Inquiry processing device, inquiry processing method, and program

Abstract

Conventionally, inquiries from users regarding a target have not been properly processed, and as a result, it has been difficult for the inquiries from users to be usefully linked to improvements in management, etc. [Solution] An inquiry processing device 1 is equipped with an inquiry reception unit 121 that receives inquiry information, which is information on user inquiries from one or more channels, a department determination means 1312 that determines the department corresponding to the inquiry information received by the inquiry reception unit 121 using department information for each of two or more departments in a department management unit 111 in which department information for each of two or more departments is stored, and acquires the department identifier of the department, and a department inquiry processing unit 132 that processes the inquiry information using the department identifier acquired by the department determination means 1312.This makes it possible to use inquiries from users to improve management, etc., when inquiries about a target from users could not be properly processed.

Description

[Technical Field]

[0001] The present invention relates to an inquiry processing device that processes inquiries from users. [Background technology]

[0002] Conventionally, there has been a call center operation support system that stores inquiry content, inquiry history, and customer information in a storage device, and when a call is received from a customer, reads out the necessary data and displays it on an operator terminal (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2021-157669 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the prior art, inquiries from users regarding the target could not be processed appropriately, and as a result, it was difficult for the inquiries from users to be usefully linked to improvements in management, etc. [Means for solving the problem]

[0005] The inquiry processing device of the first invention is an inquiry processing device that includes an inquiry reception unit that receives inquiry information, which is information on user inquiries from one or more channels, a department determination means that uses department information for each of two or more departments in a department management unit in which department information for each of two or more departments is stored to determine the department corresponding to the inquiry information received by the inquiry reception unit and acquires the department identifier of the department, and a department inquiry processing unit that processes the inquiry information using the department identifier acquired by the department determination means.

[0006] With this configuration, it is possible to automatically determine the department to which a user should respond in response to an inquiry about a target.

[0007] In addition, the inquiry processing device of the second invention is an inquiry processing device in which, compared to the first invention, the inquiry reception unit receives inquiry information from two or more channels, and further includes an inquiry storage unit that pairs the inquiry information received by the inquiry reception unit with a channel identifier that identifies the inquiry channel and stores the inquiry information in an inquiry management unit in which one or more pieces of inquiry information are stored, a statistical processing unit that obtains statistical processing results for the inquiry information for each of the two or more channel identifiers, and a statistical output unit that outputs the statistical processing results obtained by the statistical processing unit.

[0008] With this configuration, it is possible to obtain statistical processing results for inquiries for each channel of the inquiry.

[0009] Furthermore, the inquiry processing device of the third invention is an inquiry processing device in which, compared to the first invention, the inquiry reception unit receives two or more pieces of inquiry information and further includes a classification determination unit that uses some or all of the two or more pieces of inquiry information received by the inquiry reception unit to obtain two or more reasons for the inquiry information; a classification unit that determines one or more reasons to which each of the two or more pieces of inquiry information received by the inquiry reception unit belongs from the two or more reasons obtained by the classification determination unit; and an inquiry storage unit that stores each of the two or more pieces of inquiry information received by the inquiry reception unit in correspondence with the one or more reasons determined by the classification unit.

[0010] With this configuration, two or more queries can be used to automatically determine two or more reasons for the queries, and two or more reasons can be used to classify the two or more queries.

[0011] Furthermore, the inquiry processing device of the fourth invention is an inquiry processing device in which, compared to the first invention, the inquiry reception unit receives inquiry information from two or more channels, and further includes a group determination unit that groups the two or more pieces of inquiry information received by the inquiry reception unit and determines two or more groups, a representative determination unit that determines representative inquiry information for each of the two or more groups, which is inquiry information that represents the group, and a representative output unit that outputs the representative inquiry information determined by the representative determination unit.

[0012] With this configuration, two or more inquiries can be grouped into two or more groups, and a representative inquiry can be determined from each of the two or more groups.

[0013] In addition, the query processing device of the fifth invention is a query processing device that, compared to any one of the first to fourth inventions, further comprises an improvement acquisition unit that references a page storage unit in which one or more web pages related to the subject of the query are stored, and acquires web page improvement suggestions for the one or more web pages using the query information received by the query reception unit, and an improvement output unit that outputs the improvement suggestions.

[0014] With this configuration, it is possible to propose improvements to a web page using a user's inquiry about the target.

[0015] Furthermore, the inquiry processing device of the sixth invention is an inquiry processing device in which, compared to the fifth invention, the inquiry reception unit also receives response information corresponding to the inquiry information, and the improvement acquisition unit acquires improvement suggestions using the inquiry information and response information received by the inquiry reception unit.

[0016] With this configuration, it is possible to propose improvements to a web page using inquiries and answers from users about a target.

[0017] In addition, the inquiry processing device of the seventh invention is an inquiry processing device that, compared to any one of the first to sixth inventions, further includes a judgment unit that judges whether the inquiry information received by the inquiry receiving unit satisfies the processing conditions, and the department determination means obtains a department identifier only for inquiry information that the judgment unit judges to satisfy the processing conditions.

[0018] With this configuration, it is possible to determine the department only for the inquiry information that requires processing. [Effects of the Invention]

[0019] According to the inquiry processing device of the present invention, inquiries from users that could not be properly processed regarding a target can be utilized to improve management and the like. [Brief explanation of the drawings]

[0020] [Figure 1] Conceptual diagram of information system A in embodiment 1 [Figure 2] Block diagram of Information System A [Figure 3] Block diagram of the query processing device 1 [Figure 4] A flowchart illustrating an example of the operation of the inquiry processing device 1. [Figure 5] A flowchart illustrating an example of the determination process [Figure 6] Flowchart for explaining an example of same-inquiry analysis processing [Figure 7] A flowchart illustrating an example of the department determination process [Figure 8] A flowchart illustrating an example of the organization analysis process [Figure 9] 10 is a flowchart illustrating an example of the reason creation process. [Figure 10] Flowchart illustrating an example of classification processing [Figure 11] A flowchart illustrating an example of the grouping process [Figure 12] A flowchart illustrating an example of the representative determination process [Figure 13] A flowchart illustrating an example of the statistical processing [Figure 14] A flowchart illustrating an example of the improvement proposal acquisition process. [Figure 15] An example of the department management table [Figure 16] An example of an inquiry management table [Figure 17] Figure showing an example of the prompt management table [Figure 18] Figure showing an example of the prompt management table [Figure 19] Figure showing an example of the improvement proposal [Figure 20] Block diagram of the computer system DETAILED DESCRIPTION OF THE INVENTION

[0021] Hereinafter, embodiments of an inquiry processing device and the like will be described with reference to the drawings. Note that components with the same reference numerals in the embodiments perform similar operations, and therefore repeated description may be omitted.

[0022] (Embodiment 1) In this embodiment, an inquiry processing device will be described that receives inquiry information from two or more channels, stores the inquiry information in pairs with a channel identifier, and performs statistical processing for each channel.

[0023] In this embodiment, a description will be given of an inquiry processing device that obtains two or more reasons based on part or all of two or more pieces of accepted inquiry information.

[0024] In this embodiment, a description will be given of an inquiry processing device that determines one or more reasons for each of two or more pieces of inquiry information.

[0025] In this embodiment, a query processing device that groups two or more pieces of query information and determines a representative query from each group will be described.

[0026] In this embodiment, a query processing device that makes suggestions for improving a web page based on query information will be described. Note that the query processing device may also make suggestions for improving a web page using a response to the query information in addition to the query information.

[0027] In this embodiment, an inquiry processing device that excludes inquiry information that does not require processing will be described.

[0028] In this specification, information X being associated with information Y means that information Y can be obtained from information X, or information X can be obtained from information Y, and the method of association is not important. Information X and information Y may be linked, may exist in the same buffer, information X may be included in information Y, or information Y may be included in information X, etc.

[0029] Furthermore, in this specification, selecting or determining information Z means obtaining information Z, obtaining a pointer to information Z, obtaining the ID of information Z, setting a flag on information Z, etc., and it is sufficient if information Z can be accessed.

[0030] 1 is a conceptual diagram of an information system A according to this embodiment. The information system A includes a query processing device 1, one or more terminal devices 2, and one or more generation AI devices 3.

[0031] The query processing device 1 is a device that processes query information. The query processing device 1 is typically a server. For example, the query processing device 1 is a cloud server or an ASP server, but the type does not matter. The query processing device 1 may also be a terminal. If the query processing device 1 is a terminal, the query processing device 1 is, for example, a so-called personal computer, smartphone, or tablet terminal, but the type does not matter.

[0032] The terminal device 2 is a terminal used by a user. The terminal device 2 may be, for example, a personal computer, a smartphone, or a tablet terminal, but the type is not important. The user here is a person who obtains the processing results of the inquiry information. The user may be, for example, a manager, a webpage creator, or a member of the webpage creation department.

[0033] The generation AI device 3 is a device that has the function of a generation AI. Here, the generation AI device 3 typically has the function of a text generation AI. The generation AI may be, for example, ChatGPT or Google Bard, but the type is not important. Google is a registered trademark. The generation AI device 3 may be, for example, a cloud server or an ASP server, but the type is not important. The generation AI device 3 will be referred to as a generation AI as appropriate. The query processing device 1 may also have the function of a generation AI. In such a case, the generation AI device 3 is not necessary for the information system A.

[0034] The query processing device 1 and one or more terminal devices 2, and the query processing device 1 and one or more generation AI devices 3 can communicate with each other via a network such as the Internet.

[0035] Fig. 2 is an example of a block diagram of an information system A according to this embodiment. Fig. 3 is an example of a block diagram of an inquiry processing device 1.

[0036] The query processing device 1 includes a storage unit 11, a reception unit 12, a processing unit 13, and an output unit 14. The storage unit 11 includes a department management unit 111, a query management unit 112, a prompt management unit 113, and a page storage unit 114. The reception unit 12 includes a query reception unit 121. The processing unit 13 includes a judgment unit 130, a query analysis unit 131, a department query processing unit 132, a query accumulation unit 133, a classification determination unit 134, a classification unit 135, a group determination unit 136, a representative determination unit 137, an improvement acquisition unit 138, and a statistical processing unit 139. The query analysis unit 131 includes a channel acquisition means 1311, a department determination means 1312, and a query attribute value acquisition means 1313. The output unit 14 includes a representative output unit 141, an improvement output unit 142, and a statistical output unit 143.

[0037] The terminal device 2 includes a terminal storage unit 21, a terminal reception unit 22, a terminal processing unit 23, a terminal transmission unit 24, a terminal reception unit 25, and a terminal output unit 26.

[0038] Various types of information are stored in the storage unit 11 that constitutes the inquiry processing device 1. The various types of information include, for example, department information (to be described later), inquiry information (to be described later), prompts (to be described later), and one or more learning models.

[0039] The learning model is, for example, an inquiry information judgment model, a department determination model, one or more inquiry attribute value acquisition models, or a classification model.

[0040] The inquiry information judgment model is a learning model for determining whether inquiry information satisfies a processing condition. The inquiry information judgment model is information configured, for example, by a learning unit (not shown) performing machine learning learning processing using two or more sets of training data with inquiry information or information based on the inquiry information as an explanatory variable and a judgment result (whether the processing condition is satisfied or not) as a target variable, and is information used in machine learning prediction processing. The learning model may also be called a learner, a classifier, a classification model, etc. The learning unit (not shown) may be included in the query processing device 1 or in a learning device (not shown). The information based on inquiry information may be, for example, information obtained by vectorizing the inquiry information, information obtained by obtaining one or more independent words from the inquiry information and vectorizing a set of the independent words, or one or more independent words obtained from the inquiry information. The information based on inquiry information may also be called inquiry information because it is information originating from the inquiry information.

[0041] The department determination model is a learning model for determining a department corresponding to inquiry information. The department determination model is information configured, for example, by a learning unit (not shown) performing machine learning learning processing using two or more pieces of training data with inquiry information or information based on the inquiry information as explanatory variables and a department identifier as a target variable, and is information used in machine learning prediction processing.

[0042] The query attribute value acquisition model is a learning model for acquiring one or more query attribute values. The query attribute value acquisition model is information configured, for example, by a learning unit (not shown) performing machine learning learning processing using two or more pieces of training data in which query information or information based on the query information is used as an explanatory variable and query attribute values ​​are used as target variables, and is information used in machine learning prediction processing. The query attribute values ​​are, for example, an emotion identifier, a text type, a degree of urgency, and a response result. It is also preferable that a query attribute value acquisition model exists for each of two or more query attribute values.

[0043] The emotion identifier is information that identifies the emotion of the user who made the inquiry. Examples of emotion identifiers are 'compliment', 'positive', 'negative', and 'neutral'.

[0044] The text type is the type of text in the inquiry information. Examples of text types are 'request', which indicates an inquiry form or request, 'conversation', which indicates the content of a conversation between a customer and an operator, and 'notes', which indicates notes or records left by the operator.

[0045] The urgency level is the degree of urgency of the response to the inquiry. Examples of urgency levels are 'critical', which indicates that an urgent response is required, 'high', which indicates that a prompt response is required, 'medium', which indicates that a normal response is required, and 'low', which indicates that the priority is low.

[0046] The response result is information that indicates the result of the response to the inquiry. Examples of response results include 'resolved', which indicates that the problem has been resolved, 'pending', which indicates that the problem has not yet been resolved, and 'escalated', which indicates that the problem has been escalated.

[0047] The classification model is a learning model for reasons corresponding to inquiry information. The classification model is information configured, for example, by a learning unit (not shown) performing machine learning learning processing using two or more sets of training data with inquiry information or information based on the inquiry information as explanatory variables and classification identifiers as objective variables, and is information used in machine learning prediction processing.

[0048] The reason is information for classifying the inquiry information. It can also be said that the reason is a classification item or classification keyword of the inquiry information. Examples of the reason are "lost card," "login related," and "address change."

[0049] Note that the machine learning algorithm in this specification may be any algorithm, such as deep learning, random forest, decision tree, SVM, etc. For machine learning, various machine learning functions such as the TensorFlow (registered trademark) library, the random forest module of the R language, fastText, TinySVM, etc., and various existing libraries can be used.

[0050] The department management unit 111 stores one or more department information. The department management unit 111 normally stores two or more department information. It is preferable that the department management unit 111 stores one or more department information corresponding to each of two or more organizations. The department information in the department management unit 111 is associated with, for example, an organization identifier. The department information is associated with, for example, a notification flag and contact information.

[0051] Department information is information about a department in an organization. Department information is associated with a department identifier, for example. Department information is, for example, a character string describing the department, one or more keywords indicating the characteristics of the department, or the names of one or more products for which the department is responsible. Department information may be, for example, a vector using a character string describing the department, one or more keywords indicating the characteristics of the department, or one or more products for which the department is responsible.

[0052] The department identifier is information that identifies a department, such as the department name or department ID.

[0053] An organization identifier is information that identifies an organization. The organization identifier is, for example, the organization name or the organization ID. An organization is usually a company, but it may also be an association, a sole proprietorship, or the like.

[0054] The notification flag is information that indicates whether or not to notify the department or person in charge of the inquiry information. The notification flag is, for example, "Do not notify (0)" or "Notify (1)." The notification flag is, for example, "Do not notify (0)," "Notify in case of emergency (1)," or "Always notify (2)."

[0055] The contact information is information indicating the destination to which the inquiry information is to be notified, such as an email address, a phone number, or a user ID for a chat app or SNS.

[0056] The inquiry management unit 112 stores one or more pieces of inquiry information. The inquiry information in the inquiry management unit 112 corresponds to, for example, a channel identifier. The inquiry information in the inquiry management unit 112 corresponds to, for example, an organization identifier or a department identifier. The inquiry information in the inquiry management unit 112 corresponds to, for example, one or more reasons. The inquiry information in the inquiry management unit 112 corresponds to, for example, a group identifier. The inquiry information in the inquiry management unit 112 corresponds to, for example, an inquiry vector. The inquiry information in the inquiry management unit 112 corresponds to, for example, time information. The time information is information that specifies the time when the inquiry information was received. The time information is, for example, a date and time, but the granularity is not important.

[0057] Inquiry information is information about a user's inquiry about a target from one or more channels. The target is the subject of the user's inquiry. The target may be, for example, a product sold to the user or a service provided to the user, but it does not matter. The product may be, for example, software or a device, but it does not matter. Inquiry information is information indicating questions, opinions, views, etc. from the user. Inquiry information is, for example, a character string, but it can also be an image, audio information, video, etc.

[0058] A channel identifier is information that identifies a channel. For example, a channel identifier is a channel name or a channel ID. A channel is the route through which inquiry information from a user arrives. A channel can also be said to be information that identifies the source from which the inquiry information was entered. For example, a channel is a telephone call, chat, email, or operator memo.

[0059] One or more prompts are stored in the prompt management unit 113. A prompt may be a prompt template for configuring a prompt. A prompt template has one or more variables.

[0060] The prompt management unit 113 stores, for example, an inquiry judgment prompt, a department determination prompt, an inquiry analysis prompt, a classification determination prompt, a classification prompt, an inquiry analysis prompt, and an improvement suggestion prompt.

[0061] An inquiry judgment prompt is a prompt for obtaining a judgment result as to whether the inquiry information satisfies the processing conditions. For example, an inquiry judgment prompt is, "Please process the inquiry data that contains a mixture of various customer support contents, determine whether it contains the main subject of the user's inquiry, and respond with 'yes' or 'no'."

[0062] The processing conditions are conditions for performing some kind of processing on the inquiry information. The processing conditions are, for example, conditions for storing the inquiry information. The processing conditions are, for example, conditions for performing statistical processing using the inquiry information. The processing conditions are, for example, conditions for determining a department identifier corresponding to the inquiry information. The processing conditions are, for example, conditions for determining the reason for the inquiry information. The processing conditions are, for example, conditions for determining the group to which the inquiry information belongs. The processing conditions are, for example, conditions used to obtain improvement suggestions for a web page.

[0063] The processing conditions are not satisfied when, for example, the inquiry information does not contain information based on the user's voice information (silent information) or the inquiry information contains only a greeting.

[0064] The department determination prompt is a prompt for determining the department corresponding to the inquiry information. For example, the department determination prompt is "Please select the department name for the following inquiry information from the department name list below and output it. [Inquiry information] <Inquiry information> [Department name list] <Department information>". Note that in the prompt, character strings enclosed in "<" and ">" are variables, and information is substituted into them. The received inquiry information is substituted into <Inquiry information>. The department information of the department management unit 111 is substituted into <Department information>.

[0065] A query analysis prompt is a prompt for analyzing a single query and obtaining one or more query attribute values. For example, a query analysis prompt might say, "Your role is to analyze user comments from customer support inquiry records. Analyze the following query information according to the following criteria: - sentiment: Please select one of the user's sentiments from ('compliment', 'positive', 'negative', 'neutral'). [Query information]<Query information>."

[0066] A classification decision prompt is a prompt for outputting two or more reasons using two or more pieces of query information. An example of a classification decision prompt is, "Please output 10 reasons for classifying the following query set, which is two or more pieces of query information. [Query set] <Query set>." Note that reasons are keywords for classifying query information.

[0067] A classification prompt is a prompt for determining one or more reasons to which the inquiry information belongs from two or more reasons. An example of a classification prompt is, "Out of the following 10 reasons, please output the reason to which the following inquiry information applies. Note that you may output two or more reasons. [Inquiry information] <Inquiry information> [Reason] <Reason>."

[0068] An inquiry analysis prompt is a prompt for analyzing inquiry information. For example, an inquiry analysis prompt is, "Your role is to analyze user comments from customer support inquiry records. Please perform the analysis according to the following criteria:..."

[0069] An improvement suggestion prompt is a prompt for obtaining improvement suggestions. For example, an improvement suggestion prompt is, "Consider the following query set, and tell us what is missing or insufficient in the following web page! [Query set] <Query set> [Web page] <Web page>"

[0070] One or more web pages are stored in the page storage unit 114. It is preferable that the one or more web pages are associated with an organization identifier. In other words, it is preferable that a web page for each organization is stored in the page storage unit 114. Storing a web page can be considered to be the same as storing a URL for accessing the web page.

[0071] The reception unit 12 receives various types of information and instructions, such as inquiry information.

[0072] Here, acceptance typically refers to the reception of information transmitted via a wired or wireless communication line, but may also be a concept that includes the reception of information input from an input device such as a keyboard, mouse, or touch panel, or the reception of information read from a recording medium such as an optical disk, magnetic disk, or semiconductor memory.

[0073] The inquiry reception unit 121 receives one or more pieces of inquiry information. The inquiry reception unit 121 typically receives two or more pieces of inquiry information. The inquiry reception unit 121 receives inquiry information from one or more channels. The inquiry reception unit 121 typically receives inquiry information from two or more channels. It is preferable that the inquiry information received by the inquiry reception unit 121 is associated with a channel identifier. It is preferable that the inquiry reception unit 121 also receives response information associated with the inquiry information. It is preferable that the inquiry information received by the inquiry reception unit 121 is associated with an organization identifier.

[0074] The inquiry reception unit 121 receives inquiry information from, for example, a server of one or more call centers. The inquiry reception unit 121 receives inquiry information from, for example, each terminal of an operator of one or more call centers. The inquiry reception unit 121 receives inquiry information from, for example, a terminal device 2 of a user making an inquiry.

[0075] The processing unit 13 performs various types of processing, such as processing performed by the judgment unit 130, the department determination means 1312, the department inquiry processing unit 132, the inquiry accumulation unit 133, the classification determination unit 134, the classification unit 135, the group determination unit 136, the representative determination unit 137, the improvement acquisition unit 138, or the statistical processing unit 139.

[0076] Note that, when the inquiry information received by the inquiry receiving unit 121 is voice information, it is preferable that the processing unit 13 performs voice recognition processing on the inquiry information to acquire inquiry information that is a character string. Such inquiry information that is a character string may also be said to be inquiry information received by the inquiry receiving unit 121. Furthermore, the processing unit 13 may process the inquiry information received by the inquiry receiving unit 121 to acquire information based on the inquiry information. Such information based on the inquiry information is, for example, an inquiry vector or one or more keywords. Furthermore, such inquiry information may also be said to be inquiry information received by the inquiry receiving unit 121.

[0077] The determination unit 130 determines whether the inquiry information received by the inquiry receiving unit 121 satisfies the processing conditions and acquires the determination result. The determination result is, for example, "Yes (e.g., "1")" or "No (e.g., "0")".

[0078] The determination unit 130 acquires the determination result by, for example, one of the following methods (1) to (3). (1) Using generative AI

[0079] The determination unit 130 acquires the inquiry information received by the inquiry receiving unit 121. The determination unit 130 acquires the inquiry judgment prompt from the prompt management unit 113. The determination unit 130 provides the inquiry information and the inquiry judgment prompt to the generation AI. Then, the determination unit 130 acquires the judgment result from the generation AI.

[0080] In addition, providing information and a prompt to the generation AI can be considered to be the same as substituting information into one or more variables in the prompt template, constructing a prompt, and providing the prompt to the generation AI. (2) Machine learning method

[0081] The judgment unit 130 acquires the inquiry information received by the inquiry receiving unit 121. The judgment unit 130 acquires the inquiry information judgment model from the storage unit 11. The judgment unit 130 provides the inquiry information and the inquiry information judgment model to a prediction module that performs machine learning prediction processing, executes the prediction module, and acquires a judgment result. (3) Natural language processing method

[0082] The determination unit 130 acquires the inquiry information accepted by the inquiry receiving unit 121. If the inquiry information is voice information, the determination unit 130 performs voice recognition processing on the voice information to acquire the inquiry information which is a character string. Next, the inquiry receiving unit 121 performs morphological analysis on the inquiry information which is a character string to acquire one or more independent words. Next, the inquiry receiving unit 121 acquires a determination result as to whether any of the one or more independent words matches any of the one or more keywords in the storage unit 11.

[0083] The inquiry analysis unit 131 analyzes the inquiry information received by the inquiry reception unit 121 and acquires one or more inquiry attribute values. The inquiry attribute values ​​are, for example, a channel identifier that identifies the channel through which the inquiry information was received, a department identifier that identifies the department corresponding to the inquiry information, an emotion identifier, a text type, a level of urgency, and a response result.

[0084] The channel acquisition unit 1311 acquires a channel identifier that identifies the channel on which the inquiry information is received. The channel identifier is information associated with the inquiry information received by the inquiry receiving unit 121.

[0085] The department determination means 1312 acquires a department identifier for the inquiry information accepted by the inquiry receiving unit 121. That is, the department determination means 1312 determines a department to handle the inquiry indicated by the inquiry information. The department determination means 1312 may acquire an organization identifier associated with the inquiry information accepted by the inquiry receiving unit 121.

[0086] It is preferable that the department determination means 1312 acquires a department identifier only for the inquiry information that the determination unit 130 determines satisfies the processing conditions.

[0087] The department determination means 1312, for example, acquires two or more department information items paired with the accepted organization identifier from the department management unit 111. The department determination means 1312 uses the two or more department information items to acquire one or two or more department identifiers.

[0088] The department determination means 1312 acquires the department identifier by, for example, one of the following methods (1) to (3). (1) Natural language processing method (1-1) Keyword method

[0089] The department determination means 1312 acquires one or more keywords from the inquiry information received by the inquiry receiving unit 121. For each of two or more pieces of department information in the department management unit 111, the department determination means 1312 acquires the number of keywords included in the department information from the one or more acquired keywords. The department determination means 1312 acquires one or more department identifiers corresponding to department information whose number of keywords satisfies the applicable condition. The applicable condition is that the number of keywords is equal to or greater than a threshold value, or that the number of keywords is at a maximum. (1-2) Vector method

[0090] The department determination means 1312 vectorizes the inquiry information received by the inquiry receiving unit 121 and acquires the inquiry vector. For each of two or more pieces of department information in the department management unit 111, the department determination means 1312 acquires the distance between the vector based on the department information and the inquiry vector, and acquires one or more department identifiers corresponding to the department information whose distance satisfies the relevant condition. The relevant condition here is that the distance is equal to or less than a threshold, or that the distance is the minimum. (2) Using generative AI

[0091] The department determination means 1312 acquires the inquiry information received by the inquiry receiving unit 121. The department determination means 1312 acquires two or more pieces of department information from the department management unit 111. The department determination means 1312 acquires the department determination prompt from the prompt management unit 113. The department determination means 1312 provides the inquiry information, two or more pieces of department information, and the department determination prompt to the generation AI, and acquires one or more department identifiers from the generation AI. (3) Machine learning method

[0092] The department determination means 1312 acquires the inquiry information received by the inquiry receiving unit 121. The department determination means 1312 acquires the department determination model from the storage unit 11. The department determination means 1312 provides the inquiry information and the department determination model to a prediction module that performs machine learning prediction processing, executes the prediction module, and acquires a department identifier.

[0093] The query attribute value acquisition unit 1313 acquires one or more query attribute values ​​using query information. The query attribute values ​​are attribute values ​​of the query information. Examples of the query attribute values ​​include an emotion identifier, a text type, a degree of urgency, and a response result.

[0094] The queried attribute value acquisition means 1313 acquires one or more queried attribute values ​​by, for example, one of the following methods (1) and (2). (1) Using generative AI

[0095] The query attribute value acquisition means 1313 acquires query information accepted by the query acceptance unit 121. The query attribute value acquisition means 1313 acquires a query analysis prompt from the prompt management unit 113. The query attribute value acquisition means 1313 provides the query information and the query analysis prompt to the generation AI, and acquires one or more query attribute values ​​from the generation AI. (2) Machine learning method

[0096] The query attribute value acquisition means 1313 acquires query information accepted by the query acceptance unit 121. The query attribute value acquisition means 1313 acquires, for each of one or more query attribute values, a query attribute value acquisition model corresponding to the query attribute value to be acquired. For each of one or more query attribute values, the query attribute value acquisition means 1313 provides the acquired query information and the acquired query attribute value acquisition model to a prediction module that performs machine learning prediction processing, executes the prediction module, and acquires the query attribute value.

[0097] The department inquiry processor 132 processes the inquiry information using the department identifier acquired by the department determination means 1312. Such processing includes, for example, notification processing, accumulation processing, and statistical processing. (1) Notification processing performed by the department inquiry processing unit 132

[0098] The department inquiry processing unit 132 acquires contact information paired with the department identifier acquired by the department determination means 1312 from the department management unit 111. The department inquiry processing unit 132 transmits the inquiry information accepted by the inquiry acceptance unit 121 or information based on the inquiry information to the contact indicated by the contact information. Here, the information based on the inquiry information is, for example, information summarizing the inquiry information.

[0099] It is preferable that the department inquiry processing unit 132 transmits the inquiry information accepted by the inquiry accepting unit 121 or information based on the inquiry information to the contact indicated by the contact information only when the notification conditions are met. The notification conditions are, for example, conditions based on a notification flag paired with a department identifier acquired by the department determination means 1312. The notification conditions are, for example, conditions based on one or more inquiry attribute values ​​(e.g., urgency). (2) Accumulation processing performed by the department inquiry processing unit 132

[0100] The department inquiry processing unit 132 stores the inquiry information received by the inquiry receiving unit 121 or information based on the inquiry information in the inquiry management unit 112, paired with the department identifier acquired by the department determination means 1312. Here, the information based on the inquiry information is, for example, information that summarizes the inquiry information. The department inquiry processing unit 132 may store one or more inquiry attribute values ​​in paired with the department identifier acquired by the department determination means 1312. (3) Statistical processing performed by the department inquiry processing unit 132

[0101] The department inquiry processing unit 132 performs statistical processing on one or more pieces of inquiry information paired with each of two or more department identifiers. For example, the department inquiry processing unit 132 acquires the number or percentage of inquiry information for each of two or more department identifiers. For example, the department inquiry processing unit 132 acquires the number or percentage of inquiry information for each of two or more department identifiers and one or more reasons. The content of the statistical processing is not important.

[0102] The inquiry storage unit 133 pairs the inquiry information received by the inquiry reception unit 121 with a channel identifier that identifies the channel of the inquiry, and stores the paired information in the inquiry management unit 112. The inquiry storage unit 133 may also pair the inquiry information received by the inquiry reception unit 121 with a department identifier or one or more inquiry attribute values, and store the paired information in the inquiry management unit 112.

[0103] The inquiry storage unit 133 stores, for example, two or more pieces of inquiry information received by the inquiry receiving unit 121 in the inquiry management unit 112 in association with one or more reasons determined by the classification unit 135 .

[0104] The category determining unit 134 uses part or all of the two or more pieces of inquiry information received by the inquiry receiving unit 121 to obtain two or more reasons for the inquiry information.

[0105] The classification determination unit 134 acquires two or more reasons by, for example, the following method (1) or (2). (1) Using generative AI

[0106] The category determination unit 134 acquires a category determination prompt from the prompt management unit 113. The category determination unit 134 acquires two or more pieces of inquiry information or information based on each of the two or more pieces of inquiry information from the inquiry management unit 112. The category determination unit 134 provides the two or more pieces of inquiry information or information based on each of the two or more pieces of inquiry information and the category determination prompt to the generation AI, and acquires two or more reasons from the generation AI. (2) Natural language processing method

[0107] The category determination unit 134 acquires two or more pieces of query information or information based on each of the two or more pieces of query information from the query management unit 112. Next, the category determination unit 134 acquires one or two or more feature words from each of the two or more pieces of query information or each piece of information based on each of the two or more pieces of query information. The category determination unit 134 aggregates the two or more acquired feature words to acquire two or more feature words.

[0108] A characteristic term is an independent word, a characteristic term, for example, a term whose tf / idf value is equal to or greater than a threshold.

[0109] Aggregating feature words means processing two or more feature words as unique terms, or making them into a single term that is synonymous or similar to two or more feature words.

[0110] The classification unit 135 determines one or more reasons to which each of the two or more pieces of inquiry information received by the inquiry receiving unit 121 belongs. The one or more reasons are one or more reasons out of the two or more reasons acquired by the classification determination unit 134.

[0111] The classification unit 135 acquires two or more reasons by, for example, one of the following methods (1) to (3). (1) Using generative AI

[0112] The classification unit 135 acquires inquiry information to be classified. The classification unit 135 acquires two or more reasons. The classification unit 135 acquires a classification prompt from the prompt management unit 113. The classification unit 135 provides the inquiry information, the two or more reasons, and the classification prompt to the generation AI, and acquires one or more classification identifiers from the generation AI. (2) Machine learning method

[0113] The classification unit 135 acquires inquiry information to be classified. The classification unit 135 acquires a classification model from the storage unit 11. The classification unit 135 provides the inquiry information and the classification model to a prediction module that performs machine learning prediction processing, executes the prediction module, and acquires a classification identifier. (3) Natural language processing method

[0114] The classification unit 135 acquires inquiry information to be classified. The classification unit 135 vectorizes the inquiry information. The classification unit 135 calculates the similarity between the vector and a vector paired with the reason for each of two or more reasons. The classification unit 135 acquires reasons paired with vectors corresponding to one or more similarities that satisfy the adoption conditions. Note that the adoption conditions include, for example, that the similarity is maximum, or that the similarity is equal to or greater than a threshold. The vector paired with a reason is, for example, a vector of a reason that is a word (for example, a vector acquired by Word2vec), or a vector acquired from a character string that explains the reason.

[0115] The group determination unit 136 groups two or more pieces of inquiry information received by the inquiry receiving unit 121 and determines two or more groups.

[0116] For example, the group determination unit 136 vectorizes the inquiry information for each of the two or more pieces of inquiry information in the inquiry management unit 112, and acquires an inquiry vector. Next, the group determination unit 136 groups the two or more inquiry vectors, for example, by using the k-means algorithm. For example, the group determination unit 136 associates a group identifier with each of the two or more pieces of inquiry information. Note that the group determination unit 136 may group the two or more inquiry vectors by using a clustering method other than the k-means algorithm. Examples of clustering methods other than the k-means algorithm include Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Gaussian Mixture Model (GMM), Self-Organizing Map (SOM), and Spectral Clustering. Furthermore, the group identifier is information for identifying a group, such as a group ID. In addition, the group determination unit 136 may determine that each piece of inquiry information other than the representative inquiry information belongs to the group to which the representative inquiry information that is closest (most similar) from among the determined two or more pieces of representative inquiry information belongs.

[0117] The representative determination unit 137 determines, for each of one or more groups, representative inquiry information that is inquiry information that represents the group. Note that the representative determination unit 137 may determine one or more pieces of representative inquiry information before the groups are determined.

[0118] For example, for each of two or more groups, the representative determination unit 137 calculates the sum of distances between each of the inquiry vectors of two or more pieces of inquiry information belonging to the group and one or more other inquiry vectors in the same group. The representative determination unit 137 determines the inquiry information corresponding to the inquiry vector with the smallest sum of distances as the representative inquiry information of the group.

[0119] The improvement acquisition unit 138 refers to the page storage unit 114 in which one or more web pages related to the target are stored, and acquires improvement suggestions for one or more web pages using one or more pieces of inquiry information received by the inquiry reception unit 121.

[0120] The improvement acquisition unit 138, for example, refers to the page storage unit 114 in which one or more web pages related to the target are stored, and uses the inquiry information received by the inquiry reception unit 121 to acquire improvement suggestions for the web pages related to information that is missing from one or more web pages.

[0121] It is preferable that the improvement acquisition unit 138 acquires an improvement proposal using the inquiry information and response information received by the inquiry receiving unit 121.

[0122] The improvement acquisition unit 138 acquires one or more web pages that are paired with the acquired organization identifier, for example, by referring to the page storage unit 114. The improvement acquisition unit 138 acquires improvement suggestions for the one or more web pages regarding information that is missing from the one or more web pages, for example, by using the inquiry information accepted by the inquiry acceptance unit 121.

[0123] It is preferable that the improvement acquisition unit 138 acquires improvement proposals using, for example, two or more pieces of representative inquiry information determined by the representative determination unit 137.

[0124] The improvement acquisition unit 138 acquires the improvement proposal by, for example, one of the following methods (1) and (2). (1) Using generative AI

[0125] The improvement acquisition unit 138 acquires two or more pieces of inquiry information from the inquiry management unit 112. The improvement acquisition unit 138 acquires one or more web pages from the page storage unit 114. The improvement acquisition unit 138 acquires an improvement suggestion prompt from the prompt management unit 113. Next, the improvement acquisition unit 138 provides the generation AI with an inquiry set, which is a set of two or more pieces of inquiry information, one or more web pages, and the improvement suggestion prompt, and acquires one or more improvement suggestions from the generation AI. (2) Natural language processing method

[0126] The improvement acquisition unit 138 acquires two or more pieces of inquiry information from the inquiry management unit 112. The improvement acquisition unit 138 vectorizes each of the two or more pieces of inquiry information and acquires an inquiry vector. The improvement acquisition unit 138 vectorizes each of one or more processing units included in each of one or more web pages and acquires a processing unit vector. For each of two or more inquiry vectors, the improvement acquisition unit 138 calculates a similarity between the inquiry vector and one or more processing unit vectors. If none of the one or more similarities for each inquiry vector satisfy the adoption condition, the improvement acquisition unit 138 determines that the inquiry information paired with the inquiry vector is information not listed on the web page, and acquires an improvement proposal that encourages adding a response to the inquiry information to the web page. Note that the adoption condition may be, for example, that the similarity is equal to or greater than a threshold. Furthermore, the processing unit may be, for example, a page or a frame, but is not limited thereto.

[0127] The statistical processing unit 139 performs statistical processing on two or more pieces of inquiry information and obtains the statistical processing results.

[0128] The statistical processing unit 139 acquires statistical processing results for inquiry information, for example, for each of two or more channel identifiers. The statistical processing unit 139 acquires, for example, the number or proportion of inquiry information for each of two or more channel identifiers. The statistical processing unit 139 acquires, for example, the number or proportion of inquiry information for each of two or more channel identifiers and for each reason. The content of the statistical processing is not important.

[0129] The output unit 14 outputs various types of information, such as representative inquiry information, improvement proposals, and statistical processing results.

[0130] Here, output refers to, for example, transmission to terminal device 2, but it may also be a concept that includes display on a display, projection using a projector, printing on a printer, sound output, transmission to an external device other than terminal device 2, storage on a recording medium, and handing over processing results to other processing devices or other programs.

[0131] The representative output unit 141 outputs one or more pieces of representative inquiry information determined by the representative determination unit 137 .

[0132] The improvement output unit 142 outputs one or more improvement proposals acquired by the improvement acquisition unit 138.

[0133] The statistics output unit 143 outputs one or more statistical processing results acquired by the statistical processing unit 139 .

[0134] Various types of information are stored in the terminal storage unit 21 of the terminal device 2. The various types of information are, for example, an organization identifier and a user identifier. The organization identifier may also serve as a user identifier. In other words, once the user identifier is determined, the organization identifier may also be determined.

[0135] The terminal receiving unit 22 receives input of instructions, information, etc. from the user. The instructions, information, etc. are, for example, a suggestion output instruction. The suggestion output instruction is an instruction to output an improvement suggestion.

[0136] The means for inputting instructions and information may be any means, such as a touch panel, keyboard, mouse, or menu screen.

[0137] The device processing unit 23 performs various types of processing, such as processing to change the structure of instructions, information, etc. received by the terminal receiving unit 22 to instructions, information, etc., for transmission, processing to change the structure of information received by the terminal receiving unit 25 to output, etc.

[0138] The terminal transmitting unit 24 transmits various information, instructions, etc. to the inquiry processing device 1. The various information, instructions, etc. are, for example, an organization identifier, a user identifier, and an instruction to output a proposal.

[0139] The terminal receiving unit 25 receives various types of information from the inquiry processing device 1. The various types of information include, for example, inquiry information, representative inquiry information, and improvement suggestions.

[0140] The terminal output unit 26 outputs various types of information, such as inquiry information, representative inquiry information, and improvement suggestions.

[0141] Here, output means, for example, display on a display, but it may also be a concept that includes projection using a projector, printing on a printer, sound output, storage on a recording medium, transmission to another processing device, or handing over processing results to another processing device or other program, etc.

[0142] The storage unit 11, department management unit 111, inquiry management unit 112, prompt management unit 113, page storage unit 114, and terminal storage unit 21 are preferably non-volatile recording media, but can also be realized as volatile recording media.

[0143] There is no restriction on the process by which information is stored in the storage unit 11 etc. For example, information may be stored in the storage unit 11 etc. via a recording medium, information transmitted via a communication line etc. may be stored in the storage unit 11 etc., or information input via an input device may be stored in the storage unit 11 etc.

[0144] The reception unit 12 and the inquiry reception unit 121 are preferably realized by wireless or wired communication means, but may also be realized by a means for receiving broadcasts, a device driver for an input means such as a touch panel or keyboard, or control software for a menu screen.

[0145] The processing unit 13, judgment unit 130, department determination means 1312, department query processing unit 132, query accumulation unit 133, classification determination unit 134, classification unit 135, group determination unit 136, representative determination unit 137, improvement acquisition unit 138, and statistical processing unit 139 can usually be realized by a processor, memory, etc. The processing procedures of the processing unit 13, etc. are usually realized by software, and the software is recorded on a recording medium such as a ROM. However, they may also be realized by hardware (dedicated circuit). The processor may be a CPU, MPU, GPU, etc., and the type is not important.

[0146] The output unit 14, the representative output unit 141, the improvement output unit 142, and the statistical output unit 143 are preferably realized by wireless or wired communication means, but may also be realized by driver software for an output device such as a display or speaker, or by a combination of driver software for an output device and the output device.

[0147] The terminal reception unit 22 can be realized by a device driver for an input means such as a touch panel or a keyboard, or control software for a menu screen.

[0148] The terminal transmitting unit 24 is usually realized by a wireless or wired communication means, but may also be realized by a broadcasting means.

[0149] The terminal receiving unit 25 is usually realized by a wireless or wired communication means, but may also be realized by a means for receiving broadcasts.

[0150] The terminal output unit 26 may or may not include an output device such as a display, a speaker, etc. The terminal output unit 26 may be realized by driver software for an output device, or by a combination of driver software for an output device and the output device, etc.

[0151] Next, an example of the operation of the inquiry processing device 1 will be described with reference to the flowchart of FIG.

[0152] (Step S401) The inquiry receiving unit 121 determines whether or not inquiry information has been received. If inquiry information has been received, the process proceeds to step S402, and if inquiry information has not been received, the process proceeds to step S411.

[0153] (Step S402) The processing unit 13 determines whether the inquiry information received in step S401 is voice information. If it is voice information, the process proceeds to step S403, and if it is a character string, the process proceeds to step S404.

[0154] (Step S403) The processing unit 13 performs a speech recognition process on the inquiry information received in step S401 to acquire inquiry information in the form of a character string. Note that the inquiry information in the form of a character string may also be simply referred to as inquiry information.

[0155] (Step S404) The determination unit 130 performs a determination process using the query information of the character string. An example of the determination process will be described with reference to the flowchart of FIG.

[0156] (Step S405) If the determination result in step S404 is that "the processing conditions are met," the process proceeds to step S406, and if the determination result is that "the processing conditions are not met," the process returns to step S401.

[0157] (Step S406) The inquiry analysis unit 131 analyzes the inquiry information and acquires two or more inquiry attribute values. An example of such inquiry analysis processing will be described with reference to the flowchart of FIG.

[0158] (Step S407) The query accumulation unit 133 acquires the two or more query attribute values ​​acquired in step S406.

[0159] (Step S408) The query storage unit 133 associates two or more query attribute values ​​with the query information and stores them in the query management unit 112. It is preferable that the query storage unit 133 also associates the query vector acquired from the query information with the query information and stores it in the query management unit 112.

[0160] (Step S409) The department inquiry processing unit 132 determines whether the inquiry information received in step S401 matches the department notification conditions. If the inquiry information matches the department notification conditions, the process proceeds to step S410. If the inquiry information does not match the department notification conditions, the process returns to step S401.

[0161] The department notification conditions are conditions for notifying a department of inquiry information. The department notification conditions may be the same as the notification conditions.

[0162] (Step S410) The department inquiry processing unit 132 acquires a department identifier paired with the inquiry information. The department inquiry processing unit 132 acquires contact information paired with the department identifier from the department management unit 111. The department inquiry processing unit 132 notifies the contact indicated by the contact information of the inquiry information etc. accepted in step S401. Return to step S401. Note that the inquiry information etc. may be just the inquiry information, or may be the inquiry information and one or more inquiry attribute values ​​etc.

[0163] (Step S411) The processing unit 13 determines whether it is time to analyze the inquiry information. If it is time to analyze the inquiry information, the process proceeds to step S412, and if it is not time to analyze the inquiry information, the process proceeds to step S421.

[0164] The timing for analyzing the inquiry information may be, for example, when a predetermined time has come, when a predetermined number of pieces of inquiry information or more have been accumulated, or when an instruction from the user has been received.

[0165] (Step S412) The processing unit 13 assigns 1 to the counter i.

[0166] (Step S413) The processing unit 13 judges whether or not the i-th organization exists. If the i-th organization exists, the process proceeds to step S414, and if not, the process returns to step S401.

[0167] The i-th organization exists when, for example, the department management unit 111 has the i-th organization identifier.

[0168] (Step S414) The processing unit 13 acquires the organization identifier of the i-th organization from the department management unit 111.

[0169] (Step S415) The processing unit 13 analyzes the inquiry information of the i-th organization. An example of such organization analysis processing will be described with reference to the flowchart of FIG.

[0170] (Step S416) The improvement acquisition unit 138 acquires improvement suggestions for the web page of the i-th organization. An example of such improvement suggestion acquisition processing will be described with reference to the flowchart of FIG.

[0171] (Step S417) The decision unit 130 decides whether or not the organization notification condition is satisfied. If the organization notification condition is satisfied, the process proceeds to step S418, and if not, the process proceeds to step S420.

[0172] The organization notification condition is a condition for notifying an organization of the results of the organization analysis process or improvement proposals. The organization notification condition is, for example, a condition based on the acquired results of the organization analysis process or the contents of the improvement proposals. The organization notification condition is, for example, that the number of inquiry information for the organization is equal to or exceeds a threshold, or that an improvement proposal exists.

[0173] (Step S418) The department inquiry processor 132 acquires information to be notified, such as representative inquiry information and improvement suggestions.

[0174] (Step S419) The department inquiry processing unit 132 acquires one or more pieces of contact information paired with the organization identifier of the i-th organization from the department management unit 111. The department inquiry processing unit 132 notifies the contacts indicated by the one or more pieces of contact information of the information acquired in step S418.

[0175] (Step S420) The processing unit 13 increments the counter i by 1. The process returns to step S413.

[0176] (Step S421) The reception unit 12 determines whether or not an instruction to output information has been received. If an instruction to output information has been received, the process proceeds to step S422, and if an instruction to output information has not been received, the process returns to step S401. Here, the reception unit 12 determines whether or not an instruction to output information has been received from the terminal device 2.

[0177] (Step S422) The processing unit 13 acquires one or more pieces of information specified by the instruction to output information.

[0178] (Step S423) The output unit 14 outputs the one or more pieces of information acquired in step S422. Here, the output unit 14 transmits the one or more pieces of information to, for example, the terminal device 2 that has transmitted the instruction to output the information.

[0179] In the flowchart of FIG. 4, the process ends when the power is turned off or an interrupt occurs to end the process.

[0180] Next, an example of the determination process in step S404 will be described with reference to the flowchart in FIG.

[0181] (Step S501) The determination unit 130 acquires the inquiry information received by the inquiry receiving unit 121.

[0182] (Step S502) The determination unit 130 acquires an inquiry determination prompt from the prompt management unit 113.

[0183] (Step S503) The determination unit 130 provides the generation AI with the inquiry information acquired in step S501 and the inquiry determination prompt acquired in step S502.

[0184] (Step S504) The determination unit 130 determines whether or not an answer has been acquired from the generation AI. If an answer has been acquired, the process proceeds to step S505, and if an answer has not been acquired, the process returns to step S504.

[0185] (Step S505) The determination unit 130 obtains the determination result from the response obtained in step S504, and returns to the upper level process.

[0186] Next, an example of the inquiry analysis process in step S406 will be described with reference to the flowchart in FIG.

[0187] (Step S601) The inquiry analysis unit 131 acquires inquiry information.

[0188] (Step S602) The channel obtaining means 1311 obtains a channel identifier that identifies the channel on which the inquiry information is received.

[0189] (Step S603) The department determination means 1312 determines the department that should handle the inquiry information. An example of such department determination processing will be described with reference to the flowchart of FIG.

[0190] (Step S604) The query attribute value acquisition unit 1313 acquires a query analysis prompt from the prompt management unit 113.

[0191] (Step S605) The query attribute value acquiring means 1313 provides the query information and the query analysis prompt to the generating AI.

[0192] (Step S606) The query attribute value acquisition means 1313 determines whether or not an answer has been acquired from the generation AI. If an answer has been acquired, the process proceeds to step S607, and if an answer has not been acquired, the process returns to step S606.

[0193] (Step S607) The query attribute value acquisition means 1313 acquires one or more query attribute values ​​from the response acquired in step S606, and returns to the upper processing.

[0194] Next, an example of the department determination process in step S603 will be described with reference to the flowchart in FIG.

[0195] (Step S701) The department determination means 1312 performs morphological analysis on the acquired inquiry information.

[0196] (Step S702) The section determination means 1312 acquires one or more keywords from the result of the morphological analysis. The keywords are usually independent words. For example, the keywords are terms of a specific part of speech such as a noun.

[0197] (Step S703) The department determination means 1312 assigns 1 to the counter i.

[0198] (Step S704) The department determination means 1312 judges whether or not the i-th department information exists in the department management unit 111. If the i-th department information exists, the process proceeds to step S705, and if not, the process returns to the upper level process.

[0199] (Step S705) The department determination means 1312 acquires the i-th department information from the department management unit 111.

[0200] (Step S706) The department determination means 1312 uses one or more keywords and department information to determine whether the inquiry information corresponding to the one or more keywords satisfies the relevant condition for the i-th department information. If the relevant condition is met, the process proceeds to step S707, and if the relevant condition is not met, the process proceeds to step S708.

[0201] The applicable conditions are, for example, that the department information contains one or more keywords, that the number of keywords contained in the department information is the maximum, that the distance between the vectorized department information and the vector obtained from one or more keywords is within a threshold, or that the distance between the vectorized department information and the vector obtained from one or more keywords is the minimum.

[0202] (Step S707) The department determination means 1312 acquires the department identifier paired with the i-th department information, and stores the department identifier in association with the inquiry information.

[0203] (Step S708) The department determination means 1312 increments the counter i by 1. The process returns to step S704.

[0204] Next, an example of the organization analysis process in step S415 will be described with reference to the flowchart of FIG.

[0205] (Step S801) The processing unit 13 acquires all the inquiry information to be analyzed from the inquiry information of the relevant organization. The acquired inquiry information may be all the inquiry information paired with the organization identifier of the relevant organization, or inquiry information for a specific period (for example, the last month, this fiscal year) among the inquiry information paired with the organization identifier of the relevant organization.

[0206] (Step S802) The classification determination unit 134 determines whether or not there are two or more reasons paired with the department identifier in the department management unit 111. If there are two or more reasons, the process proceeds to step S803; if there are no reasons, the process proceeds to step S804.

[0207] (Step S803) The classification determination unit 134 determines whether or not to create a reason for the organization identified by the organization identifier. If a reason is to be created, the process proceeds to step S804; if not, the process proceeds to step S805.

[0208] Reasons are created even when two or more reasons exist in the department management unit 111 if, for example, a period of time equal to or greater than a threshold has passed since the creation of the two or more reasons, if the number of pieces of inquiry information at the time the two or more reasons were created has increased to a number equal to or greater than a threshold, or if a flag indicating that a reason must be created during organizational analysis is managed in pairs with the organizational identifier.

[0209] (Step S804) The category determining unit 134 creates a reason for the organization identified by the organization identifier. An example of the reason creation process will be described with reference to the flowchart in FIG.

[0210] (Step S805) The classification unit 135 acquires from the department management unit 111 two or more reasons that are paired with the department identifier.

[0211] (Step S806) The classification unit 135 classifies the inquiry information to be analyzed using two or more reasons. An example of such classification processing will be described with reference to the flowchart of FIG.

[0212] (Step S807) The group determination unit 136 groups the inquiry information to be analyzed. An example of such grouping processing will be described with reference to the flowchart in FIG.

[0213] (Step S808) The representative determination unit 137 determines representative inquiry information for each of one or more groups. An example of such representative determination processing will be described with reference to the flowchart in FIG.

[0214] (Step S809) The statistical processing unit 139 performs statistical processing on the inquiry information of the organization, and returns to the upper level processing. An example of such statistical processing will be described with reference to the flowchart of FIG.

[0215] Next, an example of the reason creation process in step S804 will be described with reference to the flowchart in FIG.

[0216] (Step S901) The classification determination unit 134 acquires two or more pieces of inquiry information that are paired with the organization identifier of interest and that serve as the basis for creating reasons from the inquiry management unit 112. The two or more pieces of inquiry information that serve as the basis for creating reasons may be all of the inquiry information that are paired with the organization identifier, or may be some of the inquiry information. In the case of some of the inquiry information, for example, the classification determination unit 134 acquires inquiry information from a period within a threshold from the most recent inquiry information, or a number of inquiry information items within a threshold from the most recent inquiry information.

[0217] (Step S902) The category determination unit 134 acquires a category determination prompt from the prompt management unit 113.

[0218] (Step S903) The category determination unit 134 passes the two or more pieces of inquiry information acquired in step S901 and the category determination prompt acquired in step S902 to the generation AI.

[0219] (Step S904) The classification determination unit 134 determines whether or not an answer has been acquired from the generation AI. If an answer has been acquired, the process proceeds to step S905, and if an answer has not been acquired, the process returns to step S904.

[0220] (Step S905) The category determining unit 134 obtains two or more reasons from the answer obtained in step S904.

[0221] (Step S906) The classification determination unit 134 stores the two or more reasons acquired in step S905 in association with the organization identifier in the department management unit 111. The process returns to the upper level process.

[0222] Next, an example of the classification process in step S806 will be described with reference to the flowchart in FIG.

[0223] (Step S1001) The classification unit 135 acquires two or more reasons.

[0224] (Step S1002) The classification unit 135 acquires a classification prompt from the prompt management unit 113.

[0225] (Step S1003) The classification unit 135 assigns 1 to a counter i.

[0226] (Step S1004) The classification unit 135 determines whether or not the i-th inquiry information to be classified exists. If the i-th inquiry information exists, the process proceeds to step S1005, and if not, the process returns to the upper process.

[0227] (Step S1005) The classification unit 135 acquires the i-th inquiry information.

[0228] (Step S1006) The classification unit 135 passes the i-th inquiry information, the two or more reasons acquired in step S1001, and the classification prompt acquired in step S1002 to the generation AI.

[0229] (Step S1007) The classification unit 135 determines whether or not an answer has been acquired from the generation AI. If an answer has been acquired, the process proceeds to step S1008, and if an answer has not been acquired, the process returns to step S1007.

[0230] (Step S1008) The classification unit 135 acquires a reason from the answer acquired in step S1007.

[0231] (Step S1009) The classification unit 135 associates the reason acquired in step S1008 with the i-th inquiry information.

[0232] (Step S1010) The classification unit 135 increments the counter i by one.

[0233] Next, an example of the grouping process in step S807 will be described with reference to the flowchart in FIG.

[0234] (Step S1101) The group determination unit 136 acquires two or more pieces of inquiry information to be grouped.

[0235] (Step S1102) The group determination unit 136 assigns 1 to a counter i.

[0236] (Step S1103) The group determination unit 136 determines whether or not the i-th inquiry information exists. If the i-th inquiry information exists, the process proceeds to step S1104, and if not, the process proceeds to step S1106.

[0237] (Step S1104) The group determination unit 136 vectorizes the i-th inquiry information, acquires the inquiry vector, and associates the inquiry vector with the i-th inquiry information.

[0238] (Step S1105) The group determination unit 136 increments the counter i by 1. The process returns to step S1103.

[0239] (Step S1106) The group determination unit 136 groups two or more query vectors using a clustering method such as the k-means method.

[0240] (Step S1107) The group determination unit 136 associates a group identifier that identifies a group with each of the two or more query vectors, and returns to the upper-level processing.

[0241] Next, an example of the representative determination process in step S808 will be described with reference to the flowchart in FIG.

[0242] (Step S1201) The representative determining unit 137 assigns 1 to a counter i.

[0243] (Step S1202) Representative determination unit 137 determines whether or not the i-th group exists. If the i-th group exists, the process proceeds to step S1203, and if not, the process returns to the upper level process.

[0244] (Step S1203) The representative determining unit 137 assigns 1 to a counter j.

[0245] (Step S1204) The representative determination unit 137 determines whether or not the jth inquiry information included in the ith group exists. If the jth inquiry information exists, the process proceeds to step S1205; if not, the process proceeds to step S1214.

[0246] (Step S1205) The representative determination unit 137 acquires the inquiry vector paired with the j-th inquiry information included in the i-th group.

[0247] (Step S1206) The representative determining unit 137 assigns 1 to a counter k.

[0248] (Step S1207) The representative determination unit 137 determines whether or not the kth other inquiry information excluding the jth inquiry information exists in the i-th group. If the kth other inquiry information exists, the process proceeds to step S1208; if not, the process proceeds to step S1212.

[0249] (Step S1208) The representative determination unit 137 acquires the inquiry vector paired with the kth other inquiry information excluding the jth inquiry information in the i-th group.

[0250] (Step S1209) The representative determination unit 137 calculates the distance between the two query vectors. Note that the two query vectors are the vectors acquired in steps S1205 and S1208.

[0251] (Step S1210) The representative determination unit 137 adds the distance to the total distance corresponding to the j-th inquiry information included in the i-th group. Note that the initial value of the total distance is 0.

[0252] (Step S1211) The representative determination unit 137 increments the counter k by 1. The process returns to step S1207.

[0253] (Step S1212) The representative determination unit 137 associates the total distance with the j-th inquiry information included in the i-th group.

[0254] (Step S1213) The representative determination unit 137 increments the counter j by 1. The process returns to step S1204.

[0255] (Step S1214) The representative determination unit 137 determines the inquiry information with the smallest total distance from among the inquiry information of the i-th group as the representative inquiry information. The representative determination unit 137 stores the representative inquiry information in association with the group identifier of the i-th group. The storage destination may be, for example, the inquiry management unit 112, but is not limited thereto.

[0256] (Step S1215) The representative determination unit 137 increments the counter i by 1. The process returns to step S1202.

[0257] Next, an example of the statistical processing in step S809 will be described with reference to the flowchart in FIG.

[0258] (Step S1301) The statistical processing unit 139 assigns 1 to a counter i.

[0259] (Step S1302) The statistical processing unit 139 determines whether or not the i-th channel exists. If the i-th channel exists, the process proceeds to step S1303, and if not, the process proceeds to step S1305.

[0260] (Step S1303) The statistical processing unit 139 acquires the number of pieces of inquiry information paired with the channel identifier of the i-th channel, and stores the number paired with the channel identifier of the i-th channel.

[0261] (Step S1304) The statistical processing unit 139 increments the counter i by 1. The process returns to step S1302.

[0262] (Step S1305) The statistical processing unit 139 assigns 1 to the counter i.

[0263] (Step S1306) The statistical processing unit 139 determines whether or not the i-th organization exists. If the i-th organization exists, the process proceeds to step S1307, and if not, the process returns to the upper process.

[0264] (Step S1307) The statistical processing unit 139 acquires the number of pieces of inquiry information paired with the organization identifier of the i-th organization, and stores the number paired with the organization identifier of the i-th organization.

[0265] (Step S1308) The statistical processing unit 139 assigns 1 to the counter j.

[0266] (Step S1309) The statistical processing unit 139 determines whether or not the j-th reason exists. If the j-th reason exists, the process proceeds to step S1310, and if not, the process proceeds to step S1312.

[0267] (Step S1310) The statistical processing unit 139 acquires the number of pieces of inquiry information paired with the organization identifier of the i-th organization and the j-th reason, and stores the number paired with the organization identifier of the i-th organization and the j-th reason.

[0268] (Step S1311) The statistical processing unit 139 increments the counter j by 1. The process returns to step S1309.

[0269] (Step S1312) The statistical processing unit 139 increments the counter i by 1. The process returns to step S1307.

[0270] 13, the statistical processing unit 139 may acquire the number of pieces of inquiry information for each department. Also, the statistical processing unit 139 may acquire the number of pieces of inquiry information for each department and each reason.

[0271] Next, an example of the good proposal acquisition process in step S416 will be described with reference to the flowchart of FIG.

[0272] (Step S1401) The improvement acquisition unit 138 acquires from the inquiry management unit 112 two or more pieces of inquiry information paired with the organization identifier of the organization of interest.

[0273] (Step S1402) The improvement acquisition unit 138 refers to the page storage unit 114 and acquires one or more web pages that are paired with the organization identifier of the organization of interest.

[0274] (Step S1403) The improvement acquisition unit 138 acquires an improvement suggestion prompt from the prompt management unit 113.

[0275] (Step S1404) The improvement acquisition unit 138 provides the generation AI with the two or more pieces of inquiry information acquired in step S1401, the one or more web pages acquired in step S1402, and the improvement suggestion prompt acquired in step S1403.

[0276] (Step S1405) The improvement acquisition unit 138 determines whether or not an answer has been acquired from the generation AI. If an answer has been acquired, the process proceeds to step S1406, and if an answer has not been acquired, the process returns to step S1405.

[0277] (Step S1406) The improvement acquisition unit 138 acquires one or more improvement proposals from the response acquired in step S1405, and stores the one or more improvement proposals in pairs with the organization identifier of the organization of interest. The process returns to the upper level process.

[0278] A specific example of the operation of the information system A in this embodiment will be described below.

[0279] The department management unit 111 of the inquiry processing device 1 stores a department management table shown in FIG. 15. The department management table is a table for managing department information for each organization. The department management table manages one or more records each having an "ID," an "organization identifier," a "department identifier," a "notification flag," "contact information," and "department information." The "department information" includes a "keyword" and a "department description." The "ID" is information for identifying a record. The "notification flag" is information indicating whether or not the inquiry information is to be immediately notified to the department. A notification flag of "0" indicates that the department will not immediately notify the department of the inquiry information. A notification flag of "1" indicates that the department will immediately notify the department of the inquiry information only if the inquiry attribute value (urgency) of the inquiry information indicates "urgent." A notification flag of "2" indicates that the department will always immediately notify the department of the inquiry information. The "contact information" is information indicating the contact information of the department. The "contact information" is information indicating the destination to which the inquiry information is to be notified. A "keyword" is a term that indicates the characteristics of the department, such as the name of a product handled by the department. "Department Description" is a description of the department.

[0280] The inquiry management unit 112 stores an inquiry management table having the structure shown in FIG. 16. The inquiry management table is a table for managing inquiry information for each organization. The inquiry management table manages one or more records having "ID," "inquiry information," "organization identifier," "department identifier," "channel identifier," "reason," "group identifier," "inquiry vector," and "date and time." In this case, "inquiry information" is a character string. Inquiries received by telephone are processed through voice recognition, and a character string corresponding to the inquiry is stored. "Organization identifier" is information for identifying the organization that is the subject of the inquiry. "Department identifier" is information for identifying the department that is the subject of the inquiry. "Channel identifier" is information for identifying the channel through which the inquiry was made. "Reason" is one or more reasons to which the inquiry information applies. "Group identifier" is the identifier of the group to which the inquiry information belongs. "Inquiry vector" is information obtained by vectorizing the inquiry information. "Date and time" is the date and time when the inquiry was made. The "Date and time" may be entered by an operator and does not need to be accurate.

[0281] The prompt management unit 113 stores a prompt management table shown in Figures 17 and 18. The prompt management table is a table for managing prompts. The prompt management table manages one or more records that have a "prompt identifier" and a "prompt."

[0282] The page storage unit 114 stores one or more web pages for each organization, or URLs for accessing websites for each organization.

[0283] In the above situation, the following three specific examples will be explained. Specific Example 1 is processing for one piece of inquiry information. Specific Example 2 is processing for a set of inquiries, which is a large number of pieces of inquiry information. The processing for the set of inquiries includes reason determination processing, classification determination processing, organization analysis processing, and improvement proposal processing. Specific Example 3 is improvement proposal processing using inquiry information and a web page.

[0284] (Example 1) The inquiry receiving unit 121 of the inquiry processing device 1 receives inquiry information from a large number of call center servers and chat servers (not shown). The received inquiry information is associated with an organization identifier (e.g., company name) and a channel identifier. The following describes the processing for one piece of inquiry information (e.g., "I can't change my address because I can't log in...").

[0285] The processing unit 13 determines whether each piece of received inquiry information is voice information. If the inquiry information is voice information, the processing unit 13 performs voice recognition processing on the inquiry information to obtain the inquiry information in the form of a character string.

[0286] Next, the determination unit 130 performs the determination process described using the flowchart in FIG. 5 on the query information of the character string. That is, the determination unit 130 obtains a query determination prompt from the prompt management table (FIG. 17). Next, the determination unit 130 provides the query information and the obtained query determination prompt to the generation AI. Then, the determination unit 130 obtains an answer from the generation AI for each piece of query information. Next, the determination unit 130 obtains a determination result ("yes" or "no") from the obtained answer for each piece of query information. Here, the determination unit 130 obtains the determination result "yes." Note that the following process is performed only on query information corresponding to the determination result "yes."

[0287] First, the inquiry analysis unit 131 analyzes the inquiry information by the inquiry analysis process described using the flowchart in Fig. 6, and acquires two or more inquiry attribute values. That is, the channel acquisition means 1311 acquires a channel identifier (e.g., "chat") that identifies the channel through which the inquiry information (e.g., "I can't log in, so I can't change my address...") was received. The department determination means 1312 acquires the organization identifier "Company A" that pairs with the inquiry information. Furthermore, the department determination means 1312 acquires a department identifier (e.g., "Department AA") that corresponds to the inquiry information by the department determination process described using the flowchart in Fig. 7.

[0288] The query attribute value acquisition means 1313 also acquires a query analysis prompt from the prompt management table (FIG. 17). Next, the query attribute value acquisition means 1313 provides the query information and the query analysis prompt to the generation AI. Then, the query attribute value acquisition means 1313 acquires an answer from the generation AI. Next, the query attribute value acquisition means 1313 acquires one or more query attribute values ​​from the answer. Here, it is assumed that the acquired query attribute values ​​are, for example, emotion "neutral," text type "request," urgency "medium," and final result "pending." It is also assumed that the query attribute value acquisition means 1313 vectorizes the query information and acquires a query vector (x1, x2, . . .). The query attribute value acquisition means 1313 also acquires the date and time "2024 / 11 / 28 13:11" from a clock (not shown).

[0289] Next, the inquiry storage unit 133 associates two or more inquiry attribute values ​​with the inquiry information and stores them in the inquiry management table (FIG. 16). Such records are records with "ID=1" in FIG. 16 that do not have a reason or group identifier.

[0290] Next, the department inquiry processing unit 132 determines whether the inquiry information matches the department notification conditions. Here, the department identifier paired with the inquiry information is "Department AA," and the notification flag paired with the department identifier is "2." The notification flag "2" is a flag indicating that all inquiry information should be sent, so the department inquiry processing unit 132 determines that the inquiry information matches the department notification conditions. The department inquiry processing unit 132 acquires the department identifier "Department AA." The department inquiry processing unit 132 acquires the contact information "aa@x.jp" paired with the department identifier "Department AA." The department inquiry processing unit 132 sends the inquiry information, etc., by email to the contact indicated by the contact information. Through the above processing, the person in charge of "Department AA" can immediately view the inquiry information in their email client.

[0291] (Example 2) It is assumed that the processing unit 13 has determined that it is time to analyze the inquiry information. Then, the processing unit 13 processes the inquiry set for each organization as follows. Here, an example will be described using the organization identifier "Company A."

[0292] The processing unit 13 acquires the organization identifier "Company A." Next, the processing unit 13 performs the organization analysis process described with reference to the flowchart in FIG. 8 using all pieces of inquiry information paired with the organization identifier "Company A."

[0293] First, the processing unit 13 acquires all pieces of inquiry information paired with the organization identifier "Company A" from the inquiry information management table (FIG. 16).

[0294] Next, the category determination unit 134 determines two or more reasons for the inquiry information with the organization identifier "Company A" through the reasons determination process described using the flowchart in Figure 9. That is, the category determination unit 134 obtains a category determination prompt from the prompt management table (Figure 18). Next, the category determination unit 134 substitutes the obtained multiple pieces of inquiry information into the variable <inquiry set> of the category determination prompt to construct a category determination prompt to be passed to the generation AI. Next, the category determination unit 134 passes the category determination prompt to the generation AI. Next, the category determination unit 134 obtains an answer from the generation AI. Next, the category determination unit 134 obtains two or more reasons from the answer. Here, it is assumed that the two or more reasons are "lost card," "login-related," "address change," "late payment," etc. Next, the category determination unit 134 stores the obtained two or more reasons in association with the organization identifier "Company A."

[0295] Next, the classification unit 135 acquires two or more reasons, such as "lost card," "login-related," "address change," and "late payment," acquired by the classification determination unit 134. The classification unit 135 also acquires a classification prompt from the prompt management table (FIG. 18). Next, the classification unit 135 acquires inquiry information to be classified that is paired with the organization identifier "Company A." Next, the classification unit 135 assigns the acquired inquiry information (e.g., "I can't log in, so I can't change my address...") to the variable <inquiry information> of the classification prompt, and assigns the acquired two or more reasons to the variable <reason> to construct a classification prompt to be passed to the generation AI. Next, the classification unit 135 passes the classification prompt to the generation AI. The classification unit 135 acquires an answer from the generation AI. The classification unit 135 acquires a reason (e.g., "login-related," "address change") from the answer. Next, the classification unit 135 associates the reason with the inquiry information and stores it. This information is the "reason" information of the record with "ID=1" in Fig. 16. The above process is performed for all inquiry information to be classified for "Company A", and one or more reasons are associated with all inquiry information.

[0296] Next, the group determination unit 136 performs the grouping process described using the flowchart in FIG. 11 and groups the inquiry information to be analyzed for "Company A."

[0297] Next, the representative determination unit 137 determines representative inquiry information for each of two or more groups of inquiry information to be analyzed for "Company A" through the representative determination process described using the flowchart in FIG.

[0298] Furthermore, the statistical processing unit 139 performs statistical processing on all inquiry information to be analyzed for "Company A" by the processing explained using the flowchart in FIG.

[0299] Through the above process, the reason and group identifier were associated with each inquiry information to be analyzed for "Company A." In addition, the statistical processing results of the inquiry information were associated with the organization identifier "Company A" or the identifiers of each department of Company A.

[0300] Furthermore, the representative inquiry information of each of the two or more groups may be notified to, for example, a person in charge or a representative of company A.

[0301] (Example 3) The improvement acquisition unit 138 acquires two or more pieces of inquiry information paired with the organization identifier of the organization of interest (here, "Company A") from the inquiry management table (FIG. 16). The improvement acquisition unit 138 also refers to the page storage unit 114 and acquires one or more web pages paired with the organization identifier "Company A."

[0302] Next, the improvement acquisition unit 138 acquires an improvement suggestion prompt from the prompt management table (Figure 18). Then, the improvement acquisition unit 138 places the acquired two or more pieces of inquiry information in the variable <inquiry set> of the improvement suggestion prompt (Figure 18). Furthermore, the improvement acquisition unit 138 places the acquired one or more web pages in the variable <web page> of the improvement suggestion prompt (Figure 18). Then, the improvement acquisition unit 138 constructs an improvement suggestion prompt to be provided to the generation AI. Next, the improvement acquisition unit 138 provides the improvement suggestion prompt to the generation AI. Then, the improvement acquisition unit 138 acquires a response from the generation AI. Next, the improvement acquisition unit 138 acquires one or more improvement suggestions from the response, and stores the one or more improvement suggestions in pairs with the organization identifier "Company A" of the organization of interest. An example of such an improvement suggestion is shown in Figure 19.

[0303] As described above, according to this embodiment, it is possible to automatically determine the department to which a user should respond in response to an inquiry about a target.

[0304] Furthermore, according to this embodiment, it is possible to obtain statistical processing results for inquiries for each channel of the inquiry.

[0305] Furthermore, according to this embodiment, two or more inquiries can be used to automatically determine two or more reasons for the inquiries, and two or more inquiries can be classified using the two or more reasons.

[0306] Furthermore, according to this embodiment, two or more inquiries can be grouped into two or more groups, and a representative inquiry can be determined from each of the two or more groups.

[0307] Furthermore, according to this embodiment, it is possible to propose improvements to a web page using inquiries about a target from a user.

[0308] Furthermore, according to this embodiment, it is possible to make suggestions for improving a web page using inquiries and responses from users regarding a target.

[0309] Furthermore, according to this embodiment, it is possible to determine a department only for inquiry information that requires processing.

[0310] In the above embodiment, the representative determination unit 137 may determine one or more pieces of representative inquiry information, and then the group determination unit 136 may determine that each piece of inquiry information other than the representative inquiry information belongs to the group to which the closest (most similar) representative inquiry information belongs from among the determined two or more pieces of representative inquiry information.

[0311] The processing in this embodiment may be implemented by software. This software may be distributed by software download or the like. Furthermore, this software may be recorded on a recording medium such as a CD-ROM and distributed. This also applies to other embodiments in this specification. The software implementing the inquiry processing device 1 in this embodiment is the following program. That is, this program causes a computer to function as an inquiry reception unit that receives inquiry information, which is information about a user's inquiry from one or more channels; a department determination means that uses department information about two or more departments stored in a department management unit to determine a department corresponding to the inquiry information received by the inquiry reception unit and acquires a department identifier for the department; and a department inquiry processing unit that processes the inquiry information using the department identifier acquired by the department determination means.

[0312] FIG. 20 is a block diagram of a computer system 300 that executes the programs described in this specification to realize the query processing device 1 and the like according to the various embodiments described above.

[0313] In FIG. 20, a computer system 300 includes a computer 301 including a CD-ROM drive, a keyboard 302, a mouse 303, and a monitor 304.

[0314] 20, computer 301 includes, in addition to CD-ROM drive 3012, MPU 3013, bus 3014 connected to CD-ROM drive 3012 etc., ROM 3015 for storing programs such as a boot-up program, RAM 3016 connected to MPU 3013 for temporarily storing instructions of application programs and providing temporary storage space, and hard disk 3017 for storing application programs, system programs, and data. Although not shown here, computer 301 may further include a network card for providing connection to a LAN.

[0315] A program that causes the computer system 300 to execute the functions of the inquiry processing device 1 of the above-described embodiment, etc., may be stored on a CD-ROM 3101, inserted into the CD-ROM drive 3012, and then transferred to the hard disk 3017. Alternatively, the program may be transmitted to the computer 301 via a network (not shown) and stored on the hard disk 3017. The program is loaded into the RAM 3016 when executed. The program may also be loaded directly from the CD-ROM 3101 or the network.

[0316] The program does not necessarily include an operating system (OS) or a third-party program that causes the computer 301 to execute functions such as the query processing device 1 of the above-described embodiment. The program need only include instructions that call appropriate functions (modules) in a controlled manner to achieve the desired results. How the computer system 300 operates is well known, and a detailed description thereof will be omitted.

[0317] In addition, in the above program, the steps of transmitting information and receiving information do not include processing performed by hardware, such as processing performed by a modem or interface card in the transmission step (processing that can only be performed by hardware).

[0318] The computer that executes the program may be a single computer or a plurality of computers, that is, it may perform centralized processing or distributed processing.

[0319] Furthermore, in each of the above embodiments, it goes without saying that two or more communication means present in one device may be physically realized by one medium.

[0320] Furthermore, in each of the above embodiments, each process may be realized by centralized processing in a single device, or may be realized by distributed processing in a plurality of devices.

[0321] The present invention is not limited to the above-described embodiment, and various modifications are possible, and it goes without saying that these modifications are also included within the scope of the present invention. [Industrial Applicability]

[0322] As described above, the inquiry processing device 1 of the present invention has the effect of being able to utilize inquiries from users to improve management, etc., as a result of being unable to properly process inquiries from users regarding targets, and is useful as a server, etc. that processes inquiry information sent from one or more call centers. [Explanation of symbols]

[0323] A. Information Systems 1. Inquiry processing device 2. Terminal Device 3 Generation AI device 11 Storage area 12 Reception 13 Processing section 14 Output section 21 Terminal storage section 22 Terminal Reception 23 Terminal processing section 24 Terminal transmitter 25 Terminal receiving section 26 Terminal Output Unit 111 Department Management Department 112 Inquiry Management Department 113 Prompt Management Department 114 Page Storage 121 Inquiry Reception Department 130 Judgment Department 131 Inquiry Analysis Department 132 Department Inquiry Processing Unit 133 Inquiry Storage Unit 134 Classification determination unit 135 Classification Department 136 Group Decision Department 137 Representative Determination Department 138 Improvement Acquisition Department 139 Statistical Processing Unit 141 Representative output section 142 Improved Output Section 143 Statistics output section 1311 Channel Acquisition Method 1312 Department determination means 1313 Query attribute value acquisition means

Claims

1. an inquiry receiving unit that receives inquiry information that is information on user inquiries from each of two or more channels; a department determination unit that determines a department corresponding to the inquiry information received by the inquiry receiving unit using department information of two or more departments stored in a department management unit in which department information relating to each of the two or more departments is stored, and acquires a department identifier of the department; a department inquiry processing unit that processes the inquiry information using the department identifier acquired by the department determination means; an inquiry storage unit that stores the inquiry information received by the inquiry reception unit in an inquiry management unit that stores one or more pieces of inquiry information, in a pair with a channel identifier that identifies a channel of the inquiry; a statistical processing unit that acquires a statistical processing result for the inquiry information for each of the two or more channel identifiers; a statistical output unit that outputs the statistical processing result acquired by the statistical processing unit, The department inquiry processing unit a notification process of acquiring contact information paired with the department identifier acquired by the department determination means from a department management unit that stores one or more department information pieces having contact information corresponding to the department identifier, and transmitting the inquiry information accepted by the inquiry acceptance unit or information based on the inquiry information to the contact point indicated by the contact information; a storage process for storing the inquiry information received by the inquiry receiving unit or information based on the inquiry information in a pair with the department identifier acquired by the department determination means; or For each of the two or more department identifiers, perform a statistical process to obtain the number or percentage of the inquiry information using one or more pieces of inquiry information paired with the department identifier; The inquiry receiving unit Also receiving response information corresponding to the inquiry information; an improvement acquisition unit that refers to a page storage unit in which a web page is stored, calculates a similarity between each of two or more processing units in the web page and each of the two or more pieces of inquiry information accepted by the inquiry acceptance unit, and acquires an improvement proposal that encourages adding to the web page the answer information for the inquiry information for which there is no processing unit that satisfies an adoption condition that the similarity is equal to or greater than a threshold; and an improvement output unit that outputs the improvement proposal.

2. an inquiry receiving unit that receives inquiry information that is information on user inquiries from each of two or more channels; a department determination unit that determines a department corresponding to the inquiry information received by the inquiry receiving unit using department information of two or more departments stored in a department management unit in which department information relating to each of the two or more departments is stored, and acquires a department identifier of the department; a department inquiry processing unit that processes the inquiry information using the department identifier acquired by the department determination means; an inquiry storage unit that stores the inquiry information received by the inquiry reception unit in an inquiry management unit that stores one or more pieces of inquiry information, in a pair with a channel identifier that identifies a channel of the inquiry; a statistical processing unit that acquires a statistical processing result for the inquiry information for each of the two or more channel identifiers; a statistical output unit that outputs the statistical processing result acquired by the statistical processing unit, The department inquiry processing unit a notification process of acquiring contact information paired with the department identifier acquired by the department determination means from a department management unit that stores one or more department information pieces having contact information corresponding to the department identifier, and transmitting the inquiry information accepted by the inquiry acceptance unit or information based on the inquiry information to the contact point indicated by the contact information; a storage process for storing the inquiry information received by the inquiry receiving unit or information based on the inquiry information in a pair with the department identifier acquired by the department determination means; or For each of the two or more department identifiers, perform a statistical process to obtain the number or percentage of the inquiry information using one or more pieces of inquiry information paired with the department identifier; an improvement acquisition unit that provides the generation AI with an improvement proposal prompt, which is a prompt for acquiring improvement proposals for the web page and is stored in the prompt management unit and is one or more pieces of inquiry information and web pages in the inquiry management unit, and acquires the improvement proposals from the generation AI; and an improvement output unit that outputs the improvement proposal.

3. an inquiry receiving unit that receives inquiry information that is information on user inquiries from each of two or more channels; a department determination unit that determines a department corresponding to the inquiry information received by the inquiry receiving unit using department information of two or more departments stored in a department management unit in which department information relating to each of the two or more departments is stored, and acquires a department identifier of the department; a department inquiry processing unit that processes the inquiry information using the department identifier acquired by the department determination means; an inquiry storage unit that stores the inquiry information received by the inquiry reception unit in an inquiry management unit that stores one or more pieces of inquiry information, in a pair with a channel identifier that identifies a channel of the inquiry; a statistical processing unit that acquires a statistical processing result for the inquiry information for each of the two or more channel identifiers; a statistical output unit that outputs the statistical processing result acquired by the statistical processing unit, The department inquiry processing unit a notification process of acquiring contact information paired with the department identifier acquired by the department determination means from a department management unit that stores one or more department information pieces having contact information corresponding to the department identifier, and transmitting the inquiry information accepted by the inquiry acceptance unit or information based on the inquiry information to the contact point indicated by the contact information; a storage process for storing the inquiry information received by the inquiry receiving unit or information based on the inquiry information in a pair with the department identifier acquired by the department determination means; or For each of the two or more department identifiers, perform a statistical process to obtain the number or percentage of the inquiry information using one or more pieces of inquiry information paired with the department identifier; a group determination unit that groups the two or more pieces of inquiry information received by the inquiry reception unit and determines two or more groups; a representative determination unit that determines, for each of the two or more groups, representative inquiry information that is inquiry information that represents the group; and a representative output unit that outputs the representative inquiry information determined by the representative determination unit.

4. an inquiry receiving unit that receives inquiry information that is information on user inquiries from each of two or more channels; a department determination unit that determines a department corresponding to the inquiry information received by the inquiry receiving unit using department information of two or more departments stored in a department management unit in which department information relating to each of the two or more departments is stored, and acquires a department identifier of the department; a department inquiry processing unit that processes the inquiry information using the department identifier acquired by the department determination means; an inquiry storage unit that stores the inquiry information received by the inquiry reception unit in an inquiry management unit that stores one or more pieces of inquiry information, in a pair with a channel identifier that identifies a channel of the inquiry; a statistical processing unit that acquires a statistical processing result for the inquiry information for each of the two or more channel identifiers; a statistical output unit that outputs the statistical processing result acquired by the statistical processing unit, The department inquiry processing unit a notification process of acquiring contact information paired with the department identifier acquired by the department determination means from a department management unit that stores one or more department information pieces having contact information corresponding to the department identifier, and transmitting the inquiry information accepted by the inquiry acceptance unit or information based on the inquiry information to the contact point indicated by the contact information; a storage process for storing the inquiry information received by the inquiry receiving unit or information based on the inquiry information in a pair with the department identifier acquired by the department determination means; or For each of the two or more department identifiers, perform a statistical process to obtain the number or percentage of the inquiry information using one or more pieces of inquiry information paired with the department identifier; The system further includes a determination unit that determines whether or not information based on user voice information in the inquiry information received by the inquiry reception unit is silent information, or whether or not the inquiry information received by the inquiry reception unit includes only a greeting, The department determination means An inquiry processing device in which the judgment unit does not acquire a department identifier for inquiry information in which the judgment unit determines that the information based on the user's voice information in the inquiry information received by the inquiry reception unit is silent information, or that the inquiry information received by the inquiry reception unit contains only a greeting.

5. The system further includes a determination unit that determines whether or not information based on user voice information in the inquiry information received by the inquiry reception unit is silent information, or whether or not the inquiry information received by the inquiry reception unit includes only a greeting, The department determination means The inquiry processing device of claim 1, wherein the judgment unit does not acquire a department identifier for inquiry information for which the judgment unit determines that the information based on the user's voice information in the inquiry information received by the inquiry reception unit is silent information, or that the inquiry information received by the inquiry reception unit contains only a greeting.

6. The system further includes a determination unit that determines whether or not information based on user voice information in the inquiry information received by the inquiry reception unit is silent information, or whether or not the inquiry information received by the inquiry reception unit includes only a greeting, The department determination means The inquiry processing device of claim 2, wherein the judgment unit does not acquire a department identifier for inquiry information for which the judgment unit determines that the information based on the user's voice information in the inquiry information received by the inquiry reception unit is silent information, or that the inquiry information received by the inquiry reception unit contains only a greeting.

7. The system further includes a determination unit that determines whether or not information based on user voice information in the inquiry information received by the inquiry reception unit is silent information, or whether or not the inquiry information received by the inquiry reception unit includes only a greeting, The department determination means The inquiry processing device of claim 3, wherein the judgment unit does not acquire a department identifier for inquiry information for which the judgment unit determines that the information based on the user's voice information in the inquiry information received by the inquiry reception unit is silent information or that the inquiry information received by the inquiry reception unit contains only a greeting.

8. 8. An inquiry processing method comprising all of the processes performed by the inquiry processing device according to claim 1.

9. Computer, A program for causing the query processing device according to any one of claims 1 to 7 to function.

Images