Information processing system, information processing method and program

Abstract

To provide a technology that can provide appropriate answers to inquiries from users. [Solution] An information processing system according to one aspect of the present disclosure includes a search data creation unit that creates search data based on attribute data that associates a first attribute of an expected sender, a second attribute of an expected inquiry content, and answer identification information representing a user who is expected to answer the inquiry content; a first identification unit that, in response to receiving an inquiry, identifies a third attribute of the sender of the inquiry and a fourth attribute of the inquiry content; and a second identification unit that, based on the third attribute, the fourth attribute, the search data, and the attribute data, identifies a user who will answer the inquiry content, identified by answer identification information corresponding to at least one of a first attribute corresponding to the third attribute and a second attribute corresponding to the fourth attribute.

Description

[Technical Field]

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

[0002] There is known a technique for controlling an operator to be connected to in response to an automatic voice response from a user in a call center system (which may also be called a contact center system) (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2018-101941 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the prior art, there are cases where an appropriate response cannot be given to an inquiry from a user.

[0005] The present disclosure has been made in consideration of the above points, and aims to provide a technology that can provide an appropriate response to an inquiry from a user. [Means for solving the problem]

[0006] An information processing system according to one aspect of the present disclosure is an information processing system including one or more information processing devices, and includes: a search data creation unit that creates search data consisting of first search data including the first attribute and second search data including the second attribute based on attribute data in which a first attribute representing an attribute of an expected sender, a second attribute representing an attribute of an expected inquiry content, and answer identification information representing the identification information of a user expected to answer the inquiry content are associated; a first identification unit that, in response to receiving an inquiry, identifies a third attribute representing an attribute of the sender of the inquiry and a fourth attribute representing an attribute of the inquiry content; and a second identification unit that, based on the third attribute, the fourth attribute, the search data, and the attribute data, identifies a user who will answer the inquiry content, identified by answer identification information corresponding to at least one of the first attribute corresponding to the third attribute and the second attribute corresponding to the fourth attribute. [Effects of the Invention]

[0007] To provide a technology that can provide an appropriate response to inquiries from users. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a diagram illustrating an example of the overall configuration of a contact center system according to an embodiment of the present invention. [Figure 2] FIG. 2 is a diagram illustrating an example of a functional configuration of a server according to the present embodiment. [Figure 3] FIG. 10 is a diagram illustrating an example of attribute data. [Figure 4] FIG. 10 is a diagram illustrating an example of a search data creation process according to the present embodiment. [Figure 5] FIG. 10 is a diagram illustrating an example of attribute record number identification data. [Figure 6] FIG. 10 is a diagram showing an example of attribute record number group specifying data. [Figure 7] FIG. 10 is a diagram illustrating an example of similar attribute data. [Figure 8]FIG. 10 is a diagram illustrating an example of extracted data. [Figure 9] 10 is a flowchart illustrating an example of a reply process according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] An embodiment of the present invention will be described in detail below with reference to the drawings. A contact center system 1 capable of providing appropriate answers to inquiries from users at a contact center will be described below. However, a contact center is just one example, and the following embodiment can also be applied to, for example, an office or store where an appropriate answer is desired to be given to an inquiry from a user. More generally, the following embodiment can be applied to any situation where an appropriate answer is desired to be given to an inquiry from a certain person.

[0010] In the following, as an example, it is assumed that a user makes an inquiry to an interactive voice response (IVR), and an operator who can provide an appropriate answer to the inquiry is identified and then the operator is connected to the operator. However, this is just an example, and it is also possible to identify content that represents an appropriate answer to the user's inquiry, and then present that content to an operator who is handling the user's call. Specific examples of content that represents an appropriate answer include documents or images containing the answer, knowledge such as FAQs (Frequently Asked Questions), etc.

[0011] <Example of overall configuration of contact center system 1> An example of the overall configuration of a contact center system 1 according to this embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of the overall configuration of a contact center system 1 according to this embodiment.

[0012] 1, the contact center system 1 according to this embodiment includes a server 10, a plurality of operator terminals 20, a PBX (Private Branch eXchange) 30, a NW switch 40, and a user terminal 50. Here, the server 10, the operator terminals 20, the PBX 30, and the NW switch 40 are installed in a contact center environment E, which is a system environment of a contact center. Note that the contact center environment E is not limited to a system environment within the same building, and may be, for example, a system environment within multiple geographically separated buildings.

[0013] The server 10 identifies an operator who can provide an appropriate response to the inquiry from the user terminal 50, and controls the connection of the operator terminal 20 used by that operator to the user terminal 50. More specifically, the server 10 executes the following processes (1) to (3).

[0014] (1) First, when a voice call connection is established between the server 10 and the user terminal 50, the server 10 responds by automated voice response with a voice such as "Thank you for calling. Please tell us your inquiry."

[0015] (2) Next, when the server 10 receives a voice packet representing the inquiry content in response to the response shown in (1) above from the user terminal 50, it performs various processes, including voice recognition processing, on the voice data contained in the voice packet to identify the attributes of the sender and the attributes of the inquiry content. Here, the attributes of the sender include, for example, the time period of the sender, the region of the sender, the gender of the user, the age or generation of the user, etc. Furthermore, the attributes of the inquiry content include, for example, words contained in the text representing the inquiry content.

[0016] (3) Then, the server 10 identifies an operator who can provide an appropriate response based on the attributes identified in (2) above and data called search data that has been created in advance, and then transmits a voice call transfer request to the PBX 30. As a result, the voice call between the server 10 and the user is transferred to the operator terminal 20 used by the operator.

[0017] The server 10 can be realized by, for example, a computer (information processing device) such as a general-purpose server or a computer system (information processing system).

[0018] The operator terminal 20 is a terminal used by an operator and functions as an IP (Internet Protocol) telephone. An operator is a person who mainly handles telephone calls with users of a contact center (e.g., customers of a certain product or service). The operator terminal 20 can be realized by a computer (information processing device), such as a PC (personal computer), smartphone, tablet terminal, or wearable device.

[0019] The PBX 30 is a telephone exchange (IP-PBX) and is connected to a communication network 60 including various types of communication networks such as a VoIP (Voice over Internet Protocol) network, a PSTN (Public Switched Telephone Network), the Internet, etc. When the PBX 30 receives a voice call connection request from a user terminal 50, it establishes a connection between the user terminal 50 and the server 10. When the PBX 30 receives a voice call transfer request from the server 10, it disconnects the connection between the user terminal 50 and the server 10 and establishes a connection between the user terminal 50 and the operator terminal 20.

[0020] The NW switch 40 is a network device that transfers packets (voice packets) transmitted from the PBX 30 to the server 10 or the corresponding operator terminal 20.

[0021] The user terminal 50 is a variety of terminals used by users of the contact center, such as a smartphone, a mobile phone, a landline phone, a PC that functions as an IP phone, a tablet terminal, a wearable device, and the like.

[0022] The overall configuration of the contact center system 1 shown in Fig. 1 is an example, and is not limited to this, and other configurations may be used. For example, in the example shown in Fig. 1, the server 10 is included in the contact center environment E (i.e., the server 10 is an on-premise type), but all or part of the functions of the server 10 may be implemented by a cloud service or the like. Similarly, in the example shown in Fig. 1, the PBX 30 is an on-premise type telephone exchange, but may be implemented by a cloud service.

[0023] <Server 10 functional configuration example> An example of the functional configuration of the server 10 according to this embodiment will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of the functional configuration of the server 10 according to this embodiment.

[0024] As shown in FIG. 2 , the server 10 according to this embodiment includes a search data creation unit 101, an automatic response unit 102, an attribute identification unit 103, a response identification unit 104, and a transfer request unit 105. These units are implemented, for example, by one or more programs installed in the server 10, which are executed by a computing device such as a CPU (Central Processing Unit). The server 10 also includes an attribute data storage unit 106 and a search data storage unit 107. These storage units are implemented, for example, by storage areas of storage devices such as a hard disk drive (HDD), a solid state drive (SSD), or a flash memory. At least one of the attribute data storage unit 106 and the search data storage unit 107 may be implemented by storage areas of a storage device communicably connected to the server 10.

[0025] The search data creation unit 101 creates search data for searching for an operator to connect with the user, based on the attribute data stored in the attribute data storage unit 106. The search data creation unit 101 also saves the search data in the search data storage unit 107. The attribute data is data in a table format that associates the attributes of the caller, the attributes of the inquiry content, answer identification information that identifies the operator, and a record number. Hereinafter, the "caller attribute" (i.e., the expected caller attribute) included in the attribute data will be referred to as the "first attribute," and the "inquiry content attribute" (i.e., the expected attribute of the inquiry content) will be referred to as the "second attribute." Specific examples of attribute data and search data will be described later.

[0026] When a voice call connection is established between the automatic response unit 102 and the user terminal 50, the automatic response unit 102 sends a voice packet to the user terminal 50 containing voice data such as, for example, "Thank you for calling. Please tell us your inquiry."

[0027] When the attribute identification unit 103 receives a voice packet from the user terminal 50 via the PBX 30 and the NW switch 40, it performs various processes, including voice recognition processing, on the voice data contained in the voice packet to identify the attribute of the caller and the attribute of the inquiry content. Hereinafter, the "caller attribute" identified by the attribute identification unit 103 will be referred to as the "third attribute," and the "inquiry content attribute" will be referred to as the "fourth attribute." Examples of processes other than voice recognition processing include a process for identifying or estimating the time zone of the caller from the voice packet, a process for identifying or estimating the region of the caller from the voice packet, a process for estimating the gender of the speaker from the voice, and a process for estimating the age or generation of the speaker from the voice. However, in addition to these, the process may also include, for example, a process for estimating the speaker's emotions from the voice.

[0028] The answer identification unit 104 identifies an answer (i.e., an operator to connect with the user) based on the search data stored in the search data storage unit 107 and the third attribute and fourth attribute identified by the attribute identification unit 103.

[0029] The transfer request unit 105 creates a transfer request for transferring the voice call with the user to the operator identified by the answer identification unit 104 , and transmits the transfer request to the PBX 30 .

[0030] The attribute data storage unit 106 stores the attribute data. The attribute data is created in advance by, for example, a contact center manager or a data analyst.

[0031] The search data storage unit 107 stores the search data created and saved by the search data creation unit 101 .

[0032] ≪Attribute Data≫ An example of the attribute data stored in the attribute data storage unit 106 will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the attribute data.

[0033] The attribute data 1000 shown in FIG. 3 is made up of one or more records, and each record includes a first attribute, a second attribute, answer identification information, and an attribute record number.

[0034] The first attribute is the attribute of the sender. In the example shown in Figure 3, the first attribute is composed of attribute 1-1 that indicates the time zone of the sender, attribute 1-2 that indicates the region of the sender, attribute 1-3 that indicates the gender of the user, and attribute 1-4 that indicates the age of the user.

[0035] The second attribute is an attribute of the inquiry content. In the example shown in Figure 3, words such as "product A," "product B," "product C," "purchase," and "account transfer" are included as second attributes.

[0036] The answer identification information is identification information for identifying an answer. In this embodiment, the answer identification information is assumed to be identification information of an operator (for example, an operator ID, etc.).

[0037] The attribute record number is identification information that identifies each record included in the attribute data.

[0038] Each record included in the attribute data means that when the content of an inquiry from a user satisfies a first attribute and a second attribute, the user is connected to an operator indicated by answer identification information corresponding to the first attribute and the second attribute. In other words, each record included in the attribute data is data in which the first attribute and the second attribute are associated with the identification information of an operator who can give an appropriate answer to the content of an inquiry that satisfies the first attribute and the second attribute as answer identification information.

[0039] It goes without saying that the attribute data 1000 shown in Fig. 3 is just an example. For example, the first attributes of the attribute data 1000 shown in Fig. 3 include attributes 1-1 to 1-4, but the number of first attributes is not limited to four. Similarly, each record constituting the attribute data 1000 shown in Fig. 3 includes four second attributes, but the number of second attributes included in each record is not limited to four, and any number of second attributes may be included.

[0040] <Search data creation process> An example of the search data creation process according to this embodiment will be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of the search data creation process according to this embodiment. Note that the search data creation process is executed in advance before the answer process described later.

[0041] The search data creation unit 101 creates first attribute record number identification data (step S101). The first attribute record number identification data is table-format data consisting of records containing a first attribute and the attribute record number of a record that can be uniquely identified from the first attribute, when the record in the attribute data can be uniquely identified by the first attribute.

[0042] An example of the first attribute record number identification data created in step S101 is shown in Fig. 5(A). The first attribute record number identification data 1110 shown in Fig. 5(A) is made up of one or more records, and each record includes a first attribute and an attribute record number that is uniquely identified by the first attribute.

[0043] For example, the first attribute record number identification data 1110 shown in Fig. 5(A) includes a record of (attribute 1-1, attribute 1-2, attribute 1-3, attribute 1-4, attribute record number) = (morning, Tohoku region, male, young, #1). This is because when (attribute 1-1, attribute 1-2, attribute 1-3, attribute 1-4) = (morning, Tohoku region, male, young), the record (record with record number "#1") included in the attribute data 1000 shown in Fig. 3 can be uniquely identified.

[0044] The search data creation unit 101 creates second attribute record number identification data (step S102). The second attribute record number identification data is table-format data consisting of records containing a second attribute and the attribute record number of a record that can be uniquely identified from the second attribute when the record in the attribute data can be uniquely identified by the second attribute.

[0045] An example of the second attribute record number identification data created in step S102 is shown in Fig. 5(B). The second attribute record number identification data 1120 shown in Fig. 5(B) is made up of one or more records, and each record includes a second attribute and an attribute record number that is uniquely identified by the second attribute.

[0046] For example, the second attribute record number identification data 1120 shown in Fig. 5(B) includes a record where (second attribute, attribute record number) = (account transfer, #1). This is because when the second attribute = account transfer, the record (record with record number "#1") included in the attribute data 1000 shown in Fig. 3 can be uniquely identified.

[0047] 5(B) includes a record where (second attribute, attribute record number)=(exchange, #3). This is because when the second attribute=exchange, the record (record with record number "#3") included in the attribute data 1000 shown in FIG. 3 can be uniquely identified.

[0048] The search data creation unit 101 creates first attribute record number group identification data (step S103). The first attribute record number group identification data is table-format data consisting of records containing a first attribute and the attribute record numbers of two or more records that can be identified from the first attribute, when two or more records in the attribute data can be identified by the first attribute.

[0049] An example of the first attribute record number group identification data created in step S103 is shown in Fig. 6(A). The first attribute record number group identification data 1210 shown in Fig. 6(A) is made up of one or more records, and each record includes a first attribute and two or more attribute record numbers identified by the first attribute.

[0050] For example, the first attribute record number group identification data 1210 shown in Figure 6(A) includes the record (attribute 1-1, attribute 1-2, attribute 1-3, attribute 1-4, attribute record number) = (daytime, Kanto region, female, middle-aged, (#2, #3)). This is because when (attribute 1-1, attribute 1-2, attribute 1-3, attribute 1-4) = (daytime, Kanto region, female, middle-aged), it is possible to identify the record with record number "#2" and the record with record number "#3" from among the records included in the attribute data 1000 shown in Figure 3.

[0051] The search data creation unit 101 creates second attribute record number group identification data (step S104). The second attribute record number group identification data is table-format data consisting of records containing a second attribute and the attribute record numbers of two or more records that can be identified from the second attribute, when two or more records in the attribute data can be identified by the second attribute.

[0052] An example of the second attribute record number group identification data created in step S104 is shown in Figure 6(B). The second attribute record number group identification data 1220 shown in Figure 6(B) is made up of one or more records, and each record includes a second attribute and two or more attribute record numbers identified by the second attribute.

[0053] For example, the second attribute record number group identification data 1220 shown in Fig. 6(B) includes a record where (second attribute, attribute record number) = (product A, (#1, #2)). This is because when the second attribute = product A, the record with record number "#1" and the record with record number "#2" can be identified from among the records included in the attribute data 1000 shown in Fig. 3.

[0054] 6(B) includes a record (second attribute, attribute record number)=(product B, (#2, #3)). This is because, when the second attribute=product B, the record with record number "#2" and the record with record number "#3" can be identified from among the records included in the attribute data 1000 shown in FIG.

[0055] The search data creation unit 101 creates similar attribute data (step S105). The similar attribute data is data in a table format that is made up of records that include second attributes (words) included in the attribute data and similar attributes (synonyms) that are similar to the second attributes.

[0056] An example of the similar attribute data created in step S105 above is shown in Fig. 7. The similar attribute data 1300 shown in Fig. 7 is made up of one or more records, and each record includes a second attribute (word) and its similar attribute (synonym).

[0057] For example, the similar attribute data 1300 shown in FIG. 7 includes a record of (second attribute, similar attribute)=(purchase, (purchase, buy, . . .)). Also, for example, the similar attribute data 1300 shown in FIG. 7 includes a record of (second attribute, similar attribute)=(repair, (fix, repair, . . .)). Note that the search data creation unit 101 can identify similar attributes for each second attribute by using, for example, a thesaurus or an ontology.

[0058] The search data creation unit 101 creates first extracted data (step S106). The first extracted data is data in a list format in which the second attributes included in the attribute data are listed without duplication.

[0059] An example of the first extracted data created in step S106 is shown in Fig. 8(A). The first extracted data 1410 shown in Fig. 8(A) includes records in which (attribute 1-1, attribute 1-2, attribute 1-3, attribute 1-4) = (morning, Tohoku region, male, young), (afternoon, Kanto region, female, middle-aged). This is because the attribute data 1000 shown in Fig. 3 includes a record in which (attribute 1-1, attribute 1-2, attribute 1-3, attribute 1-4) = (morning, Tohoku region, male, young) and a record in which (attribute 1-1, attribute 1-2, attribute 1-3, attribute 1-4) = (afternoon, Kanto region, female, middle-aged).

[0060] The search data creation unit 101 creates second extracted data (step S107). The second extracted data is data in a list format that lists the second attribute included in the attribute data and its similar attributes without duplication.

[0061] An example of the second extracted data created in step S107 above is shown in Fig. 8(B). The second extracted data 1420 shown in Fig. 8(B) includes the second attribute = Product A, Product B,..., purchase, purchasing, buying,... This is because the attribute data includes records that include Product A, Product B, purchase, etc. as second attributes, and purchase and buy are similar attributes (synonyms) to purchase.

[0062] The search data creating unit 101 creates data consisting of the first attribute record number specifying data, the first attribute record number group specifying data, and the first extracted data as first search data (step S108).

[0063] The search data creating unit 101 creates data configured from the second attribute record number specifying data, the second attribute record number group specifying data, the similar attribute data, and the second extracted data as second search data (step S109).

[0064] The search data creating unit 101 stores the data consisting of the first search data and the second search data as search data in the search data storage unit 107 (step S110).

[0065] The search data creation process is executed, for example, every time the attribute data stored in the attribute data storage unit 106 is updated.

[0066] <Response processing> An example of the answering process according to this embodiment will be described with reference to Fig. 9. Fig. 9 is a flowchart showing an example of the answering process according to this embodiment. The answering process is executed every time a voice call connection is established between the user terminal 50 and the server 10.

[0067] The automatic response unit 102 transmits a voice packet containing voice data of a voice such as, for example, "Thank you for calling. Please tell us your inquiry" to the user terminal 50 (step S201). As a result, the user speaks a voice representing the inquiry, and a voice packet containing voice data representing that voice is transmitted from the user terminal 50 to the server 10.

[0068] When the attribute identification unit 103 receives a voice packet from the user terminal 50 via the PBX 30 and the NW switch 40, it performs various processes, including voice recognition processing, on the voice data included in the voice packet to identify a third attribute and a fourth attribute (step S202). The attribute identification unit 103 can identify the third attribute, for example, by the following steps 1-1 to 1-5. Also, the attribute identification unit 103 can identify the fourth attribute, for example, by the following steps 2-1 to 2-3.

[0069] Step 1-1: The attribute specifying unit 103 specifies the region of the source from the source IP address included in the voice packet.

[0070] Step 1-2: The attribute specification unit 103 specifies the time zone of the region specified in step 1-1 above based on the time zone information, and sets this time zone as the time zone of the sender.

[0071] Step 1-3: The attribute identification unit 103 estimates the gender of the speaker by applying a known gender estimation technique to the voice represented by the voice data included in the voice packet, and sets this gender as the gender of the user.

[0072] Step 1-4: The attribute identification unit 103 estimates the age of the speaker by applying a known age estimation technique to the voice represented by the voice data included in the voice packet, and sets this age as the age of the user.

[0073] Step 1-5: The attribute specification unit 103 determines the region of the sender, the time zone of the sender, the sex of the user, and the age of the user as the third attribute.

[0074] Step 2-1: The attribute specifying unit 103 creates text data by applying a known voice recognition technique to the voice represented by the voice data included in the voice packet.

[0075] Step 2-2: The attribute specification unit 103 extracts words by applying a known word extraction technique to the text data created in step 2-1 above.

[0076] Step 2-3: The attribute specification unit 103 assigns each of the words extracted in the above step 2-2 to a fourth attribute.

[0077] The answer identification unit 104 identifies a first attribute record number set based on the third attribute identified in step S202 and the first search data included in the search data stored in the search data storage unit 107 (step S203). The first attribute record number set is a set of attribute record numbers of records included in the attribute data, whose first attribute matches the third attribute. The answer identification unit 104 can identify the first attribute record number set, for example, by the following steps 3-1 to 3-6.

[0078] Step 3-1: The answer identification unit 104 determines whether or not the third attribute is included in the first extracted data.

[0079] Step 3-2: If the answer identification unit 104 determines that the third attribute is included in the first extracted data, it determines whether the third attribute is included in the first attribute record number identification data or the first attribute record number group identification data.

[0080] Step 3-3: If the answer identification unit 104 determines that the third attribute is included in the first attribute record number identification data, it identifies the attribute record number corresponding to the third attribute. In this case, one attribute record number is identified.

[0081] Step 3-4: If the answer identification unit 104 determines that the third attribute is included in the first attribute record number group identification data, it identifies the attribute record number corresponding to the third attribute. In this case, two or more attribute record numbers are identified.

[0082] Step 3-5: The answer identification unit 104 determines the set made up of the attribute record numbers identified in step 3-3 above or the attribute record numbers identified in step 3-4 above as a first attribute record number set.

[0083] Step 3-6: If the answer identification unit 104 determines that the third attribute is not included in the first extracted data, it determines, for example, a set consisting of all attribute record numbers (i.e., the attribute record numbers of all records that make up the attribute data) as the first attribute record number set.

[0084] The answer identification unit 104 identifies a second attribute record number set based on the fourth attribute identified in step S202 above and the second search data included in the search data stored in the search data storage unit 107 (step S204). The second attribute record number set is a set of attribute record numbers of records included in the attribute data, in which the second attribute or an attribute similar thereto matches the fourth attribute. The answer identification unit 104 can identify the second attribute record number set, for example, by the following steps 4-1 to 4-12. Note that, in general, multiple fourth attributes (i.e., multiple words) are identified in step S202 above.

[0085] Step 4-1: The answer identification unit 104 determines, for each of the fourth attributes, whether or not the fourth attribute is included in the second extracted data.

[0086] Step 4-2: The answer identification unit 104 determines, for each of the fourth attributes determined to be included in the second extracted data, whether or not the fourth attribute is included as a similar attribute in the similar attribute data.

[0087] Step 4-4: For each fourth attribute that is not determined to be included as a similar attribute in the similar attribute data, the answer identification unit 104 determines whether the fourth attribute is included in the second attribute record number identification data or the second attribute record number group identification data.

[0088] Step 4-5: For each fourth attribute determined to be included in the second attribute record number identification data, the answer identification unit 104 identifies the attribute record number corresponding to that fourth attribute. In this case, one attribute record number is identified.

[0089] Step 4-6: For each fourth attribute determined to be included in the second attribute record number group identification data, the answer identification unit 104 identifies the attribute record number corresponding to that fourth attribute. In this case, two or more attribute record numbers are identified.

[0090] Step 4-7: The answer identification unit 104 converts each of the fourth attributes determined to be included as a similar attribute in the similar attribute data into a second attribute (i.e., the original word that is not a synonym). Hereinafter, the fourth attribute converted into the original word that is not a synonym will be referred to as the "converted fourth attribute."

[0091] Step 4-8: The answer identification unit 104 determines, for each converted fourth attribute, whether the converted fourth attribute is included in the second attribute record number identification data or the second attribute record number group identification data.

[0092] Step 4-9: For each converted fourth attribute determined to be included in the second attribute record number identification data, the answer identification unit 104 identifies the attribute record number corresponding to that converted fourth attribute. In this case, one attribute record number is identified.

[0093] Step 4-10: For each converted fourth attribute determined to be included in the second attribute record number group identification data, the answer identification unit 104 identifies the attribute record number corresponding to that converted fourth attribute. In this case, two or more attribute record numbers are identified.

[0094] Step 4-11: The answer identification unit 104 sets the set made up of the attribute record numbers identified in steps 4-5, 4-6, 4-9, and 4-10 above as a second attribute record number set.

[0095] Step 4-12: If it is determined in step 4-1 above that not all fourth attributes are included in the second extracted data, the answer identification unit 104 determines, for example, a set consisting of all attribute record numbers (i.e., the attribute record numbers of all records that make up the attribute data) as the second attribute record number set.

[0096] The answer identification unit 104 identifies the intersection of the first attribute record number set and the second attribute record number set (i.e., the set of attribute record numbers that are commonly included in the first attribute record number set and the second attribute record number set) as the third attribute record number set (step S205).

[0097] The answer identification unit 104 acquires one attribute record number from the third attribute record number set (Step S206). For example, the answer identification unit 104 may randomly acquire one attribute record number from the third attribute record number set.

[0098] The answer identification unit 104 identifies answer identification information corresponding to the attribute record number acquired in step S104 (step S207) from among the answer identification information included in the attribute data stored in the attribute data storage unit 106. In other words, the answer identification unit 104 identifies answer identification information of a record including the attribute record number acquired in step S104 from among the records constituting the attribute data.

[0099] The transfer request unit 105 transmits a transfer request to the PBX 30 for the operator terminal 20 used by the operator indicated by the answer identification information identified in step S207 (step S208). As a result, the voice call with the user terminal 50 is transferred by the PBX 30 to the operator terminal 20, and a voice call connection is established between the user terminal 50 and the operator terminal 20.

[0100] <Modification> Modifications of the above embodiment will be described below. The following modifications can be combined as appropriate as long as they do not contradict each other.

[0101] Variation 1 In the above embodiment, it is mainly assumed that a user speaks an inquiry in response to an automated voice response. However, this is merely an example, and it is also possible to assume, for example, a case in which an operator is answering a telephone call with a user. In this case, when a user speaks an inquiry during the telephone call, content representing an appropriate answer to the inquiry may be identified and the content may be presented to the operator. This can be achieved by using content identification information as the "answer identification information" in the above embodiment. Furthermore, in this case, it is not necessary to identify one answer identification information; multiple answer identification information may be identified (for example, multiple attribute record numbers may be selected in step S206 of FIG. 9).

[0102] Variation 2 The content in the above-mentioned first modification may be, for example, a document or image containing an answer, or knowledge such as an FAQ, but is not limited to these. For example, the content may be an inquiry from a user that further clarifies the inquiry. For example, an appropriate word or sentence from among words or sentences that represent the 5W1H may be used as the answer.

[0103] Variation 3 In the above embodiment, the attributes of the inquiry content are words contained in the text representing the inquiry content, but the attributes may be, for example, the "type of inquiry content" identified by semantic interpretation of the text. Note that the semantic interpretation of the text can be realized by known natural language processing techniques.

[0104] <Summary> As described above, the server 10 according to this embodiment can identify an appropriate response to an inquiry based on the attributes of the user and the attributes of the inquiry from that user. This can be expected to have various effects, such as improving the efficiency of contact center operations and customer satisfaction.

[0105] The present invention is not limited to the above-described specifically disclosed embodiments, and various modifications, changes, and combinations with known technologies are possible without departing from the scope of the claims. [Explanation of symbols]

[0106] 1. Contact Center System 10 Servers 20 Operator terminal 30 PBX 40 Network Switch 50 User terminals 60 Communication Network 101 Search Data Creation Department 102 Automatic response unit 103 Attribute identification part 104 Answer Specification Section 105 Transfer request section 106 Attribute data storage unit 107 Search data storage unit

Claims

1. An information processing system including one or more information processing devices, a search data creation unit that creates search data consisting of first search data including the first attribute and second search data including the second attribute, based on attribute data in which a first attribute representing an attribute of an expected sender, a second attribute representing an attribute of an expected inquiry content, and answer identification information representing identification information of a user expected to answer the inquiry content are associated with the first attribute, the search data creation unit creating search data consisting of first search data including the first attribute and second search data including the second attribute; a first identification unit that, in response to receiving an inquiry, identifies a third attribute representing an attribute of a sender of the inquiry and a fourth attribute representing an attribute of the content of the inquiry; a second identification unit that identifies a user who will provide an answer to the inquiry, the user being identified by answer identification information corresponding to at least one of a first attribute corresponding to the third attribute and a second attribute corresponding to the fourth attribute, based on the third attribute, the fourth attribute, the search data, and the attribute data; An information processing system having the above.

2. The information processing system according to claim 1 , wherein the second search data includes the second attribute and a similar attribute representing an attribute similar to the second attribute.

3. 3. The information processing system according to claim 1, wherein the attributes of the sender include a time zone of the sender, a region of the sender, and an attribute of a user who made the inquiry.

4. An information processing system including one or more information processing devices, a search data creation step of creating search data consisting of first search data including the first attribute and second search data including the second attribute, based on attribute data in which a first attribute representing an attribute of an expected sender, a second attribute representing an attribute of an expected inquiry content, and answer identification information representing identification information of a user expected to answer the inquiry content are associated with each other; a first identification step of identifying, in response to receiving a query, a third attribute representing an attribute of a sender of the query and a fourth attribute representing an attribute of content of the query; a second identification step of identifying a user who will provide an answer to the inquiry, the user being identified by answer identification information corresponding to at least one of a first attribute corresponding to the third attribute and a second attribute corresponding to the fourth attribute, based on the third attribute, the fourth attribute, the search data, and the attribute data; An information processing method that performs the above.

5. An information processing system including one or more information processing devices, a search data creation step of creating search data consisting of first search data including the first attribute and second search data including the second attribute, based on attribute data in which a first attribute representing an attribute of an expected sender, a second attribute representing an attribute of an expected inquiry content, and answer identification information representing identification information of a user expected to answer the inquiry content are associated with each other; a first identification step of identifying, in response to receiving a query, a third attribute representing an attribute of a sender of the query and a fourth attribute representing an attribute of content of the query; a second identification step of identifying a user who will provide an answer to the inquiry, the user being identified by answer identification information corresponding to at least one of a first attribute corresponding to the third attribute and a second attribute corresponding to the fourth attribute, based on the third attribute, the fourth attribute, the search data, and the attribute data; A program that executes the following.

Images