JP6524181B2 - INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING PROGRAM - Google Patents

Description

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

  BACKGROUND Conventionally, there has been known an interactive agent system which outputs a message corresponding to a message to a user terminal in response to receiving a message from the user terminal. In such a dialogue agent system, there are provided techniques for outputting various messages in response to a message received from a user terminal, and outputting a message suitable for the user of the user terminal.

  Moreover, in the above-mentioned dialogue agent system, when a predetermined keyword is included in a message from a user terminal, there is known a technique of outputting an advertisement corresponding to the keyword as a message to the user terminal.

JP, 2013-12012, A JP, 2011-146046, A

  However, the above-mentioned prior art can not always improve the quality of interaction. Specifically, since the above-mentioned prior art determines the output of the advertisement according to the rules concerning the dialogue set in advance, if the flow of the dialogue does not match the actual situation of the contents of the dialogue, the quality of the dialogue is reduced as a result. May not be the output of highly appealing advertisements.

  The present application aims to provide an information processing apparatus, an information processing method, and an information processing program that can improve the quality of interaction.

  The information processing apparatus according to the present application is selected as a response to the utterance information on the utterance of the user who uses the voice dialogue, and the acquisition unit acquires the number of times the information displayed on the screen is specified by the user And updating the evaluation regarding the voice dialogue when selecting a response to the user's speech based on the acquired number of times.

  According to one aspect of the embodiment, the effect is achieved that the quality of interaction can be improved.

FIG. 1 is a diagram showing an example of automatic dialogue processing according to the embodiment. FIG. 2 is a diagram illustrating an example of a determination tree according to the embodiment. FIG. 3 is a diagram showing a configuration example of a dialog agent system according to the embodiment. FIG. 4 is a diagram illustrating an exemplary configuration of the information processing apparatus according to the embodiment. FIG. 5 is a diagram showing an example of the dialogue information storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of the advertisement information storage unit according to the embodiment. FIG. 7 is a diagram illustrating an example of the user terminal according to the embodiment. FIG. 8 is a diagram illustrating an example of a determination tree according to the embodiment. FIG. 9 is a sequence diagram showing an automatic interaction processing procedure according to the embodiment. FIG. 10 is a diagram illustrating an example of a determination tree according to a modification. FIG. 11 is a diagram illustrating an example of a determination tree according to a modification. FIG. 12 is a hardware configuration diagram showing an example of a computer for realizing the function of the information processing apparatus.

  Hereinafter, an information processing apparatus, an information processing method, and a mode for implementing an information processing program according to the present application (hereinafter, referred to as “embodiment”) will be described in detail with reference to the drawings. Note that the information processing apparatus, the information processing method, and the information processing program according to the present application are not limited by the embodiment. Moreover, the same code | symbol is attached | subjected to the same site | part in the following each embodiment, and the overlapping description is abbreviate | omitted.

  First, an example of automatic dialogue processing according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of automatic dialogue processing according to the embodiment. The response generation server 100 illustrated in FIG. 1 is an information processing apparatus that provides a voice service that outputs a response message based on response information to utterance information related to an utterance input by the user, which is an input message. Specifically, the response generation server 100 selects the response information to be output with respect to the speech information from the user using the determination tree as the determination information which is the information on the rule used for the dialogue agent system 1.

[1-1. Judgment tree]
Here, the determination tree used by the response generation server 100 will be described with reference to FIG. FIG. 2 is a diagram illustrating an example of a determination tree according to the embodiment. That is, the dialogue agent system 1 realizes the dialogue with the user using the determination tree as shown in FIG. 2 as the information on the dialogue rule. Specifically, the response generation server 100 determines response information to be returned to the user for the utterance information which is the user's utterance based on the determination tree as shown in FIG.

  In the example shown in FIG. 2, a broken line block indicates a detection node, and a solid line block indicates an operation node. Moreover, node ID to N101-N113 is each attached | subjected to these blocks. For example, a broken line block ““ curry ”detection” of the node ID “N101” indicates a detection node, and a solid line block ““ delicious ”of the node ID“ N102 ”indicates an operation node. The detection node defines the processing procedure corresponding to the utterance information from the user, and the operation node defines the processing procedure corresponding to the response information. Thus, the decision tree shown in FIG. 2 includes detection nodes and operation nodes.

  Also, the nodes shown in FIG. 2 are related by being connected by an arrow line. Specifically, the node on the start point side of the arrow line is associated as a connection source node, and the node on the arrow tip side is associated as a connection destination node. For example, in the arrow line associating the node of node ID "N104" with the node of node ID "N106", the connection source node is a detection node of node ID "N104" and the connection destination node is an operation of node ID "N106" It indicates that it is a node. The node with the node ID “N104” is also associated with the operation node with the node ID “N107” as a connection source node. Here, the response generation server 100 detects a keyword from the speech of the user, and if a detection node corresponding to the keyword is associated as a connection destination node, the response generation server 100 transitions to the detection node. Specifically, the response generation server 100 responds to the response information corresponding to the operation node of the node ID "N103" "" where curry? Roppongi? If "Roppongi" is included in the user's speech after responding "" to the user, it is determined that "Roppongi" detection corresponding to the node ID "N104" has been performed, and the connection destination node A transition is made to an operating node of either a certain node ID “N106” or a node ID “N107”. Then, the response information of the corresponding operation node is returned to the user. Specifically, when transitioning to the node ID "N106", the response generation server 100 responds to the user with response information "" I like curry at A store "" corresponding to the operation node of the node ID "N106". . Thus, the dialogue agent system 1 advances the dialogue with the user.

[1-2. Node and transition probability]
Here, the operation nodes in the determination tree shown in FIG. 2 include an advertisement node which is an operation node related to an advertisement and other operation nodes. For example, the operation node of the node ID "N102" is not an advertisement node because it is response information that does not include a specific store name or product name "I'm delicious". On the other hand, the operation node of the node ID "N106" is an advertisement node because it is response information including a specific store name "I like curry at A store". The dialogue agent system 1 provides an advertisement to the user in a natural conversation by intermingling such an advertisement node with other operation nodes. Here, the response generation server 100 receives registration of the contents of the advertisement node, various information related to the advertisement node, the connection relationship between the advertisement node and the operation node, and the like from the terminal device used by the advertiser and the advertisement agency. It is also good. When accepting such registration, the response generation server 100 generates a new operation node in order to guide the dialog with the user from the dialog corresponding to the registered operation node to the dialog corresponding to the advertisement node to be registered. The registration may be received along with the registration of the advertisement node.

  Also, each node in the decision tree is associated with one another including the transition probability. In the example shown in FIG. 2, the transition probability is attached above the arrow line of the determination tree, and the transition from each detection node to the operation node is performed according to the transition probability. For example, since the transition probabilities of the operating nodes of the node ID “N106” and the node ID “N107” shown in FIG. 2 are both 0.5, the transition from the detection node of the node ID “N104” is 50%. . Specifically, the response generation server 100 responds to the N103 response information "" where curry? Roppongi? When "Roppongi" is included in the speech information from the user after responding "" to the user, it is determined that N104 "Roppongi detection" has been performed, and transition to N106 or N107 with a probability of 50% respectively Do. That is, in the example shown in FIG. 2, the transition from the operation node to the detection node is performed based on the speech information from the user, and the transition from the detection node to the operation node is performed based on the transition probability.

[1-3. Automatic dialogue processing]
Referring back to FIG. 1, the automatic interaction processing according to the embodiment will be described. As shown in FIG. 1, the response generation server 100 receives speech information on the speech of the user as an input message from the user terminal 10 (step S11). An outline of processing in which the dialogue agent system 1 provides a voice service to the user, such as generation of speech information in the user terminal 10, will be described later. Subsequently, the response generation server 100 selects response information corresponding to the acquired utterance information from the determination tree, and transmits the selected response information to the user terminal 10 (step S12). At this time, when there is related information related to the selected response information, the response generation server 100 also transmits the related information. As the related information, various information related to the advertisement is used, such as information related to the response information related to the advertisement, such as information on the URL of the homepage of the advertiser and information on the campaign performed by the advertiser. Further, the related information may be registered by the advertiser together with the response information, or may be registered after the registration of the response information. Then, when the user terminal 10 outputs the response information and the user terminal 10 receives the related information, the related information is displayed on the user terminal 10 in a speculable manner. When selecting the response information corresponding to the utterance information, the response generation server 100 selects the response information based on the transition probability associated with the transition from the detection node to the operation node in the determination tree.

  Next, when the related information displayed on the user terminal 10 so as to allow specification is specified by the user, specification information on specification of the related information by the user is transmitted to the advertisement log server 50 (step S13). The advertisement log server 50 that has acquired the designation information transmits the web page corresponding to the related information to the user terminal 10 (step S14), and the user terminal 10 displays the acquired web page. At this time, the advertisement log server 50 counts the number of times the web page is displayed (the number of impressions) related to the related information displayed based on the designated information, that is, the number of times the advertisement is designated by the user. Here, the advertisement log server 50 is an information processing apparatus such as a web server, for example. The advertisement log server 50 may count only the number of times of display of the Web page related to the related information displayed based on the designation information. In this case, the user terminal 10 transmits the designated information to the corresponding web server or the like, and displays the web page acquired from the web server or the like. Then, the advertisement log server 50 acquires information on the number of displays from the Web server or the like at predetermined intervals such as every other day.

  Next, the advertisement log server 50 transmits, to the response generation server 100, log information including the number of display of the Web page related to the related information, that is, the number of times the advertisement is specified by the user every predetermined period, for example, every other day. (Step S15). The response generation server 100 that has acquired the log information updates the transition probability based on the log information (step S16).

  As described above, the response generation server 100 according to the embodiment updates the transition probability, which is the probability based on the evaluation regarding the voice interaction, using the log information including the number of times of display of the Web page displayed based on the designation information. The Web page displayed in the dialogue can also give a high rating to the flow of the conversation that the user would like to browse. In other words, the response generation server 100 can improve the effectiveness of the advertisement by automatically evaluating the dialog by the determination tree and making the flow of the dialog with high evaluation more likely to occur.

[1-4. Configuration of Dialog Agent System]
As exemplified in FIG. 3, in the dialogue agent system 1 according to the present embodiment, the user terminal 10, the speech recognition server 20, the speech synthesis server 30, the service API (Application Program Interface) server 40, the advertisement log A server 50 and a response generation server 100 are included. The user terminal 10, the voice recognition server 20, the voice synthesis server 30, the service API server 40, the advertisement log server 50, and the response generation server 100 transmit and receive information via the communication network 60.

  From here, an outline of processing in which the dialog agent system 1 provides a voice service to the user will be described. The user terminal 10 is an information processing apparatus such as a mobile phone, a smartphone, a PDA (Personal Digital Assistant), a tablet PC, a notebook PC, and a desktop PC. The user terminal 10 transmits speech data of speech to the speech recognition server 20 when it detects speech of the user after activation of the application.

  When the speech recognition server 20 receives speech data of an utterance from the user terminal 10, the speech recognition server 20 converts the speech data into text data and transmits the text data of the speech to the user terminal 10. The user terminal 10 having received the text data of the speech from the speech recognition server 20 transmits the text data of the speech to the response generation server 100 as speech information.

  As described above, the response generation server 100 transmits response information to the user terminal 10 in accordance with the utterance information transmitted from the user terminal 10. Specifically, when receiving the speech information from the user terminal 10, the response generation server 100 selects the response information based on the determination tree. Then, the response generation server 100 transmits the text data of the response information to the voice synthesis server 30. The speech synthesis server 30 transmits, to the response generation server 100, an intermediate description of the response information generated by performing speech synthesis processing for synthesizing speech from text data of the response information. The response generation server 100 transmits, to the user terminal 10, response information including an intermediate notation for voice output and text data for display. Further, when there is related information related to the response information, the response generation server 100 transmits the related information to the user terminal 10. The response generation server 100 acquires it from the service API server 40 as needed and transmits it to the user terminal 10.

  The user terminal 10 outputs the voice of the response using the intermediate notation for voice output included in the received response information, and displays the content of the response using the text data for display included in the response information. . Further, when the user terminal 10 receives the related information, the user terminal 10 displays the received related information in a specifiable manner. In this manner, the dialogue agent system 1 realizes a voice service that makes an appropriate response to the user's speech.

[2. Configuration of information processing apparatus]
Next, the configuration of the response generation server 100 according to the embodiment will be described with reference to FIG. FIG. 4 is a diagram showing a configuration example of the response generation server 100 according to the embodiment. As illustrated in FIG. 4, the response generation server 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The response generation server 100 includes an input unit (for example, a keyboard or a mouse) that receives various operations from the administrator of the response generation server 100 and a display unit (for example, a liquid crystal display or the like) for displaying various information. You may have.

(Communication unit 110)
The communication unit 110 is realized by, for example, a network interface card (NIC). The communication unit 110 is connected to the communication network 60 by wire or wirelessly. Then, the communication unit 110 transmits and receives information to and from the advertisement log server 50, the user terminal 10, and the like via the communication network 60.

(Storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. As illustrated in FIG. 4, the storage unit 120 according to the embodiment includes a dialogue information storage unit 121 and an advertisement information storage unit 122.

(Dialogue information storage unit 121)
The dialogue information storage unit 121 according to the embodiment stores information on dialogue. For example, the dialogue information storage unit 121 stores information on a judgment tree as shown in FIG. 2 as information on dialogue.

  FIG. 5 shows an example of the dialogue information storage unit 121 according to the embodiment. As shown in FIG. 5, the dialogue information storage unit 121 has items such as “node ID”, “transition destination node ID”, “transition probability”, and “detection word”.

  The “node ID” corresponds to the node ID of the determination tree shown in FIG. 2 and indicates identification information for identifying each node. The “transition destination node ID” indicates identification information for identifying a node that transitions from the node of that node ID. Specifically, “transition destination node ID” indicates identification information for identifying a node corresponding to the connection destination node when the node ID is the connection source node in the determination tree shown in FIG. The “transition probability” indicates the probability of transition from the node of the node ID to each node of the transition destination node ID. The “detection word” indicates a keyword for transitioning from the node of the node ID to each node of the transition destination node ID.

  The example illustrated in FIG. 5 corresponds to the determination tree illustrated in FIG. 2 and indicates that there are three transition destination node IDs transitioning from N101: N102, N103, and N106. Further, in FIG. 5, the transition probability from N101 to N102 is “0.33”, the transition probability from N101 to N103 is “0.33”, and the transition probability from N101 to N106 is “0.33”. It is shown that. Here, as shown in the determination tree of FIG. 2, there is no transition destination node that transitions from N102, so the transition destination node ID of the corresponding part is “−”.

  Further, in the example shown in FIG. 5, it is shown that there are two transition destination node IDs transitioning from N103: N104 and N105. In addition, since N103 is an operation node, the transition to the transition destination node ID is performed by detecting a keyword included in the user's utterance information, so the “detection word” for transition of each transition destination node ID is transitioned It is stored in association with the destination node ID. Specifically, since the transition from N103 to N104 is performed by detection of the detection word "Roppongi", the detection word in the column where "Node ID" is N103 and "Transition Destination Node ID" is N104 is "Roppongi It is ". Similarly, the detection word of the column in which the “node ID” is N103 and the “transition destination node ID” is N105 is “other”. Thus, the dialog information storage unit 121 stores the transition destination node ID, the transition probability, and the like in association with the node ID. Further, the dialogue information storage unit 121 may store response information in association with the node ID. Then, the dialogue information storage unit 121 may store an advertisement ID, which will be described later, in association with the node ID of the node related to the advertisement, and may refer to the response information associated with the corresponding advertisement ID. The dialogue information storage unit 121 may store information in any format as long as it can store information related to the determination tree as shown in FIG. For example, the dialogue information storage unit 121 may separately store the detection node and the operation node.

(Advertising information storage unit 122)
The advertisement information storage unit 122 according to the embodiment stores information on an advertisement. For example, the advertisement information storage unit 122 stores, as information on an advertisement, response information on an advertisement node, related information, and a list.

  FIG. 6 shows an example of the advertisement information storage unit 122 according to the embodiment. As shown in FIG. 6, the advertisement information storage unit 122 has items such as “response information ID”, “response information”, “node ID”, “related information ID”, and “related information”.

  The “response information ID” indicates identification information for identifying response information on an advertisement. “Response information” indicates response information on the advertisement identified by the response information ID. “Node ID” indicates identification information for identifying a node corresponding to the response information ID in the determination tree shown in FIG. “Related information ID” indicates identification information for identifying related information related to response information. “Related information” indicates related information identified by the related information ID.

  The example shown in FIG. 6 shows information on the advertisement output by the determination tree shown in FIG. That is, the example shown in FIG. 6 corresponds to the node related to the advertisement in the determination tree shown in FIG. 2, and the response information related to four nodes N106, N107, N111 and N112 which are nodes related to the advertisement It shows. Specifically, the example illustrated in FIG. 6 indicates that the response information corresponding to the response information ID “AI1” is “I like curry at A store” and the node ID corresponding to AI1 is “N106”. It shows. The related information ID corresponding to AI1 is "RI11", and the related information corresponding to AI1 is "www.a-curry ...". Thus, the advertisement information storage unit 122 associates and stores the response information and the related information. Note that the advertisement information storage unit 122 may associate and store a plurality of pieces of related information with one piece of response information. For example, the advertisement information storage unit 122 may store, for example, related information of RI12 in addition to RI11 as related information corresponding to AI1. In addition, the number of times of transmission and the number of times of display included in log information acquired from the advertisement log server 50 described later may be stored for each piece of related information.

  The control unit 130 is configured such that, for example, various programs (corresponding to an example of an information processing program) stored in a storage device in the response generation server 100 by a central processing unit (CPU) or a micro processing unit (MPU) It is realized by being implemented as a work area. Further, the control unit 130 is realized by, for example, an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  As shown in FIG. 4, the control unit 130 includes an acquisition unit 131, a selection unit 132, a transmission unit 133, and an update unit 134, and implements or executes the function and action of the automatic interaction described below. . The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 4, and any other configuration may be used as long as it performs the automatic dialogue described later. Further, the connection relationship of each processing unit included in the control unit 130 is not limited to the connection relationship illustrated in FIG. 4, and may be another connection relationship.

(Acquisition unit 131)
The acquisition unit 131 acquires the number of times an advertisement has been specified by the user. Specifically, the acquisition unit 131 acquires, from the advertisement log server 50, log information including the number of times of display of the Web page displayed based on the designation information, that is, the number of times the advertisement is designated by the user. The log information acquired by the acquisition unit 131 may include the related information ID and the number of displays associated with each related information ID. In addition, the acquisition unit 131 may acquire log information from the advertisement log server 50 at preset intervals, such as every other day. The speech information on the speech of the user is acquired from the user terminal 10 as an input message. In addition, the acquisition unit 131 acquires, from the speech synthesis server 30, an intermediate description of the response information generated by the speech synthesis server 30 performing speech synthesis processing to synthesize speech from the text data of the response information.

(Selection unit 132)
The selection unit 132 selects response information corresponding to the utterance information acquired by the acquisition unit 131 based on the determination tree. Specifically, when selecting the response information corresponding to the utterance information, the selection unit 132 selects the response information based on the transition probability associated with the transition from the detection node to the operation node in the determination tree.

(Transmission unit 133)
The transmission unit 133 transmits, to the user terminal 10, an intermediate notation for voice output, text data for display, and the like as the response information selected by the selection unit 132. The user terminal 10 having received the response information outputs the voice of the response using the intermediate notation for voice output, and displays the content of the response using the text data for display included in the response information.

  Also, the transmitting unit 133 transmits the text data of the response information selected by the selecting unit 132 to the voice synthesis server 30. The speech synthesis server 30 that has received the text data of the response information performs speech synthesis processing to synthesize speech and generates an intermediate representation of the response information.

  In addition, when there is related information related to the response information selected by the selection unit 132, the transmission unit 133 transmits the specifiable related information to the user terminal 10. Then, the user terminal 10 displays the received related information in a specifiable manner.

  Here, FIG. 7 illustrates an example of the dialogue display page displayed on the user terminal 10 that has received the response information from the response generation server 100. The user terminal 10 displays the content of the dialog with the dialog agent system 1 as text information on the dialog display page W10. The character information posted in the right side balloon in the dialogue display page W10 corresponds to the user's speech, and the character information posted in the left side balloon in the dialogue display page W10 is the user according to the response information received from the response generation server 100 It corresponds to the output of the terminal 10. That is, the user terminal 10 outputs a voice based on the response information when the balloon on the left side in the dialogue display page W10 is displayed.

  Next, the correspondence between the dialogue display page shown in FIG. 7 and the determination tree shown in FIG. 2 will be described based on the following processing. First, when the user terminal 10 receives an utterance of the user “delicious curry” from the user, the user terminal 10 displays “delicious curry” in the dialogue display page W10 of FIG. 7. At this time, the acquisition unit 131 acquires, from the user terminal 10, utterance information regarding the user's utterance "delicious curry". Then, the selection unit 132 determines that N101 "" curry "detection" in the determination tree of FIG. 2 has been performed, based on the transition probability among the three nodes of the connection destination nodes N102, N103, and N106 of N101. Select a node to transition. Specifically, in the determination tree of FIG. 2, the nodes N102, N103, and N106 are selected with a probability of 33%. Here, assuming that the selection unit 132 selects N103, the transmission unit 133 transmits response information corresponding to N103 to the user terminal 10. Then, the user terminal 10 displays "Which curry? Roppongi?" After the "delicious curry" which is an utterance of the user in the dialogue display page W10 of Fig. 7, and "Which curry? Roppongi?" Output voice.

  Subsequently, when the user terminal 10 receives the user's utterance "No, otherwise." From the user, "What curry? Roppongi?" In the dialogue display page W10 of Fig. 7 is followed by "No, other." Is displayed. At this time, the acquisition unit 131 acquires, from the user terminal 10, speech information on the user's speech "No, otherwise." Then, the selection unit 132 determines that N105 “others detection” in the determination tree of FIG. 2 is performed, and the node transits based on the transition probability among the two nodes of the connection destination nodes N108 and N113 of N105. Choose Specifically, in the determination tree of FIG. 2, the nodes N108 and N113 are selected with a probability of 50%. Here, assuming that the selection unit 132 selects N108, the transmission unit 133 transmits response information corresponding to N108 to the user terminal 10. Then, the user terminal 10 displays "What kind of curry do you like?" In the dialogue display page W10 of FIG. Output the voice.

  Furthermore, when the user terminal 10 receives the user's utterance "key curry" from the user, the user terminal 10 displays "key curry" following "what curry do you like?" In the dialogue display page W10 of FIG. Do. At this time, the acquisition unit 131 acquires, from the user terminal 10, utterance information on the user's utterance "key curry". Then, the selection unit 132 determines that N109 “'keyma detection” in the determination tree of FIG. 2 has been performed, and makes a transition based on the transition probability among two nodes of the connection destination nodes N111 and N112 of N109. Choose Specifically, in the determination tree of FIG. 2, each node of N111 and N112 is selected with a probability of 50%. Here, assuming that the selection unit 132 selects N111, the transmission unit 133 transmits response information corresponding to N111 to the user terminal 10. Then, the user terminal 10 displays "I like the key curry at C store" in the dialog display page W10 of FIG. Output a voice saying that I like Keema curry at C store.

  Here, since the user terminal 10 outputs the response information on the advertisement node saying “I like the key curry at C store”, the transmitting unit 133 can designate relating to the response information selected by the selecting unit 132. The related information is transmitted to the user terminal 10. Then, the user terminal 10 displays the received related information in a specifiable manner. Specifically, the user terminal 10 having received the related information receives the response information “I like the key store curry at C store” R10, the URL (Uniform Resource Locator) of the Web page of the C store which is the related information ) Can be specified. In this case, “can be specified” means that a hyperlink is set and the web page of the designated C store is displayed when the user touches the surface on which the related information of the user terminal 10 is displayed with a finger, etc. Can be mentioned. Note that the display of the related information is not limited to the above example, and may be displayed at a position apart from the response information, for example, displayed at the lower side of the screen.

  Then, when the user designates the URL of the Web page of the C store which is the related information displayed in the dialogue display page W10 of the user terminal 10, for example, the Web page W20 of the C store as shown in FIG. Is displayed on. Specifically, when the user designates the URL of the Web page of the C store which is the related information displayed in the interactive display page W10 of the user terminal 10, the specified information regarding the specification of the related information is transmitted to the advertisement log server 50 Ru. Then, the advertisement log server 50 having received the designation information acquires a web page corresponding to the designated related information by an appropriate means, and transmits the web page to the user terminal 10. At this time, the advertisement log server 50 stores the number of times of display of the Web page displayed based on the designation information. Thereafter, the user terminal 10 displays the acquired web page.

(Update unit 134)
The update unit 134 updates the evaluation on the voice dialogue related to the advertisement specified by the user based on the number of times the advertisement is specified by the user included in the log information acquired by the acquisition unit 131. Specifically, according to the log information including the number of times of display of the Web page corresponding to the related information acquired from the advertisement log server 50 by the acquisition unit 131, that is, the number of times the advertisement is specified by the user. Update the transition probability, which is the probability based on the evaluation on the speech dialogue. For example, the updating unit 134 updates the transition probability such that the probability of transitioning to the node of the response information related to the related information is higher as the number of times of display is larger. As in the example shown in FIG. 7, when a large number of related information related to N111 “I like the key curry at C store” is specified, and the Web page corresponding to the related information has a display count exceeding a predetermined threshold, The transition probability is updated so that the probability that the flow of conversation is directed to N111 is high.

  Also, the updating unit 134 updates, for example, the transition probability of transition to the node that has transitioned to the selected node. In the determination tree shown in FIG. 2, for example, when nodes are selected in the order of N101-N103-N105-N108-N109-N111, the updating unit 134 transitions from N05 to N108, and the transition probability of transition from N109 to N111. The transition probability and the transition probability of transition from N101 to N103 are updated high. Specifically, in the example illustrated in FIG. 8, the updating unit 134 sets the transition probability of transition from N109 to N111 from “0.5” to “0.75” and the transition probability from N105 to N108 “0”. .5 "and" 0.75 "and the transition probability from N101 to N103 is updated high from" 0.33 "to" 0.5 ". In addition, along with the update of the above transition probability, the transition probability from the same detection node to another node transitioning is also updated. Specifically, the transition probability of transition from N109 to N112 is from “0.5” to “0.25”, and the transition probability of transition from N105 to N113 is from “0.5” to “0.25”, and The transition probabilities of transition from N101 to N102 to N106 are updated to be low from “0.33” to “0.25”, respectively. As a result, the response generation server 100 can improve the effectiveness of the advertisement by automatically evaluating the dialog by the determination tree and making the flow of the dialog with high evaluation more likely to occur. When there are a plurality of other transition nodes as in N101, the transition probability may be updated according to the ratio of the transition probability of each node.

[3. Automatic dialogue procedure]
Next, the procedure of the automatic dialogue process including the update process of the transition probability according to the embodiment will be described with reference to FIG. FIG. 9 is a sequence diagram showing an automatic dialogue processing procedure including a transition probability update process according to the embodiment.

  As shown in FIG. 9, the response generation server 100 receives, as an input message, speech information on the speech of the user from the user terminal 10 (step S101). Then, the response generation server 100 selects response information based on the transition probability associated with the transition from the detection node to the operation node in the determination tree, and transmits the selected response information to the user terminal 10 (step S102). At this time, when there is related information related to the selected response information, the response generation server 100 transmits the related information to the user terminal 10 (step S103).

  Then, the response information is output by the user terminal 10, and the related information is displayed on the user terminal 10 so as to be specified (step S104). Thereafter, when the related information displayed on the user terminal 10 so as to allow specification is specified by the user, specification information regarding specification of the related information by the user is transmitted to the advertisement log server 50 (step S105).

  Subsequently, the advertisement log server 50 that has acquired the designation information transmits a web page corresponding to the related information to the user terminal 10 (step S106), and the user terminal 10 displays the acquired web (step S107). At this time, the advertisement log server 50 counts the number of times of display of the Web page displayed based on the designated information.

  Next, the response generation server 100 receives, from the advertisement log server 50, log information including the number of times of display of the Web page displayed based on the designated information every predetermined period, for example, every other day (step S108). The response generation server 100 that has acquired the log information updates the transition probability based on the log information (step S109).

[4. Modified example]
The dialogue agent system 1 according to the embodiment described above may be implemented in various different forms other than the embodiment described above. So, below, embodiment which deform | transformed said dialog agent system 1 is described.

[4-1. Update by specified number / displayed number]
In the above embodiment, the response generation server 100 updates the transition probability based only on the number of times the related information displayed on the user terminal 10 is specified. However, the response generation server may update the transition probability based on the ratio of the designated number of times the associated information is displayed. As a result, since the transition probability is updated based on the probability that the related information is specified instead of the number of times the related information is specified, it is possible to make the flow of dialogue having a high probability of specifying the related information more likely to occur. Can improve the effectiveness of the advertisement.

[4-2. Scope of update]
In the above embodiment, the response generation server 100 updates the transition probability up to the top N 101 in the determination tree shown in FIG. However, the response generation server may update the transition probability for nodes up to a predetermined range.

  Here, FIG. 10 illustrates an example of the determination tree after the transition probability of the determination tree illustrated in FIG. 2 is updated. In the example illustrated in FIG. 10, when many pieces of related information related to N111 are specified, and the Web page corresponding to the related information is the number of times of display exceeding a predetermined threshold, the response generation server determines the determination tree illustrated in FIG. The transition probability of is updated so that the flow of dialogue is directed to N111.

  For example, the response generation server may update the transition probabilities of the top two detection nodes. Specifically, the response generation server 100 transitions from “0.5” to “0.75” the transition probability of transition from the detection node N109 one rank higher to N111, and from the detection node N105 two ranks higher to N108. Update the transition probability from "0.5" to "0.75". In addition, along with the update of the above transition probability, the transition probability from the same detection node to another node transitioning is also updated. Specifically, the transition probability of transition from N109 to N112 is updated from "0.5" to "0.25", and the transition probability from N105 to N113 is updated from "0.5" to "0.25". Do. As a result, the response generation server 100 can improve the effectiveness of the advertisement by automatically evaluating the dialog by the determination tree and making the flow of the dialog with high evaluation more likely to occur. Here, unlike the example shown in FIG. 8, the example shown in FIG. 10 does not update the transition probability of the transition from the three upper detection nodes N101 to N103. This makes it possible to improve the effectiveness of the advertisement while suppressing the decrease in dialogue diversity.

[4-3. Size of update]
In addition, the response generation server may update the transition probability regarding the node according to the number of transitions until the web page transitions to the node related to the response information corresponding to the related information, which is the number of display times exceeding a predetermined threshold.

  Here, FIG. 11 illustrates an example of the determination tree after the transition probability of the determination tree illustrated in FIG. 2 is updated. In the example illustrated in FIG. 11, when many pieces of related information related to N111 are specified, and the Web page corresponding to the related information is the number of times of display exceeding a predetermined threshold, the response generation server determines the determination tree illustrated in FIG. The transition probability of is updated so that the flow of dialogue is directed to N111.

  For example, the response generation server updates, for example, the transition probability of transition from N109 to N111, the transition probability of transition from N05 to N108, and the transition probability of transition from N101 to N103. Specifically, in the example illustrated in FIG. 11, the response generation server updates the transition probability of transition from N109 to N111 to a high value from “0.5” to “0.75”. That is, in the response generation server, the transition probability of transition from N109 to N111 is 1.5 times, and the fluctuation rate is 150%. Then, the transition probability of transitioning from N105 to N108 is updated high from “0.5” to “0.6”. That is, in the response generation server, the transition probability of transition from N105 to N108 is 1.2 times, and the fluctuation rate is 120%. Also, the transition probability of transitioning from N101 to N103 is updated high from “0.33” to “0.35”. That is, in the response generation server, the transition probability of transition from N101 to N103 is 1.05 times, and the fluctuation rate is 105%. Thereby, the response generation server 100 can improve the effectiveness of the advertisement while suppressing the decrease in the diversity of the dialogue. Further, the response generation server may calculate the variation rate of the transition probability of each detection node using a predetermined propagation function. In this case, assuming that the response probability of the transition probability of the detection node that makes a direct transition to the first node, in the above example, N111, is a predetermined value x, the response probability of the upper detection node is y (x> y) A propagation function may be used in which the fluctuation rate of the upper detection node is z (y> z) and the fluctuation rate decreases as the number of transitions increases from the first node.

[4-4. Judgment information]
In the above embodiment, a determination tree as shown in FIG. 2 is used as the determination information. However, the determination information is not limited to a tree shape like a determination tree, and may be, for example, a node map shape. When such node map-like determination information is used, the root node (corresponding to N101 in the example shown in FIG. 2) is a node when the conversation starts.

[4-5. Target of evaluation]
Further, in the above embodiment, the response generation server 100 updates the transition probability based only on the number of times the related information displayed on the user terminal 10 is specified. However, the response generation server updates the transition probability based on so-called popular words such as seasonal words, buzz words used in television and SNS (Social Networking Service), and words in the top ranks of search queries. May be For example, the response generation server 100 may update the transition probability based on the number of times the user using the dialogue agent system 1 has designated an advertisement related to the content of the voice dialogue within a predetermined time. In addition, the response generation server 100 may update the transition probability based on the number of times the advertisement related to the content of the voice interaction is designated within a predetermined time, for the user in the login state. Further, in the embodiment described above, the response generation server 100 updates the transition probability in accordance with the number of times of specifying the related information displayed on the user terminal 10. However, the embodiment is not limited to this. For example, the response generation server 100 performs the transition according to the designated number of related information displayed on any display device operating in cooperation with the user terminal 10. The probability may be updated. Further, in the dialog with the user, the response generation server 10 outputs the related information as a voice, and when the user makes a response that specifies the related information, it is assumed that the related information is selected, the transition probability is You may update it. In addition, the response generation server 10 selects how to select related information (for example, whether the displayed related information is selected, whether the related information output by voice is selected, or is selected by voice) Weighting may be performed at the time of updating the transition probability depending on whether or not it is selected by the operation. Thus, the response generation server 100 may not be premised on screen display of related information.

[4-6. Device configuration〕
In addition, the response generation server 100 illustrated in FIG. 4 may not have the dialogue information storage unit 121 or the advertisement information storage unit 122. Specifically, the response generation server 100 may be connected to a database server that holds the dialogue information storage unit 121 and the advertisement information storage unit 122. In the above embodiment, the dialogue agent system 1 includes the response generation server 100 and the advertisement log server 50. However, the response generation server 100 and the advertisement log server 50 are formed as one device. May be

[4-7. effect〕
As described above, the response generation server 100 according to the embodiment includes the acquisition unit 131 and the update unit 134. The acquisition unit 131 acquires the number of times the information displayed on the screen is designated by the user. The updating unit 134 updates the evaluation regarding the voice dialogue related to the information designated by the user based on the number of times acquired by the acquiring unit 131. For example, the acquisition unit 131 acquires the number of times the advertisement has been specified. Then, based on the number of times acquired by the acquisition unit 131, the update unit 134 updates the evaluation regarding the voice dialogue related to the advertisement specified by the user.

  Thereby, the response generation server 100 according to the embodiment can improve the quality of interaction. For example, since the response generation server 100 updates the evaluation regarding the voice dialogue according to the number of times the advertisement is designated, many dialogues that can improve the effectiveness of the advertisement can be performed.

  In addition, the response generation server 100 according to the embodiment includes the transmission unit 133. The transmitting unit 133 can be designated related to the response information selected based on the transition probability which is the probability to be selected as a response to the utterance information on the user's utterance using the speech interaction, which is the probability based on the evaluation on the speech interaction. Relevant information is transmitted to the user terminal 10. The updating unit 134 updates the transition probability corresponding to the selected response information according to the number of times the related information transmitted by the transmitting unit 133 is specified by the user.

  As a result, the response generation server 100 according to the embodiment improves the effectiveness of the advertisement because the transition probability corresponding to the response information selected according to the number of times the related information related to the response information is specified is updated. Can.

  Further, in the response generation server 100 according to the embodiment, the updating unit 134 selects the response according to the ratio of the number of times the related information is designated among the number of times the related information related to the selected response information is displayed. Update transition probabilities corresponding to information.

  As a result, the response generation server 100 according to the embodiment updates the transition probability based on the probability that the related information is specified, not the number of times the related information is specified, so that the probability that the related information is specified is By making high conversational flow more likely to occur, the effectiveness of advertising can be improved.

  In addition, in the response generation server 100 according to the embodiment, the transmission unit 133 is associated with the response information corresponding to the node selected based on the determination information in which nodes relating to the utterance information or the response information are associated by the transition probability. Sends related information that can be specified to the user terminal. The updating unit 134 updates the transition probability of transition to the selected node according to the number of times the related information transmitted by the transmitting unit 133 is specified by the user.

  As a result, the response generation server 100 according to the embodiment improves the effectiveness of the advertisement because the transition probability corresponding to the response information selected according to the number of times the related information related to the response information is specified is updated. Can.

  In addition, in the response generation server 100 according to the embodiment, the updating unit 134 transitions to a node in a predetermined range including the selected node according to the number of times the related information transmitted by the transmitting unit 133 is specified by the user. Update transition probabilities.

  Thereby, the response generation server 100 according to the embodiment can improve the effect of the advertisement while suppressing the decrease in the diversity of the dialogue.

  In addition, in the response generation server 100 according to the embodiment, the updating unit 134 transitions to a node that has transitioned to the selected node according to the number of times the related information transmitted by the transmitting unit 133 is specified by the user. Update transition probabilities.

  Thereby, the response generation server 100 according to the embodiment can improve the effect of the advertisement while suppressing the decrease in the diversity of the dialogue.

  Further, in the response generation server 100 according to the embodiment, the updating unit 134 updates the transition probability of transitioning to the node transitioned to the selected node according to the number of transitions until transitioning to the selected node. Change the ratio.

  Thereby, the response generation server 100 according to the embodiment can improve the effect of the advertisement while suppressing the decrease in the diversity of the dialogue.

[4-8. program〕
The information processing apparatus according to each embodiment described above is realized by, for example, a computer 1000 configured as shown in FIG. FIG. 12 is a hardware configuration diagram showing an example of a computer 1000 for realizing the functions of the respective information processing apparatuses. The computer 1000 includes 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 to control each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, 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 the program, and the like. The communication interface 1500 receives data from another device via the communication network 60, sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to the other device via the communication network 60.

  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 an input device via the input / output interface 1600. The CPU 1100 also outputs the generated 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 CPU 1100 with the program via the RAM 1200. The CPU 1100 loads such a 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 digital versatile disc (DVD) or a phase change rewritable disc (PD), a magneto-optical recording medium such as a magneto-optical disk (MO), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer 1000 functions as the response generation server 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 130 by executing a program loaded on the RAM 1200. In addition, the HDD 1400 stores data in the storage unit 120 in the information processing apparatus of the embodiment. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired from another device via the communication network 60.

[4-9. Other]
Further, among the processes described in the above-described embodiments, all or part of the process described as being automatically performed may be manually performed, or the process described as being manually performed. All or part of can be performed automatically by known methods. In addition, information including processing procedures, specific names, various data and parameters shown in the above-mentioned documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

  Further, each component of each device illustrated is functionally conceptual, and does not necessarily have to be physically configured as illustrated. That is, the specific form of the distribution and integration of each device is not limited to the illustrated one, and all or a part thereof may be functionally or physically dispersed in any unit depending on various loads, usage conditions, etc. It can be integrated and configured. For example, the acquisition unit 131 and the transmission unit 133 illustrated in FIG. 4 may be integrated. Further, the voice recognition processing for recognizing the voice described above is realized by the user terminal 10, and transmits the result of the voice recognition processing executed by the user terminal 10 to the response generation server 100 to realize each of the functions described above. May be

  In the embodiment described above, an example has been described in which the quality of the conversation in which the advertisement is displayed is evaluated according to the number of times the advertisement is selected. However, the embodiments are not limited to this. That is, in the case where the response generation server 100 has a function that can be shared with other users, such as information displayed by the user terminal 10 in a dialog, a function that performs evaluation such as “Like!” According to the number of times of evaluation and sharing performed by the function, the dialog may be evaluated. Also, for example, the response generation server 100 may be configured to use, among other information displayed on the user terminal 10, for example, an advertisement such as a banner advertisement displayed together with a web page, or information posted on a social network service or blog etc. The quality of dialogue can be evaluated according to the evaluation etc. on the information on the dialogue service provided by the response generation server 100.

  Also, the response generation server 100 may evaluate the quality of interaction using a log associated with the user who has conducted the interaction. For example, the response generation server 100 is a log that indicates the position of the user who conducted the dialog, the content browsed by the user, the application acquired by the user, the product purchased by the user, the attribute of the user, the operation performed by the user, etc. Analyze the life log) Then, when the user visits a store related to the advertisement output in the dialog, the response generation server 100, when the user purchases a product or an application related to the advertisement, when the user views the content related to the advertisement, etc. May update the transition probabilities as having a good quality of interaction including such advertisements.

  In the case of executing such processing, for example, the acquisition unit 131 acquires the life log of the user who has conducted the interaction from the user terminal 10, the log collection server that collects the life log, or the like. Then, the updating unit 134 updates the transition probability according to the action performed by the user after the interaction. For example, the updating unit 134 responds to the advertisement when the product related to the advertisement output during the dialogue is viewed or purchased, or when the user visits a store associated with the advertisement. Increase the probability of transition to the ad node. That is, the updating unit 134 updates the evaluation related to the dialogue based on the user's action history after the dialogue. The acquiring unit 131 and the updating unit 134 may execute any other process described above. Further, the updating unit 134 not only evaluates the behavior history after the voice dialogue, but also, for example, evaluates the dialogue according to the comparison result of the behavior history before the voice dialogue and the behavior history after the voice dialogue. It may be updated.

  As described above, the response generation server 100 acquires the action history of the user, and updates the evaluation regarding the interaction performed with the user based on the acquired action history. Thus, the response generation server 100 can improve the quality of interaction.

  Moreover, it is possible to combine suitably each embodiment mentioned above in the range which does not contradict process content.

  Although some of the embodiments of the present application have been described in detail based on the drawings, these are only examples, and various modifications can be made based on the knowledge of those skilled in the art, including the aspects described in the rows of the disclosure of the invention. It is possible to implement the invention in other improved forms.

  In addition, the "section (module, unit)" described above can be read as "means" or "circuit". For example, the acquisition unit can be read as an acquisition unit or an acquisition circuit.

DESCRIPTION OF SYMBOLS 1 dialogue agent system 10 user terminal 20 speech recognition server 30 speech synthesis server 40 service API server 50 advertisement log server 100 response generation server 120 storage unit 131 acquisition unit 132 selection unit 133 transmission unit 134 update unit

Claims (15)

An acquisition unit which is selected as a response to speech information on a speech of a user using a speech dialogue, and acquires the number of times the information displayed on the screen is designated by the user;
An evaluation on the voice dialogue at the time of selecting a response to the speech of the user , which is a probability to be selected as a response to speech information on the speech of the user using the speech dialogue based on the number of times acquired by the acquisition unit An update unit that updates a transition probability , which is a probability based on
An information processing apparatus comprising: Transmitting unit that transmits the possible relevant information related to the selected response information based on the previous Ki遷 transfer probability to the user terminal,
And further
The updating unit is
The transition probability corresponding to the selected response information is updated according to the number of times the related information transmitted by the transmission unit is designated by the user.
An information processing apparatus according to claim 1, characterized in that. An acquisition unit for acquiring the number of times the information displayed on the screen is designated by the user;
An updating unit that updates an evaluation on a voice dialogue related to the information specified by the user based on the number of times acquired by the acquisition unit;
Designable related information related to response information selected based on a transition probability that is a probability to be selected as a response to speech information on a user's speech using the speech dialog, the probability being based on an evaluation on the speech dialog A transmitting unit that transmits to the user terminal;
Equipped with
The updating unit is
An information processing apparatus, comprising: updating a transition probability corresponding to the selected response information according to the number of times the related information transmitted by the transmission unit is designated by the user. The updating unit is
The transition probability corresponding to the selected response information is updated according to the ratio of the number of times the related information is specified among the number of times the related information related to the selected response information is displayed.
The information processing apparatus according to claim 2 or claim 3, characterized in that: The transmission unit is
Transmitting, to the user terminal, specifiable related information related to response information corresponding to the node selected based on the determination information in which nodes relating to the utterance information or the response information are related by the transition probability.
The updating unit is
The transition probability of transition to the selected node is updated according to the number of times the related information transmitted by the transmission unit is designated by the user.
The information processing apparatus according to any one of claims 2 to 4, characterized in that: The updating unit is
Updating a transition probability of transitioning to a node in a predetermined range including the selected node according to the number of times the related information transmitted by the transmitter is designated by the user;
The information processing apparatus according to claim 5, characterized in that: The updating unit is
Updating a transition probability of transition to a node transitioned to the selected node according to the number of times the related information transmitted by the transmission unit is designated by the user;
7. An information processing apparatus according to claim 6, wherein: The updating unit is
According to the number of transitions until transition to the selected node, the rate of updating the transition probability of transition to the node transitioned to the selected node is changed.
The information processing apparatus according to claim 6 or 7, characterized in that: The acquisition unit acquires the number of times an advertisement has been specified by the user,
The information processing apparatus according to any one of claims 1 to 8, wherein the updating unit updates a transition probability that is a probability based on an evaluation related to a voice dialogue related to the advertisement. An acquisition unit for acquiring an action history of the user who has performed the voice dialogue, the information selected as a response to the speech information on the speech of the user using the speech dialogue is displayed on the screen;
The probability that a probability of being selected as a response to utterance information related to an utterance of a user using the audio interaction is selected based on the action history acquired by the acquisition unit, and relates to the audio interaction when selecting a response to the utterance of the user An updating unit that updates a transition probability , which is a probability based on an evaluation;
An information processing apparatus comprising: An acquisition unit for acquiring an action history of a user who has conducted a voice dialogue;
An updating unit that updates an evaluation related to the voice dialogue based on the action history acquired by the acquiring unit;
Designable related information related to response information selected based on a transition probability that is a probability to be selected as a response to speech information on a user's speech using the speech dialog, the probability being based on an evaluation on the speech dialog A transmitting unit that transmits to the user terminal;
Equipped with
The updating unit is
An information processing apparatus, comprising: updating a transition probability corresponding to the selected response information according to the number of times the related information transmitted by the transmission unit is designated by the user. An information processing method executed by a computer,
An acquisition step of acquiring the number of times the information displayed on the screen is selected by the user as a response to the utterance information on the utterance of the user using the voice dialogue;
An evaluation regarding the voice dialogue at the time of selecting a response to the speech of the user , which is a probability to be selected as a response to speech information on the speech of the user using the speech dialogue based on the number acquired in the acquisition step Updating the transition probability , which is the probability based on
An information processing method comprising: An acquisition procedure for acquiring the number of times the information displayed on the screen is selected as a response to the utterance information related to the utterance of the user using the voice dialogue,
An evaluation regarding the voice dialogue at the time of selecting a response to the speech of the user , the probability being selected as a response to speech information on the speech of the user using the speech dialogue based on the number of times acquired by the acquisition procedure Update procedure for updating transition probability which is probability based on
An information processing program characterized by causing a computer to execute. An information processing method executed by a computer,
An acquisition step of acquiring the number of times the information displayed on the screen is designated by the user;
An updating step of updating an evaluation of a voice dialogue related to the information designated by the user based on the number of times acquired by the acquiring step;
Designable related information related to response information selected based on a transition probability that is a probability to be selected as a response to speech information on a user's speech using the speech dialog, the probability being based on an evaluation on the speech dialog Transmitting to the user terminal;
Including
The updating process is
An information processing method comprising: updating a transition probability corresponding to the selected response information according to the number of times the related information transmitted in the transmitting step is designated by the user. An acquisition procedure for acquiring the number of times the information displayed on the screen is designated by the user;
An update procedure for updating the evaluation of the voice dialogue related to the information specified by the user based on the number of times acquired by the acquisition procedure;
Designable related information related to response information selected based on a transition probability that is a probability to be selected as a response to speech information on a user's speech using the speech dialog, the probability being based on an evaluation on the speech dialog A transmission procedure for transmitting to the user terminal;
On your computer,
The update procedure is
An information processing program, comprising: updating a transition probability corresponding to the selected response information according to the number of times the related information transmitted by the transmission procedure is designated by the user.

Images