JP6598418B1 - Information output device, information output method, and program - Google Patents

Abstract

Conventionally, it has been difficult to retrieve information by accepting a dynamically changing conversation sentence even in a query for obtaining the same search result. An information output device includes a conversation sentence receiving unit that receives a conversation sentence, an intent determination part that determines an intent corresponding to the conversation sentence, and one or more conversation sentence information corresponding to the intent. A conversation sentence information determination unit that determines conversation sentence information that most closely approximates the conversation sentence, and one or more entities corresponding to one or more entities associated with the conversation sentence information. An entity acquisition unit for acquiring an entity; a parameter acquisition unit for acquiring one or more parameters corresponding to the one or more entities; an API information acquisition unit for acquiring API information corresponding to the intent; A query information configuration unit that configures query information using the parameters and the API information, a search unit that executes the query information and obtains a search result, and a search result output ; And a part. [Selection] Figure 1

Description

  The present invention relates to an information output device or the like that receives a conversation sentence, searches information in a database in an organization such as a company, and outputs the result.

Conventionally, in order to search information in a database in an organization, for example, a technique for creating a dedicated program or acquiring information from a database using a search tool and outputting the information is used.
In recent years, there has been a technique for searching the Internet with words uttered by a user and turning on / off a predetermined device (for example, see Non-Patent Document 1).

“Siri”, [online], Apple Inc., [Research May 17, 1966], Internet [URL: https://www.apple.com/jp/siri/]

  However, a conversational sentence (which may be called a natural language sentence) changes dynamically depending on, for example, a person who issues the query or an organization such as a company to which the person belongs even if the query is for the same search result. For example, there are many conversations that ask about the overtime hours of a specific employee for a specific month, such as “Tell me about Nakamura's overtime hours last month” or “Tell me about Ichiro Nakamura's overtime last month.” To do.

  In the conventional technology as described above, it has been difficult to search for information by accepting a dynamically changing conversation sentence even in a query for the same search result.

  The information output device according to the first aspect of the invention is information managed for each business process, and includes an intent storage unit that stores one or more intents that are information having an action name that identifies the business process, An API information storage unit for storing one or more API information, which is information associated with a tent, information for performing information search, and information including information for specifying a parameter that is one or more variables; A corpus storage unit that stores one or more pieces of conversational sentence information that is information associated with an intent, and is one of one or more entities that are words associated with one or more pieces of conversational sentence information. An entity storage unit to be stored; a conversation sentence reception unit that receives a conversation sentence; an intent determination part that determines an intent corresponding to the conversation sentence received by the conversation sentence reception unit; and an intent A conversational sentence information determination unit for determining conversational sentence information that is closest to the conversational sentence received by the conversational sentence reception unit from one or more conversational sentence information corresponding to the intent determined by the fixed part; An entity acquisition unit that acquires one or more entities corresponding to one or more entities associated with the conversation sentence information determined by the department and that is a word of the conversation sentence received by the conversation sentence reception unit; A parameter acquisition unit that acquires one or more parameters corresponding to each of the one or more entities acquired by the API, and an API information acquisition unit that acquires API information corresponding to the intent determined by the intent determination unit from the API information storage unit. Inquiry information for searching for information using one or more parameters acquired by the parameter acquisition unit and API information acquired by the API information acquisition unit A query information configuration unit, a search unit that executes the query information configured by the query information configuration unit, acquires a search result, and a search result output unit that outputs the search result acquired by the search unit It is the information output device which comprises.

  With this configuration, it is possible to accept a conversation sentence that changes dynamically even in an inquiry for the same search result, and to search for information.

  Further, in the information output device of the second invention, in contrast to the first invention, the intent determination unit acquires the text corresponding to the conversation sentence received by the conversation sentence reception unit, and one or more self-supporting from the text An information output device that acquires a word and determines an intent having an action name having the same or similar word as one or more independent words.

  With this configuration, it is possible to accept a conversation sentence that changes dynamically even in an inquiry for the same search result, and to search for information.

  The information output device according to the third aspect of the present invention is a day word that is a word related to the day and information related to the day corresponding to the day word and constitutes inquiry information with respect to the first or second invention. A date conversion information storage unit that stores one or more date conversion information having date information acquisition information for acquiring date information that is information used in the event, and the parameter acquisition unit includes: This is an information output device that acquires date conversion information corresponding to a day word in one or more acquired entities from the date conversion information storage unit, and acquires date information that is a parameter using the date conversion information.

  With this configuration, even a query for the same search result can accept a dynamically changing conversation sentence and appropriately search for information.

  In the above configuration, the parameter acquisition unit determines whether there is a Japanese word in one or more entities acquired by the entity acquisition unit, and the determination unit 341 determines that a Japanese word exists. In this case, there may be provided date information acquisition means for acquiring the date conversion information corresponding to the date word from the date conversion information storage unit and acquiring the day information as a parameter using the date conversion information. As a result, regardless of the presence of a Japanese word, it is possible to accept a conversation sentence that dynamically changes even in a query for the same search result, and to appropriately search for information.

  In the information output device according to the fourth aspect of the present invention, for any one of the first to third aspects, the entity in the entity storage unit is associated with the entity name that is the name of the entity, and the table is identified. An entity in which one or more entity mapping information having a table identifier, an attribute name in the table identified by the table identifier, and a translation item name that is information identifying the entity to be converted and an entity name are stored A parameter information acquisition unit, further comprising: a mapping information storage unit; and a PK item storage unit in which one or more PK items having a table identifier and a primary key identifier for specifying a primary key of a table identified by the table identifier are stored The entity that acquires the entity name corresponding to the entity acquired by the entity acquisition unit The entity name acquisition means, the translation item name acquisition means for acquiring the translation item name paired with the entity name acquired by the entity name acquisition means from the entity mapping information storage unit, and the entity name acquired by the entity name acquisition means A table identifier acquisition unit for acquiring a table identifier from the entity mapping information storage unit, a primary key identifier acquisition unit for acquiring a primary key identifier paired with the table identifier acquired by the table identifier acquisition unit from the PK item storage unit, and a table From the table identified by the table identifier acquired by the identifier acquisition unit, the attribute value of the translation item name acquired by the translation item name acquisition unit is an attribute value included in the record that matches the entity acquired by the entity acquisition unit, The primary key identifier acquired by the primary key identifier acquisition means An information output apparatus comprising a conversion parameter obtaining means for obtaining a transformed parameter which is a sexual value.

  With this configuration, even a query for the same search result can accept a dynamically changing conversation sentence and appropriately search for information.

  The information output device according to the fifth aspect of the present invention provides the inquiry information configuration unit according to any one of the first to fourth aspects, wherein the inquiry information configuration unit includes one or more variables included in the API information acquired by the API information acquisition unit. This is an information output device that configures inquiry information by arranging the parameters acquired by the parameter acquisition unit at the locations.

  With this configuration, it is possible to accept a conversation sentence that changes dynamically even in an inquiry for the same search result, and to search for information.

  In the information output device according to the sixth aspect of the present invention, with respect to any one of the first to fifth aspects, the reception unit includes a voice reception unit that receives the voice of the conversation sentence, and a voice recognition process for the voice. An information output device comprising speech recognition means for obtaining a conversational sentence that is a character string.

  With such a configuration, it is possible to receive a spoken sentence that changes dynamically even when inquiring for the same search result, and to search for information.

  According to the present invention, it is possible to search for information by receiving a dynamically changing conversation sentence even in a query for obtaining the same search result.

Block diagram of an information output device in an embodiment Flowchart explaining operation of information output device Flowchart explaining parameter acquisition processing Data structure diagram of table information Intent data structure diagram The figure which shows an example of the content of an API information storage part The figure which shows the figure which shows an example of the content of a corpus storage part The figure which shows the example of the 1 or more entity corresponding to each entity name Data structure diagram of entity mapping information Data structure diagram of PK item External view of computer system The figure which shows an example of an internal structure of a computer system

  Hereinafter, embodiments of an information output device and the like will be described with reference to the drawings. In addition, since the component which attached | subjected the same code | symbol in embodiment performs the same operation | movement, description may be abbreviate | omitted again.

  The information output device in the present embodiment is, for example, a server. The server is, for example, a server in a company that provides services such as information retrieval, but may be a cloud server, an ASP server, or the like, and the type is not limited. The server is communicably connected to one or more terminals (not shown) via a network such as a LAN or the Internet, a wireless or wired communication line, and the like. The terminal is, for example, a portable terminal of a user who uses a service such as information retrieval, but may be a stationary PC or the like, and the type is not limited. The mobile terminal is, for example, a tablet terminal, a smartphone, a mobile phone, a notebook PC, or the like, but the type is not limited.

  However, the information output device may be, for example, a stand-alone terminal, and the means for realizing it is not limited.

  FIG. 1 is a block diagram of an information output apparatus according to this embodiment. The information output device includes a storage unit 1, a reception unit 2, a processing unit 3, and an output unit 4. The storage unit 1 includes a table storage unit 11, an intent storage unit 12, an API information storage unit 13, a corpus storage unit 14, an entity storage unit 15, an entity mapping information storage unit 16, a PK item storage unit 17, and a daily conversion information storage. The unit 18 is provided. The reception unit 2 includes a conversation sentence reception unit 21. The conversation sentence receiving unit 21 includes a voice receiving unit 211 and a voice recognition unit 212.

  The processing unit 3 includes an intent determination unit 31, a conversation sentence information determination unit 32, an entity acquisition unit 33, a parameter acquisition unit 34, an API information acquisition unit 35, an inquiry information configuration unit 36, and a search unit 37. The parameter acquisition unit 34 includes a determination unit 341, a date information acquisition unit 342, an entity name acquisition unit 343, a translation item name acquisition unit 344, a table identifier acquisition unit 345, a primary key identifier acquisition unit 346, and a conversion parameter acquisition unit 347. . The output unit 4 includes a search result output unit 41.

  The storage unit 1 can store various types of information. The various information includes, for example, a table, intent, API information, corpus, entity, entity mapping information, PK item, and date conversion information. Information about the table and the like will be described later. Other information will be explained in a timely manner.

  The table storage unit 11 stores one or more tables. The table may be a tabular database, for example. For example, one or more item names are registered in the table, and further, one or more values are registered for each of the one or more item names. The item name may be referred to as an attribute name, and one or more values corresponding to one item name may be referred to as an attribute value. The table is, for example, a relational database table, TSV, Excel, CSV or the like, but the type is not limited.

  Specifically, the stored table is, for example, an employee master, a business master, a working time table, or the like. Master data related to employees is registered in the employee master. The master data relating to the employee is, for example, data such as an employee code and an employee name. Master data related to business is registered in the business master. The master data related to the business is, for example, data such as a business ID and a business name, but the type is not limited.

  Data on working hours is registered in the working time table. The data related to working hours is, for example, variable data such as date, overtime hours, total working hours, and work IDs, but the type thereof is not limited. The total working time is the sum of working hours up to regular hours and overtime hours.

  In the working time table, data relating to working hours as described above is usually registered in association with employee codes. However, the information associated with the data related to working hours may be, for example, an employee name or any information that can identify the employee.

  The intent storage unit 12 stores one or more intents. An intent is information managed for each business process. The management for each business process may be stored in the intent storage unit 12 in association with information specifying the business process, for example. The information for specifying the business process is usually an action name described later, but the format is not limited. Also, the association includes, for example, a case where the intent has information for specifying the business process.

  Business processing is processing related to business. For example, the business may be a work performed in an organization such as a company or a group. The business is, for example, working until regular time, overtime after regular time, vacation, absenteeism, A case, B case, accounting, manufacturing, etc., but the type is not limited. The business process is, for example, information retrieval. The search may be referred to as an inquiry, for example. The searched information is, for example, attendance information such as overtime hours and working hours, but may be financial information such as balances and stock prices, or operating conditions of the production line, and the contents thereof are not limited.

  However, the business process may be, for example, information registration or information-based processing (for example, salary calculation based on attendance information, financial transaction based on financial information, etc.), and the type thereof is not limited.

  An intent usually has an action name that identifies a business process. The action name is the name of the action. An action is a business process that is usually executed via an API. However, the action may be, for example, a business process executed according to an SQL statement.

  Note that the action name usually corresponds to API information described later. Therefore, it may be considered that the intent is associated with the API information via, for example, an action name.

  An intent also usually has an intent name. The intent name is the name of the intent. Therefore, the intent can be considered as information that associates the intent specified by the intent name or the intent name with the action name or the action specified by the action name.

  Specifically, the action name is, for example, “inquiry of overtime hours”, “inquiry of working hours data”, or the like, but may be any information as long as it can specify the business process.

  The API information storage unit 13 stores one or more API information. API information is information related to the API. The API is an interface for using the function of the program. The API is, for example, software such as a function, a method, or an execution module. The API is, for example, a Web API, but other APIs may be used. The Web API is an API constructed using a web communication protocol such as HTTP or HTTPS. Since API such as WebAPI is a known technique, detailed description thereof is omitted.

  API information is information associated with an intent. As described above, the API information is associated with an intent through, for example, an action name.

  The API information is usually information for performing an information search. However, the API information may be information for performing information registration or processing based on the information, for example.

  The API information has one or more parameter specifying information. The parameter specifying information is information for specifying a parameter. The parameter may be a value having a specific attribute. The value is usually a variable. Variables can be called arguments.

  The parameter is usually information obtained by converting the entity, but may be the entity itself. The parameter is, for example, an argument given to the API or a SQL statement variable.

  The parameter may be composed of a combination of an attribute name and a value, for example. The attribute name and value pair is specifically, for example, “chain_code = 2”, “sta_date = 20190401, end_date = 20190430”, etc., but the format is not limited.

  The parameter specifying information is, for example, a parameter name. The parameter name is the name of the parameter. Alternatively, the parameter specifying information is, for example, an attribute name, but may be anything as long as it is information that can specify a parameter.

  The API information is, for example, a method. For example, “search_overtime (employee code = $ 1, start date = $ 2, end date = $ 3)” or “search_work time (employee code = $ 1, work date = $ 2, work ID = $ 3) "etc., but the format is not limited. Since the method is publicly known, detailed description thereof is omitted.

  Alternatively, the API information may be, for example, an SQL sentence. The SQL statement may be a statement for making an inquiry to the database. The SQL statement is, for example, “select_overtime hours_from_table name = $ 1_where_employee code = $ 2, business date = $ 3”, but the structure is not limited. Since the SQL sentence is publicly known, detailed description thereof is omitted.

  Alternatively, the API information may be, for example, a combination of a URL and a method, and the structure thereof does not matter. Specifically, the combination of the URL and the method is, for example, “http: //develop.soppra ...? Employee code = $ 1 & start date = $ 2 & end date = $ 3”. Does not matter. Note that this type of API information may be referred to as Web API information, for example.

  The corpus storage unit 14 stores one or more pieces of conversation sentence information. The conversation sentence information is conversation sentence information. The conversation sentence information is usually an example sentence of the conversation sentence. Examples of sentences are, for example, “Tell me about the last working hours of Nakamura last month” and “Tell me about the working hours of A project yesterday in Nakamura”, etc.

  However, the conversation sentence information may be a conversation sentence template. The template may be, for example, “tell {employee entity {date entity} {overtime entity}” or “{employee entity} {date entity} {business entity} {work entity}. However, the format is not limited. Note that information represented by “{”, “}” such as {employee entity} included in the template may be called a variable, for example. The entity and the entity name such as “employee entity” will be described later.

  The conversation sentence information is usually associated with an intent. In other words, the corpus storage unit 14 stores, for example, one or more pieces of conversation sentence information for each of one or more intents stored in the intent storage unit 12 (see FIG. 7: described later).

  Further, in the corpus storage unit 14, one or more entity information is usually stored for each one or more pieces of stored conversational sentence information. The entity information is information on one or more entities associated with one conversation sentence information. When the conversation sentence information is an example sentence, the entity information includes, for example, an entity, a start position, an end position, and an entity name.

  The entity included in the entity information is a representative value among one or more entities corresponding to the entity name included in the entity information. The representative value is, for example, the first entity among one or more entities corresponding to one entity name, but may be any entity.

  The start position is a position where the entity starts in the conversation sentence information. The start position is expressed by a value (for example, “1”, “4”, etc.) indicating the number of the first character of the entity in the character string constituting the conversation sentence, for example. Similarly, the end position is a position at which the entity ends in the conversation sentence information. For example, a value (for example, “2”, “5”, etc.) indicating what number the last character of the entity is. ). However, the expression format of the start position and the end position is not limited. Note that the start position and the end position may be referred to as offsets. Further, the offset may be expressed by the number of bytes, and the format is not limited.

  The entity name is the name of the entity. The entity name is, for example, “employee entity”, “date entity”, “overtime hours entity”, or the like, but any format can be used as long as it is information that can express the attributes of the entity. An employee entity is an entity related to an employee. A date entity is an entity related to a date. The overtime hours entity is an entity related to overtime hours.

  Alternatively, the entity information may include, for example, an entity name and order information when the conversational sentence information is a template. The order information is a value indicating what number variable the entity name corresponds to in one or more variables included in the template. However, the structure of entity information does not matter.

  Specifically, the corpus storage unit 14 includes, for example, conversation sentence information “Tell me about the last working hours of Nakamura last month” and three entity information “Nakamura, 1, 2, Employee entity”, “ “Last month, 4, 5, date entity” and “overtime hours, 7, 10, overtime entity” may be stored.

  Note that the corpus in the present embodiment may be considered as, for example, each of one or more pieces of conversation sentence information stored in the corpus storage unit 14, or one or more pieces of conversation sentence information and each piece of conversation sentence information. It can also be considered as a set of entity information associated with each other.

  The entity storage unit 15 stores one or more entities. An entity is one or more words associated with conversational sentence information. A word is a unit constituting a sentence. For example, the word may be simply referred to as “word” or “word” or may be considered as a kind of morpheme (for example, an independent word described later).

  In the entity storage unit 15, for example, one or more entities are stored in association with one or more entity names.

  The entity usually corresponds to any one or two or more pieces of conversation sentence information among one or more pieces of conversation sentence information stored in the corpus storage unit 14. Therefore, for example, one or two or more entities may be stored in the entity storage unit 15 for each one or more pieces of conversation sentence information stored in the corpus storage unit 14.

  The word associated with the conversation sentence information is usually an independent word. An independent word is a word that can constitute a phrase alone, for example, a noun, but may be a verb, an adjective, or the like. However, the associated word may be an attached word. An ancillary word is a word that cannot constitute a phrase by itself and that constitutes a phrase with another independent word, such as an auxiliary verb or a particle. That is, the corresponding word is usually an independent word, but it may be an independent word with an attached word.

  Moreover, the word which respond | corresponds may be a collocation word, for example. A collocation is a word that expresses a certain meaning by connecting two or more autonomous words, and may be called a compound word. The collocation is, for example, “overtime hours” in which “overtime” and “time” are combined, “A case” in which “A” and “case” are combined, etc., but a group of names such as “Ichiro Nakamura” However, it may be anything as long as it is a set of two or more words.

  When the conversation sentence information is an example sentence, the corresponding word is one or more words (that is, information in the conversation sentence information) included in the example sentence, but the conversation sentence information is a template. Is a word to be inserted at the position of one or two or more variables included in the template (that is, information added to the conversation sentence information).

  The entity mapping information storage unit 16 stores one or more entity mapping information. The entity mapping information may be information that associates a table identifier and a translation item name with an entity name.

  The entity mapping information includes, for example, a table identifier, a translation item name, and an entity name. The table identifier is information for identifying one or more tables stored in the table storage unit 11. The table identifier is, for example, “MST_SHAIN” or “TRN_TIME_CARD”, but may be any information as long as it can identify the table.

  The translation item name is an attribute name in the table identified by the table identifier, and is information specifying the entity to be converted. The entity to be converted is an entity to be converted to a parameter (for example, an entity “Ichiro Nakamura” to be converted to a parameter “shain_code = 1”, or an entity to be converted to a parameter “sta_date = 20190401, end_date = 20190430” “last month Etc.).

  The translation item name is, for example, an item name corresponding to a key other than the primary key among one or more item names included in the table identified by the table identifier, and the item name converted to the item name corresponding to the primary key It may be. The item name corresponding to the primary key is, for example, a primary key identifier.

  The translation item name is, for example, “SHAIN_CODE” or “TIME_CARD_DATE”, but may be anything as long as it can identify the entity to be converted.

  The PK item storage unit 17 stores one or more PK items. The PK item is an item corresponding to the primary key. The PK item has, for example, a table identifier and a primary key identifier. The primary key identifier is information for specifying the primary key of the table identified by the table identifier.

  The primary key identifier is, for example, “SHAIN_CODE” in the case of a table identified by the table identifier “MST_SHAIN” (hereinafter referred to as “employee master”), and the table identified by the table identifier “TRN_TIME_CARD” (hereinafter referred to as “working time table”). There are two cases, “SHAIN_CODE” and “TIME_CARD_DATE”.

  The date conversion information storage unit 18 stores one or more date conversion information. The date conversion information is information for converting a day word into a date. The day word is a word related to the day. The day word is usually a word associated with the entity name “date entity”, for example, “last month”, “yesterday”, “last week”, “this year”, “this month”, “last year”, “previous term” “This year” or the like, but any information that can be converted into a date is acceptable.

  The date conversion information includes date words and date information acquisition information. The day information acquisition information is information for acquiring day information. The day information is information related to the day corresponding to the day word, and is information used when constructing the inquiry information. The date information may be, for example, information indicating a date such as “April 1”, or may be information indicating a period from the start date to the end date such as “4/1 to 4/30”. It doesn't matter. The date information acquisition information is, for example, a function name or a method name, but may be API information or a program itself, and its format is not limited.

  Specifically, the date information acquisition information for the date word “last month” includes, for example, current time information (for example, “May 10, 2019, 11:15”: the same applies below), and the current time information has. Get the previous month (for example, “April”) for the month (for example, “May”), refer to the calendar information for the previous month, and find the day information from the first day to the last day of the previous month ( For example, a program for acquiring “4/1 to 4/30” or the like may be used.

  Also, the date information acquisition information for the day word “this year” is obtained from, for example, the current time information and the calendar information of the year (for example, “2019”) included in the current time information, from the first day of the year. Further, API information for obtaining date information (for example, “2019/1/1 to 2019/5/10”) up to the date of the current time information may be used.

  Further, the date information acquisition information for the date word “yesterday” is a method for acquiring current time information and acquiring date information (for example, “5/9”) of the day before the date included in the current time information, or The method name may be used.

  The accepting unit 2 accepts various types of information. The various information is, for example, a conversation sentence. The receiving unit 2 receives information such as a conversation sentence from a terminal, for example, but may receive the information via an input device such as a keyboard, a touch panel, or a microphone. Or the reception part 2 may receive the information read from recording media, such as a disk and a semiconductor memory, for example, and the aspect of the reception is not ask | required.

  The conversation sentence receiving unit 21 receives a conversation sentence. A conversation sentence is a sentence in which a person talks, and may be a sentence in a natural language. The reception of the conversation sentence is, for example, reception by voice, but may be reception by text. Voice is a voice uttered by a person. The text is a character string obtained by voice recognition of a voice uttered by a person. The character string is composed of an array of one or more characters.

  The voice receiving unit 211 receives the voice of the conversation sentence. The voice receiving unit 211 receives the voice of the conversation sentence, for example, from the terminal as a pair with the terminal identifier, but may receive the voice via the microphone. The terminal identifier is information for identifying the terminal. The terminal identifier is, for example, a MAC address, an IP address, an ID, or the like, but may be any information that can identify the terminal. The terminal identifier may be a user identifier that identifies a user of the terminal. The user identifier is, for example, an e-mail address, a telephone number, or the like, but may be an ID, an address, a name, or the like, or any information that can identify the user.

  The voice recognition unit 212 performs voice recognition processing on the voice received by the voice reception unit 211 and acquires a conversational sentence that is a character string. Note that the voice recognition process is a known technique and will not be described in detail.

  The processing unit 3 performs various processes. The various processes include, for example, an intent determination unit 31, a conversation sentence information determination unit 32, an entity acquisition unit 33, a parameter acquisition unit 34, an API information acquisition unit 35, an inquiry information configuration unit 36, a search unit 37, and a determination unit. 341, date information acquisition unit 342, entity name acquisition unit 343, translation item name acquisition unit 344, table identifier acquisition unit 345, primary key identifier acquisition unit 346, conversion parameter acquisition unit 347, and the like. In addition, the various types of processing include, for example, various types of determination described with reference to flowcharts.

  For example, the processing unit 3 performs processing such as the intent determination unit 31 in response to the conversation sentence receiving unit 21 receiving the conversation sentence. When a conversation sentence is transmitted from one or more terminals in pairs with the terminal identifier, the processing unit 3 performs the processing of the intent determination unit 31 and the like for each of the one or more terminal identifiers.

  The intent determination unit 31 determines an intent corresponding to the conversation sentence received by the conversation sentence reception unit 21.

  Specifically, the intent determination unit 31 first acquires, for example, text corresponding to the conversation sentence received by the conversation sentence reception unit 21. As described above, the text is, for example, the result of voice recognition of the conversation sentence received by the conversation sentence reception unit 21, but may be the conversation sentence itself received by the conversation sentence reception unit 21.

  That is, when a conversational sentence that is a voice is received, the intent determination unit 31 recognizes the conversational sentence by voice and acquires text. In addition, when the conversation sentence which is a text is received, the intent determination part 31 should just acquire the said text.

  Next, the intent determination unit 31 acquires one or more independent words from the text by performing, for example, morphological analysis on the acquired text. Note that morphological analysis is a well-known technique and will not be described in detail.

  Then, the intent determination unit 31 determines an intent having an action name having a word that is the same as or similar to the acquired one or more independent words.

  Specifically, for example, a synonym dictionary is stored in the storage unit 1. A synonym dictionary is a dictionary related to synonyms. In the synonym dictionary, for each action name constituting one or more intents stored in the intent storage unit 12, a word that the action name has and one or more synonyms of the word are registered. ing. Specifically, for example, “overtime”, “overtime”, and the like may be registered in association with the word “overtime” included in the action name “overtime inquiry”.

  For example, when the conversation sentence receiving unit 21 accepts the conversation sentence “Tell me about last month's overtime hours in Otsuka”, the intent determination unit 31 reads “Otsuka”, “Last month”, and “Overtime hours” from the conversation sentence. One or more independent words such as the above are acquired, and the intent storage unit 12 is searched using each independent word as a key to determine whether there is an intent having an action name that matches the independent word. The match is, for example, complete match, but may be partial match. When there is an intent having an action name having a word that matches the independent word, the intent determination unit 31 determines the intent. In this example, since there is an intent having the action name “refer to overtime hours” having the word “overtime hours” that matches the independent word “overtime hours”, the intent is determined.

  When there is no intent having an action name having a word that matches the independent word, for example, the intent determining unit 31 selects one synonym from one or more synonyms corresponding to the independent word from the synonym dictionary. And the intent storage unit 12 is searched using the one synonym as a key to determine whether there is an intent having an action name having a word that matches the one synonym. When there is an intent having an action name having a word that matches the one synonym, the intent determination unit 31 determines the intent. When there is no such intent, the intent determination unit 31 performs the same processing for other synonyms and determines the intent. If there is no such intent for any of the synonyms, the intent determination unit 31 may output that the intent is not determined.

  The conversational sentence information determining unit 32 searches the corpus storage unit 14 using the intent determined by the intent determining part 31 as a key, and the conversational sentence receiving unit 21 from one or more pieces of conversational sentence information corresponding to the intent. The conversation sentence information that is most similar to the conversation sentence accepted by is determined.

  The conversation sentence information closest to the conversation sentence is, for example, conversation sentence information having the highest similarity to the conversation sentence. That is, the conversation sentence information determination unit 32 calculates, for example, the similarity between the accepted conversation sentence and one or more pieces of conversation sentence information corresponding to the determined intent, and the conversation sentence information having the maximum similarity. To decide.

  Or the conversation sentence information determination part 32 may search for the conversation template which corresponds to the template which made the position of the noun of the accepted conversation sentence the variable, for example. That is, the corpus storage unit 14 stores a template in which one or more entity names are variables. The conversation sentence information determination unit 32 stores one or more entity names of the accepted conversation sentence. And the template corresponding to the position of the acquired entity name is determined as the conversation sentence information. The position of one or more entity names in the conversation sentence is information indicating the number of entity names in the template having one or more entity names.

  The entity acquisition unit 33 corresponds to one or more entities associated with the conversation sentence information determined by the conversation sentence information determination unit 32, and is one or more words that are included in the conversation sentence received by the conversation sentence reception unit 21. Get the entity.

  The entity acquisition unit 33 acquires, for example, the start position and the end position of the entity from the corpus storage unit 14 for each of one or more entities associated with the determined conversation sentence information, and from the accepted conversation sentence The word specified by the start position and the end position is acquired.

  Specifically, as described above, for example, in the corpus storage unit 14, the conversation sentence information “Tell me about Nakamura's last overtime hours last month” and the corresponding three entity information “Nakamura, 1, 2, and employees” Entity ”,“ Last month, 4, 5, date entity ”, and“ Overtime hours, 7, 10, overtime entity ”are stored, and the conversation sentence reception unit 21 teaches the conversation sentence“ Otsuka last month overtime hours. ”And the conversation sentence information determining unit 32 determines the above-mentioned conversation sentence information“ Tell me about the last overtime hours of Nakamura last month ”, the entity acquisition unit 33 determines the accepted conversation sentence“ Otsuka last month overtime hours ” From the word “Otsuka” identified by the start position “1” and end position “2” of the first entity information, and the start position “4” and end position of the second entity information 5 "and the word" last month "specified by the starting position with the third entity information" acquires the word "overtime" specified by 7 "and the end position" 10 ".

  The parameter acquisition unit 34 acquires one or more parameters corresponding to the one or more entities acquired by the entity acquisition unit 33.

  The acquired parameter is, for example, the acquired entity itself, but may be information obtained by converting the acquired entity. That is, for example, when a date word is included in one or more acquired entities, the parameter acquisition unit 34 converts the date word into date information that is a parameter.

  The determination unit 341 configuring the parameter acquisition unit 34 determines whether or not a day word exists in one or more entities acquired by the entity acquisition unit 33. Specifically, for example, one or two or more date words are stored in the storage unit 1, and the determination unit 341 matches any one of the stored date words for each acquired one or more entities. When the determination result for at least one entity indicates a match, it is determined that a Japanese word exists in the acquired one or more entities.

  The date information acquisition unit 342 acquires date conversion information corresponding to the date word from the date conversion information storage unit 18 when the determination unit 341 determines that a date word exists in the acquired one or more entities. Using the date conversion information, date information that is a parameter is acquired.

  Specifically, for example, the storage unit 1 stores the Japanese word “last month” and the like, and the conversation sentence “Tell me about overtime last month in Otsuka” is accepted, and the three entities “Otsuka”, “ When “last month” and “overtime hours” are acquired, the determination unit 341 determines that a day word exists in the acquired three entities because the entity “last month” matches the day word “last month”. To do. For example, current time information is acquired, and date information (for example, “4/1 to 4/30”, etc.) is acquired.

  The day information acquisition unit 342 acquires day information acquisition information (for example, a program) corresponding to the day word “last month” from the day conversion information storage unit 18. Then, the date information acquisition means 342 acquires current time information (for example, “11:15 on May 10, 2019”) from the MPU built-in clock, NTP server, or the like using the date information acquisition information. The previous month (for example, “April”) is acquired with respect to the month (for example, “May”) that the current time information has. The day information acquisition unit 342 acquires date information “April 1 to April 30” from the first day to the last day of the previous month with reference to the calendar information of the previous month.

  When the date word acquired from the conversation sentence is “this year”, the date information acquisition unit 342 converts the date information acquisition information (for example, API information) corresponding to the date word “this year” into the date conversion information storage unit. 18 from. Then, the date information acquisition unit 342 acquires current time information from a built-in clock or the like using the date information acquisition information, and refers to calendar information of a year (for example, “2019”) included in the current time information. The date information (for example, “2019/1/1 to 2019/5/10”) from the first day of the year to the date of the current time information is acquired.

  When the acquired date word is “Yesterday”, the date information acquisition unit 342 acquires date information acquisition information (for example, a method) corresponding to the date word “Yesterday” from the date conversion information storage unit 18. . The date information acquisition unit 342 acquires the current time information from the built-in clock or the like using the date information acquisition information, and the day information (for example, “5/9” of the day before the date included in the current time information). )).

  The entity name acquisition unit 343 acquires the entity name corresponding to the entity from the entity storage unit 15 for each of the one or more entities acquired by the entity acquisition unit 33.

  The entity name corresponding to the entity is an entity name that is paired with a start position and an end position that match or are similar to the position of the entity corresponding to the entity in the conversation sentence in which the entity is acquired. The entity name acquisition unit 343 acquires the entity name corresponding to the entity from the entity storage unit 15 using, for example, entity information associated with the entity for each of the one or more entities acquired by the entity acquisition unit 33. May be.

  Specifically, for example, when three entities “Otsuka”, “Last month”, and “Overtime hours” are acquired from the accepted conversation sentence “Tell me about last month's overtime hours in Otsuka”, entity name acquisition means 343 is received from the three pieces of entity information stored in association with the conversation sentence information in the conversation sentence information “Tell me about last time in Nakamura last month” stored in the corpus storage unit 14. Using the first entity information with the same start position “1” and end position “2” as “Otsuka” in the conversation sentence “Tell me about overtime last month in Otsuka”, Employee entity "is acquired.

  In addition, the entity name acquisition unit 343, for example, includes the same start position “4” and end position “5” as the “last month” in the conversation sentence “Tell me about last month overtime of Otsuka” among the above three entity information. Use the second entity information to obtain the “date entity” associated with “last month”, and then the same start position as “overtime hours” in the conversation “Tell me about last month overtime in Otsuka” Using the third entity information having “7” and end position “10”, an “overtime hours entity” associated with “overtime hours” is acquired.

  For example, the translation item name acquisition unit 344 acquires, from the entity mapping information storage unit 16, a translation item name that is paired with the entity name for each of one or more entity names acquired by the entity name acquisition unit 343.

  Specifically, the entity mapping information storage unit 16 stores, for example, entity mapping information 1 having a table identifier “MST_SHAIN”, a translation item name “SHAIN_NAME”, and an entity name “employee entity”, a table identifier “TRN_TIME_CARD”, and a translation item. Entity mapping information 2 having name “TIME_CARD_DATE” and entity name “date entity”, and entity mapping information 3 having table identifier “TRN_TIME_CARD”, translation item name “ZIKANGAI_TIME”, and entity name “overtime entity” are stored. The entity name acquisition means 343 has three entity names “employee entity”, “date entity”, and “overtime work”. In the case of acquiring “ntity”, the translation item name acquisition unit 344 uses the three entity mapping information 1 to 3 to translate the item name “SHAIN_NAME” and the entity name “date entity” which are paired with the entity name “employee entity”. The translation item name “TIME_CARD_DATE” paired with “” and the translation item name “ZIKANGAI_TIM” paired with “overtime entity” are acquired.

  The table identifier acquisition unit 345 acquires a table identifier paired with the entity name from the entity mapping information storage unit 16 for each of one or more entity names acquired by the entity name acquisition unit 343.

  Specifically, the table identifier acquisition unit 345 uses, for example, the three entity mapping information 1 to 3 described above, the table identifier “MST_SHAIN” that is paired with the entity name “employee entity”, and the entity name “date entity”. The table identifier “TRN_TIME_CARD” to be paired and the table identifier “TRN_TIME_CARD” to be paired with the entity name “overtime entity” are acquired.

  The primary key identifier acquisition unit 346 acquires a primary key identifier that is paired with the table identifier acquired by the table identifier acquisition unit 345 from the PK item storage unit 17.

  Specifically, the PK item storage unit 17 includes, for example, a PK item 1 having a table identifier “MST_SHAIN” and a primary key identifier “SHAIN_CODE”, and a PK item having a table identifier “TRN_TIME_CARD” and a primary key identifier “SHAIN_CODE”. 2. PK item 3 having a table identifier “TRN_TIME_CARD” and a primary key identifier “TIME_CARD_DATE”, a PK item 4 having a table identifier “MST_GYOMU” and a primary key identifier “GYOUMU_ID”, and the like are stored. The acquisition unit 346 uses the PK items 1 to 4 to pair the table identifier “MST_SHAIN” with the primary key identifier “SHAIN_CODE” and the table identifier “TRN_TIME_CARD”. Becomes the primary key identifier "SHAIN_CODE", primary key identifier "TIME_CARD_DATE" become paired table identifier "TRN_TIME_CARD", and acquires the primary key identifier "GYOUMU_ID" become paired table identifier "MST_GYOUMU".

  The conversion parameter acquisition unit 347 has the attribute value of the translation item name acquired by the translation item name acquisition unit 344 from the table identified by the table identifier acquired by the table identifier acquisition unit 345, and the entity acquired by the entity acquisition unit 33. The converted parameter which is the attribute value included in the matching record and which is the attribute value of the primary key identifier acquired by the primary key identifier acquisition unit 346 is acquired.

  Specifically, the conversion parameter acquisition unit 347 determines that the attribute value of the acquired translation item name “SHAIN_NAME” from the employee master identified by the acquired table identifier “MST_SHAIN” is the acquired entity “Otsuka”. The converted parameter “chain_code = 2”, which is the attribute value included in the matching record and the attribute value of the acquired primary key identifier “SHAIN_CODE”, is acquired.

  Further, the conversion parameter acquisition unit 347 obtains attribute values of two acquired translation item names “TIME_CARD_DATE” and “SHAIN_NAME” from the working time table identified by the acquired table identifier “TRN_TIME_CARD”. Two primary key identifiers “SHAIN_CODE” that are attribute values included in the record that matches the entity “April 1 to April 30” converted from “Last month” and the acquired entity “Otsuka” And the converted parameters “chain_code = 2, sta_date = 20190401, end_date = 20190430” which are attribute values of “TIME_CARD_DATE” are acquired.

  The API information acquisition unit 35 acquires API information corresponding to the intent determined by the intent determination unit 31 from the API information storage unit 13.

  The API information acquisition unit 35 acquires, for example, API information having an action name corresponding to the intent determined by the intent determination unit 31 from the API information storage unit 13.

  Specifically, the API information storage unit 13 stores, for example, an action name “inquiry overtime” and three or more parameter specifying information “employee code, stain_code”, “start date, sta_date”, and “end date, end_date”. And API information 2 having action name “working time data inquiry” and three or more parameter specifying information “employee code, stain_code”, “work date, time_card_date”, “business ID, gyoumu_id”, etc. When the intent stored and the intent specified by the intent name “overtime inquiry intent” is acquired, the API information acquisition unit 35 acquires the API information 1 having the action name “overtime inquiry” included in the intent. To get.

  The inquiry information configuration unit 36 uses the one or more parameters acquired by the parameter acquisition unit 34 and the API information acquired by the API information acquisition unit 35 to configure the inquiry information. The inquiry information is information for searching for information, and is usually executable information. The inquiry information is, for example, a function or method in which an argument is inserted, but may be a completed SQL sentence or a combination of a URL and a parameter.

  The inquiry information configuration unit 36 is, for example, a parameter corresponding to each location at one or more variable locations included in the API information acquired by the API information acquisition unit 35, and arranges the parameters acquired by the parameter acquisition unit 34. By doing so, the inquiry information is configured.

  Specifically, for example, the inquiry information “https: // http: //www.google.com/support/index.html” where “shain_code = 2”, sta_date = 20190401 ”, and end_date” = 20190430 are arranged at each of three or more variables included in the acquired API information 1. /Develop.soppra...?chain_code=2 & sta_date = 20190401 & end_date = 20190430 "may be configured.

  The search unit 37 executes the query information configured by the query information configuration unit 36 and acquires the search result. For example, the inquiry information “https: //develop.soppra ...? Chain_code = 2 & sta_date = 20190401 & end_date = 20190430” is executed, and April 1 to April 30 of the employee “Jiro Otsuka” identified by the employee code 2 The overtime hours “0401 = 1, 0402 = 0,... 4030 = 2” corresponding to each date up to the date may be acquired. Note that the inquiry information such as SQL and the detailed operation of the search unit 37 will be described with specific examples and modifications.

  The output unit 4 outputs various information. The various information is, for example, a search result.

  For example, the output unit 4 receives information such as a search result, which is a result of the processing unit 3 performing various processes in response to the reception unit 2 receiving information such as a conversation sentence in pair with the terminal identifier. Sent to the terminal identified by the identifier. Alternatively, for example, in response to the reception unit 2 receiving information such as a conversation sentence via an input device such as a touch panel or a microphone, the output unit 4 outputs information such as a search result to an output device such as a display or a speaker. You may output via.

  However, the output unit 4 may print various types of information, for example, with a printer, store it in a recording medium, deliver it to another program, or send it to an external device. An aspect is not ask | required.

  The search result output unit 41 outputs the search result acquired by the search unit 37. The search result output unit 41 transmits, for example, the search result acquired by the search unit 37 in response to the conversation sentence receiving unit 21 receiving a conversation sentence paired with the terminal identifier to the terminal identified by the terminal identifier. . Alternatively, the search result output unit 41 outputs the search result acquired by the search unit 37 in response to the conversation sentence reception unit 21 receiving a conversation sentence via an input device such as a microphone, for example, as a display or a speaker. You may output via a device.

  Storage unit 1, table storage unit 11, intent storage unit 12, API information storage unit 13, corpus storage unit 14, entity storage unit 15, entity mapping information storage unit 16, PK item storage unit 17, and date conversion information storage unit 18 is preferably a non-volatile recording medium such as a hard disk or a flash memory, but can also be realized as a volatile recording medium such as a RAM.

  The process in which information is stored in the storage unit 1 or the like is not limited. For example, information may be stored in the storage unit 1 or the like via a recording medium, or information transmitted via a network, a communication line, or the like may be stored in the storage unit 1 or the like. Alternatively, information input via the input device may be stored in the storage unit 1 or the like. The input device may be anything such as a keyboard, a mouse, a touch panel, and a microphone.

  The reception unit 2, the conversation sentence reception unit 21, the voice reception unit 211, and the voice recognition unit 212 may or may not include an input device. The receiving unit 2 and the like can be realized by driver software of the input device or by the input device and its driver software.

  Processing unit 3, intent determination unit 31, conversation sentence information determination unit 32, entity acquisition unit 33, parameter acquisition unit 34, API information acquisition unit 35, inquiry information configuration unit 36, search unit 37, determination means 341, date information The acquisition unit 342, the entity name acquisition unit 343, the translation item name acquisition unit 344, the table identifier acquisition unit 345, the primary key identifier acquisition unit 346, and the conversion parameter acquisition unit 347 can be usually realized by an MPU, a memory, or the like. The processing procedure of the processing unit 3 or the like is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, the processing procedure may be realized by hardware (dedicated circuit).

  The output unit 4 and the search result output unit 41 may or may not include an output device such as a display or a speaker. The output unit 4 and the like can be realized by driver software of the output device, or by the output device and its driver software.

  The reception function of the reception unit 2 or the like is usually realized by a wireless or wired communication means (for example, a communication module such as a network interface controller (NIC) or a modem), but a means for receiving a broadcast (for example, a broadcast) (Receiving module). In addition, the transmission function of the output unit 4 and the like is usually realized by a wireless or wired communication unit, but may be realized by a broadcasting unit (for example, a broadcasting module).

  Next, the operation of the information output apparatus will be described with reference to the flowcharts of FIGS.

  FIG. 2 is a flowchart for explaining the operation of the information output apparatus. When a conversation sentence is transmitted from one or more terminals to a pair with a terminal identifier, the flowcharts of FIGS. 2 and 3 are executed for each of the one or more terminal identifiers.

  (Step S201) The processing unit 3 determines whether or not the conversational sentence reception unit 21 has accepted a conversational sentence. When it is determined that the conversation sentence receiving unit 21 has received a conversation sentence, the process proceeds to step S202, and when it is determined that it has not been received, the process returns to step S201.

  (Step S202) The intent determination unit 31 determines an intent corresponding to the conversation sentence received in step S201 from one or more intents stored in the intent storage unit 12.

  (Step S203) The conversation sentence information determination unit 32 determines conversation sentence information that most closely approximates the conversation sentence accepted in Step S201 from one or more conversation sentence information corresponding to the intent determined in Step S202. To do.

  (Step S204) The entity acquisition unit 33 stores one or more entities corresponding to one or more entities associated with the conversation sentence information determined in step S203 and included in the conversation sentence received in step S201. Obtained from the unit 15.

  (Step S205) The parameter acquisition unit 34 executes a process of acquiring one or more parameters corresponding to the one or more entities acquired in step S204 (hereinafter may be referred to as a parameter acquisition process). The parameter acquisition process will be described with reference to FIG.

  (Step S206) The API information acquisition unit 35 acquires API information corresponding to the intent determined in Step S202 from the API information storage unit 13.

  (Step S207) The inquiry information configuration unit 36 configures inquiry information using the one or more parameters acquired in step S205 and the API information acquired in step S206.

  (Step S208) The search unit 37 executes the inquiry information configured in step S207, and acquires the search result.

  (Step S209) The search result output unit 41 outputs the search result acquired in step S208. Thereafter, the process returns to step S201.

  In the flowchart of FIG. 2, the process starts in response to power-on of the information output device or program startup, and the process ends by power-off or a process end interrupt. However, the trigger for starting or ending the process does not matter.

  FIG. 3 is a flowchart for explaining the parameter acquisition processing in step S205.

  (Step S301) The parameter acquisition unit 34 sets an initial value 1 to the variable i. The variable i is a variable for sequentially selecting unselected entities among one or more entities acquired in step S204.

  (Step S302) The parameter acquisition unit 34 determines whether there is an i-th entity. If it is determined that there is an i-th entity, the process proceeds to step S303, and if it is determined that there is no i-th entity, the process returns to a higher-level process.

  (Step S303) The entity name acquisition unit 343 acquires the entity name corresponding to the i-th entity from the entity storage unit 15.

  (Step S304) The translation item name acquisition unit 344 acquires from the entity mapping information storage unit 16 a translation item name that is paired with the entity name acquired in step S303.

  (Step S305) The table identifier acquisition unit 345 acquires from the entity mapping information storage unit 16 a table identifier that is paired with the entity name acquired in step S303.

  (Step S306) The primary key identifier acquisition unit 346 acquires from the PK item storage unit 17 a primary key identifier that is paired with the table identifier acquired in step S305.

  (Step S307) The determination unit 341 determines whether or not the i-th entity is a Japanese word. If it is determined that the i-th entity is a Japanese word, the process proceeds to step S308. If it is determined that the i-th entity is not a Japanese word, the process proceeds to step S309.

  (Step S308) The date information acquisition unit 342 acquires date conversion information corresponding to the date word from the date conversion information storage unit 18, and uses the acquired date conversion information to set date information (start date, end) as parameters. Date).

  (Step S309) The conversion parameter acquisition unit 347 is an attribute value included in a record in which the attribute value of the translation item name matches the i-th entity from the table identified by the table identifier acquired in Step S305. The converted parameters (Shain_code = 1, sta_date = 20190401, end_date = 20190430, etc.), which are the attribute values of the primary key identifier acquired in step S306, are acquired.

  (Step S310) The parameter acquisition unit 34 increments the variable i. Thereafter, the process returns to step S302.

  Hereinafter, a specific operation example of the information output apparatus in the present embodiment will be described. The following description can be modified in various ways and does not limit the scope of the present invention.

  The information output device in this example is a stand-alone terminal. In the table storage unit 11 of the information output device, for example, three pieces of table information as shown in FIG. 4 are stored. FIG. 4 is a data structure diagram of the table information. The table information includes a table identifier and a table. Each stored table information is associated with an ID (for example, “1”, “2”, etc.).

  For example, the table information corresponding to ID “1” (hereinafter sometimes referred to as table information 1) has a table identifier “MST_SHAIN” and a first table (employee master). In the employee master, the first item name “SHAIN_CODE” and the corresponding two or more values “1”, “2”... And the second item name “SHAIN_CODE” and the corresponding two or more values “ Ichiro Nakamura, “Jiro Otsuka”, etc. are registered.

  Further, the table information 2 corresponding to the ID “2” has a table identifier “MST_GYOMU” and a second table (business master). The business master includes a first item name “GYOMU_ID” and two or more corresponding values “a”, “b”..., And a second item name “GYOMU_NAME” and two or more corresponding values “ "A case", "B case", etc. are registered.

  Further, the table information 3 includes a table identifier “TRN_TIME_CARD” and a third table (working time table). In the working time table, the first item name “TRN_TIME_CARD” and two or more corresponding values “4/1”, “4/1”... “4/2”, “4/2”. “4/30”, “4/30”..., Second item name “SHAIN_CODE” and two or more corresponding values “1”, “2”... “1”, “2”. "1", "2", third item name "ZIKANGAI_TIME" and corresponding two or more values "2", "1" ... "1", "0" ... "3", " 2 ”, the fourth item name“ TOTAL_TIME ”and two or more corresponding values“ 10 ”,“ 9 ”...“ 9 ”,“ 8 ”...“ 11 ”,“ 10 ”, and fifth Item name “GYOUMU_ID” and two or more corresponding values “a”, “b”... “A”, “b”. "Etc. are registered.

  For example, two or more intents as shown in FIG. 5 are stored in the intent storage unit 12. FIG. 5 is a data structure diagram of an intent. The intent has an intent name and an action name. Each stored intent is associated with an ID (for example, “1”, “2”, etc.).

  For example, the intent 1 corresponding to the ID “1” has an intent name “overtime inquiry intent” and an action name “overtime inquiry”. The intent 2 has an intent name “work inquiry data inquiry intent” and an action name “work inquiry data inquiry”.

  The API information storage unit 13 stores, for example, a set of pairs of action names and API information as shown in FIG. FIG. 6 is a diagram illustrating an example of the contents of the API information storage unit 13. A pair of action name and API information is, for example, a pair of action name “inquiry overtime” and API information “search_overtime (employee code, start date, end date)”, action name “inquiry of working time data” And API information “search_working time (employee code, business date, business ID)”.

  In the corpus storage unit 14, for example, as shown in FIG. 7, one or two or more pieces of conversation sentence information are stored in association with one or more pieces of each intent. Correspondingly, one or more entity information is also stored. FIG. 7 is a diagram illustrating an example of the contents of the corpus storage unit 14. The entity information includes an entity, a start position, an end position, and an entity name.

  For example, five pieces of conversational sentence information 1 to 5 are associated with the first intent “overtime hours inquiry intent”. Among them, the conversation sentence information 1 is “tell me Nakamura's last overtime hours last month”, the conversation sentence information 2 is “tell me last month Nakamura's overtime hours”, and the conversation sentence information 3 is “ “Tell me about overtime hours in Nakamura”, “Speaking overtime hours last month” is “Teach me overtime hours last month”, and Sentence information 5 is “tell me overtime hours”.

  The conversation sentence information 1 associated with the “overtime inquiry intent” includes first entity information having an entity “Nakamura”, a start position “1”, an end position “2”, and an entity name “employee entity”. , Entity “Last month”, start position “4”, end position “5”, and second entity information having entity name “date entity”, entity “overtime”, start position “7”, end position “10” ", And the third entity information having the entity name" overtime entity ".

  The conversation sentence information 2 includes the fourth entity information having the entity “Last month”, the start position “1”, the end position “2”, and the entity name “Date entity”, the entity “Nakamura”, and the start position “ The fifth entity information having 4 ”, end position“ 5 ”, and entity name“ employee entity ”, entity“ overtime hours ”, start position“ 7 ”, end position“ 10 ”, and entity name“ overtime entity ” Is associated with the sixth entity information.

  The conversation information 3 includes the seventh entity information having the entity “Nakamura”, the start position “1”, the end position “2”, and the entity name “employee entity”, the entity “overtime hours”, and the start position. The eighth entity information having “4”, end position “7”, and entity name “overtime entity” is associated.

  The conversation sentence information 4 includes the ninth entity information having the entity “last month”, the start position “1”, the end position “2”, and the entity name “date entity”, the entity “overtime hours”, and the start position. The tenth entity information having “4”, end position “7”, and entity name “overtime entity” is associated.

  Further, the conversation sentence information 5 is associated with eleventh entity information having the entity “overtime hours”, the start position “1”, the end position “4”, and the entity name “overtime entity”.

  On the other hand, for example, 15 pieces of conversation text information 1 to 15 are associated with the second intent “working time data reference intent”. Of these, Sentence Sentence 1 is “Tell me the working hours of Ichiro Nakamura yesterday's A Project”, and Sentence Sentence 2 is “Tell me how Ichiro Nakamura worked yesterday's A Cases”. The conversation sentence 15 is “tell me the working hours”. The conversation sentences 2 and below are sentences in which the order of words is changed or some words are omitted from the conversation sentence 1.

  The conversation sentence information 1 associated with the “working time data inquiry intent” includes the first entity having the entity “Ichiro Nakamura”, the start position “1”, the end position “4”, and the entity name “employee entity”. Information, entity “Yesterday”, start position “6”, end position “7”, and second entity information having entity name “date entity”, entity “working time”, start position “13”, end position “16” is associated with third entity information having the entity name “working time entity”. Each of the conversation sentences 2 to 15 is associated with one or more pieces of entity information configured in the same manner.

  For example, as shown in FIG. 8, one or more entities are stored in the entity storage unit 15 in association with one or more entity names. FIG. 8 is a diagram illustrating an example of one or more entities (hereinafter sometimes referred to as entity groups) corresponding to each entity name.

  For example, the entity group corresponding to the entity name “employee entity” includes “Ichiro Nakamura”, “Jiro Otsuka”, and the like. The entity group corresponding to the entity name “date entity” includes “last month”, “yesterday”, and the like. The entity group corresponding to the entity name “overtime entity” includes “overtime”, “overtime”, and the like. The entity group corresponding to the entity name “business entity” includes “A case”, “B case”, and the like. The entity group corresponding to the entity name “working time entity” includes “working time”, “working”, and the like.

  The entity mapping information storage unit 16 stores, for example, two or more entity mapping information (entity mapping information 1 to 4 etc.) as shown in FIG. FIG. 9 is a data structure diagram of entity mapping information. The entity mapping information includes a table identifier, a translation item name, and an entity name.

  Since entity mapping information 1 to 3 has been described above, it will not be repeated. The entity mapping information 4 has a table identifier “MST_GYOMUMU”, a translation item name “GYOUMU_ID”, and an entity name “business entity”.

  The PK item storage unit 17 stores, for example, two or more PK items (PK items 1 to 4 etc.) as shown in FIG. FIG. 10 is a data structure diagram of the PK item. The PK item has a table identifier and a primary key identifier. Since PK items 1 to 4 have been described above, they will not be repeated.

  The date conversion information storage unit 18 stores a set (not shown) of pairs of date words and date information acquisition information. The pair of the day word and the day information acquisition information is, for example, a pair of the day word “last month” and the day information acquisition information 1, a pair of the day word “yesterday” and the day information acquisition information 2, and the like. For example, the date information acquisition information 1 corresponding to the day word “last month” acquires the current time information, acquires the previous month with respect to the month included in the current time information, and refers to the calendar information of the previous month In this program, the day information from the first day to the last day of the previous month is acquired. The date information acquisition information 2 corresponding to the day word “yesterday” is a method for acquiring current time information and acquiring day information of the day before the date included in the current time information.

  The current time is 11:15 on May 10, 2019. Now, assume that the user inputs a voice message “Tell me about overtime last month in Otsuka” to the terminal.

  In the information output device, the voice receiving unit 211 receives the voice through the microphone, and the voice recognition unit 212 performs voice recognition processing on the voice, and the conversation sentence “Tell me the overtime of Otsuka last month”. get.

  The intent determination unit 31 determines an intent corresponding to the conversation sentence from two or more intents 1, 2,... Stored in the intent storage unit 12. Specifically, the intent determination unit 31 acquires, for example, three independent words “Otsuka”, “Last month”, and “Overtime” from the conversation sentence by morphological analysis, and the intent storage unit using each independent word as a key. 12 is searched to determine an intent 1 having an action name “refer to overtime hours” partially matching “overtime hours”.

  The conversation sentence information determination unit 32 refers to the corpus storage unit 14 (FIG. 7), and the conversation sentence that is closest to the conversation sentence among the five pieces of conversation sentence information 1 to 5 corresponding to the determined intent 1. Determine sentence information. Here, for the conversation sentence, only the sentence entity “Nakamura”, which is the employee entity specified by the start position “1” and the end position “2”, is different, and the other sentence is the same. The

  The entity acquisition unit 33 is an entity corresponding to the three entities “Nakamura”, “Last month”, and “Overtime hours” associated with the determined conversation sentence information 1, and includes three entities included in the conversation sentence. A certain “Otsuka”, “Last month”, and “Overtime hours” are acquired from the entity storage unit 15.

  Specifically, the conversation sentence information determination unit 32 refers to the first entity information among the first to third entity information corresponding to the conversation sentence information 1, and starts the position “1” in the conversation sentence. Then, it is determined that “Otsuka” specified by the end position “2” is an employee entity. Next, the conversation sentence information determination unit 32 refers to the entity storage unit 15 and acquires an entity “Jiro Otsuka” partially matching “Otsuka” from the entity group corresponding to the entity name “employee entity”.

  Further, the conversation sentence information determination unit 32 refers to the second entity information, and determines that “last month” specified by the start position “4” and the end position “5” in the conversation sentence is a date entity. From the entity group corresponding to the entity name “date entity”, the entity “last month” that completely matches “last month” is acquired.

  Further, the conversation sentence information determination unit 32 refers to the third entity information and determines that the “overtime hours” specified by the start position “7” and the end position “10” in the conversation sentence are overtime entities. Then, an entity “overtime hours” that completely matches “overtime hours” is acquired from the entity group corresponding to the entity name “overtime entities”.

  When the three entities “Jiro Otsuka”, “Last month”, and “Overtime hours” corresponding to the conversation sentence are acquired in this way, the parameter acquisition unit 34 acquires three parameters corresponding to the three entities. .

  Specifically, first, regarding the first entity “Jiro Otsuka”, the entity name acquisition unit 343 constituting the parameter acquisition unit 34 uses the first entity information to obtain the entity name “employee entity” from the entity storage unit 15. get. Next, the translation item name acquisition unit 344 acquires the translation item name “SHAIN_NAME” paired with the acquired entity name “employee entity” from the entity mapping information storage unit 16 using the entity mapping information 1. Further, the table identifier acquisition unit 345 acquires the table identifier “MST_SHAIN” that is paired with the acquired entity name “employee entity” from the entity mapping information storage unit 16 using the entity mapping information 1.

  Next, the primary key identifier acquisition unit 346 acquires the primary key identifier “SHAIN_CODE” paired with the acquired table identifier “MST_SHAIN” from the PK item storage unit 17 using the PK item 1. In addition, the determination unit 341 determines that the first entity “Otsuka” is not a Japanese word, and accordingly, the conversion parameter acquisition unit 347 determines the table (employee master) identified by the acquired table identifier “MST_SHAIN”. The attribute value of the translation item name “SHAIN_NAME” is the attribute value included in the record that matches the first entity “Jiro Otsuka”, and is the attribute value of the acquired primary key identifier “SHAIN_CODE”. The converted parameter “chain_code = 2” of the eye is acquired.

  Next, for the second entity “last month”, the entity name acquisition unit 343 acquires the entity name “date entity” corresponding to “last month”, and the translation item name acquisition unit 344 acquires the acquired entity name “date”. The translation item name “TIME_CARD_DATE” paired with the “entity” is acquired using the entity mapping information 2. The table identifier acquisition unit 345 acquires the table identifier “TRN_TIME_CARD” paired with the acquired entity name “date entity” from the entity mapping information storage unit 16 using the entity mapping information 2.

  Next, the primary key identifier acquisition unit 346 acquires two primary key identifiers “SHAIN_CODE” and “TIME_CARD_DATE” that are paired with the acquired table identifier “TRN_TIME_CARD” using the two PK items 2 and 3. The determination unit 341 determines that the second entity “last month” is a day word, and accordingly, the day information acquisition unit 342 stores the day conversion information corresponding to the day word “last month” in the day conversion information. The date information “4/1 to 4/30” is acquired using the acquired date conversion information.

  Specifically, the date information acquisition unit 342 acquires the current time information “May 10, 2019, 11:15” from the built-in clock or the like, and the month before “May” included in the current time information is April. The date information “4/1 to 4/30” indicating 30 days from the start date “4/1” to the end date “4/30” is acquired.

  From the table (working time table) identified by the acquired table identifier “TRN_TIME_CARD”, the conversion parameter acquisition unit 347 has the attribute value of the translation item name “TIME_CARD_DATE” corresponding to the second entity “last month”. The attribute values included in the record that matches “4/1” and the end date “4/30”, and the attribute values of the two acquired primary key identifiers “SHAIN_CODE” and “TIME_CARD_DATE” The third converted parameters “sta_date = 20190401” and “end_date = 20190430” are obtained.

  Next, for the third entity “overtime hours”, the entity name acquisition unit 343 acquires the entity name “overtime entity” corresponding to “overtime hours”, and the translation item name acquisition unit 344 acquires the acquired entity name. The translation item name “ZIKANGAI_TIME” paired with “overtime entity” is acquired using the entity mapping information 3. Further, the table identifier acquisition unit 345 acquires the table identifier “TRN_TIME_CARD” paired with the acquired entity name “overtime entity” using the entity mapping information 3.

  Since the two primary key identifiers “SHAIN_CODE” and “TIME_CARD_DATE” that are paired with the acquired table identifier “TRN_TIME_CARD” have already been acquired, the primary key identifier acquisition unit 346 normally does not acquire them. You may acquire it again.

  In addition, the determination unit 341 determines that the third entity “overtime hours” is not a day word, and the conversion parameter acquisition unit 347 has a translation item name included in the working time table identified by the acquired table identifier “TRN_TIME_CARD”. The fourth converted parameter “zikangai_time” corresponding to “ZIKANGAI_TIME” is acquired.

  In this way, when the four parameters “chain_code = 2”, “sta_date = 20190401”, “end_date = 20190430” and “zikangai_time” corresponding to the conversation sentence “Tell me about the overtime hours of Otsuka last month” are acquired, the API The information acquisition unit 35 acquires API information “search_overtime hours (employee code, start date, end date)” corresponding to the action name “overtime check” of the determined intent 1 from the API information storage unit 13. .

  The inquiry information configuration unit 36 substitutes the acquired four parameters into the corresponding variables of the acquired API information “search_overtime (employee code, start date, end date)” to obtain the inquiry information. “Search_zikangai_time (chain_code = 2, sta_date = 20190401, end_date = 20190430”) is configured.

  The search unit 37 executes the configured inquiry information and acquires a search result. Here, from the overtime table identified by the table identifier “TRN_TIME_CARD”, the value of the item name “TIME_CARD_DATE” is “4/1” to “4/30” and the value of SHAIN_CODE is “2” 30 From the records, 30 values “1, 0,... 2” corresponding to the item name “ZIKANGAI_TIME” are acquired, and a search result “20 hours” obtained by totaling the 30 values is acquired.

  The search result output unit 41 outputs a response sentence including the acquired search result “20 hours”. The output response sentence may be, for example, “20 hours” or “Otsuka-san's April overtime is 20 hours”. Specifically, for example, a template of a response sentence is stored in the storage unit 1, and the search result output unit 41 stores the search result “20 hours” and “ The response sentence may be configured by substituting “Otsuka” and “April” acquired in the search process.

  Although the detailed description is omitted, for example, for the conversation sentence “Tell me the working hours of Jiro Otsuka yesterday”, four parameters “chain_code = 2”, “time_card_date = 20190509”, “ gyoumu_id = a ”and“ total_time ”may be acquired, and the query information“ search_total_time (shain_code = 2, time_card_date = 20190509, gyomu_id = a ”may be configured.

(Modification 1)
When the API information is an SQL statement “select_overtime_from_table_name_where_employee code, business date”, the parameter acquisition unit 34 has four parameters “shain_code = 2”, “time_caid_date = 20190509”, “trn_time_card”, And “zikangai_time” may be acquired, and the inquiry information configuration unit 36 may configure the inquiry information “select_zikangai_time_from_trn_time_card_where_chain_code = 2, time_caged_date = 20190509”.

(Modification 2)
When the API information is a combination of URL and method “http: //develop.soppra ...? Employee code & start date & end date”, the parameter acquisition unit 34 has four parameters “chain_code = 2”, “Sta_date = 20190401”, “end_date = 20190430”, and “zikangai_time” are acquired, and the inquiry information configuration unit 36 obtains inquiry information “http: //develop.soppra... "May be configured.

  As described above, according to the present embodiment, the intent storage unit 12 stores one or more intents that are information managed for each business process and have an action name that identifies the business process. The information storage unit 13 stores one or more API information, which is information associated with an intent, information for performing information search, and information including information for specifying a parameter that is one or more variables. In the corpus storage unit 14, one or more pieces of conversation sentence information that is information associated with an intent and conversation sentence information is stored, and the entity storage unit 15 is associated with any one or more pieces of conversation sentence information. One or more entities that are words are stored, the information output apparatus accepts a conversation sentence, determines an intent corresponding to the accepted conversation sentence, and corresponds to the determined intent. The conversation sentence information closest to the accepted conversation sentence is determined from the above conversation sentence information, and the words of the accepted conversation sentence correspond to one or more entities associated with the decided conversation sentence information. One or more entities are acquired, one or more parameters corresponding to each acquired one or more entities are acquired, API information corresponding to the determined intent is acquired from the API information storage unit 13, and the acquired 1 By using the above parameters and the acquired API information, query information for information search is configured, the configured query information is executed, the search result is acquired, and the acquired search result is output. Even a query for the same search result can accept a dynamically changing conversation sentence and search for information.

  In addition, the information output device acquires a text corresponding to the received conversation sentence, acquires one or more independent words from the text, and has an intent having an action name having a word that is the same as or similar to the one or more independent words. By determining, it is possible to accept a conversation sentence that dynamically changes even in a query for the same search result, and to search for information.

  In addition, the date conversion information storage unit 18 acquires date information which is a word related to the date and information related to the date corresponding to the date word and which is information used when constructing the inquiry information. One or more date conversion information having date information acquisition information is stored, and the information output device acquires the date conversion information corresponding to the day word in the acquired one or more entities from the date conversion information storage unit 18, and By acquiring the day information that is a parameter using the day conversion information, it is possible to accept a conversation sentence that dynamically changes even in a query for the same search result, and to appropriately search for information.

  In the above configuration, the information output device determines whether or not a day word exists in the acquired one or more entities, and if it is determined that a day word exists, the date conversion information corresponding to the day word May be acquired from the day conversion information storage unit 18, and the day information that is a parameter may be acquired using the day conversion information. As a result, regardless of the presence of a Japanese word, it is possible to accept a conversation sentence that dynamically changes even in a query for the same search result, and to appropriately search for information.

  The entity in the entity storage unit 15 is associated with an entity name that is the name of the entity, and the entity mapping information storage unit 16 has a table identifier that identifies the table and an attribute name in the table identified by the table identifier. A table identified by the table identifier and the table identifier in the PK item storage unit 17 in which one or more entity mapping information having a translation item name and an entity name, which are information for specifying the entity to be converted, is stored. One or more PK items having a primary key identifier that identifies the primary key of the first key are stored, and the information output device acquires an entity name corresponding to the acquired entity, and sets a translation item name that is paired with the acquired entity name. Acquired from the entity mapping information storage unit 16 and acquired A table identifier paired with the entity name is acquired from the entity mapping information storage unit 16, a primary key identifier paired with the acquired table identifier is acquired from the PK item storage unit 17, and the table identified by the acquired table identifier is used. , The attribute value of the acquired translation item name is the attribute value included in the record that matches the acquired entity, and the same search result is obtained by acquiring the converted parameter that is the attribute value of the acquired primary key identifier. It can accept a dynamically changing conversation sentence even in the inquiry that is requested, and can appropriately search for information.

  In addition, the information output device is a parameter corresponding to each location at one or more variable locations included in the acquired API information, and by arranging the acquired parameters and configuring the query information, the same search result It is possible to search for information by accepting a dynamically changing conversation sentence even in a query for requesting the user.

  In addition, the information output device accepts the voice of the conversation sentence, performs voice recognition processing on the voice, and acquires the conversation sentence that is a character string, so that even the query for the same search result is based on the voice that dynamically changes You can accept conversational sentences and search for information.

  Furthermore, the processing in the present embodiment may be realized by software. Then, this software may be distributed by software download or the like. Further, this software may be recorded and distributed on a recording medium such as a CD-ROM. This also applies to other embodiments in this specification.

  In addition, the software which implement | achieves the information output device in this Embodiment is the following programs, for example. That is, this program is information managed for each business process, and is associated with the intent storage unit 12 in which one or more intents that are information having an action name for identifying the business process are stored. API information storage unit 13 that stores one or more API information that is information for performing information retrieval and information that specifies parameters that are one or more variables. The corpus storage unit 14 that stores one or more pieces of conversation sentence information that is information attached to the conversation sentence, and an entity that stores one or more entities that are words associated with any one or more pieces of conversation sentence information A computer that can access the storage unit 15 corresponds to a conversation sentence receiving unit 21 that receives a conversation sentence, and a conversation sentence received by the conversation sentence receiving unit 21. An intent determination unit 31 that determines an intent, and one or more conversational sentence information corresponding to the intent determined by the intent determination unit 31 is the closest to the conversational sentence received by the conversational sentence reception unit 21 Corresponding to the conversation sentence information determining section 32 for determining the conversation sentence information to be performed and one or more entities associated with the conversation sentence information determined by the conversation sentence information determining section 32, the conversation sentence receiving section 21 receives the conversation sentence information. An entity acquisition unit 33 that acquires one or more entities that are words included in the conversation sentence; a parameter acquisition unit 34 that acquires one or more parameters corresponding to each of the one or more entities acquired by the entity acquisition unit 33; An API information acquisition unit that acquires API information corresponding to the intent determined by the intent determination unit 31 from the API information storage unit 13. 5, one or more parameters acquired by the parameter acquisition unit 34, and API information acquired by the API information acquisition unit 35, a query information configuration unit 36 that configures query information for information search In order to function as the search unit 37 that executes the query information configured by the query information configuration unit 36 and acquires the search result, and the search result output unit 41 that outputs the search result acquired by the search unit 37 It is a program.

  FIG. 11 is an external view of a computer system 900 that realizes an information output apparatus by executing a program according to the present embodiment. The present embodiment can be realized by computer hardware and a computer program executed on the computer hardware. In FIG. 11, the computer system 900 includes a computer 901 including a disk drive 905, a keyboard 902, a mouse 903, a display 904, a microphone 917, and a speaker 918. Note that the entire system including the keyboard 902, the mouse 903, the display 904, the microphone 917, and the speaker 918 may be called a computer.

  FIG. 12 is a diagram illustrating an example of the internal configuration of the computer system 900. In FIG. 12, in addition to the disk drive 905, a computer 901 is connected to an MPU 911, a ROM 912 for storing a program such as a bootup program, and the MPU 911, and temporarily stores an instruction of an application program. A RAM 913 that provides storage space, a storage 914 that stores application programs, system programs, and data, a bus 915 that interconnects the MPU 911, ROM 912, and the like, and a connection to a network such as an external network or an internal network is provided. A network card 916. The storage 914 is, for example, a hard disk, SSD, flash memory, or the like.

  A program that causes the computer system 900 to execute the function of the information output device may be stored in a disk 921 such as a DVD or a CD-ROM, inserted into the disk drive 905, and transferred to the storage 914. Alternatively, the program may be transmitted to the computer 901 via the network and stored in the storage 914. The program is loaded into the RAM 913 when executed. The program may be loaded directly from the disk 921 or the network. Further, the program may be read into the computer system 900 via another removable recording medium (for example, a DVD or a memory card) instead of the disk 921.

  The program does not necessarily include an operating system (OS) or a third-party program that executes the function of the information output device in 901 indicating the details of the computer. The program may include only a part of an instruction that calls an appropriate function or module in a controlled manner and obtains a desired result. How the computer system 900 operates is well known and will not be described in detail.

  The computer system 900 described above is a server or a stationary PC, but the information output device may be realized by a mobile terminal such as a tablet terminal, a smartphone, or a notebook PC. In this case, for example, the keyboard 902 and the mouse 903 may be replaced with a touch panel, the disk drive 905 may be replaced with a memory card slot, and the disk 921 may be replaced with a memory card. However, the above is an example, and the hardware configuration of the computer that realizes the information output apparatus is not limited.

  In the above program, in a transmission step for transmitting information, a reception step for receiving information, etc., processing performed by hardware, for example, processing performed by a modem or an interface card in the transmission step (only performed by hardware). Not included) is not included.

  Further, the computer that executes the program may be singular or plural. That is, centralized processing may be performed, or distributed processing may be performed.

  Further, in each of the above embodiments, two or more communication means (for example, the reception function of the reception unit 2 and the transmission function of the output unit 4) existing in one apparatus may be physically realized by one medium. Needless to say, it is good.

  In each of the above embodiments, each process (each function) may be realized by centralized processing by a single device (system), or by distributed processing by a plurality of devices. May be.

  The present invention is not limited to the above-described embodiments, and various modifications are possible, and it goes without saying that these are also included in the scope of the present invention.

  As described above, the information output device according to the present invention has an effect that it can accept a conversation sentence that dynamically changes even in a query for the same search result and can search for information, and is useful as an information output device or the like. is there.

Claims (8)

An intent storage unit for storing one or more intents, which are information managed for each business process and are information having an action name for identifying the business process;
An API information storage unit for storing one or more API information, which is information associated with an intent, information for performing information search, and information having information for specifying a parameter that is one or more variables When,
A corpus storage unit for storing one or more pieces of conversation sentence information that is information associated with an intent and is information of a conversation sentence;
An entity storage unit that stores one or more entities that are words associated with any one or more pieces of conversation sentence information;
A conversation acceptance unit that accepts conversations;
An intent determination unit for determining an intent corresponding to the conversation sentence received by the conversation sentence reception unit;
A conversational sentence information determining unit that determines conversational sentence information that is closest to the conversational sentence received by the conversational sentence receiving unit from among one or more pieces of conversational sentence information corresponding to the intent determined by the intent determining unit;
Entity acquisition for acquiring one or more entities corresponding to one or more entities associated with the conversation sentence information determined by the conversation sentence information determination unit and corresponding to the words of the conversation sentence received by the conversation sentence reception unit And
A parameter acquisition unit for acquiring one or more parameters corresponding to each of the one or more entities acquired by the entity acquisition unit;
An API information acquisition unit that acquires API information corresponding to the intent determined by the intent determination unit from the API information storage unit;
Using one or more parameters acquired by the parameter acquisition unit and API information acquired by the API information acquisition unit, a query information configuration unit that configures query information for information search;
A query unit configured to execute query information configured by the query information configuration unit and obtain a search result;
An information output device comprising: a search result output unit that outputs a search result acquired by the search unit. The intent determination unit
An intent that acquires text corresponding to a conversation sentence received by the conversation sentence reception unit, acquires one or more independent words from the text, and has an action name having a word that is the same as or similar to the one or more independent words The information output apparatus according to claim 1, wherein the information is determined. One or more having a day word that is a word related to the day and date information acquisition information for acquiring day information that is information related to the day corresponding to the day word and that is used when constructing the inquiry information A date conversion information storage unit for storing the date conversion information of
The parameter acquisition unit
A request for acquiring date conversion information corresponding to a day word in one or more entities acquired by the entity acquisition unit from the date conversion information storage unit, and acquiring date information as a parameter using the date conversion information. The information output device according to claim 1 or 2. The entity in the entity storage unit corresponds to an entity name that is the name of the entity,
One or more entity mapping information including a table identifier for specifying a table, an attribute name in the table identified by the table identifier, and a translation item name that is information for specifying an entity to be converted and an entity name. An entity mapping information storage unit to be stored;
A PK item storage unit that stores one or more PK items having a table identifier and a primary key identifier that identifies a primary key of the table identified by the table identifier;
The parameter acquisition unit
An entity name acquisition means for acquiring an entity name corresponding to the entity acquired by the entity acquisition unit;
A translation item name acquisition unit that acquires a translation item name paired with the entity name acquired by the entity name acquisition unit from the entity mapping information storage unit;
Table identifier acquisition means for acquiring a table identifier paired with the entity name acquired by the entity name acquisition means from the entity mapping information storage unit;
Primary key identifier acquisition means for acquiring a primary key identifier paired with the table identifier acquired by the table identifier acquisition means from the PK item storage unit;
The attribute included in the record whose attribute value of the translation item name acquired by the translation item name acquisition unit matches the entity acquired by the entity acquisition unit from the table identified by the table identifier acquired by the table identifier acquisition unit The conversion parameter acquisition unit that acquires a converted parameter that is a value and is an attribute value of the primary key identifier acquired by the primary key identifier acquisition unit, according to any one of claims 1 to 3. Information output device. The inquiry information component is
A parameter that corresponds to each location of each of the one or more variables included in the API information acquired by the API information acquisition unit, and that configures the query information by arranging the parameter acquired by the parameter acquisition unit. The information output device according to any one of claims 1 to 4. The reception unit
A voice receiving means for receiving a voice of a conversation sentence;
The information output apparatus according to claim 1, further comprising: a voice recognition unit that performs voice recognition processing on the voice and acquires a conversational sentence that is a character string. Information managed for each business process, intent storage section that stores one or more intents that have an action name that identifies the business process, information associated with the intent, and information retrieval Is an API information storage unit that stores one or more API information that is information including information for specifying a parameter that is one or more variables, information associated with an intent, A corpus storage unit that stores one or more conversational sentence information that is information, an entity storage unit that stores one or more entities that are words associated with any one or more conversational sentence information, a conversational sentence reception unit, and an intent Implemented by a decision unit, conversation sentence information decision unit, entity acquisition unit, parameter acquisition unit, API information acquisition unit, query information configuration unit, search unit, and search result output unit It is an information output method,
The conversation sentence accepting unit accepts a conversation sentence;
The intent determination unit determines an intent corresponding to the conversation sentence received by the conversation sentence reception unit; and
The conversational sentence information determination unit determines conversational sentence information that most closely approximates the conversational sentence received by the conversational sentence reception unit from one or more conversational sentence information corresponding to the intent determined by the intent determination unit. Conversation text information determination step to be performed;
The entity acquisition unit corresponds to one or more entities associated with the conversation sentence information determined by the conversation sentence information determination unit, and is one or more words that are included in the conversation sentence received by the conversation sentence reception unit An entity acquisition step for acquiring an entity;
A parameter acquisition step in which the parameter acquisition unit acquires one or more parameters corresponding to each of the one or more entities acquired by the entity acquisition unit;
An API information acquisition step in which the API information acquisition unit acquires API information corresponding to the intent determined by the intent determination unit from the API information storage unit;
The inquiry information constituting the inquiry information for the information search using the one or more parameters acquired by the parameter acquisition unit and the API information acquired by the API information acquisition unit. Configuration steps;
A search step in which the search unit executes the query information configured by the query information configuration unit and obtains a search result;
An information output method including: a search result output step in which the output unit outputs a search result acquired by the search unit. Information managed for each business process, intent storage section that stores one or more intents that have an action name that identifies the business process, information associated with the intent, and information retrieval Is an API information storage unit that stores one or more API information that is information including information for specifying a parameter that is one or more variables, information associated with an intent, A computer capable of accessing a corpus storage unit storing one or more conversational sentence information as information, and an entity storage unit storing one or more entities corresponding to any one or more conversational sentence information,
A conversation acceptance unit that accepts conversations;
An intent determination unit for determining an intent corresponding to the conversation sentence received by the conversation sentence reception unit;
A conversational sentence information determining unit that determines conversational sentence information that is closest to the conversational sentence received by the conversational sentence receiving unit from among one or more pieces of conversational sentence information corresponding to the intent determined by the intent determining unit;
Entity acquisition for acquiring one or more entities corresponding to one or more entities associated with the conversation sentence information determined by the conversation sentence information determination unit and corresponding to the words of the conversation sentence received by the conversation sentence reception unit And
A parameter acquisition unit for acquiring one or more parameters corresponding to each of the one or more entities acquired by the entity acquisition unit;
An API information acquisition unit that acquires API information corresponding to the intent determined by the intent determination unit from the API information storage unit;
Using one or more parameters acquired by the parameter acquisition unit and API information acquired by the API information acquisition unit, a query information configuration unit that configures query information for information search;
A query unit configured to execute query information configured by the query information configuration unit and obtain a search result;
The program for functioning as a search result output part which outputs the search result which the said search part acquired.

Images