Information processing apparatus and program
The information processing device estimates intimacy scores from user politeness in e-commerce interactions, adjusting virtual staff responses to enhance empathy and trust, addressing mechanical conversations and improving customer engagement.
Patent Information
- Application Number
- JP2025142603
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-08-28
- Publication Date
- 2025-10-30
AI Technical Summary
Existing systems fail to effectively estimate user intimacy in virtual customer service interactions, leading to mechanical and unempathetic conversations in e-commerce platforms, which hinders the development of genuine customer relationships.
An information processing device that analyzes user utterances to estimate intimacy scores based on politeness levels, adjusting the conversational politeness of virtual staff to match user changes, thereby enhancing empathy and trust.
Enhances user intimacy and trust by dynamically adjusting virtual staff responses to align with user politeness levels, improving customer engagement and sales potential.
Smart Images
Figure 2025164897000001_ABST
Abstract
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 the virtual space (metaverse) on the Internet. In this environment, just like in real stores, it is important from the perspective of sales promotion for e-commerce sites to have staff recommend products through conversations with customers, uncover customer needs and help realize the products users are looking for, 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 provide individual customer service to all users who visit an e-commerce site. Therefore, it is assumed that virtual staff (called virtual users or digital staff) will be created on a computer, and that the digital staff will provide one-on-one customer service to customers (called real users) in place of real staff.
[0004] It is expected that generative AI will be used to create statements that digital staff will use to advance conversations with customers via chat, etc. The generative AI will receive a generation request along with the conversation history between the digital staff and the customer. The generative AI will analyze the conversation history and create the next statement that the digital staff should make. Since it is used on e-commerce sites, the ultimate goal is sales, which requires high conversational skills and customer service abilities like those of excellent real staff. Excellent real staff, whether consciously or unconsciously, are skilled at advancing conversations in a way that builds intimate relationships while gaining empathy and trust from customers.
[0005] However, generating utterances based solely on the input conversation history between the digital staff and the customer was not enough to move away from a mechanical conversation. Summary of the Invention [Problem to be solved by the invention]
[0006] The goal is to estimate the intimacy felt by the user. [Means for solving the problem]
[0007] The information processing device of this embodiment is an information processing device having a memory for storing a program, a processor for executing the program, and a communication interface for communicating with a user terminal via an electrical public communication network, and by executing the program, the processor functions as a means for receiving data of a user's utterances from the user terminal, a means for identifying the degree of politeness of the language used in the user's utterances, and an intimacy estimation means for estimating an intimacy score representing the degree of intimacy between the user and the processor based on the degree of politeness of the language used in the user's utterances. The politeness level is divided into several stages, The intimacy degree estimation means When the politeness of the language of the user's utterance is at the same level as the politeness of the language of the user's immediately preceding utterance, the current value of the intimacy score is maintained; when the politeness of the user's utterance has decreased by one or two or more levels compared to the politeness of the user's immediately preceding utterance, adding a predetermined first value to the current value of the intimacy score; When the politeness of the language used in the user's utterance becomes one or two or more levels higher than the politeness of the language used in the user's immediately previous utterance, a predetermined second value is subtracted from the current value of the intimacy score. [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 processor in FIG. [Figure 4] FIG. 4 is a flowchart showing the flow of conversation processing of the information processing device of FIG. [Figure 5] FIG. 5 is a flowchart showing the flow of the empathy level estimation process of FIG. [Figure 6] FIG. 6 is a flowchart showing the flow of the reliability estimation process of FIG. [Figure 7] FIG. 7 is a flowchart showing the flow of the intimacy degree estimation process of FIG. [Figure 8] FIG. 8 is a flowchart showing the flow of wording conversion processing by the information processing device of FIG. [Figure 9] FIG. 9 is a diagram showing an example of persona information of a digital staff member. [Figure 10] FIG. 10 is a diagram showing an example of changes in empathy score, reliability score, intimacy score, and purchase likelihood score as the conversation progresses, and changes in wording according to this embodiment. [Figure 11] FIG. 11 is a diagram showing an example of changes in the empathy score, the trust score, the intimacy score, and the purchase likelihood score, as well as changes in wording, following FIG. DETAILED DESCRIPTION OF THE INVENTION
[0009] An information processing device according to an embodiment of the present invention will be described below with reference to the drawings. The information processing device according to this embodiment is applied to a situation in which a virtual user (a virtual user) created on a computer converses with a real user. Here, an example will be described in which a customer visiting an e-commerce site converses with a virtual staff member (a digital staff member) created on a computer in a chat room provided on the e-commerce site. In this example, the customer corresponds to the real user, and the digital staff member corresponds to the virtual user. Of course, the present invention is not limited to a situation in which the real user corresponds to the customer and the virtual user corresponds to the digital staff member.
[0010] As shown in FIG. 1 , an information processing device 1 according to this embodiment is connected to a statement generation device 2 functioning as a generation AI, an EC server 3, and a user terminal 4 via an electrical public communication network 5 such as the Internet. The user terminal 4 connects to the EC server 3, and a customer (real user) visits the EC site operated by the EC server 3. The EC site provides a chat room, etc., where the customer converses with a digital staff member (virtual user) and purchases a product. The information processing device 1 receives customer statement data input from the user terminal 4 directly from the user terminal 4 or indirectly via the EC server 3, creates a statement by the digital staff member in response to the customer statement, and transmits the data to the user terminal 4 directly or indirectly via the EC server 3. By repeating this process, a conversation between the customer and the digital staff member progresses in the chat room. The information processing device 1 transmits a statement generation request to the statement generation device 2 along with the ordered customer statements and digital staff member statements, i.e., the conversation history between the customer and the digital staff member.
[0011] In this embodiment, a determination is made based on the customer's comments to determine whether the customer has a positive or negative opinion of the digital staff member's comments. Based on the determination result, a sympathy score is calculated to estimate the degree of empathy the customer has with the digital staff member's comments. Based on the determination result, a trust score is calculated to estimate the degree of trust the customer has in the digital staff member's comments. The determination result of whether the customer's comments are positive or negative is applied to either the sympathy score or the trust score, depending on whether the digital staff member's comments are in line with the topic of the conversation. For example, if the e-commerce site is an apparel shop, apparel would be the topic of the conversation.
[0012] If the customer is judged to have a positive reaction to the digital staff's comments, the trust score or empathy score is increased, and if the customer is judged to have a negative reaction, the trust score or empathy score is decreased. Of course, an increase in the trust score, empathy score, and further the intimacy score (described later) means that the customer's trust, empathy, and intimacy with the digital staff increases.
[0013] By repeating this process, it is possible to determine how the empathy score and the trust score change as the conversation progresses, and further to identify what statements made by the digital staff member caused these changes.
[0014] Furthermore, in real-life human relationships, as intimacy increases, language tends to become less polite, gradually shifting from honorific language to friendly language. It is believed that by reducing the level of politeness in language and shifting from honorific language to friendly language, intimacy can be deepened. In other words, if the customer uses friendly, friendly language but the digital staff continues to use honorific language, the customer may lose a sense of intimacy.
[0015] Therefore, in this embodiment, the politeness level of the digital staff member's utterances generated by the statement generation device 2 is changed according to the situation so as to follow changes in the politeness level of the customer's utterance. The politeness level of the customer's utterances is identified, and the politeness level of the digital staff member's utterances is determined based on the identified change in the politeness level of the customer's utterances. When the politeness level of the customer's utterances decreases, the politeness level of the digital staff member's utterances is correspondingly decreased by one level from the current politeness level. When the politeness level of the customer's utterances increases, the politeness level of the digital staff member's utterances is also increased by one level from the current politeness level. In this way, in this embodiment, by changing the politeness level of the digital staff member's utterances to match the politeness level of the customer's utterances, it is possible to increase the customer's sense of intimacy while preventing a decrease in the sense of intimacy.
[0016] In this embodiment, the customer's intimacy score with the digital staff member is calculated based on changes in the politeness of the language used in the customer's speech. When the politeness of the language used in the customer's speech decreases, the customer's intimacy score with the digital staff member is increased. When the politeness of the language used in the customer's speech increases, the customer's intimacy score with the digital staff member is decreased.
[0017] When a request for generating a message is sent to the message generation device 2, the history of the conversation between the customer and the digital staff member is sent as well as the changes in the empathy score, the trust score, and the intimacy score, thereby enabling the digital staff member's message to be generated in accordance with the flow of the conversation and in a way that increases the empathy score and the trust score rather than decreasing them.
[0018] 2, the information processing device 1 as a conversation device has a processor 11 connected to it via a system bus 10 with a RAM 12, a ROM 13, a storage unit 14, an input device 15, a display 16, and a communication interface 17. The processor 11 is composed of, for example, a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit). The processor 11 executes a conversation program loaded from the storage unit 14 and ROM 13 into the RAM 12, and processes the conversation between the customer and the digital staff.
[0019] The RAM 12 functions as a main memory, work area, etc. for the processor 11. The ROM 13 or storage unit 14 stores a BIOS (Basic Input Output System) executed by the processor 11, an operating system program (OS), a conversation processing program according to this embodiment, programs for realizing various other functions, various data required for these processes, etc.
[0020] 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 conversation processing program, the memory unit 14 stores data related to the conversation history between the customer and the digital staff, customer persona information and persona extension information, exemplified in Figure 9, etc.
[0021] As shown in Figure 3, by executing the conversation processing program, processor 11 functions as a control unit 21, a natural language analysis processing unit 22, an empathy estimation processing unit 23, a reliability estimation processing unit 24, an intimacy estimation processing unit 25, a purchase possibility estimation processing unit 26, a persona information update unit 27, a persona extension information update unit 28, a wording conversion processing unit 29, a statement generation request processing unit 30, a receiving processing unit 31, and a transmitting processing unit 32.
[0022] The data of the comment input by the customer from the user terminal 4 is received by the receiving processing unit 31 via the EC server 3. Note that the data of the comment input by the customer from the user terminal 4 may be received directly from the user terminal 4 to the receiving processing unit 31 without going through the EC server 3.
[0023] The natural language analysis processing unit 22 performs natural language analysis on the data of customer utterances received via the reception processing unit 31, breaking it down into parts of speech, extracting character strings of nouns in particular, and performing syntactic analysis. The natural language analysis processing unit 22 also performs natural language analysis on the utterances of digital staff members transmitted to the EC server 3 via the transmission processing unit 32, breaking it down into parts of speech, extracting character strings of nouns, and performing syntactic analysis. The parts of speech broken down by the natural language analysis processing unit 22, the extracted nouns, and the syntactic analysis results are used in the processes of the empathy estimation processing unit 23, the reliability estimation processing unit 24, the persona information update unit 27, and the persona extension information update unit 28.
[0024] The empathy estimation processing unit 23 calculates an empathy score when the content of the digital staff member's statement is not in line with the topic of the conversation, and does not calculate an empathy score when the content of the digital staff member's statement is in line with the topic of the conversation. For example, if the e-commerce site is an apparel shop, the topic of the conversation is the apparel field. Specifically, if the nouns included in the digital staff member's statement are apparel-related, the content of the digital staff member's statement is determined to be in line with the topic of the conversation. If the nouns included in the digital staff member's statement are not apparel-related and unrelated to apparel, the content of the digital staff member's statement is determined to be in line with the topic of the conversation. This determination process may involve creating an apparel-related terminology dictionary in advance and storing it in the storage unit 14, comparing the nouns included in the digital staff member's statement with the dictionary to determine whether they are listed in the apparel-related terminology dictionary, or it may involve using a trained model that uses training data to estimate the suitability of nouns and conversation topics.
[0025] When a customer responds positively to a comment made by the digital staff member, a predetermined value is added to the current value of the empathy score to increase the empathy score. When a customer responds negatively to a comment made by the digital staff member, a predetermined value is subtracted from the current value of the empathy score to decrease the empathy score. Typically, the added value and the subtracted value are the same, but the absolute value of the added value may be higher or lower than the absolute value of the subtracted value. The determination process for identifying whether a customer's comment is positive or negative in response to a comment made by the digital staff member may involve creating a dictionary containing multiple positive expressions and multiple negative expressions in advance and storing it in the memory unit 14, and determining whether the customer's comment contains any positive or negative expression. Alternatively, a trained model trained by machine learning may be used to estimate multiple expressions and the likelihood of a comment being positive or negative as training data.
[0026] The reliability estimation processing unit 24 calculates a reliability score when the content of the digital staff member's statement is in line with the topic of the conversation, and does not calculate a reliability score when the content of the digital staff member's statement is not in line with the topic of the conversation. When a customer makes a positive comment in response to a comment made by the digital staff member, a predetermined value is added to the current value of the reliability score to increase the reliability score. When a customer sends a negative comment in response to a comment made by the digital staff member, a predetermined value is subtracted from the current value of the reliability score to decrease the reliability score. Typically, the added value and the subtracted value are the same value, but the absolute value of the added value may be higher or lower than the absolute value of the subtracted value.
[0027] The intimacy estimation processor 25 compares the language used in the customer's speech with the language used in the digital staff's speech, and calculates an intimacy score that represents the customer's level of intimacy with the digital staff based on the comparison result. Specifically, when the politeness of the customer's speech decreases, a predetermined value is added to the current value of the intimacy score to increase the intimacy score. When the politeness of the customer's speech increases, a predetermined value is subtracted from the current value of the intimacy score to decrease the intimacy score. Typically, the added value and the subtracted value are the same value, but the absolute value of the added value may be higher or lower than the absolute value of the subtracted value.
[0028] The degree of politeness of language is determined by creating a dictionary in advance of multiple ending expressions for each of multiple levels of politeness, typically from honorific language to friendly language, and storing the dictionary in the memory unit 14. The ending expressions used in customer utterances are then compared with the dictionary to determine the degree of politeness of the corresponding ending expressions.
[0029] It is assumed that as the empathy score, reliability score, and intimacy score increase, the likelihood that a customer will purchase a product increases. Therefore, the purchase likelihood estimation processing unit 26 calculates a purchase likelihood score (overall score) that indicates the likelihood that a customer will purchase a product based on the calculated empathy score, reliability score, and intimacy score. For example, the purchase likelihood score is calculated by adding the current value of the purchase likelihood score to the amount of change in the empathy score, reliability score, and intimacy score, or a value obtained by multiplying the amount of change by a predetermined coefficient such as 0.5. Note that the purchase likelihood score may be calculated by simply adding the empathy score, reliability score, and intimacy score, or by weighted addition of the empathy score, reliability score, and intimacy score. The calculation method may be changed as desired.
[0030] The persona information update unit 27 generates new persona information related to the place of origin, preferences, etc. based on the parts of speech and syntactic analysis results decomposed by the natural language analysis processing unit 22, and adds it to the existing persona information related to the customer to update it. The persona information is initially user information registered on the EC site. As the conversation progresses, new persona information is generated and added. The persona information is stored in the memory unit 14.
[0031] The persona extension information update unit 28 generates persona extension information that associates changes in the empathy score and the reliability score with the content of the digital staff member's conversation, in this case, nouns, that are thought to have caused those changes. In other words, the persona extension information is generated as information that can identify whether nouns in the digital staff member's statements lead to an increase or decrease in the empathy score and the reliability score. For example, persona extension information for a certain customer is generated by associating an increase in the reliability score with "blue" and "jacket." Persona extension information is generated as appropriate as the conversation progresses and is stored in the memory unit 14.
[0032] The language conversion processing unit 29 converts the language used in the digital staff member's message received from the message generation device 2 into language with a set level of politeness. Initially, the digital staff member's message received from the message generation device 2 is often mechanical, businesslike, and dry. As it is, it does not indicate a high level of intimacy. Therefore, a dictionary is created in advance to convert the language into multiple levels of politeness, from honorific language to friendly language, and is stored in the memory unit 14. The language conversion processing unit 29 converts the words and phrases used in the digital staff member's message received from the message generation device 2 into language with a set level of politeness, using the dictionary.
[0033] As will be described in more detail below, the politeness level of the customer's language is identified, and when that level changes as the conversation progresses, the politeness level of the language used by the digital staff is changed to reflect that change. For example, when the politeness level of the customer's language decreases, that is, when the customer's intimacy with the digital staff increases, the politeness level of the language used by the digital staff is decreased by one level from the current level. When the politeness level of the customer's language increases, that is, when the customer's intimacy with the digital staff decreases, the politeness level of the language used by the digital staff is increased by one level from the current level. By changing the politeness level of the language used by the digital staff in this way to reflect changes in the politeness level of the customer, the customer's intimacy with the digital staff can be increased and a decrease in the customer's intimacy with the digital staff can be prevented.
[0034] The message generation request processing unit 30 transmits data on the conversation history between the customer and the digital staff member, including the customer's most recent statement, along with a request to generate a message from the digital staff member in response to the customer's statement, to the message generation device 2. Furthermore, in addition to the conversation history data, the message generation request processing unit 30 transmits persona information, persona extension information, changes in empathy score, changes in trust score, changes in intimacy score, and changes in purchase likelihood score to the message generation device 2. By referring to this information, the message generation device 2 can generate a message from the digital staff member that follows the flow of the conversation and that increases the empathy score and trust score rather than decreasing them.
[0035] 4 shows the flow of conversation processing of the information processing device 1. When a conversation starts, under the control of the control unit 21, the empathy estimation processing unit 23, the reliability estimation processing unit 24, the intimacy estimation processing unit 25, and the purchase possibility estimation processing unit 26 initialize their respective scores (S1). For example, the empathy score, the reliability score, and the intimacy score are initialized to zero, and the purchase possibility score is initialized to 50 as a median value. When a conversation is repeated between the same customer and digital staff member, the empathy score, the reliability score, the intimacy score, and the purchase possibility score at the end of the previous conversation may be carried over.
[0036] Data on customer comments is received from the EC server 3 via the receiving processor 31 (S2). Data on digital staff comments is read from the memory unit 14. The customer comments and the digital staff comments are subjected to natural language analysis processing (S3). Parts of speech are broken down, nouns are extracted, and syntactic analysis is performed.
[0037] Using the natural language analysis results, the empathy estimation processing unit 23 executes an empathy estimation process to calculate an empathy score (S4), the reliability estimation processing unit 24 executes a reliability estimation process to calculate a reliability score (S5), and the intimacy estimation processing unit 25 executes an intimacy estimation process to calculate an intimacy score (S6). Each process will be described later. The purchase possibility estimation processing unit 26 calculates a purchase possibility score representing the likelihood that the customer will purchase a product based on the empathy score, the reliability score, and the intimacy score (S7). The method for calculating the purchase possibility score representing the likelihood that the customer will purchase a product on the e-commerce site from the empathy score, the reliability score, and the intimacy score is arbitrary. For example, the purchase possibility score is calculated by adding the amount of change in the empathy score, the reliability score, and the intimacy score, or a value obtained by multiplying the amount of change by a predetermined coefficient such as 0.5, to the current value of the purchase possibility score.
[0038] Next, the persona extension information update unit 28 generates persona extension information that associates changes in the empathy score, trust score, and intimacy score with the noun in the digital staff member's statement made immediately before the customer's statement indicating the change (S8). This allows the system to identify the noun in the digital staff member's statement that caused a change when a customer's empathy score, trust score, or intimacy score changes. For example, when a customer's trust score increases, the system can determine that the increase was caused by "blue" and "jackets," in other words, that the customer is interested in "blue" and "jackets," or identify the customer's preferences.
[0039] In the next step S9, the message generation request processor 30 generates a message generation request together with the conversation history, persona information, persona extension information, empathy score transition, reliability score transition, intimacy score transition, and purchase possibility score transition. The transmission processor 32 transmits the message generation request together with the data of the conversation history, persona information, persona extension information, empathy score transition, reliability score transition, intimacy score transition, and purchase possibility score transition to the message generation device 2 via the communication interface 17 (S9).
[0040] The receiving processing unit 31 receives the data of the digital staff member's message from the message generation device 2 via the communication interface 17 (S10). The language conversion processing unit 29 converts the language of the digital staff member's message to a set level of politeness (S11). The sending processing unit 32 transmits the data of the digital staff member's message, with the language converted, to the EC server 3 via the communication interface 17 (S12). If the conversation is continuing (S13, NO), the process returns to step S2 and waits for the next customer's message. If the conversation has ended (S13, YES), the conversation process ends.
[0041] Fig. 5 shows the flow of the empathy estimation process in step S4 in Fig. 4. Please refer to examples of changes in empathy score, trust score, intimacy score, and purchase likelihood score, as well as changes in wording, shown in Figs. 10 and 11.
[0042] The empathy estimation processing unit 23 determines whether the content of the digital staff member's utterance is in line with the topic of the conversation based on the analysis results of the natural language analysis processing unit 22 (S21). For example, if the e-commerce site is an apparel shop, the topic of the conversation is the apparel field. Typically, the nouns included in the digital staff member's utterance are checked against an apparel-related terminology dictionary to see if they are listed in the apparel-related terminology dictionary. If the nouns included in the digital staff member's utterance match any term listed in the apparel-related terminology dictionary, the content of the digital staff member's utterance is determined to be in line with the topic of the conversation (S21, YES). If the nouns included in the digital staff member's utterance do not match any term listed in the apparel-related terminology dictionary, the content of the digital staff member's utterance is determined to be not in line with the topic of the conversation (S21, NO). If it is determined that the content of the digital staff member's utterance is in line with the topic of the conversation (S21, YES), the processing waits for the next utterance from the digital staff member. When it is determined that the content of the digital staff member's remarks is not in line with the topic of the conversation (S21, NO), the process proceeds to the next step S22, and the calculation process of the empathy score begins. Note that when it is determined that the digital staff member's remarks are in line with the topic of the conversation, that is, when it is determined that the digital staff member's remarks are within the scope of the topic of the conversation, the empathy score is not calculated, but a reliability score is calculated. In other words, when the digital staff member's remarks are casual conversation, the empathy score is calculated, and when the digital staff member's remarks are not casual conversation but are actually in line with the topic of the consultation, a reliability score is calculated.
[0043] In step S22, the natural language analysis processing unit 22 analyzes the customer's statement, and in step S23, the empathy estimation processing unit 23 distinguishes whether the customer's statement is positive, negative, or neither in relation to the digital staff member's statement based on the analysis result of the natural language analysis processing unit 22. Typically, the predicate included in the customer's statement is compared with a dictionary created in advance that includes a plurality of positive expressions and a plurality of negative expressions, and whether the predicate is included in the dictionary is checked to determine whether the customer's statement is positive, negative, or neither.
[0044] When the customer's comment is positive, the empathy estimation processing unit 23 adds a predetermined value I1 to the current value of the empathy score, thereby increasing the empathy score (S24). When the customer's comment is negative, the empathy estimation processing unit 23 subtracts a predetermined value D1 from the current value of the empathy score, thereby decreasing the empathy score (S25). When the customer's comment is neither positive nor negative, the empathy estimation processing unit 23 determines that the customer is indifferent to the comments made by the digital staff member, and subtracts a predetermined value D2, the absolute value of which is greater than the predetermined value D1, from the current value of the empathy score, thereby further decreasing the empathy score (S26).
[0045] 6 shows the flow of the reliability estimation process in step S5 in FIG. 4. The reliability estimation processing unit 24 determines whether the content of the digital staff member's statement is in line with the topic of the conversation based on the analysis result of the natural language analysis processing unit 22 (S31). The method of this determination is the same as step S21. If it is determined that the content of the digital staff member's statement is not in line with the topic of the conversation (S31, YES), the process waits for the next statement from the digital staff member. If it is determined that the content of the digital staff member's statement is in line with the topic of the conversation (S31, NO), the process proceeds to the next step S32, where the calculation process of the reliability score begins.
[0046] In step S32, the natural language analysis processing unit 22 analyzes the customer's comment, and in step S33, the reliability estimation processing unit 24 determines whether the customer's comment is positive, negative, or neither in relation to the comment made by the digital staff member, based on the analysis result of the natural language analysis processing unit 22. The method for this determination is the same as in (S1) S23.
[0047] When the customer's comment is positive, the reliability estimation processing unit 24 adds a predetermined value I11 to the current value of the reliability score, thereby increasing the reliability score (S34). When the customer's comment is negative, the reliability estimation processing unit 24 subtracts a predetermined value D11 from the current value of the reliability score, thereby decreasing the reliability score (S35). When the customer's comment is neither positive nor negative, the reliability estimation processing unit 24 determines that the customer is indifferent to the comments made by the digital staff, and subtracts a predetermined value D12, the absolute value of which is greater than the predetermined value D11, from the current value of the reliability score, thereby further decreasing the reliability score (S36).
[0048] Fig. 7 shows the flow of the intimacy estimation process in step S6 in Fig. 4. The intimacy estimation processor 25 identifies the level of politeness of the language used in the customer's speech (S41). The determination of the level of politeness is performed by comparing the endings of the customer's speech with a dictionary of multiple endings associated with multiple levels of politeness, from honorific language to friendly language, and checking the level of politeness of the endings listed in the dictionary that match the endings of the customer's speech.
[0049] The intimacy estimation processor 25 determines whether the politeness level of the specified customer's speech has changed from the politeness level of the previous customer's speech (S42). If the politeness level has not changed (S42, NO), the process returns to step S41 and waits for the next customer's speech. If the politeness level has changed (S42, YES), the process determines whether the politeness level of the specified customer's speech has decreased compared to the politeness level of the previous customer's speech (S43).
[0050] When it is determined that the level of politeness of the specified customer's speech has decreased compared to the level of politeness of the previous customer's speech (S43, YES), a predetermined value I21 is added to the current value of the intimacy score to increase the intimacy score (S44).When it is determined that the level of politeness of the specified customer's speech has increased compared to the level of politeness of the previous customer's speech (S43, NO), a predetermined value D21 is subtracted from the current value of the intimacy score to decrease the intimacy score (S45).
[0051] FIG. 8 shows the flow of the wording change process. The wording change process is executed in parallel with the conversation process shown in FIG. 4. Prior to the conversation, the wording conversion processing unit 29 first initially sets the wording of the digital staff member's speech to, for example, "5," which is the middle level of politeness out of 11 levels (S51). When receiving a customer's speech, the wording conversion processing unit 29 identifies the level of politeness of the customer's speech (S52). Then, the wording conversion processing unit 29 determines whether the level of politeness of the identified customer's speech has changed from the level of politeness of the previous customer's speech (S53).
[0052] If the politeness level has not changed (S53, NO), the process returns to step S52 and waits for the next customer's comment. If the politeness level has changed (S53, YES), it is determined whether the politeness level of the specified customer's comment has decreased compared to the politeness level of the previous customer's comment (S54).
[0053] When it is determined that the level of politeness in the speech of the identified customer has decreased compared to the level of politeness in the speech of the previous customer (S54, YES), that is, when the customer's intimacy with the digital staff member has increased, the digital staff member's language is accordingly changed to a level of politeness that is one level lower (S55).When it is determined that the level of politeness in the speech of the identified customer has increased compared to the level of politeness in the speech of the previous customer (S54, NO), that is, when the customer's intimacy with the digital staff member has decreased, the digital staff member's language is accordingly changed to a level of politeness that is one level higher (S56).
[0054] If the conversation is continuing (S57, NO), the process returns to step S52 and waits for the next customer utterance. If the conversation has ended (S57, YES), the wording change process ends.
[0055] As described above, according to this embodiment, the customer's empathy score, trust score, and intimacy score for the digital staff member's comments are calculated, and the changes in these empathy scores and trust scores, as well as the conversation history, are sent to the comment generation device 2 along with a request to generate a comment.This allows the comment generation device 2 to generate comments from the digital staff member that increase the empathy score and trust score and prevent a decrease in empathy and trust.
[0056] Furthermore, according to this embodiment, by changing the level of politeness of the digital staff's language in response to changes in the level of politeness of the customer's speech, it is possible to increase intimacy and prevent a decrease in intimacy.
[0057] 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]
[0058] 1...information processing device, 2...statement generation device (generation AI), 3...EC server, 4...user terminal, 11...processor, 10...system bus, 12...RAM, 13...ROM, 14...memory unit, 15...input device, 16...display, 17...communication interface, 21...control unit, 22...natural language analysis processing unit, 23...empathy estimation processing unit, 24...trust estimation processing unit, 25...intimacy estimation processing unit, 26...purchase possibility estimation processing unit, 27...persona information update unit, 28...persona extension information update unit, 29...wording conversion processing unit, 30...statement generation request processing unit, 31...receiving processing unit, 32...transmitting processing unit.
Claims
1. An information processing device having a memory for storing a program, a processor for executing the program, and a communication interface for communicating with a user terminal via an electric public communication network, The processor executes the program, means for receiving user utterance data from the user terminal; means for identifying the degree of politeness of the user's speech; functioning as an intimacy estimation means for estimating an intimacy score representing a degree of intimacy between the user and the user based on the politeness of the language used in the user's speech; The politeness level is divided into several stages, The intimacy degree estimation means When the politeness of the language of the user's utterance is at the same level as the politeness of the language of the user's immediately preceding utterance, the current value of the intimacy score is maintained; when the politeness of the user's utterance has decreased by one or two or more levels compared to the politeness of the user's immediately preceding utterance, adding a predetermined first value to the current value of the intimacy score; An information processing device that subtracts a predetermined second value from the current value of the intimacy score when the politeness of the language used in the user's utterance becomes one or two or more levels higher than the politeness of the language used in the user's previous utterance.
2. an information processing device having a communication interface for communicating with a user terminal via an electrical public communication network, means for receiving user utterance data from the user terminal; means for identifying the degree of politeness of the user's speech; functioning as an intimacy estimation means for estimating an intimacy score representing a degree of intimacy of the user based on the politeness of the language used in the user's speech; The politeness level is divided into several stages, The intimacy degree estimation means When the politeness of the language of the user's utterance is at the same level as the politeness of the language of the user's immediately preceding utterance, the current value of the intimacy score is maintained; when the politeness of the user's utterance has decreased by one or two or more levels compared to the politeness of the user's immediately preceding utterance, adding a predetermined first value to the current value of the intimacy score; A program that subtracts a predetermined second value from the current value of the intimacy score when the politeness of the language used in the user's utterance becomes one or two or more levels higher than the politeness of the language used in the user's previous utterance.