Information processing device and program

Abstract

To realize interaction with the other person without any discomfort as if a virtual user as a reality user's proxy is the reality user.SOLUTION: An information processing device 1 comprises a reception unit 25 which receives data of a statement of the other user from a user terminal 5, a request unit 27 which transmits generation request of a statement sentence of a virtual user according to the statement of the other user to a statement sentence generation device, a reception unit 28 which receives data of the statement sentence, and a transmission unit 29 which transmits the data of the statement sentence of the virtual user to the user terminal. The information processing device transmits the data of at least one comment which the reality user has contributed to an SNS server 3-1 to the statement sentence generation device as reference information, by adding the data to the generation request.SELECTED DRAWING: Figure 3

Description

[Technical Field]

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

[0002] E-commerce sites (online sales) for apparel and other products are becoming commonplace, and it is expected that in the future there will be more opportunities to open virtual stores in shopping malls in virtual spaces (metaverses) on the Internet. In this environment, just like in real stores, it is important from the perspective of sales promotion that e-commerce sites have staff who can recommend products through dialogue with users, uncover user needs and help realize the products they want, and provide one-on-one customer service to respond to various inquiries.

[0003] Generally, the number of users who visit an e-commerce site is far greater than the number of customers who visit a physical store. Therefore, it is not realistic for real staff to personally serve every user who visits an e-commerce site. Therefore, it is assumed that virtual staff (also called digital staff) will be created on a computer, and that the digital staff will serve users one-on-one in place of real staff.

[0004] There are various characters set for digital staff, but it is not easy to create a character that has the ability to serve customers. Therefore, characters that resemble real staff are sometimes set.

[0005] However, no matter how closely the virtual staff characters resemble those of real staff members, they often differ from real staff members in many ways, such as the content of their statements and the way they speak. Summary of the Invention [Problem to be solved by the invention]

[0006] The goal is to enable a virtual user acting as a substitute for a real user to converse with others as if they were a real user, without any sense of incongruity. [Means for solving the problem]

[0007] The information processing device according to this embodiment includes: An information processing device that is connected to a user terminal, at least one server selected from an SNS server, a blog site server, a word-of-mouth site server, and an EC site server, and a statement generation device (generation AI) via a communication line, and that allows a virtual user acting as a proxy for a real user to interact with other real users, a first receiving means for receiving data of comments from the other users directly from the user terminal or indirectly via at least one server selected from the SNS server, the blog site server, the review site server, and the EC site server; a first sending means for sending to the message generation device a request for generating a message from the virtual user in response to the message from the other user, the request including data of the message from the other user; a second receiving means for receiving data of the message from the message generation device; a second transmission means for transmitting the received data of the virtual user's message as a message of the virtual user to the user terminal or to at least one server selected from the SNS server, the blog site server, the review site server, and the EC site server; means for extracting noun character strings by performing natural language analysis processing on each of comments posted by other users and on at least one of the SNS server, the blog site server, the review site server, and the EC site server; a feature calculation means for calculating a feature amount that quantifies content features of each of the statements and comments of the other users based on the extracted nouns; and means for selecting, from the plurality of comments, at least one specific comment having content characteristics closest to the comment of the other user based on the feature amount; The first sending means attaches data of the selected specific comment to the generation request as reference information in addition to data of the remarks of the other user. The aforementioned The message is sent to the message generation device. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a configuration diagram of an entire system including an information processing device according to this embodiment. [Figure 2] FIG. 2 is a diagram showing the physical configuration of the information processing apparatus of FIG. [Figure 3] FIG. 3 is a diagram illustrating a functional configuration of the information processing apparatus of FIG. [Figure 4] FIG. 4 is a diagram showing the data flow of the entire system of FIG. 1 and the processing of the information processing device. [Figure 5] FIG. 5 is a diagram showing an example of the profile of FIG. [Figure 6] FIG. 6 is a diagram showing an example of the posted comments and their feature amounts in FIG. [Figure 7] FIG. 7 is a diagram showing an example of the user message and its feature amount in FIG. [Figure 8] FIG. 8 is a diagram showing an example of the distance between a user message and a posted comment in an N-dimensional space showing the feature amounts of FIGS. [Figure 9] FIG. 9 is a diagram schematically showing a flow of processing by the information processing device of FIG. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In this embodiment, a generation AI as a statement generation device generates a statement in response to a statement made by another user by referring to comments (referred to as posts, articles, word-of-mouth reviews, evaluations, messages, etc.) actually created and posted by real users on social networking services (hereinafter referred to as "SNS") as community-based services that promote and support connections between people, blog sites where users post articles about everyday matters and thoughts and display them in chronological order, review sites where users write and read reviews of products and services, and e-commerce sites that sell products and services online. This realizes that the content of the statement is consistent with the content of the other user's statement, and that the content of the statement made by the virtual user is natural and uses language that the real user would use, as if it were made by the real user that it represents.

[0010] For example, typical examples of social networking sites include Instagram (registered trademark), Facebook (registered trademark), and Twitter (currently X (registered trademark)). Typical examples of review sites include Tabelog (registered trademark) and Kakaku.com (registered trademark). There are also many blog sites, such as FC2 (registered trademark) blogs.

[0011] The following description will be given taking as an example a situation where clothes and the like are sold via an EC (electronic commerce) site that provides services for selling products and services on websites on the Internet via a network such as the Internet. In this situation, a virtual user (hereinafter referred to as a virtual staff member) acting as a proxy or representative of a real user (hereinafter referred to as a real staff member) interacts in a chat room with a real user (another user) who visits the EC site, and attempts to sell clothes and the like by serving the other user.

[0012] As shown in Figure 1, an information processing device 1 according to this embodiment is connected via a communication network, typically an Internet network 6, to a statement generation device 2 that functions as a generation AI, an SNS server 3-1 that provides an SNS, a blog site server 3-2 that provides blog services, 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 a real user.

[0013] As shown in FIG. 2, the information processing device 1 as an interactive device has a processor 11 connected to a RAM 12, a ROM 13, a storage unit 14, an input device 15, a display 16, and a communication unit 17 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 programs loaded from the storage unit 14 and ROM 13 to the RAM 12 to perform interactive processing that realizes a dialogue with a real user. The RAM 12 functions as the main memory, work area, etc. of the processor 11. The ROM 13 or the storage unit 14 stores a BIOS (Basic Input Output System), an operating system program (OS), an interactive processing program according to this embodiment, other programs for realizing various functions, various data required for these processes, etc., which are executed by the processor 11.

[0014] The input device 15 comprises a keyboard (KB) and a pointing device such as a mouse or touch panel. The display 19 is typically realized by an LCD (Liquid Crystal Display). In addition to the dialogue processing program, the memory unit 14 stores data related to comments required for dialogue processing, their respective features, profiles of real staff members, and messages exchanged between real users and virtual staff members and their order (dialogue history).

[0015] As shown in Figure 3, by executing the dialogue 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 calculation processing unit 24, a user message receiving unit 25, a posted comment selection processing unit 26, a statement generation request unit 27, a statement receiving unit 28, and a message sending unit 29.

[0016] The profile acquisition unit 21 sends a profile transmission request along with each account of the real staff member to each of the SNS server 3-1, blog site server 3-2, review site server 3-3, and EC site server 4, and receives profile data from each of the SNS server 3-1, blog site server 3-2, review site server 3-3, and EC site server 4. These profiles are compiled into a single profile, and stored in the storage unit 14 in association with the identification number of the virtual staff member who represents the real staff member.

[0017] The posted comment collection unit 22 sends requests to each of the SNS server 3-1, blog site server 3-2, review site server 3-3, and EC site server 4 to send comments (referred to as posts, articles, reviews, evaluations, messages, and other text) posted by the real staff along with each account of the real staff member, and receives data on comments actually posted by the real staff member from each of the SNS server 3-1, blog site server 3-2, and review 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 member who represents the real staff member.

[0018] The natural language analysis processor 23 performs natural language analysis on posted comments and messages, breaking them down into parts of speech and extracting noun strings. The feature calculation processor 24 calculates feature values ​​that quantify the content characteristics of each posted comment based on the extracted nouns. The feature values ​​are typically coordinates in an N-dimensional space. N axes constituting the N-dimensional space are associated with multiple types of divisions corresponding to theme categories. Each axis in the N-dimensional space is assigned a number of nouns related to each division along with their coordinate values. For example, multiple divisions are predefined for each category, such as apparel, music, health foods, books, food, and home appliances. For the apparel category, as shown in FIG. 8, each axis is assigned a generic, higher-level conceptual division such as season, inventory, size, design, item, color, price range, era, and event. Each division is further assigned a number of nouns (strings) representing specific, lower-level conceptual matters encompassed by that division. The nouns on each axis are ordered according to their semantic proximity, and each is assigned a numerical value (coordinate value) in advance. The noun strings extracted from comments (text) are compared with the nouns on the N-axis of the N-dimensional space, and if a corresponding noun string exists, the coordinate value corresponding to that noun string is assigned. Of course, if a corresponding noun string does not exist, the coordinate value on that coordinate axis is assigned a value of zero. Comments with similar features are said to be similar in content, or have similar content features.

[0019] In addition, the feature calculation process may be performed using a pre-trained model that takes comments or messages as input data and outputs feature data that quantifies the content features of the comments or messages.

[0020] The user message receiving unit 25 receives messages (comments) of real users from the user terminal 5 directly from the user terminal 5 or indirectly via the EC site server 4. In practice, messages of real users are received indirectly via at least one of the SNS server 3-1, blog site server 3-2, review site server 3-3, and EC site server 4, which serve as platforms where real users and virtual staff converse. The messages are subjected to natural language analysis by the natural language analysis processing unit 23, and their features are calculated by the feature calculation processing unit 24.

[0021] The posted comment selection processing unit 26 selects one comment that is closest to the feature amount of the real user's message, or selects a predetermined number of comments that are closest to the feature amount of the real user's message. The selected comments have content features that are similar to the real user's message (statement).

[0022] The message generation request unit 27 transmits data of the real user's message (message) to the message generation device 2 together with a request to generate a message from a virtual user in response to the real user's message. In addition to the message, the message generation request unit 27 transmits the profile of the real staff member to the message generation device 2. Furthermore, in addition to the real user's message and the real staff member's profile, the message generation request unit 27 attaches at least one comment that the real staff member actually posted on an SNS or the like and that has similar content characteristics to the real user's message as reference information to the generation request and transmits this to the message generation device 2.

[0023] Here, the following requirements are required for a normal dialogue to be established between the real user and the virtual staff member, and for the real user to recognize the dialogue with the virtual staff member without feeling uncomfortable, even if the dialogue is with a real staff member represented by the virtual staff member.

[0024] 1) The statements of the virtual staff are consistent in content so as to respond to the statements (messages) of the real users.

[0025] 2) The statements made by the virtual staff are similar to what a real staff member would say.

[0026] 3) The language used by the virtual staff mirrors that used by the real staff.

[0027] These three requirements are realized by sending comments that real staff have actually posted on social media etc. and that are similar in content to the real user's messages, in addition to the real user's comments (messages) and the real staff's profiles, as reference information to the comment generation device 2, and the comment generation device 2 then utilizes this reference information to generate comments from virtual staff members that respond to the real user's messages.

[0028] The message receiving unit 28 receives data of the message generated by the message generation device 2 from the message generation device 2. The message sending unit 29 sends the message received from the message generation device 2 as is or after appropriate modification to the user terminal 5 or the EC site server 4 as a message from the virtual staff member to the real user.

[0029] 4 shows the dialogue processing procedure centered on the information processing device 1 as the dialogue device according to this embodiment, along with the data flow. First, as a preparatory process, account data for the real staff member who is expected to be represented by the virtual staff member for each of the SNS, blog service, and review site is provided from the real staff member's terminal to the information processing device 1, along with a virtual staff member dialogue processing request. The information processing device 1 issues an identification number (ID) that identifies the virtual staff member (S11).

[0030] The profile acquisition unit 21 of the information processing device 1 sends a profile transmission request along with each account information to the SNS server 3-1, blog site server 3-2, review site server 3-3, and EC site server 4. The SNS server 3-1, blog site server 3-2, and review site server 3-3 return profile data of the actual staff registered by the actual staff when using each service to the information processing device 1. As illustrated in FIG. 5, these profiles are compiled into a single profile. In addition to basic information such as name, gender, and age, the profile includes, for example, the current occupation, characteristics of the corporate brand, and characteristics such as the actual staff's personality and preferences. The compiled profile is associated with a virtual staff member ID and stored in the storage unit 14 (S12).

[0031] Next, the posted comment collection unit 22 sends a request to send posted comments along with each account of the real staff member to each of the SNS server 3-1, blog site server 3-2, review site server 3-3, and EC site server 4, and data of comments (posted text, etc.) posted by the real staff member is received from each of the SNS server 3-1, blog site server 3-2, review site server 3-3, and EC site server 4. These posted comments are associated with the ID of the virtual staff member who represents the real staff member and stored in the storage unit 14 (S13).

[0032] 6, each comment is subjected to natural language analysis processing by the natural language analysis processing unit 23, broken down into parts of speech, and nouns are extracted (S14). Then, based on the extracted nouns, feature amounts that quantify the content features of the comment are calculated by the feature amount calculation processing unit 24 (S15). The feature amount calculation is repeated for all comments.

[0033] Coordinates in an N-dimensional space are determined as feature quantities. As shown in the example in Figure 8, multiple categories are associated with the N axes of the N-dimensional space. For example, in the apparel category, multiple categories such as season, inventory, size, design, item, color tone, price range, era, and event are associated with multiple axes. Each category is associated with multiple specific nouns (character strings) contained within it. Multiple specific nouns contained in the same category are ranked according to the similarity of their content meanings, and each is assigned a numerical value (coordinate value). Nouns extracted from comments are compared with specific nouns on each axis of the N-dimensional space, and if a corresponding character string is found, the axis number and coordinate value corresponding to that character string are assigned.

[0034] For example, for comment No. 2, "I plan to wear glen plaid pants and a blue jacket to work tomorrow," the following nouns are extracted: "tomorrow," "glen plaid," "pants," "blue," "jacket," "work," and "plan." For example, on the axis associated with time periods, specific nouns related to many periods, such as yesterday, today, tomorrow, January, February, next month, the month after next, spring, and autumn, are associated with each of these nouns, and coordinate values ​​are assigned to each of them. 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 period. Similarly, on the axis associated with item classes, specific nouns related to clothing, such as pants, skirts, blouses, shirts, dresses, suits, jackets, blazers, and coats, are associated with each of these nouns, and coordinate values ​​are assigned to each of them. The noun "pants" extracted from the comment is given the coordinate value of the corresponding specific noun on the item class axis. On the event class axis, nouns related to events, such as Father's Day, Mother's Day, sports day, birthdays, and dates, are associated with each of these nouns, and coordinate values ​​are assigned to each of them.

[0035] The calculated feature amount is stored in the storage unit 14 in association with the comment (S16).

[0036] New comments are collected at a predetermined interval, such as once a day, and feature amounts for the new comments are calculated and stored. This completes the advance preparation process.

[0037] When starting a conversation, for example, a request to open a chat room (chatbot) for one-on-one conversation is sent from the user terminal 5 to the EC site server 4 that operates the EC site. Of course, the conversation format is not limited to a chat room. In the information processing device 1, a virtual staff member who will converse with the user is selected, and a chat room between the user and the virtual staff member is opened (S17). For example, a virtual staff member who has previously conversed with the same real user is selected, or if a real staff member has served the real user in a real store, a virtual staff member who will represent the real staff member is selected. The method of selecting a virtual staff member is not limited to these methods.

[0038] For example, a message (statement) of an actual 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 features are calculated by the feature calculation processing unit 24 (S19). The natural language analysis processing and feature calculation processing for the message are the same as those for the comment.

[0039] Next, the posted comment selection processor 26 selects one or a predetermined number of comments from the real staff members (S20). Specifically, one comment having feature quantities closest to those of the message from the real user, or a predetermined number of comments having feature quantities close to those of the message from the real user, are selected. More specifically, since the feature quantities are coordinates in N-dimensional space, the distance between the feature quantities (coordinates) of the message from the real user and the feature quantities (coordinates) of the comment from the real staff member is calculated, and the comment with the shortest distance is selected, or a predetermined number of comments are selected in descending order of distance. Since the feature quantities quantify content characteristics, the selected posted comment is similar in content to the real user's message. For example, as illustrated in FIG. 9, if the real user's message is asking for recommendations on a jacket to wear on a trip, comments related to jackets and holidays are selected.

[0040] The message is sent from the message generation request unit 27 to the message generation device 2 together with a message generation request. The message generation request is accompanied by a message from the real user or a history of conversations between the real user and real staff. The message generation request is also accompanied by a profile of the real staff member represented by the virtual staff member. Furthermore, the message generation request is accompanied by reference information of comments that are similar in content to the real user's message and that are selected from comments that the real staff member actually posted on SNS or the like.

[0041] The message generation request unit 27 generates a message from a virtual staff member responding to the real user's message by referencing the real staff member's profile and comments similar in content to the real user's message, selected from comments actually posted by the real staff member on social media or the like (S21). When generating the virtual staff member's message, comments similar in content to the real user's message are referenced, so the virtual staff member's message is generated with content similar to that which a real staff member would respond to. For example, when a real user asks for a jacket recommendation, a response recommending a "blue tweed jacket" is generated from comments previously posted by the real staff member. In addition, the language used by the virtual staff member is based not only on the real staff member's profile but also on the language used in comments previously posted by the real staff member.

[0042] As described above, when generating comments from virtual staff members in response to messages from real users, in addition to the profiles of the real staff members, comments that are similar in content to the real user's message and selected from comments that the real staff members have actually posted on social media, etc., can be referenced, thereby satisfying the following three requirements with a high degree of accuracy.

[0043] 1) The statements made by the virtual staff are consistent in content with the statements (messages) made by the real users.

[0044] 2) The statements made by the virtual staff are the same as or close to what a real staff member would say.

[0045] 3) The language of the virtual staff mirrors that of the real staff.

[0046] Although several embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, as well as within the scope of the invention described in the claims and their equivalents. [Explanation of symbols]

[0047] 1...information processing device (interactive device), 2...statement 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 device that is connected to a user terminal, at least one server selected from an SNS server, a blog site server, a word-of-mouth site server, and an EC site server, and a statement generation device (generation AI) via a communication line, and that allows a virtual user acting as a representative of a real user to interact with other real users, a first receiving means for receiving data of comments from the other users directly from the user terminal or indirectly via at least one server selected from the SNS server, the blog site server, the word-of-mouth site server, and the EC site server; a first sending means for sending to the message generation device a request for generating a message from the virtual user in response to the message from the other user, the request including data of the message from the other user; a second receiving means for receiving data of the message from the message generation device; a second transmission means for transmitting the received data of the message of the virtual user to the user terminal or to at least one server selected from the SNS server, the blog site server, the word-of-mouth site server, and the EC site server; means for extracting character strings of nouns by performing natural language analysis processing on each of the statements of the other users and a plurality of comments posted to at least one of the SNS server, the blog site server, the word-of-mouth site server, and the EC site server; a feature calculation means for calculating a feature amount that quantifies content features of each of the statements and comments of the other users based on the extracted nouns; and means for selecting, from the plurality of comments, at least one specific comment having content characteristics closest to the comment of the other user based on the feature amount; The first sending means sends data of the selected specific comment as reference information to the generation request in addition to data of the other user's comments to the message generation device.

2. 2. The information processing device according to claim 1, wherein the feature calculation means associates the extracted nouns with an N-dimensional space in which N axes correspond to multiple types of categories represented by the nouns, and multiple nouns related to each category are assigned to each axis along with coordinate values, and assigns coordinates on the N-dimensional space as the feature.

3. The information processing device described in claim 1, wherein the first transmission means transmits to the statement generation device, together with data of the other user's comments and data of the specific comment, a profile registered by the actual user on at least one of the SNS server, the blog site server, the word-of-mouth site server, and the EC site server as reference information.

4. an information processing device that is connected to a user terminal via a communication network, at least one server selected from an SNS server, a blog site server, a word-of-mouth site server, and an EC site server, and a statement generation device (generation AI) via a communication line, and that allows a virtual user acting as a proxy for a real user to interact with other real users; a first receiving means for receiving data of comments made by the other users directly from the user terminal or indirectly via at least one server selected from the SNS server, the blog site server, the word-of-mouth site server, and the EC site server; a first sending means for sending to the message generation device a request for generating a message from the virtual user in response to the message from the other user, the request including data of the message from the other user; a second receiving means for receiving data of the message from the message generation device; a program that functions as a second transmission means that transmits the received data of the message of the virtual user to the user terminal or to at least one server selected from the SNS server, the blog site server, the word-of-mouth site server, and the EC site server, means for extracting character strings of nouns by performing natural language analysis processing on each of the statements of the other users and a plurality of comments posted to at least one of the SNS server, the blog site server, the word-of-mouth site server, and the EC site server; a feature calculation means for calculating a feature amount that quantifies content features of each of the statements and comments of the other users based on the extracted nouns; and a means for selecting, from the plurality of comments, at least one specific comment having content characteristics closest to the comment of the other user based on the feature amount; The first sending means is a program that sends data of the selected specific comment as reference information to the generation request in addition to data of the other user's comments to the comment generation device.

Images