Information processing device and program

Abstract

To provide an information processing device and a program, which allow for including a natural advertisement sentence in utterance generated by a machine capable of interacting with a user.SOLUTION: An information processing device retains advertisement sentences representing content of advertisements; extracts a predetermined reserved word from a conversational sentence entered by a user; and selects an advertisement sentence to be presented to the user from among the advertisement sentences according to the extracted reserved word. In addition, the information processing device executes utterance generation processing for a response sentence including the selected advertisement sentence after the conversational sentence according to a given criteria.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing device and a program. [Background technology]

[0002] Various techniques for presenting advertisements to users of information processing devices are known. For example, Patent Document 1 discloses a technique for selecting advertisements based on the content of chats between users. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 11-3348 Summary of the Invention [Problem to be solved by the invention]

[0004] In the above-mentioned conventional technology, advertisements are clearly presented to users in chats between users, but when a machine capable of interacting with a user makes an utterance containing an advertisement, the conversation with the user becomes unnatural.

[0005] The present invention has been made in consideration of the above-mentioned situation, and one of its objects is to provide an information processing device and a program that can include natural advertising text in the speech of a machine that can interact with a user. [Means for solving the problem]

[0006] One aspect of the present invention that solves the problems of the above-mentioned conventional examples is an information processing device that includes a storage means for storing advertising copy, which is the content of an advertisement; an extraction means for extracting predetermined reserved words included in a conversational text input by a user; a selection means for selecting an advertising copy to present to the user from the advertising copies based on the extracted reserved words; and an execution means for executing speech processing of a response text including the selected advertising copy following the conversational text based on predetermined criteria. [Effects of the Invention]

[0007] According to the present invention, it is possible to provide an information processing device and a program that can include natural advertising text in the speech of a machine that can interact with a user. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a block diagram illustrating an example of the configuration of an information processing system according to an embodiment of the present invention. [Figure 2] FIG. 2 is a block diagram illustrating an example of the configuration of a terminal device according to an embodiment of the present invention. [Figure 3] 1 is an explanatory diagram illustrating an example of how advertising copy is stored in the information processing system according to the embodiment of the present invention; [Figure 4] FIG. 3 is an explanatory diagram illustrating an example of setting information used in the information processing system according to the embodiment of the present invention. [Figure 5] FIG. 2 is a functional block diagram illustrating an example of a server according to an embodiment of the present invention. [Figure 6] FIG. 10 is an explanatory diagram showing an example of the contents of a conversation sentence queue used in the information processing system according to the embodiment of the present invention. [Figure 7] FIG. 2 is a functional block diagram illustrating an example of a terminal device according to an embodiment of the present invention. [Figure 8] 3 is a flowchart illustrating an example of the operation of the information processing system according to the embodiment of the present invention. [Figure 9] 10 is another flowchart illustrating an example of the operation of the information processing system according to the embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0009] An embodiment of the present invention will be described with reference to the drawings. As shown in Fig. 1, an information processing system 1 according to the embodiment of the present invention includes a server 10 and a terminal device 20 that are communicatively connected to each other via a communication means such as a network.

[0010] In one example of this embodiment, the server 10 realizes the information processing device of the present invention. As shown in FIG. 1, the server 10 in this example includes a control unit 11, a storage unit 12, and a communication unit 13. The terminal device 20 is a robot, and as shown in FIG. 2, includes at least a leg 21 and a main body 22, which houses a control unit 31, a storage unit 32, a sensor unit 33, a display unit 34, an audio output unit 35, a communication unit 36, and a drive unit 37. The leg 21 and the main body 22 are connected via an actuator that can rotate around at least one axis, allowing the orientation of the main body 22 to be rotated relative to the leg 21.

[0011] The control unit 11 of the server 10 is a program-controlled device such as a CPU, and operates according to a program stored in the storage unit 12. In this embodiment, the control unit 11 accepts action request information from the terminal device 20. In response to the accepted request information, the control unit 11 transmits action information to the terminal device 20, which is the sender of the request information, the action information including an action instruction instructing an action to be executed by the terminal device 20 and character string information representing the content of the voice to be uttered by the terminal device 20. The detailed content of the processing by the control unit 11 will be described later.

[0012] The storage unit 12 is a disk device or memory device, and holds programs executed by the control unit 11. The storage unit 12 also operates as a work memory for the control unit 11. In one example of the present embodiment, the storage unit 12 may store information for generating instructions to the terminal device 20. The contents of this information will be described later.

[0013] In one example of this embodiment, as shown in FIG. 3, the storage unit 12 stores, for each product (P) to be advertised, an advertising identifier (I), at least one advertising copy (E) that is the content of the advertisement to be delivered to the terminal device 20, information (A) that identifies the advertiser, and genre information (G) that identifies the advertising genre, in association with each other. The advertising copy may also be associated with a URL (U) of a webpage that lists information about the product (P) to be advertised. In this way, in one example of this embodiment, the storage unit 12 functions as the storage means of the present invention. Note that the number of advertising copies per product (P) is not limited to one, and there may be multiple copies.

[0014] Furthermore, in one example of the present embodiment, the storage unit 12 may hold a conversation sentence queue that accumulates conversation sentence candidates to be uttered by the terminal device 20. The contents of this conversation sentence queue will be described later.

[0015] The communication unit 13 is a network interface or the like, and sends various information to the terminal device 20 via the network in accordance with instructions input from the control unit 11. The communication unit 13 also outputs information received via the network to the control unit 11.

[0016] The control unit 31 of the terminal device 20 is a program-controlled device such as a CPU, and operates according to a program stored in the storage unit 32. In this embodiment, the control unit 31 sends action request information to the server 10 at a predetermined timing. The control unit 31 also receives action information from the server 10. Upon receiving the action information, the control unit 31 synthesizes voice data based on the character string information included in the action information. The control unit 31 also plays back the synthesized voice data and executes processing such as displaying animation according to the instructions of the received action information.

[0017] In one example of this embodiment, when a sensor unit 33, which will be described later, receives a user's voice input, the control unit 31 of the terminal device 20 converts the input voice into character string information. This process can be performed using a widely known voice recognition process, and the control unit 31 may perform this process by, for example, sending input voice information to a voice recognition server that executes voice recognition processing and receiving recognized character string information.

[0018] Furthermore, when the user inputs a voice, the control unit 31 is triggered to send action request information to the server 10. This request information includes information that identifies the trigger (for example, information that the user has input a voice) and information necessary for processing by the server 10, for example, character string information that is the recognition result of the voice input by the user.

[0019] That is, when the control unit 31 determines that a predetermined trigger has occurred, it collects information necessary for processing by the server 10 and sends request information including the collected information together with information specifying the trigger to the server 10. This trigger can be any trigger, such as when a user inputs voice, as in the previous example, or when a predetermined time has arrived. The detailed operation of this control unit 31 will be described later.

[0020] The storage unit 32 is a memory device or the like, and holds a program executed by the control unit 31. The storage unit 32 also operates as a work memory for the control unit 31. In this embodiment, the storage unit 32 may store setting information that associates the trigger (N) with information (P) that specifies information to be sent to the server 10 (FIG. 4). This setting information will be described later with a specific example.

[0021] Furthermore, in one example of this embodiment, the storage unit 32 stores image data of animations to be displayed on the display unit 34. Specifically, the storage unit 32 may store a plurality of image data of parts representing facial expressions, such as image data of animated eyes, such as image data of smiling eyes, image data of animated eyes with tears flowing, etc., and image data of animated mouths, such as image data of a closed mouth in a smiling state, image data of a closed mouth in a crying state, image data of animated mouths during speech, etc.

[0022] The sensor unit 33 includes at least a microphone, which is an audio sensor. The sensor unit 33 may also include a touch sensor, an acceleration sensor, etc. The sensor unit 33 outputs to the control unit 31 audio signals detected by each sensor, information indicating the position touched by the user, acceleration information, etc.

[0023] The display unit 34 is a liquid crystal display or the like, and displays image data representing the facial expressions of the characters, etc., in accordance with instructions input from the control unit 31. The audio output unit 35 is a speaker or the like, and produces sounds in accordance with audio signals input from the control unit 31.

[0024] The communication unit 36 ​​includes a network interface. The communication unit 36 ​​transmits and receives information to and from the server 10 via a network, either wirelessly or via a wired connection. Specifically, the communication unit 36 ​​sends request information and the like to the server 10 in accordance with instructions input from the control unit 31. The communication unit 36 ​​also outputs information received from the server 10 to the control unit 31.

[0025] The driving unit 37 drives the actuator to rotate the main body 22 relative to the leg 21 in accordance with an instruction input from the control unit 31 .

[0026] Next, a description will be given of the operation of the control unit 11 of the server 10 of this embodiment. In this embodiment, the control unit 11 of the server 10 includes a receiving unit 41, a reserved word extracting unit 42, an advertisement selecting unit 43, an action information generating unit 44, and an instruction transmitting unit 45, as shown in FIG.

[0027] The receiving unit 41 receives request information from the terminal device 20. In this embodiment, the server 10 accepts request information from the terminal device 20, which requests a process (action) to be executed by the terminal device 20. This request information includes information identifying the cause (trigger) of the action request. Types of triggers will be described later, and an example is voice input by the user. The request information based on the trigger that a user has input voice may include information indicating the content of the voice input by the user, as well as information identifying the trigger. Here, the information indicating the content of the voice input by the user may be character string information that is the result of voice recognition.

[0028] The receiving unit 41 outputs the information contained in the received request information, such as information identifying the trigger and character string information representing the content of the voice input by the user, to the reserved word extraction unit 42 and the action information generation unit 44.

[0029] Reserved word extraction unit 42 extracts reserved words included in the character string information output by receiving unit 41. Here, reserved words are predetermined keywords, and in the example of the present embodiment, a plurality of keywords are listed in advance as reserved words and stored in storage unit 12. If the listed reserved words are included in the character string information output by receiving unit 41, reserved word extraction unit 42 extracts the reserved words and outputs them to advertisement selection unit 43.

[0030] For example, when the character string information representing the conversational sentence entered by the user, which is included in the request information received from the terminal device 20, is "I've been sleep deprived recently...", if the word "sleep deprivation" is listed as a reserved word, the reserved word extraction unit 42 extracts the word "sleep deprivation" and outputs it to the advertisement selection unit 43.

[0031] The advertisement selection unit 43 selects advertisement copy to be presented to the user from among the advertisement copy stored in the storage unit 12 based on the reserved words extracted by the reserved word extraction unit 42. Specifically, the advertisement selection unit 43: (1) Select ad copy that contains the extracted reserved word or its synonyms. (2) Select an advertisement copy that includes the extracted reserved word in associated genre information.

[0032] Here, when the advertisement selection unit 43 performs the process (1) or (2) above and multiple advertisement copy are selected, the advertisement selection unit 43 further selects (narrows down and selects) one advertisement copy from the multiple advertisement copy. This narrowing down and selection method may be performed randomly or based on other conditions.

[0033] The advertisement selection unit 43 registers the selected advertisement copy as a conversational sentence in the conversational sentence queue stored in the storage unit 12. At this time, the advertisement selection unit 43 may associate the advertisement copy with expiration information, which is a predetermined time (for example, one hour) from the time of registration. As will be explained later, conversational sentences are controlled so that they are not spoken after the expiration date has passed, so by setting expiration information in this way, the advertisement copy will not be spoken after a considerable amount of time has passed since the user uttered the reserved word.

[0034] Based on the information input from the receiving unit 41, the action information generating unit 44 determines the action to be executed by the terminal device 20 that sent the request, generates action information including information instructing the action (action instruction) and information required to execute the action (hereinafter referred to as parameter information), and outputs the generated information to the instruction transmitting unit 45.

[0035] In one example of this embodiment, the memory unit 12 of the server 10 stores an action database including at least one record that associates the following information for generating instructions to the terminal device 20: occurrence conditions, information identifying the trigger, information to be compared with information representing the content of the voice input by the user (hereinafter referred to as comparison string information; however, this comparison string information may not be necessary depending on the type of trigger), and information representing the processing to be performed by the server 10 to generate action information.

[0036] The action information generation unit 44 acquires comparison string information (if any) associated with the information identifying the trigger input from the receiving unit 41 and information representing the processing that the server 10 should perform to generate action information.

[0037] If comparison string information is acquired (if comparison string information is associated with information that identifies the trigger), the action information generation unit 44 compares the comparison string information with the string information output by the receiving unit 41. If the action information generation unit 44 determines that the string information output by the receiving unit 41 matches the comparison string information, it executes the process indicated by the acquired information and generates action information.

[0038] Furthermore, if the comparison character string information has not been acquired, the action information generating unit 44 executes the process indicated by the acquired information to generate action information.

[0039] As a specific example, the action database contains records that associate information specifying a trigger that "there has been voice input by the user" with string information such as "*News [for|is]* [not|tell|read it out]*" as comparison string information to be compared with information representing the content of the voice input by the user, with the information "obtain the news string information from a specified web server on the Internet and instruct to read out the string information."

[0040] This comparison string information is also expressed as a regular expression. Therefore, the above string will match string information such as "Tell me about today's news" or "Is there any news?"

[0041] For example, when the action information generation unit 44 receives input from the receiving unit 41, including information identifying a trigger such as "there has been voice input by the user" and character string information such as "Is there any news?" representing the content of the voice input by the user, the action information generation unit 44 searches the action database for a record including the information identifying the trigger.

[0042] Here, the action information generating unit 44 finds the above record from the action database and compares the comparison string information contained in the record with the accepted string information. In the above example, the accepted string information "Is there any news?" is determined to match the comparison string information "*News [to|is]* [not|tell|read it out]*", so the action information generating unit 44 uses information contained in the above record found by the search that indicates the process to be executed by the server 10, such as "(Step 1) Obtain news string information from a specified web server on the Internet, (Step 2) Generate instructions to read the string information (Step 3) "Generate instructions to display animation information to be played when reading" is obtained, and processing is performed according to this information.

[0043] That is, the action information generation unit 44 acquires news character string information from a predetermined web server on the Internet according to the read information. The action information generation unit 44 may also generate a display instruction for animation information including information specifying image data of an animation to be displayed together with the execution of action processing performed in parallel (which may be the file name of the image data).

[0044] In this example, the action information generating unit 44 generates action information including an action instruction and parameter information, and outputs the generated action information to the instruction transmitting unit 45. The action instruction includes an instruction to read out character string information and an instruction to display animation information. The parameter information includes the acquired character string information and information specifying the image data of the animation.

[0045] Here, the information indicating the process to be executed by the server 10 may include an instruction to "select a conversation sentence." If such an instruction is included, the action information generation unit 44 selects a conversation sentence in accordance with the instruction, for example, in the following manner.

[0046] Here, the conversation sentence queue stored in the storage unit 12 of the server 10 stores a time limit (T), a speech condition (C), and a conversation sentence (D) in association with each other, as shown in FIG. 6.

[0047] The action information generation unit 44 extracts a conversation sentence that satisfies a speech condition associated with the conversation sentence from among the conversation sentences stored in the conversation sentence queue. Here, the speech condition is, for example, information indicating a time period during which speech is permitted. The action information generation unit 44 can obtain various information necessary to determine whether the speech condition is satisfied, such as information on the current date and time (date and time when processing is being executed) and weather information, from an NTP (Network Time Protocol) server or a predetermined web server via a network.

[0048] The action information generation unit 44 selects, for example, randomly, one of the conversation sentences extracted as satisfying the utterance condition. At this time, the action information generation unit 44 may read information on the deadline associated with the extracted conversation sentence from the conversation sentence queue, and delete the extracted conversation sentence from the conversation sentence queue if the deadline has already passed. In this case, the action information generation unit 44 repeats the process from selecting another conversation sentence (an unselected conversation sentence) extracted as satisfying the utterance condition.

[0049] The action information generation unit 44 determines whether the selected conversational sentence satisfies a predetermined criterion. For example, the action information generation unit 44 reads out a conversation history relating to the user of the terminal device 20 that sent the request, which is recorded by the instruction transmission unit 45 (described later). The action information generation unit 44 then determines whether the selected conversational sentence will result in a natural conversation when spoken following the currently recorded conversation history. In other words, in this example, the predetermined criterion is that there is continuity between the conversational sentence in the history and the selected advertising copy.

[0050] This determination can be achieved, for example, by using a neural network or the like that has machine-learned the text of conversations between humans to determine whether a sentence is appropriate as a continuation of the currently recorded conversation history, i.e., whether there is continuity in the conversation. This type of processing is known as next sentence prediction (NSP). As a neural network for next sentence prediction, for example, a model known as BERT (https: / / arxiv.org / pdf / 1706.03762.pdf) can be used. As training data for machine learning to perform such next sentence prediction, widely known training data and machine learning processing methods using such training data can be used, such as a method using a pair of conversation sentences (a first conversation sentence and a second conversation sentence) associated with information indicating the continuity between the first and second conversation sentences.

[0051] When a neural network is used to determine whether a selected conversational sentence is appropriate as a continuation of the currently recorded conversation history, i.e., whether there is continuity in the conversation, the output of the neural network represents the appropriateness as a numerical value. The action information generator 44 determines that the conversation is natural (continuity exists) when the numerical value exceeds a predetermined threshold value.

[0052] When the action information generation unit 44 determines that there is continuity as described above, it generates an action instruction including an instruction to read out the character string information of the conversational sentence (this conversational sentence is also a response sentence that continues the previous conversation, so it will be referred to as a response sentence here when it is necessary to distinguish it from other conversational sentences) and an instruction to display animation information. The action information generation unit 44 also generates parameter information including the character string information of the selected conversational sentence and information specifying image data of the animation, and instructs the instruction transmission unit 45 to send the generated action instruction and parameter information as action information to the terminal device 20.

[0053] The instruction transmitting unit 45 transmits the action information generated by the action information generating unit 44 to the terminal device 20 that is the sender of the request information received by the receiving unit 41. At this time, the instruction transmitting unit 45 sequentially records, for each user, the content of the voice input by the user that is accepted by the receiving unit 41 and the content of the conversation that is instructed by the action information generating unit 44 to be uttered by the terminal device 20 of the user.

[0054] Next, a description will be given of the operation of the control unit 31 of the terminal device 20. In this embodiment, the control unit 31 is configured to functionally include a request sending unit 51, an action information receiving unit 52, a voice synthesis unit 53, and an action processing execution unit 54, as exemplified in Fig. 7.

[0055] When the request sending unit 51 determines that a predetermined trigger has occurred, it collects information necessary for processing in the server 10 and sends request information including the collected information together with information specifying the trigger to the server 10. Specifically, triggers such as a voice input by the user or the arrival of a predetermined time are listed in advance, included in the setting information, and stored in the storage unit 32.

[0056] When the request sending unit 51 determines that the occurrence condition (C) is satisfied by referring to the setting information illustrated in FIG. 4, it determines that a trigger (N) associated with the satisfied occurrence condition has occurred, and refers to information (P) associated with the trigger that is necessary for processing on the server 10.

[0057] The request sending unit 51 may record, for each occurrence condition (C), the date and time when the occurrence condition was satisfied last time and request information was sent.The request sending unit 51 may then perform control so as not to send the request information if the difference between the date and time recorded in association with the satisfied occurrence condition (C) and the current date and time does not exceed the interval (T) recorded in the setting information in association with the occurrence condition (i.e., set for each occurrence condition, for example).

[0058] The request sending unit 51 then collects information necessary for processing on the server 10, which is identified by the referenced information, and sends request information including the collected information and information identifying the trigger that has occurred (which may be the trigger name), to the server 10.

[0059] The action information receiving unit 52 receives action information from the server 10 and outputs the received action information to the action processing executing unit 54.

[0060] The voice synthesis unit 53 synthesizes voice data based on character string information input from the action processing execution unit 54, which will be described later. The voice synthesis unit 53 outputs the voice data obtained by the synthesis to the action processing execution unit 54.

[0061] The action processing execution unit 54 extracts the action instruction and parameter information from the action information sent by the server 10, and executes processing in accordance with the action instruction. Specifically, as in the above example, a case will be described in which the action information receiving unit 52 receives an action instruction including an instruction to read out the acquired character string information and an instruction to display the animation information, and action information including the acquired character string information and parameter information including image data of the animation.

[0062] In this example, the action processing execution unit 54 outputs the acquired character string information to the voice synthesis unit 53 to acquire audio data. The action processing execution unit 54 also reads image data of an animation specified by information included in the action information from the storage unit 22. The action processing execution unit 54 then outputs the audio data output by the voice synthesis unit 53 to the audio output unit 35 to produce audio, and outputs the image data of the read animation to the display unit 34 to play the image data of the animation.

[0063] [Operation] The information processing system 1 of this embodiment has the above configuration and operates as follows: In the following example, it is assumed that the storage unit 12 of the server 10 stores, as an action database, information representing the process that the server 10 executes to generate action information for each trigger that is the cause of an action request.

[0064] In the following example, the information contained in this action database is: · Information identifying the trigger (T): the user is having a conversation · Action to be performed: (Step 1) Select the text information for the conversation (Step 2) Generate instructions to read the string information (Step 3) The step includes information to generate an instruction to display animation information to be played back when reading aloud.

[0065] The storage unit 12 of the server 10 stores the following information about the advertisement: advertisement target (P): sleep-improving drug AA; advertisement identifier: 1; advertisement copy (E): (1) "To improve the quality of your sleep, use the sleep aid AA" (2) "Have you tried the sleep aid AA?" · Advertiser (A): A Co., Ltd. · Genre (G): sleep, deep sleep, insomnia, lack of sleep, sleep aid, ... · URL (U): http: / / ... · Target of advertisement (P): sleep aid BB · Advertisement identifier: 2 · Ad copy (E): (1) "BB, a sleep aid used in hospitals" (2) "Have you tried the sleep improvement drug BB?" Advertiser (A): B Co., Ltd. Genre (G): sleep, falling asleep, insomnia, sleep deprivation, sleep improvement drug, ... URL (U): http: / / ... and other advertisement information are stored.

[0066] Furthermore, the memory unit 32 of the terminal device 20 stores, as setting information, for each trigger, information (C) that specifies the occurrence condition and information (P) that is related to the trigger and is necessary for processing on the server 10, as illustrated in Figure 4.

[0067] In the following example, the setting information includes the following information: · Information identifying a trigger (trigger name N): there is a voice input by the user · Occurrence condition (C): the user utters a predetermined wake word · Information identifying information required for processing by server 10 (P): character string information of the content uttered by the user · Information identifying a trigger (trigger name N): the user is having a conversation · Occurrence condition (C): the user utters a voice within 10 seconds after the sounding of the voice data · Information identifying information required for processing by server 10 (P): character string information of the content uttered by the user... Here, a wake word is a predetermined word such as "Hey, listen to me" or "Wake up," which should be recognized as the start of voice input when uttered by the user. The terminal device 20 may remove the character string portion corresponding to the wake word from the character string information of the content uttered by the user that is required for processing by server 10.

[0068] In addition, although the occurrence condition (C) is set to the user uttering the wake word, this embodiment is not limited to this and other conditions may be used.

[0069] The operations of the server 10 that holds such setting information and the terminal device 20 will be described below with reference to FIGS.

[0070] After the terminal device 20 sounds audio data such as news information in accordance with an instruction from the user, if the user responds to the audio data and says something like, "I've been getting less sleep lately too..." to the terminal device 20 (S11 in FIG. 8), the terminal device 20 executes a process of recognizing the user's voice (S12) and acquires character string information corresponding to the voice spoken by the user. As already mentioned, the voice recognition process does not have to be performed by the terminal device 20 itself, and may be performed by accessing a voice recognition processing service via a network.

[0071] The terminal device 20 refers to the setting information to check whether any of the trigger conditions has been satisfied (S13). In this case, since the user speaks immediately after the terminal device 20 rings with the voice data, it is assumed that a trigger indicating "the user is talking" has occurred (S13: Yes), and character string information of the content of what the user has spoken is collected according to the setting information. Note that, if it is determined in step S13 that none of the trigger conditions has been satisfied (S103: No), the terminal device 20 ends the process.

[0072] Here, since the content uttered by the user has already been acquired as string information in step S12, the terminal device 20 sends request information including the string information and information identifying the trigger that has occurred (trigger name "user is having a conversation") to the server 10 (S14).

[0073] The server 10 receives the request information from the terminal device 20. Then, the server 10 refers to the trigger name "users are having a conversation" included in the request information, and extracts information associated with the trigger name from the action database (S15). At this time, the server 10 also adds the conversation sentence (character string information representing the content of what the user said) included in the request information to the conversation history with the corresponding user and stores it.

[0074] In the process of step S15, information representing the process to be executed by the server 10 is acquired. Then, the server 10 executes the process represented by the acquired information (S16). Here, one of the conversation sentences included in the conversation sentence queue (for example, "Eh, are you okay?") is selected as a response sentence, and an instruction to read out the response sentence is generated, and an instruction to display animation information is generated in parallel with the reading out, and sent to the terminal device 20 as action information.

[0075] At this time, the server 10 adds the sent response sentence to the conversation history with the corresponding user and stores it.

[0076] Also, around the time of this process, the server 10 separates the character string information (the conversational text entered by the user) included in the request information received from the terminal device 20, "I've been getting less sleep lately, too..." into words using, for example, morphological analysis (each word is converted to its original form if it has conjugation), and extracts the word "less sleep" as a predetermined reserved word (reserved words are recorded in their original form) (S17). Alternatively, the server 10 may extract the word "less sleep," which is a predetermined reserved word, using pattern matching using regular expressions, or the like. Specifically, the conversational text entered by the user is sequentially checked to see if it contains any of the predetermined reserved words, and when it is determined that any of the reserved words is included, the reserved word is deemed to have been extracted.

[0077] The server 10 then selects advertising copy whose genre information includes the reserved word contained in the conversational text entered by the user (S18). In the above example, at least two advertising copy are selected: "Sleep Improvement Drug AA to Improve Sleep Quality" and "Sleep Improvement Drug BB Used in Hospitals." Note that if there are multiple advertising copy associated with one advertising identifier, the first advertising copy among them is selected.

[0078] For example, the advertisement copy (E) related to advertisement identifier: 1 is as follows: (1) "To improve the quality of your sleep, use the sleep aid AA" (2) Two advertisements, "Have you tried the sleep aid AA?", are related to each other. (1) "To improve the quality of sleep, sleep aid drug AA" is selected. An example of selecting an advertisement copy other than the first advertisement copy will be described later.

[0079] The server 10 further narrows down and selects one advertisement copy from these selected advertisement copies. As already mentioned, this narrowing down method may be, for example, random. In this example, it is assumed that "To improve the quality of sleep, use sleep aid AA." The server 10 then registers the selected advertisement copy in the conversation sentence queue (S19).

[0080] Meanwhile, the terminal device 20 sounds the response sentence included in the action information sent by the server 10 in step S16 (S20). When the user utters a conversation sentence such as "I hope you can sleep a little more deeply" in response to the sounded response sentence, the terminal device 20 executes the same processes as steps S12 to S14 and transmits request information including character string information of the conversation sentence (S21).

[0081] Moving on to FIG. 9, the server 10 receives the request information sent by the terminal device 20 in step S20, and adds and stores the conversation text (string information representing the content spoken by the user) included in this request information to the conversation history with the corresponding user.

[0082] The server 10 also references the trigger name "user is talking" included in the request information and retrieves information associated with the trigger name from the action database (S22). Here, information representing the process to be executed by the server 10 is acquired. The server 10 then executes the process represented by the acquired information. Here, a process is performed to select a conversation sentence included in the conversation sentence queue as a response sentence, and first, a conversation sentence including the advertisement copy registered in step S18, "To improve the quality of sleep, use the sleep-improving drug AA," is extracted (S23).

[0083] The server 10 sequentially determines whether the extracted conversation sentences satisfy a predetermined criterion. Specifically, the server 10 selects one of the extracted conversation sentences (an unselected one) as a candidate (S24). The server 10 then refers to the conversation history of the user of the terminal device 20 that sent the request information, and determines whether the conversation sentence selected in step S24 would result in a natural conversation when uttered following the currently stored conversation history (S25).

[0084] As an example, the server 10 obtains a numerical value (the more appropriate the value, the larger the value) representing the appropriateness of the conversational sentence selected in step S24 as a sentence following the currently recorded conversation history through a next-sentence prediction process using a BERT model that has been machine-learned from text of conversations between humans.The server 10 then determines that the conversation is natural (there is continuity) when the obtained value exceeds a predetermined threshold value, and otherwise determines that the conversation is not natural (there is no continuity).

[0085] Specifically, in the processing up to this point, the server 10 has accumulated as history conversations between the user of the terminal device 20 that sent the request information in step S21, such as: User: "I've been getting less sleep lately too..." Terminal device 20's utterance: "Hmm, are you okay?" User: "I wish I could sleep a little more deeply."

[0086] Therefore, the server 10 determines whether or not the conversation sentence selected in step S24 following these conversation sentences is appropriate as a sentence following the currently recorded conversation history.

[0087] In step S25, if the server 10 determines that the selected conversation sentence will result in a natural conversation when spoken (S25: Yes), the server 10 generates action information including an instruction to read out the character string information of the selected conversation sentence (S26), and then transmits the action information to the terminal device 20 (S27).

[0088] On the other hand, if it is determined in step S25 that the selected conversation sentence will not result in a natural conversation when spoken (S25: No), the server 10 returns to process S24 and continues the process of selecting an unselected conversation sentence. If there is no unselected conversation sentence in process S24, the server 10 executes a predetermined process, such as generating action information including an instruction to read out character string information of a predetermined conversation sentence and sending it to the terminal device 20 (S28: Execute default process).

[0089] The terminal device 20 executes a process of reading out the character string information in accordance with the instruction of the action information sent by the server 10 in step S27 or S28 (S29).

[0090] If the server 10 determines in the process of step S25 that the selected advertisement copy will result in a natural conversation following the history of the immediately preceding conversation, the server 10 generates action information including an instruction to read out the advertisement copy as a response text in step S26.

[0091] Then, the terminal device 20 reads out the advertisement "To improve the quality of your sleep, take the sleep-improving drug AA" as a response.

[0092] [URL] The conversation sentence queue may include information other than the conversation sentence (other than the character string information to be sounded) that should be provided to the user in relation to the conversation sentence. For example, when the server 10 selects an advertisement sentence and registers it in the conversation sentence queue, if there is URL information associated with the advertisement sentence, the server 10 registers the advertisement sentence as a conversation sentence and also registers the URL information in the conversation sentence queue in association with the advertisement sentence as information to be provided to the user in relation to the conversation sentence.

[0093] When the server 10 selects an advertisement text from the conversation text queue and generates action information to sound the selected advertisement text, the server 10 adds an instruction to sound a predetermined message such as "...I've sent you a URL for more detailed information" to the generated action information and sends it to the terminal device 20.

[0094] The server 10 then sends a specified email containing in its body the URL recorded in the conversational text queue in association with the selected advertisement copy to the email address (which is assumed to be pre-registered) of the user of the terminal device 20 to which the action information is addressed.

[0095] As a result, the terminal device 20 speaks the advertisement copy and also speaks "I've sent you a URL for more detailed information," and the user receives the URL for acquiring information related to the advertisement as an email addressed to the user.

[0096] Also, although the example here shows a case where a URL is sent to the user's email address, the present embodiment is not limited to this, and the URL may be sent to an application that is installed on the user's smartphone or the like and that communicates with the server 10 or the terminal device 20. In this example, the server 10 sends the URL that is recorded in the conversation sentence queue in association with the selected advertisement copy to the application installed on the smartphone of the user of the terminal device 20 that is the destination of the action information. Note that widely known techniques such as notification techniques can be used as a technique for displaying information in an application, and therefore a detailed description thereof will be omitted here.

[0097] [Records of past advertising provided] In the explanation so far, when selecting ad copy to register in the conversation queue, even if multiple ad copies are selected based on genre information, the ad copy to be spoken as conversation is narrowed down randomly. For this reason, even if an ad copy by advertiser A is spoken in a conversation one day, "To improve the quality of your sleep, take sleeping pill AA," the next day's ad copy by advertiser B may be spoken, "Sleeping pill BB, which is also used in hospitals."

[0098] In other words, it is possible that advertising copy from different advertisers may be sent for a common advertising target, which would result in the terminal device 20 engaging in inconsistent conversations and would prevent the user from treating the terminal device 20 as a person.

[0099] Therefore, in one example of this embodiment, when the server 10 instructs the user's terminal device 20 to speak an advertisement copy, the server 10 associates the advertisement identifier of the advertisement copy with the date and time when the instruction to speak was given, and records them as an advertisement history for each user.The server 10 then refers to the advertisement history when selecting an advertisement copy.

[0100] Specifically, when the server 10 selects advertising copy to present to the user from among those stored in the storage unit 12 based on reserved words extracted from conversational text uttered by the user, if there are multiple selected advertising copies, it narrows down the selection as follows: That is, the server 10 refers to the advertising history to check whether the advertising identifier of the selected advertising copy is recorded. If the advertising identifier of the selected advertising copy is recorded in the advertising history, the server 10 obtains information on the most recent date and time of the utterance instruction recorded in the advertising history. This obtains information on the date and time when advertising copy related to the same advertising target from the same advertiser was last uttered for each of the advertising copies selected based on reserved words.

[0101] The server 10 narrows down and selects the advertisement copy related to the most recent date and time information from the obtained date and time information. As a result, once an advertisement copy by advertiser A is uttered, advertisement copies by advertiser A are more likely to be uttered thereafter, and consistency of conversations on the terminal device 20 is maintained.

[0102] Furthermore, as in this example, when referring to the advertisement history, the server 10 may acquire an advertisement identifier associated with genre information including reserved words extracted from the conversational text spoken by the user, and select an advertisement copy other than the first advertisement copy from among the advertisement copies associated with the acquired advertisement identifier.

[0103] According to this example, for example, in the advertisement text (E) related to advertisement identifier: 1 (1) "To improve the quality of your sleep, use the sleep aid AA" (2) When there are two options, "Have you tried the sleep improvement drug AA?", the first one, "To improve the quality of your sleep, try the sleep improvement drug AA," will be spoken the first time. However, from the second time onwards (because it will be recorded in the advertisement history), the other advertisement, "Have you tried the sleep improvement drug AA?", will be spoken, resulting in a more natural conversation.

[0104] [Setting time periods for suppressing ads] Furthermore, since times when users are busy (such as weekday mornings) are inappropriate for advertising, when the server 10 selects a conversation sentence to be spoken by the terminal device 20 from the conversation sentence queue, the server 10 may control the selection of the advertisement sentence if the current date and time of the location of the terminal device 20 is in a time period that has been set in advance as a time period to be avoided.

[0105] In this example, the terminal device 20 may include, for example, information about the current date and time in the area where the terminal device 20 is located in the request information and notify the server 10. Furthermore, when registering advertising copy in the conversation sentence queue, the server 10 may register flag information indicating that the conversation sentence is advertising copy, in association with the advertising copy registered in the conversation sentence queue.

[0106] When the current date and time information included in the request information is included in a time period set in advance as a time period to be avoided, the server 10 selects a conversation sentence to be spoken from a conversation sentence queue, avoiding a conversation sentence associated with flag information indicating that the conversation sentence is an advertisement sentence.

[0107] [Analysis and processing of conversational text after advertisement speech] When an advertising copy is uttered as a response, the server 10 may determine the user's reaction to the utterance of the response. Specifically, the server 10 analyzes the content of the conversation received from the user after the advertising copy is uttered to determine whether the conversation continues with content related to the advertisement (whether words related to the target of the advertisement are included in the subsequent conversation) and whether the conversation is positive or negative using a method such as polarity analysis.

[0108] The server 10 then stores the results of this analysis as a history of advertising effectiveness for each user and for each advertising identifier of the spoken advertising copy, and uses the results for predetermined processing.

[0109] The predetermined process may include obtaining statistics on the advertising effectiveness history for each advertising identifier of an advertisement placed by a specific advertiser and presenting the statistics to the advertiser, thereby enabling the advertiser to obtain information such as the frequency of speech about the advertisement and user responses.

[0110] The predetermined process may also be a process of extracting, for each user, an advertisement identifier that is determined to be negative or that is determined not to lead to a conversation related to the content of the advertisement after the advertisement. In this case, the advertisement copy of the extracted advertisement identifier may be controlled not to be selected for that user.

[0111] [Advertisement Target] In the above description, the advertisement copy related to the advertisement identifier can be selected regardless of the user's attributes, such as age group and gender, but this embodiment is not limited to this. For example, the advertisement copy may be recorded in association with information representing the attributes of the target user. In this case, when selecting the advertisement copy to be spoken by the user's terminal device 20, the server 10 may refer to the user's attributes (which are registered in advance), such as the user's date of birth and gender, and select the advertisement copy from among the advertisement copies associated with the information representing the attributes.

[0112] [Other examples of standards] Here, the predetermined criterion for whether or not to utter an advertising copy is a criterion for determining whether or not there is continuity in the conversation by performing a next-sentence determination process, but this embodiment is not limited to this, and may be based on the number or frequency (number of times a keyword appears per unit time) of keywords included in the conversation history, etc.

[0113] [Processing on the terminal device] In the explanation up to this point, the server 10 functions as an example of the information processing device of the present invention, selects an advertisement, and causes the terminal device 20 to speak it, but the present embodiment is not limited to this, and the terminal device 20 may function as an example of the information processing device of the present invention and select an advertisement copy to be spoken from among advertisement copies stored in the server 10. In this example, the control unit 31 of the terminal device 20 executes the operations of the reserved word extraction unit 42 and the advertisement selection unit 43. In this example, the control unit 31 also controls the speaking of the selected advertisement copy.

[0114] [Configuration and Effects of the Embodiment] As described above, in the embodiment of the present invention, advertising copy is stored in advance, and the appropriateness of uttering it as a continuation of the conversation is judged, and the advertising copy is uttered when it is judged to be appropriate. That is, the information processing device of this embodiment is an information processing device that includes: storage means such as a disk or server that stores the advertising copy, which is the content of the advertisement; extraction means that extracts reserved words, which are predetermined keywords, contained in the conversation text input by the user; selection means that selects advertising copy to be presented to the user from the advertising copy based on the extracted reserved words; and execution means that executes speech processing of a response text including the selected advertising copy following the conversation text based on predetermined criteria. This information processing device is an information processing device that includes a terminal device located on the server or user side. It can be realized as a robot.

[0115] This allows advertising text to be included in natural conversation, reducing the abruptness of the advertisement.

[0116] Here, the predetermined criterion may be whether or not there is continuity between the conversational text and the selected advertising text, and if there is continuity, speech processing of the response text may be executed.

[0117] This allows the ad copy to be included in the natural flow of conversation, reducing the abruptness of the ad.

[0118] Furthermore, the storage means may store genre information indicating the genre of the advertisement represented by each of the advertising texts in association with each other, and the selection means may select an advertising text to be presented to the user from among advertising texts associated with the genre determined as the advertisement to be presented to the user based on the reserved words.

[0119] In this way, by narrowing down the advertisement copy by genre, the burden of processing the criteria-based determination can be reduced.

[0120] Furthermore, the execution means may suppress the utterance of the response sentence during a predetermined time period, such as a time period set as a time period when advertisements should be avoided. According to this example, it is possible to avoid presenting advertisements during times that are inappropriate for the user.

[0121] The system may further include a reaction determination means for determining a user's reaction to the response sentence utterance process when the response sentence utterance process is executed, and the result of the determination by the reaction determination means may be stored in association with information representing the content of the uttered response sentence, and may later be used for predetermined processing such as control processing to repeat or suppress the advertisement, thereby enabling control according to the effectiveness of the advertisement. [Explanation of symbols]

[0122] 1 Information processing system, 10 Server, 11 Control unit, 12 Memory unit, 13 Communication unit, 20 Terminal device, 21 Leg unit, 22 Main body unit, 31 Control unit, 32 Memory unit, 33 Sensor unit, 34 Display unit, 35 Audio output unit, 36 Communication unit, 37 Drive unit, 41 Receiving unit, 42 Reserved word extraction unit, 43 Advertisement selection unit, 44 Action information generation unit, 45 Instruction transmission unit, 51 Request transmission unit, 52 Action information reception unit, 53 Voice synthesis unit, 54 Action processing execution unit.

Claims

1. a storage means for storing advertisement copy, which is the content of the advertisement; an extraction means for extracting predetermined reserved words included in a conversational sentence input by a user; a selection means for selecting an advertising copy to be presented to a user from among the advertising copies based on the extracted reserved words; and an execution means for executing speech processing of a response sentence including the selected advertising text following the conversation sentence based on a predetermined criterion.

2. 2. The information processing device according to claim 1, The execution means is an information processing device that executes speech processing of the response sentence when the conversation sentence and the selected advertising sentence have continuity as the predetermined criterion.

3. 3. The information processing device according to claim 1, The storage means stores genre information indicating the genre of the advertisement represented by the advertising copy in association with each of the advertising copy, The selection means selects, based on the reserved words, an advertisement copy to be presented to the user from among advertisement copies associated with the genre determined as the advertisement to be presented to the user.

4. 4. The information processing device according to claim 1, The execution means is an information processing device that suppresses the utterance of the response sentence during a predetermined time period.

5. 5. The information processing device according to claim 1, The system further includes a reaction determination means for determining a user's reaction to the utterance processing of the response sentence when the utterance processing of the response sentence is executed, An information processing device that stores the result of the determination by the reaction determination means in association with information representing the content of the spoken response sentence, and uses the stored result for predetermined processing.

6. Computer, a storage means for storing advertisement copy, which is the content of the advertisement; an extraction means for extracting predetermined reserved words included in a conversational sentence input by a user; a selection means for selecting an advertising copy to be presented to a user from among the advertising copies based on the extracted reserved words; and a program that functions as an execution means for executing speech processing of a response sentence including the selected advertising copy following the conversation sentence based on predetermined criteria.

Images