, and for example, various programs stored in a storage device inside the information providing device 2 by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like are stored in a RAM (Random Access). It is realized by executing Memory) as a work area. Further, the control unit 11 is a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

The control unit 11 includes a context acquisition unit 20 (acquisition unit), a response result acquisition unit 21, a determination unit 22, a learning unit 23, a determination unit 24, and a distribution unit 25.

The context acquisition unit 20 acquires the context information of the user U. The context acquisition unit 20 acquires the surrounding information of the user U as the context information of the user U. The context acquisition unit 20 acquires information about the current position of the user U. Further, the context acquisition unit 20 acquires information about the situation around the user U, that is, the existence of another person P around the user U. The context acquisition unit 20 acquires context information from a GPS sensor (not shown) of the terminal device 3 or the like.

The context acquisition unit 20 acquires the context information of the user U who distributes the voice advertisement information at the first predetermined timing. At the first predetermined timing, the context acquisition unit 20 acquires the context information of the user U at the first predetermined timing, that is, the context information of the current user U.

The response result acquisition unit 21 acquires the response result of the user U to the utterance request information delivered to the terminal device 3 of the user U at the second predetermined timing. The second predetermined timing is a preset timing, and is a timing at which the utterance request information regarding the product is delivered.

The utterance request information is information that requests the user U to make an utterance related to the order of the product, but is not the information that the product is actually ordered. That is, the utterance request information is information for requesting the user U to make an utterance related to the order of the product on a trial basis, and the user U can order the product by the utterance according to the current context. This is information for investigating whether or not there is.

When a predetermined application is installed in the terminal device 3, the utterance request information is delivered to the terminal device 3 every hour, for example. The utterance request information is distributed to a large number of users U, and the response result acquisition unit 21 acquires the response results of the large number of users U.

The response result acquisition unit 21 acquires, as the response result of the user U to the utterance request information, whether or not the user U has spoken to the utterance request information, the voice volume level in the utterance of the user U, and the context information of the user U. The context information of the user U here is based on the selection result of the context displayed on the terminal device 3 of the user U. Further, the context information of the user U may be acquired by the above-mentioned context acquisition unit 20.

Here, the utterance request information displayed on the terminal device 3 of the user U will be described with reference to FIGS. 4A to 4C. FIG. 4A is an example (No. 1) showing utterance request information displayed on the screen D of the terminal device 3 of the user U. FIG. 4B is an example (No. 2) showing the utterance request information displayed on the screen D of the terminal device 3 of the user U. FIG. 4C is an example (No. 3) showing utterance request information displayed on the screen D of the terminal device 3 of the user U.

When the utterance request information is delivered, first, as shown in FIG. 4A, a text about the product that the user U wants to read out, for example, "Order dumplings!" Is displayed on the screen D of the terminal device 3 of the user U. Please say. Is displayed.

Then, when the user U utters "Order dumplings!", When the predetermined display time elapses without the user U speaking, or when the user U touches the screen D without speaking. On the screen D of the terminal device 3 of the user U, a display for acquiring the context information of the user U is performed.

For example, as shown in FIG. 4B, "Where are you now?" Is displayed on the screen D of the terminal device 3 of the user U, and "home", "company", "train", "restaurant", etc. Options such as "Other" are displayed. As a result, for example, when the user U selects "home", the context information that the user U is at the "home" is acquired in relation to the presence or absence of the utterance.

Next, as shown in FIG. 4C, on the screen D of the terminal device 3 of the user U, "Are there people around?" Is displayed, and "Yes" and "No" options are displayed. As a result, for example, when the user U selects "is", the context information that there is another person P around the user U is acquired regarding the presence or absence of the utterance.

Returning to FIG. 3, the response result acquisition unit 21 acquires the attribute of the user U. The attributes of the user U are, for example, the gender, age, occupation, and the like of the user U.

In this way, the response result acquisition unit 21 acquires the attributes of the user U, the presence / absence of the utterance, and the context information as the response result of the user U to the utterance summary information. The response result acquisition unit 21 acquires the attribute of the user U, the presence / absence of an utterance, and the context information in association with each other.

The determination unit 22 determines the response result of the user U acquired by the response result acquisition unit 21.

The determination unit 22 determines the response result of the user U to the utterance request information. Specifically, when the user U speaks with a voice volume equal to or higher than a predetermined voice volume level in response to the speech request information, the determination unit 22 speaks the product requested to be spoken in the current context. Is determined to be easy.

Further, the determination unit 22 currently produces a product for which the user U is requested to speak in response to the utterance request information when the user U speaks with a voice volume lower than the predetermined voice volume level or when there is no response due to the utterance. It is determined that it is difficult to speak in the context of.

The determination unit 22 may determine whether or not it is difficult to speak the product requested to be spoken in the current context, depending on whether or not the product is spoken.

The learning unit 23 generates a model to be used when determining the voice advertisement information to be delivered to the terminal device 3 of the user U. The learning unit 23 generates a model based on the response result of the user U to the utterance request information.

The learning unit 23 uses the response result of the user U to the utterance request information, specifically, whether or not the user U has spoken as teacher data, the context information of the user U when the utterance request information is delivered, and the user U. A model is generated by performing machine learning using the attribute of the user U as a feature amount. When the response result of the user U to the new utterance request information is obtained, the learning unit 23 updates the model based on the obtained response result. That is, generating a model includes updating the model when the response result of the user U to the new utterance request information is obtained.

The learning unit 23 generates a model based on the response results of a large number of users U. That is, the information providing device 2 distributes the utterance request information to a large number of users U, and generates a model based on the response results of the large number of users U to the utterance request information. The learning unit generates a model for each product.

At the first predetermined timing, the determination unit 24 determines the voice advertisement information to be delivered to the terminal device 3 of the user U by using the model based on the attribute of the user U and the context information of the current user U. The determination unit 24 determines the voice advertisement information related to the service for accepting the order uttered by the user U as the voice advertisement information to be delivered to the terminal device 3 of the user U.

Specifically, the determination unit 24 calculates the score for the product using the model based on the attribute of the user U and the context information of the current user U. Then, the determination unit 24 determines, for example, the voice advertisement information regarding the product having the highest score among the products having the score equal to or higher than the preset predetermined value as the voice advertisement information to be delivered to the terminal device 3 of the user U. ..

That is, the determination unit 24 generates a ranking for products that the user U can easily place an order by utterance based on the current context information of the user U, and distributes voice advertisement information to the terminal device 3 of the user U according to the ranking. decide.

The determination unit 24 randomly selects a product from the products whose score is equal to or higher than a predetermined value, and determines the voice advertisement information about the selected product as the voice advertisement information to be delivered to the terminal device 3 of the user U. You may.

Here, the score for the product will be described with reference to FIG. FIG. 5 is an example of a table summarizing the scores for the product IDs. The score indicates that the closer the numerical value is to "1.0", the easier it is for the user U to speak to the product. For example, the predetermined value is "0.70".

Further, in FIG. 5, for the sake of explanation, "place" and "existence of another person" are described as examples as context information, but the present invention is not limited to this, and the time zone and the type of another person P (for example,). Family members, acquaintances), etc. may be included in the context information. Further, in FIG. 5, “gender” and “age” are described as examples of the attributes of the user U, but the attributes are not limited to this, and the occupation, the area where the user lives, and the like are included in the attributes of the user U. It may be.

The product ID is an ID assigned to each product related to the voice advertisement information. The product ID may be assigned to each type of product, for example.

Regarding the product ID "D100", if the gender of the user U is "female", the age is "20s", the place is "home", and the existence of another person P is "none", The score is "0.90", which is larger than "0.70". That is, in this case, it can be determined that the user U, who is a woman in her twenties, is in a situation where it is easy to place an order by utterance with respect to the voice advertisement information regarding the product ID “D100”.

On the other hand, for the product ID "D100", when the gender of the user U is "female" and the age is "20's", the score is smaller than "0.70" except for the above conditions. .. That is, in these cases, it can be determined that the user U, who is a woman in her twenties, is in a situation where it is difficult to place an order by utterance with respect to the voice advertisement information regarding the product ID “D100”.

Further, when the gender of the user U is "female" and the age is "50s", the score is, unless the place is "park" and the existence of another person P is "yes". Greater than "0.70". That is, unless the place is "park" and the existence of another person P is "presence" for the voice advertisement information related to the product ID "D100", the user U, who is a woman in her 50s, places an order by utterance. It can be determined that the situation is easy to carry out.

Regarding the product ID "D110", when the gender of the user U is "female" and the ages are "20s" and "50s", the score is "0." regardless of the context information. Greater than 70 ". That is, with respect to the product ID "D110", it can be determined that the female user U in her twenties or fifties is in a situation where it is easy to place an order by utterance regardless of the context information.

The determination unit 24 can prevent the user U from selecting voice advertisement information about a product that is not desired to be delivered or voice advertisement information about a product that is difficult to place an order by utterance in the current context. Further, the determination unit 24 can select voice advertisement information about a product that is easy for the user U to place an order by utterance in the current context.

Returning to FIG. 3, the distribution unit 25 distributes the determined voice advertisement information to the terminal device 3 of the user U at the first predetermined timing.

Further, the distribution unit 25 distributes the utterance request information to the terminal device 3 of the user U at the second predetermined timing. The distribution unit 25 distributes the utterance request information to the terminal devices 3 of a large number of users U in which the predetermined application is installed. The distribution unit 25 distributes utterance request information regarding a randomly selected product.

The storage unit 12 is realized by, for example, a RAM, a semiconductor memory element such as a flash memory, or a storage device such as a hard disk or an optical disk.

The storage unit 12 includes an advertisement storage unit 30, an utterance request storage unit 31, and a model storage unit 32. The advertisement storage unit 30 stores voice advertisement information to be delivered to the terminal device 3 of the user U. The utterance request storage unit 31 stores the utterance request information to be delivered to the terminal device 3 of the user U. The model storage unit 32 stores a model for determining voice advertisement information to be delivered to the terminal device 3 of the user U.

[4. Model generation process]
Next, the model generation process according to the embodiment will be described with reference to FIG. FIG. 6 is a flowchart illustrating a model generation process according to the embodiment.

When the second predetermined timing is reached (S100: Yes), the information providing device 2 distributes the utterance request information to the terminal device 3 of the user U (S101). If the timing is not the second predetermined timing (S100: No), the information providing device 2 ends the current process.

The information providing device 2 acquires the response result to the utterance request information from the terminal device 3 of the user U (S102). The information providing device 2 generates a model based on the acquired response result (S103).

[5. Voice ad decision processing]
Next, the voice advertisement determination process according to the embodiment will be described with reference to FIG. 7. FIG. 7 is a flowchart illustrating the voice advertisement determination process according to the embodiment.

When the first predetermined timing is reached (S200: Yes), the information providing device 2 acquires context information from the terminal device 3 of the user U (S201). If the information providing device 2 does not have the first predetermined timing (S200: No), the information providing device 2 ends the current process.

The information providing device 2 determines the voice advertisement information based on the acquired context information of the current user U (S202). The information providing device 2 determines the voice advertisement information related to the service for accepting the order uttered by the user U based on the current context information of the user U. The information providing device 2 distributes the determined voice advertisement information to the terminal device 3 of the user U (S203).

[6. effect]
The information providing device 2 determines the voice advertisement information related to the service for accepting the order uttered by the user U based on the current context information of the user U, and distributes the determined voice advertisement information to the terminal device 3 of the user U. ..

As a result, the information providing device 2 can deliver service information related to the service for accepting orders spoken by the user U, for example, voice advertisement information, based on the current context information of the user U. Therefore, for example, when the user U does not want to order a certain product by utterance in the current context, the information providing device 2 may deliver voice advertisement information about such a product. It can be suppressed. Further, for example, when the user U does not want to deliver the voice advertisement information about a certain product in the current context, the information providing device 2 may deliver the voice advertisement information about such a product. It can be suppressed.

As described above, the information providing device 2 can improve the method of providing the voice advertisement information related to the service of accepting the order by the utterance of the user U.

Further, the information providing device 2 distributes voice advertisement information prompting an order by the utterance of the user U based on the context information of the current user U.

As a result, the information providing device 2 can deliver voice advertisement information about the product that the user U can easily place an order by utterance based on the context information of the current user U, and can promote the purchase of the product. ..

The information providing device 2 acquires surrounding information indicating the surrounding situation of the user U as context information, and determines the voice advertisement information to be delivered to the terminal device 3 of the user U based on the acquired surrounding information.

Thereby, the information providing device 2 can determine the voice advertisement information to be delivered to the terminal device 3 of the user U depending on whether or not another person P exists around the user U. Therefore, the information providing device 2 can suppress, for example, the distribution of voice advertisement information that the user U does not want to be heard by another person P.

The information providing device 2 distributes to the terminal device 3 of the user U by using the model generated based on the response result of the user U to the utterance request information and the context information of the user U when the utterance request information is distributed. Determine the audio advertising information to be used.

As a result, the information providing device 2 can suppress the distribution of voice advertisement information that the user U does not want to be heard by another person P, for example, and distributes the voice advertisement information to be distributed to the terminal device 3 of the user U. The method can be improved.

The information providing device 2 distributes the utterance request information to the terminal device 3 of the user U as display information. As a result, the information providing device 2 can prevent, for example, the utterance request information that the other person P does not want to hear from the terminal device 3 of the user U by voice.

The information providing device 2 generates a model based on the voice volume level of the user U with respect to the utterance request information and the context information of the user U when the utterance request information is delivered.

As a result, the information providing device 2 determines, for example, that when the voice volume level of the user U with respect to the utterance request information is smaller than the predetermined voice volume level, it is difficult for the user U to speak the product related to the utterance request information. Can be done. Therefore, the information providing device 2 can suppress the distribution of voice advertisement information about the product in such a context.

The information providing device 2 determines the voice advertisement information to be distributed to the terminal device 3 of the user U based on the context information of the user U, and distributes the determined voice advertisement information to the terminal device 3 of the user U.

As a result, the information providing device 2 can deliver the voice advertisement information according to the context of the user U, and can improve the method of providing the voice advertisement information.

[7. Modification example]
The information providing device 2 according to the modification may generate (update) a model based on the context information when the product is ordered for the product ordered by the distribution of the voice advertisement information.

As a result, the information providing device 2 according to the modified example can generate a model based on the actual order record, and can appropriately deliver the voice advertisement information according to the context information of the user U. Therefore, the information providing device 2 according to the modified example can improve the distribution method of the voice advertisement information.

Further, the information providing device 2 according to the modified example may generate (update) a model for each user U. The information providing device 2 according to the modified example increases the weight of the utterance request information delivered to the terminal device 3 of the user U with respect to the response result, and generates a model dedicated to the user U.

That is, the information providing device 2 according to the modified example uses a model generated based on the response results to the utterance request information delivered to a large number of users U including a certain user U as the response result of the certain user U. Customize based on.

As a result, the information providing device 2 according to the modified example can deliver voice advertisement information to each user U by using a model customized for each user U. Therefore, the information providing device 2 according to the modified example can appropriately deliver the voice advertisement information according to the characteristics of the user U. Therefore, the information providing device 2 according to the modified example can improve the distribution method of the voice advertisement information.

The information providing device 2 according to the modification may be able to acquire the model via the network N without generating the model. That is, the model may be generated by another device having the learning unit 23 or the like described above.

Further, the information providing device 2 according to the modified example may determine the voice advertisement information based on the usage status of the terminal device 3 and the context information of the current user U. For example, in the information providing device 2 according to the modified example, when earphones and headphones are used in the terminal device 3, even if the user U distributes voice advertisement information that the user U does not want to be heard by another person P to the terminal device 3. good.

As a result, the information providing device 2 according to the modified example can diversify the voice advertisement information delivered to the terminal device 3.

[8. Hardware configuration]
The information providing device 2 according to the above-described embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. FIG. 8 is a hardware configuration diagram showing an example of a computer that realizes the function of the information providing device 2. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, a program depending on the hardware of the computer 1000, and the like.

The HDD 1400 stores a program executed by the CPU 1100, data used by such a program, and the like. The communication interface 1500 receives data from another device via the network N and sends it to the CPU 1100, and transmits the data determined by the CPU 1100 to the other device via the network N.

The CPU 1100 controls an output device such as a display or a printer, and an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the determined data to the output device via the input / output interface 1600.

The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable Disk), a magneto-optical recording medium such as MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. And so on.

For example, when the computer 1000 functions as the information providing device 2 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 11 by executing the program loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be acquired from another device via the network N.

Although some of the embodiments and modifications of the present application have been described in detail with reference to the drawings, these are examples and vary based on the knowledge of those skilled in the art, including the embodiments described in the disclosure line of the invention. It is possible to carry out the present invention in another form in which the above is modified or improved.

[9. others]
Further, among the processes described in the above-described embodiments and modifications, all or part of the processes described as being automatically performed can be manually performed, or are described as being manually performed. It is also possible to automatically perform all or part of the performed processing by a known method. In addition, information including processing procedures, specific names, various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown in the figure.

Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of them may be functionally or physically distributed / physically distributed in any unit according to various loads and usage conditions. Can be integrated and configured.

Further, the above-described embodiments and modifications can be appropriately combined as long as the processing contents do not conflict with each other.

Further, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the communication unit 10 can be read as a communication means or a communication circuit.

1 Information processing system 2 Information providing device (information processing device)
3 Terminal device 11 Control unit 12 Storage unit 20 Context acquisition unit (acquisition unit)
21 Response result acquisition unit 23 Learning unit 24 Decision unit 25 Distribution unit

Claims (15)

An acquisition unit that acquires contextual information about the user,
Related to a service that accepts an order by the user according to a ranking generated for a product that the user can easily place an order by the user based on the speech request information and the acquired context information of the user. The decision-making department that determines service information,
It is provided with a distribution unit that distributes the determined service information to the terminal device of the user .
The utterance request information is information for requesting the user to make an utterance related to an order on a trial basis.
The context information is at least information indicating the existence of others around the user.
An information processing device characterized by this. The acquisition unit
The information processing apparatus according to claim 1, wherein the information processing apparatus according to claim 1 is characterized in that it acquires surrounding information indicating the surrounding situation of the user as the context information. The acquisition unit
The information processing apparatus according to claim 2, wherein as the surrounding information, information indicating at least one of the place where the user exists and the existence of another person around the user is acquired. The decision-making part
The information processing apparatus according to any one of claims 1 to 3, wherein the service information for prompting an order by the user's utterance is determined. The decision-making part
The information processing apparatus according to any one of claims 1 to 4, wherein the service information is determined by voice. The decision-making part
The information processing device according to claim 5, wherein the service information is determined by voice according to the usage status of the terminal device. The decision-making part
A claim characterized in that the service information is determined using a model generated based on the response result of the user to the utterance request information regarding the product delivered to the user in the past and the context information of the user. The information processing apparatus according to any one of 1 to 6. The information processing apparatus according to claim 7, wherein the model is generated for each user. The information processing device according to claim 7, wherein the utterance request information is delivered to the user's terminal device as display information. The information processing according to any one of claims 7 to 9, wherein the model is generated based on the voice volume level of the user for the delivered utterance request information and the context information of the user. Device. It is an information processing method executed by a computer.
The acquisition process to acquire contextual information about the user,
Related to a service that accepts an order by the user according to a ranking generated for a product that the user can easily place an order by the user based on the speech request information and the acquired context information of the user. The decision process to determine service information and
The delivery process of delivering the determined service information to the user's terminal device is included.
The utterance request information is information for requesting the user to make an utterance related to an order on a trial basis.
The context information is at least information indicating the existence of others around the user.
An information processing method characterized by that. The acquisition procedure to acquire context information about the user and
Related to a service that accepts an order by the user according to a ranking generated for a product that the user can easily place an order by the user based on the speech request information and the acquired context information of the user. The decision procedure for determining service information and
The computer is made to execute the delivery procedure for delivering the determined service information to the user's terminal device .
The utterance request information is information for requesting the user to make an utterance related to an order on a trial basis.
The context information is at least information indicating the existence of others around the user.
An information processing program characterized by this. An acquisition unit that acquires contextual information about the user,
Based on the utterance request information and the acquired context information, the determination unit determines the voice advertisement information to be delivered to the user's terminal device according to the ranking generated for the product for which the user can easily place an order by utterance. ,
It is provided with a distribution unit that distributes the determined voice advertisement information to the terminal device of the user .
The utterance request information is information for requesting the user to make an utterance related to an order on a trial basis.
The context information is at least information indicating the existence of others around the user.
An information processing device characterized by this. It is an information processing method executed by a computer.
The acquisition process to acquire contextual information about the user,
A determination step of determining voice advertisement information to be delivered to the user's terminal device according to a ranking generated for a product for which the user can easily place an order by utterance based on the utterance request information and the acquired context information. ,
The delivery process of delivering the determined voice advertisement information to the user's terminal device is included.
The utterance request information is information for requesting the user to make an utterance related to an order on a trial basis.
The context information is at least information indicating the existence of others around the user.
An information processing method characterized by that. The acquisition procedure to acquire context information about the user and
A determination procedure for determining voice advertisement information to be delivered to the user's terminal device according to a ranking generated for a product for which the user can easily place an order by utterance based on the utterance request information and the acquired context information. ,
The computer is made to execute the delivery procedure of delivering the determined voice advertisement information to the user's terminal device.
The utterance request information is information for requesting the user to make an utterance related to an order on a trial basis.
The context information is at least information indicating the existence of others around the user.
An information processing program characterized by this.

Images