Information processing device and program

Abstract

To allow a virtual user as a proxy of an actual user to naturally converse with others as if it was the actual user.SOLUTION: An information processing device 1 is connected via a communication line 6 to a user terminal 5 relating to an actual other user, an SNS server 3-1, and an utterance sentence generation device (generation AI) 2; and generates a response sentence of a virtual user as a proxy of an actual user for utterance of the other user. The information processing device receives data of utterance of the other user from the user terminal. The information processing device receives a plurality of posts of the actual user from the SNS server. The information processing device selects a post from the plurality of posts based on both a plurality of nouns included in each of the plurality of posts and a plurality of nouns included in the utterance of the other user. The information processing device instructs the utterance sentence generation device to generate a response sentence of the virtual user for the utterance of the other user by referring to the selected post. The information processing device receives data of the response sentence of the virtual user which is generated by the utterance sentence generation device from the utterance sentence generation device; and transmits it to the user terminal.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus and a program.

Background Art

[0002] Currently, EC sites (online sales) such as apparel have become widespread, and it is assumed that in the future, there will be an increasing number of opportunities to open virtual stores in shopping malls in the virtual space (metaverse) on the Internet. In such a situation, in EC sites as well as in physical stores, it is considered important from the perspective of sales promotion to provide one-on-one customer service in which staff introduce recommended products through interaction with users, dig out users' needs, materialize products that users desire, and respond to various inquiries.

[0003] Generally, the number of users visiting an EC site is much larger than the number of customers visiting a physical store. Therefore, it is not realistic for actual staff to serve each user who visits the EC site individually. Thus, it is assumed that a virtual staff (also called digital staff) is constructed on a computer, and the digital staff serves users one-on-one instead of the actual staff.

[0004] Various characters are set for digital staff, but it is not easy to generate a character with customer service ability. Therefore, a character similar to an actual staff may be set.

[0005] However, no matter how much the character of the virtual staff is made similar to that of the actual staff, it often clearly differs from the actual staff in various aspects such as the content of speech and diction.

Summary of the Invention

Problems to be Solved by the Invention

[0006] The purpose is to enable a virtual user acting as an agent for an actual user to interact with others without any sense of discomfort as if the virtual user were an actual user.

Means for Solving the Problem

[0007] The information processing apparatus according to the present embodiment is connected via a communication line to a user terminal related to an actual other user, an SNS server, and a speech generation apparatus (generation AI), and is an information processing apparatus that generates a response sentence of a virtual user acting as an agent for an actual user in response to a speech of the other user, means for receiving data of the speech of the other user from the user terminal; means for receiving a plurality of posts by the actual user from the SNS server; means for selecting a specific post closest to the content of the speech of the other user from the plurality of posts based on a plurality of nouns included in each of the plurality of posts and a plurality of nouns included in the speech of the other user; means for transmitting data of the selected specific post and data of the speech of the other user to the speech generation apparatus together with a response sentence generation instruction in order to generate a response sentence of the virtual user to the speech of the other user with reference to the selected specific post; means for receiving data of the response sentence of the virtual user generated by the speech generation apparatus in response to the response sentence generation instruction from the speech generation apparatus; and means for transmitting data of the response sentence of the virtual user to the user terminal.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

[0009] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In this embodiment, a social networking service (hereinafter referred to as "SNS"), which is a community-type service that promotes and supports connections between people, a blog site where users post daily matters, thoughts, etc. as articles and display them in chronological order, a word-of-mouth site where users write and view evaluations of products and services, and an EC site where products and services are sold on the Internet. By referring to comments (articles such as posted texts, article texts, word-of-mouth texts, evaluation texts, messages, etc.) actually created and posted by real users, a generation AI as a speech generation device generates a speech text in response to the speech of other user, so that the speech content matches the speech of other users, and moreover, the content of the speech of the virtual user is natural and free of discomfort in the word usage that the real user would use as if the real user represented by it would send it.

[0010] For example, representative examples of SNS include "Instagram (registered trademark)", "Facebook (registered trademark)", "Twitter (registered trademark) which is X at present", etc. Representative examples of review sites include "Tabelog (registered trademark)", "Price.com (registered trademark)", etc. Also, as for blog sites, there are many sites such as blogs on FC2 (registered trademark).

[0011] In the following description, taking as an example the scenario of selling clothing etc. via an EC (electronic commerce) site that develops a service of selling goods and services on a web site on the Internet via a network such as the Internet. Also, in this scenario, a virtual user (hereinafter referred to as a virtual staff) that acts on behalf of or substitutes for an actual user (hereinafter referred to as an actual staff) will be described by taking as an example the situation where the virtual user interacts with an actual user (other user) who has visited the EC site in a chat room and tries to sell clothing etc. by serving the other user.

[0012] As shown in FIG. 1, for the information processing apparatus 1 according to the present embodiment, typically via the Internet line network 6 as a communication line network, a speech generation apparatus 2 that functions as a generation AI, an SNS server 3-1 that provides an SNS, a blog site server 3-2 that provides a blog service, a review site server 3-3 that operates a review site, an EC site server 4 that operates an EC site, and a user terminal 5 used by an actual user are connected.

[0013] As shown in FIG. 2, an information processing apparatus 1 as an interaction apparatus has a RAM 12, a ROM 13, a storage unit 14, an input device 15, a display 16, and a communication unit 17 connected to a processor 11 via a system bus 10. The processor 11 is composed of, for example, a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit). The processor 11 executes a program loaded from the storage unit 14 and the ROM 13 into the RAM 12, and executes interaction processing for realizing interaction with an actual user. The RAM 12 functions as a main memory, a work area, etc. of the processor 11. The ROM 13 or the storage unit 14 stores a BIOS (Basic Input Output System) executed by the processor 11, an operating system program (OS), an interaction processing program according to the present embodiment, programs for realizing various other functions, various data required for those processes, etc.

[0014] The input device 15 consists of a keyboard (KB), a pointing device such as a mouse or a touch panel, etc. The display 19 is typically realized by an LCD (Liquid Crystal Display). In the storage unit 14, in addition to the interaction processing program, data regarding comments required for interaction processing, etc., respective feature amounts, profiles of actual staff, interactive messages between the actual user and the virtual staff and their order (interaction history), etc. are stored.

[0015] As shown in FIG. 3, by executing the interaction processing program, the processor 11 functions as a control unit 20, a profile acquisition unit 21, a posted comment collection unit 22, a natural language analysis processing unit 23, a feature amount calculation processing unit 24, a user message reception unit 25, a posted comment selection processing unit 26, a speech generation request unit 27, a speech reception unit 28, and a message transmission unit 29.

[0016] The profile acquisition unit 21 transmits a profile transmission request together with each account of the actual staff to each of the SNS server 3-1, the blog site server 3-2, the word-of-mouth site server 3-3, and the EC site server 4, and receives profile data from each of the SNS server 3-1, the blog site server 3-2, the word-of-mouth site server 3-3, and the EC site server 4. These profiles are edited into a single profile and stored in the storage unit 14 in association with the identification number of the virtual staff who acts on behalf of the actual staff.

[0017] The posted comment collection unit 22 transmits a transmission request for comments (such as posts, articles, word-of-mouth texts, evaluation texts, messages, etc.) posted by the actual staff together with each account of the actual staff to each of the SNS server 3-1, the blog site server 3-2, the word-of-mouth site server 3-3, and the EC site server 4, and receives data of the comments actually posted by the actual staff from each of the SNS server 3-1, the blog site server 3-2, and the word-of-mouth site server 3-3. These posted comments are stored in the storage unit 14 in association with the identification number (ID) of the virtual staff who acts on behalf of the actual staff.

[0018] The natural language analysis processing unit 23 performs natural language analysis processing on the posted comments and messages, decomposes them into parts of speech, and extracts noun character strings. The feature quantity calculation processing unit 24 calculates a feature quantity that quantifies the content features for each posted comment based on the extracted nouns. The feature quantity is typically coordinates in an N-dimensional space. A plurality of types of classifications corresponding to the theme categories are respectively associated with the N axes that make up the N-dimensional space. A plurality of nouns related to each classification are assigned to each axis of the N-dimensional space together with coordinate values. For example, for each category such as apparel, music, health food, books, food, and home appliances, a plurality of types of classifications are predefined. In the case of the apparel category, as illustrated in FIG. 8, classifications of generic upper concepts such as time period, inventory, size, design, item, color tone, price range, age, and event are associated with each axis, and furthermore, for each classification, a number of nouns (character strings) representing specific lower concept matters included in each classification are set. The many nouns set on each of these axes are ordered according to semantic proximity, and numerical values (coordinate values) are assigned in advance. The noun character string extracted from the comment (text) is queried against the nouns on the N axes of the N-dimensional space, and if there is a corresponding noun character string, the coordinate value corresponding to the noun character string is given. Of course, when there is no corresponding noun character string, a zero value is given to the coordinate value of that coordinate axis. Comments with similar feature quantities can be said to be similar in content and have similar content features.

[0019] Note that as the feature quantity calculation processing, a learned model that has been pre-learned to output data of feature quantities that quantify the content features of comments and messages using the comments and messages as input data may be used.

[0020] The user message receiving unit 25 receives a message (utterance) from an actual user from the user terminal 5, either directly from the user terminal 5 or indirectly via the EC site server 4. In practice, the message from the actual user is received indirectly via at least one of the SNS server 3-1, the blog site server 3-2, the word-of-mouth site server 3-3, and the EC site server 4, which are platforms where the actual user interacts with the virtual staff. This message is subjected to natural language analysis by the natural language analysis processing unit 23, and its feature amount is calculated by the feature amount calculation processing unit 24.

[0021] The posted comment selection processing unit 26 selects one comment that is closest to the feature amount of the message from the actual user, or selects a predetermined number of top comments that are close to the feature amount of the message from the actual user. The selected comment has content features that are approximate to the message (utterance) from the actual user.

[0022] The utterance generation request unit 27 transmits the data of the message (utterance) from the actual user to the utterance generation device 2 together with a request for generating an utterance of a virtual user according to the message from the actual user. The utterance generation request unit 27 transmits the profile of the actual staff to the utterance generation device 2 in addition to the message. Furthermore, in addition to the message from the actual user and the profile of the actual staff, the utterance generation request unit 27 attaches at least one comment that the actual staff actually posted on SNS or the like and whose content features are approximate to the message from the actual user as reference information to the generation request and transmits it to the utterance generation device 2.

[0023] Here, in order for a normal interaction to be established between the actual user and the virtual staff, and for the interaction with the virtual staff to be recognized by the actual user without discomfort whether it is an interaction with the actual staff represented by the virtual staff, the following requirements are necessary.

[0024] 1) The utterance of the virtual staff is content-consistent so as to respond to the utterance (message) of the actual user.

[0025] 2) The content spoken by the virtual staff is close to the content that an actual staff would speak.

[0026] 3) The diction of the virtual staff reflects the diction of the actual staff.

[0027] In addition to the speech (messages) of actual users and the profiles of actual staff, these three requirements are realized by the speech generation device 2 referring to the post comments that actual staff actually post on SNS, etc. and are content-wise approximate to the messages of actual users, and the speech generation device 2 utilizing these reference information to generate the speech sentences of the virtual staff in response to the messages of actual users.

[0028] The speech sentence receiving unit 28 receives the data of the speech sentences generated by the speech generation device 2 from the speech generation device 2. The message transmitting unit 29 transmits the speech sentences received from the speech generation device 2 as they are or after appropriate modification as messages of the virtual staff to the user terminal 5 or the EC site server 4 for the actual user.

[0029] FIG. 4 shows the dialogue processing procedure centered on the information processing device 1 as the dialogue device according to the present embodiment together with the data flow. First, as preprocessing, the data of the accounts of actual staff assuming proxy by virtual staff regarding each of SNS, blog service, and review site is provided from the terminal of the actual staff to the information processing device 1 together with the virtual staff dialogue processing request. An identification number (ID) for identifying the virtual staff is issued in the information processing device 1 (S11).

[0030] A profile transmission request is sent from the profile acquisition unit 21 of the information processing apparatus 1 to the SNS server 3-1, the blog site server 3-2, the word-of-mouth site server 3-3, and the EC site server 4, together with the respective account information. Profile data of the actual staff registered by the actual staff when using their respective services is returned from the SNS server 3-1, the blog site server 3-2, and the word-of-mouth site server 3-3 to the information processing apparatus 1. As illustrated in FIG. 5, these profiles are edited into a single profile. The profile includes basic information such as name, gender, and age, and also includes characteristics such as the current occupation, characteristics of the corporate brand, and the personality and preferences of the actual staff. The edited profile is stored in the storage unit 14 with a virtual staff ID associated therewith (S12).

[0031] Next, a post comment transmission request is sent from the post comment collection unit 22 to each of the SNS server 3-1, the blog site server 3-2, the word-of-mouth site server 3-3, and the EC site server 4, together with the respective accounts of the actual staff. Data of the comments (posts, etc.) posted by the actual staff is received from each of the SNS server 3-1, the blog site server 3-2, the word-of-mouth site server 3-3, and the EC site server 4. These post comments are stored in the storage unit 14 with the ID of the virtual staff acting on behalf of the actual staff associated therewith (S13).

[0032] As illustrated in FIG. 6, each comment is subjected to natural language analysis processing by the natural language analysis processing unit 23, decomposed into parts of speech, and nouns are extracted (S14). Then, based on the extracted nouns, a feature quantity quantifying the content feature of the comment is calculated by the feature quantity calculation processing unit 24 (S15). Feature quantity calculation is repeated for all comments.

[0033] Coordinates in an N-dimensional space are determined as feature quantities. As illustrated in FIG. 8, a plurality of divisions are respectively associated with the N axes of the N-dimensional space. For example, in the case of apparel categories, a plurality of divisions such as time, inventory, size, design, item, color tone, price range, age, event, etc. are respectively associated with a plurality of axes. A plurality of specific nouns (character strings) included in each division are associated therewith. The plurality of specific nouns included in the same division are ordered according to the approximate nature of their semantic content, and numerical values (coordinate values) are respectively assigned thereto. The nouns extracted from the comment are queried against the specific nouns on each axis of the N-dimensional space, and if a corresponding character string exists, the axis number and coordinate value corresponding to that character string are given.

[0034] For example, for Comment No. 2, "I plan to go to work tomorrow wearing a blue jacket with a Glen check pattern pants.", the nouns "tomorrow", "Glen check", "pants", "blue", "jacket", "work", "plan" are extracted. For example, on the axis associated with the time division, a large number of specific nouns related to time such as yesterday, today, tomorrow, January, February, next month, the month after next, spring, autumn, etc. are associated, and coordinate values are respectively assigned thereto. The noun "tomorrow" extracted from the comment is given the coordinate value assigned to the specific noun "tomorrow" on the axis associated with the time division. Similarly, on the axis associated with the item division, specific nouns related to clothing such as pants, skirt, blouse, shirt, dress, suit, jacket, blazer, coat, etc. are associated, and coordinate values are respectively assigned thereto. The noun "pants" extracted from the comment is given the coordinate value of the corresponding specific noun on the item division axis. On the event division axis, nouns related to events such as Father's Day, Mother's Day, sports meet, birthday, date, etc. are associated, and coordinate values are respectively assigned thereto.

[0035] The calculated feature quantity is associated with the comment and stored in the storage unit 14 (S16).

[0036] New comments are collected at a predetermined cycle such as every day, feature quantities are calculated for the new comments, and they are accumulated. With the above, the pre - preparation process is completed.

[0037] At the start of the dialogue, for example, a request to open a chat room (chat bot) for one - on - one dialogue is sent from the user terminal 5 to the EC - site server 4 that operates the EC site. Of course, the dialogue form is not limited to the chat room. In the information processing apparatus 1, a virtual staff member who will have a dialogue with the user is selected, and a chat room between the user and the virtual staff member is opened (S17). For example, if a virtual staff member who has had a dialogue with the same real user in the past is selected, or if a real staff member has served a real user in a physical store, a virtual staff member who acts as an agent for that real staff member is selected. The method of selecting the virtual staff member is not limited to these methods.

[0038] For example, a message (utterance) of a real user input from the user terminal 5 shown in FIG. 7 is received by the user message receiving unit 25 from the user terminal 5 via the EC - site server 4. This message is subjected to natural language analysis by the natural language analysis processing unit 23 (S18), and its feature quantity is calculated by the feature quantity calculation processing unit 24 (S19). The natural language analysis processing and feature quantity calculation processing for the message are the same as those for the comment.

[0039] Next, one or a predetermined number of comments are selected from the comments of the actual staff by the posted comment selection processing unit 26 (S20). Specifically, one comment having the feature amount closest to the feature amount of the message from the actual user, or a predetermined number of comments having feature amounts close to the feature amount of the message from the actual user are selected. More specifically, since the feature amount is a coordinate in the N-dimensional space, the distance between the feature amount (coordinate) of the message from the actual user and the feature amount (coordinate) of the comment of the actual staff is calculated, and one comment with the shortest distance is selected, or a predetermined number of comments are selected in ascending order of the distance. Since the feature amount is a quantification of the content feature, the selected posted comment is content-wise approximated to the message of the actual user. For example, as illustrated in FIG. 9, when the message of the actual user is about asking for a recommendation of a jacket for traveling, comments regarding jackets and holidays are selected.

[0040] It is transmitted from the speech generation request unit 27 to the speech generation device 2 together with the speech generation request. The speech generation request is attached with the message of the actual user or the history of the dialogue between the actual user and the actual staff. Further, the speech generation request is attached with the profile of the actual staff that the virtual staff represents. Furthermore, the speech generation request is attached with, as reference information, a comment selected from the comments actually posted by the actual staff on SNS or the like and content-wise close to the message of the actual user.

[0041] In the speech generation request unit 27, a speech sentence of a virtual staff member that responds to a message of an actual user is generated (S21) by referring to the profile of an actual staff member and a comment that is content - close to the message of the actual user selected from the comments actually posted by the actual staff member on SNS or the like. When generating the speech sentence of the virtual staff member, since a comment that is content - close to the message of the actual user is referred to, the speech sentence of the virtual staff member is generated with content close to the content that the actual staff member would respond with. For example, when an actual user asks for a jacket recommendation, an answer recommending "a blue tweed jacket" is generated from the comments posted by the actual staff member in the past. Also, the diction of the virtual staff member applies not only the profile of the actual staff member but also the diction used in the comments posted by the actual staff member in the past.

[0042] As described above, in generating the speech of the virtual staff member that responds to the message of the actual user, in addition to the profile of the actual staff member, a comment that is content - close to the message of the actual user selected from the comments actually posted by the actual staff member on SNS or the like can be referred to, so the following three requirements can be satisfied with high precision.

[0043] 1) The speech of the virtual staff member is content - consistent with the speech (message) of the actual user.

[0044] 2) The content spoken by the virtual staff member is the same as or close to the content that the actual staff member would speak.

[0045] 3) The diction of the virtual staff member reflects the diction of the actual staff member.

[0046] Although several embodiments of the present invention have been described, these embodiments are presented by way of example and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and their modifications are included in the scope and gist of the invention, as well as in the invention described in the claims and its equivalent scope.

Explanation of Signs

[0047] 1... Information processing device (dialogue device), 2... Utterance generation device (generative AI), 3-1... SNS server, 3-2... Blog site server, 3-3... Word-of-mouth site server, 4... EC site server, 5... User terminal.

Claims

1. An information processing apparatus connected via a communication line to a user terminal related to an actual other user, an SNS server, and a speech generation device (generation AI), and generating a response sentence of a virtual user as an agent of the actual user in response to the speech of the other user, comprising: means for receiving data of the speech of the other user from the user terminal; means for receiving a plurality of posts by the actual user from the SNS server; means for selecting a specific post that is closest to the content of the speech of the other user from the plurality of posts based on a plurality of nouns included in each of the plurality of posts and a plurality of nouns included in the speech of the other user; means for transmitting data of the selected specific post and data of the speech of the other user to the speech generation device together with a response sentence generation instruction in order to generate a response sentence of the virtual user to the speech of the other user with reference to the selected specific post; means for receiving data of the response sentence of the virtual user generated by the speech generation device in response to the response sentence generation instruction from the speech generation device; means for transmitting data of the response sentence of the virtual user to the user terminal. An information processing apparatus.

2. An information processing apparatus connected via a communication line to a user terminal related to an actual other user, an SNS server, and a speech generation device (generation AI), and generating a response sentence of a virtual user as an agent of the actual user in response to the speech of the other user, means for receiving data of the speech of the other user from the user terminal; means for receiving a plurality of posts by the actual user from the SNS server; means for selecting a specific post that is closest to the content of the speech of the other user from the plurality of posts based on a plurality of nouns included in each of the plurality of posts and a plurality of nouns included in the speech of the other user; means for transmitting data of the selected specific post and data of the speech of the other user to the speech generation device together with a response sentence generation instruction in order to generate a response sentence of the virtual user to the speech of the other user with reference to the selected specific post; means for receiving data of the response sentence of the virtual user generated by the speech generation device in response to the response sentence generation instruction from the speech generation device; A program that functions as means for transmitting data of the response sentence of the virtual user to the user terminal.

Images