WO2019216054A1 - Interactive server - Google Patents

Interactive server Download PDF

Info

Publication number
WO2019216054A1
WO2019216054A1 PCT/JP2019/014169 JP2019014169W WO2019216054A1 WO 2019216054 A1 WO2019216054 A1 WO 2019216054A1 JP 2019014169 W JP2019014169 W JP 2019014169W WO 2019216054 A1 WO2019216054 A1 WO 2019216054A1
Authority
WO
WIPO (PCT)
Prior art keywords
search
user information
user
keyword
response
Prior art date
Application number
PCT/JP2019/014169
Other languages
French (fr)
Japanese (ja)
Inventor
昂宗 橋本
拓 藤本
友理子 尾▲崎▼
Original Assignee
株式会社Ｎｔｔドコモ
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社Ｎｔｔドコモ filed Critical 株式会社Ｎｔｔドコモ
Priority to JP2020518184A priority Critical patent/JP6975323B2/en
Publication of WO2019216054A1 publication Critical patent/WO2019216054A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types

Definitions

  • the present invention relates to a dialog server that performs a search based on an input keyword.
  • Patent Document 1 controls the output of answers to questions written in natural text, avoids the risk of selecting answers that do not match the customer's intent, and efficiently handles the narrowing down of answers
  • this Patent Document 1 there is a description about narrowing down the number of cases by performing an inverse question or a related question when the number of cases is equal to or more than a predetermined number when performing a FAQ search.
  • an object of the present invention is to provide a dialog server that can reduce the number of dialogs for searching.
  • the dialog server acquires an input keyword from a user terminal operated by the user in the dialog server that responds to a search result based on an input by the user, and A response candidate corresponding to the input keyword and the user information is acquired from an acquisition unit that acquires user information associated with the user and a search database that stores one or more search keywords and response candidates in association with each other.
  • the number of dialogues can be reduced.
  • FIG. It is a block diagram which shows the function structure of the dialogue server 100 and user terminal 200 of this embodiment. It is a sequence diagram which shows operation
  • FIG. It is a sequence diagram which shows a process when a user denies with respect to the question sentence candidate shown from the dialogue server 100. It is a figure which shows the dialogue screen when the question sentence candidate determined using user information is denied. It is a figure which shows the dialog screen (other example) in the user terminal. It is a specific example of the truth table database 104 used in the dialog screen of FIG.
  • FIG. 2 is a diagram illustrating a hardware configuration of a dialog server 100.
  • FIG. 1 shows the dialogue screen when not using user information, and its truth table database. It is a figure which shows the dialog screen and truth table database 104 when selecting user information suitably.
  • 2 is a diagram illustrating a hardware configuration of a dialog server 100.
  • FIG. 1 is a block diagram showing functional configurations of the interactive server 100 and the user terminal 200 of the present embodiment.
  • the dialog server 100 is a device that searches for response candidates according to the input keyword transmitted from the user terminal 200 and transmits the response candidate to the user terminal 200. For example, it is used in a FAQ search system.
  • the dialogue server 100 includes a reception unit 101 (acquisition unit), a search unit 102, a response unit 103, a truth table database 104, and a FAQ database 105.
  • the user terminal 200 includes a key reception unit 201, a user information storage unit 202, a communication unit 203, and a display unit 204. First, each component of the dialogue server 100 will be described.
  • the receiving unit 101 is a part that receives an input sentence transmitted from the user terminal 200 and acquires an input keyword.
  • the search unit 102 is a part that searches the truth table database 104 based on the input keyword and obtains response candidates.
  • the response candidates are, for example, question sentence candidates for input keywords in the FAQ search system.
  • the search unit 102 uses the user information transmitted from the user terminal 200 to perform a search for further narrowing down the response candidates. Note that instead of the user information, the search unit 102 may select a search keyword for narrowing down response candidates based on the usage frequency or the like, and acquire the search keyword from the truth table database 104 as a replay key.
  • the response unit 103 is a part that transmits the response candidate or the return key searched by the search unit 102 to the user terminal 200.
  • the truth table database 104 stores one or a plurality of search keywords and question sentence candidates that are response candidates in association with each other.
  • the truth table database 104 is created by the administrator of the dialogue server 100 based on the question sentence candidates in the FAQ database 105.
  • the dialogue server 100 includes an information processing unit that performs morphological analysis.
  • the information processing unit automatically extracts a search keyword from a question sentence candidate with reference to the FAQ database 105, and constructs a truth table database 104. May be.
  • it is preferable that a different keyword is set for each question sentence candidate so that the question sentence candidate can be uniquely determined.
  • the FAQ database 105 stores a question sentence and its answer in association with each other.
  • the question sentence and the question sentence candidate are a question sentence desired by the user or a candidate thereof.
  • a sentence such as “terminal operation method”.
  • the question sentence is referred to as a question sentence candidate in a state before being determined, but the content is not changed.
  • the answer is an answer to the question text.
  • the information is related to the operation method.
  • the answer may be shown in text, or may be a link destination to an external server describing the operation method.
  • the truth table database 104 and the FAQ database 105 may be constructed as one database.
  • the key receiving unit 201 is a part that receives an input sentence when operated by a user.
  • the user information storage unit 202 is a part that stores user information of the user terminal 200.
  • the user information is, for example, setting information such as the model name of the user terminal 200, the model identifier, the user's gender / characteristics, the user's address, and the language used by the terminal.
  • the so-called user information is identification information for identifying the user or the user terminal 200, or information indicating characteristics, settings, or attributes thereof. Such information may be set by the user or may be set in advance in the terminal.
  • the communication unit 203 is a part that transmits the input text input by the user, the affirmative / negative instruction for the answer and the user information to the dialogue server 100. In addition, it is a part that receives a question sentence candidate or a question keyword from the dialogue server 100.
  • the display unit 204 is a part that displays an input sentence, a question sentence candidate, or a query keyword input by the user in an interactive format. That is, the display unit 204 is a part that displays a dialogue screen with the dialogue server 100.
  • FIG. 2 is a sequence diagram showing the operation.
  • the key receiving unit 201 receives an input sentence from the user (S101), the communication unit 203 extracts user information from the user information storage unit 202 (S102), and inputs the input sentence and the user information. It transmits to the dialogue server 100 (S103).
  • the receiving unit 101 receives the input text and user information transmitted from the user terminal 200.
  • the receiving unit 101 extracts an input keyword from the input sentence and recognizes the input content (S104).
  • the search unit 102 performs a search process on the truth table database 104 based on the extracted input keyword, and extracts one or a plurality of question sentence candidates (S105). When there are a plurality of extracted question sentence candidates, the search unit 102 compares the user information acquired in step S103 with each search keyword of the extracted plurality of question sentence candidates (S106). One or more pieces of user information may be compared. Further, as will be described later, a combination of a plurality of pieces of user information may be changed for comparison. Moreover, it is preferable to give priority to the user information used for the search that is described in the truth table database 104 as a search keyword.
  • the search unit 102 determines the question sentence candidate associated with the search keyword that matches the user information as a result of the comparison (S107). If a plurality of question sentence candidates remain even if the user information is used, the search unit 102 may determine all of them as question sentence candidates or match the search keywords in the truth table database 104. One question sentence candidate may be determined based on the degree of (number of keyword matches).
  • the response unit 103 transmits the determined question sentence candidate to the user terminal 200.
  • the user instructs an intention of affirmation / negative for the question sentence candidate.
  • the user terminal 200 transmits a message to that effect to the dialogue server 100 (S108).
  • the search unit 102 acquires an answer corresponding to the question sentence candidate that has received an affirmative instruction from the user terminal 200 from the FAQ database 105 (S109).
  • the response unit 103 transmits the question sentence (question sentence candidate) and the answer to the user terminal 200 (S110).
  • the question sentence candidates can be narrowed down without an unnecessary dialogue, and the number of dialogues can be reduced.
  • FIG. 3 is a diagram illustrating a specific example of an interactive screen on the user terminal 200.
  • the balloon u ⁇ b> 1 indicates an input sentence input by the user operating the key receiving unit 201.
  • a dotted frame u11 indicates user information stored in the user information storage unit 202.
  • the user terminal: terminal A and gender: male are stored as user information.
  • the dotted frame u11 is clearly shown for convenience of explanation, but is not displayed on the actual dialogue screen.
  • a balloon s2 indicates a question sentence candidate searched in the dialogue server 100.
  • the receiving unit 101 receives the input sentence indicated by the balloon u1, and extracts “operation method” as an input keyword from the input sentence (corresponding to S104 in FIG. 2).
  • the search unit 102 performs a search based on the “operation method” and acquires a question sentence candidate (corresponding to S105 in FIG. 2).
  • the truth table database 104 stores question sentence candidates and search keywords in association with each other.
  • the search keyword “terminal A” and “operation method” are associated with the question sentence candidate “operation method of terminal A”.
  • terminal B” and “operation method” are associated with “operation method of terminal B”.
  • PC operation method” is associated with “PC” and “operation method”.
  • the truth table database 104 naturally stores other question sentence candidates and their search keywords.
  • the search unit 102 searches the truth table database 104 using the search keyword “operation method” as a key, and asks question sentence candidates “operation method of terminal A”, “operation method of terminal B”, and “PC The “operation method” is extracted (S105 in FIG. 2).
  • the search unit 102 narrows down question sentence candidates using the user information.
  • the search unit 102 compares the user information and the search keyword of each question sentence candidate (S106 in FIG. 2), and uses the user information: “method of operating terminal A” including terminal A as a question sentence candidate. Determine (S107 in FIG. 2).
  • the response unit 103 generates a message including the question sentence candidate extracted by the search unit 102 and performs transmission processing. Specifically, as described in the balloon s2, “Do you want to display an answer to“ How to operate terminal A ”?” Is generated and transmitted to the user terminal 200. The user terminal 200 displays the message on the dialog screen.
  • FIG. 5 is a sequence diagram showing the operation. Steps S101 to S107 are the same as those in FIG.
  • the search unit 102 is included in the question sentence candidate that has been instructed negatively. Instead of the user information, one search keyword is acquired as a return key from the truth table database 104 (S112). As described above, the selection as the answer key is determined based on the usage frequency in the truth table database 104.
  • the search unit 102 determines a question sentence candidate including the one search keyword selected as the answer key (S113).
  • the response unit 103 transmits the question sentence candidate to the user terminal 200.
  • the display unit 204 displays the question sentence candidate, and the key reception unit 201 receives an affirmative / negative instruction for the question sentence candidate from the user.
  • the query process is performed using the search keyword (listen keyword), but the question sentence candidates may be narrowed down using another user information instead of the query keyword.
  • FIG. 6 is a diagram showing an interactive screen in the above-described processing.
  • a balloon u3 is an input sentence input by the user.
  • the dotted frame u31 is user information stored in the user terminal 200.
  • the dialogue server 100 When the dialogue server 100 receives the input text and the user information from the user terminal 200, the dialogue server 100 determines the “operation method of the terminal A” as a question text candidate using the user information and transmits it. In FIG. 6, the dialogue server 100 displays an answer about “How to operate terminal A”? ] Message is generated and sent.
  • the user terminal 200 performs a negative operation on the question sentence candidate and transmits a negative instruction to the dialogue server 100.
  • “No” is displayed as indicated by the balloon u32.
  • the receiving unit 101 receives a negative message question “terminal A operation method”, and the search unit 102 determines that the user information: terminal A is denied.
  • the search unit 102 excludes the user information: terminal A from the search keyword, extracts another new search keyword from the truth table database 104, and performs a search based on the search keyword.
  • the search unit 102 selects “terminal B” as a search keyword, and transmits it to the user terminal 200 as a return keyword.
  • terminal A user information
  • operation method normal
  • the acquired key indicates the keyword used for the search
  • the parentheses indicate the origin of the keyword.
  • FIG. 7 is a diagram showing an interactive screen (another example) on the user terminal 200.
  • the user terminal 200 stores constellation: Gemini and blood type 0 as user information, as indicated by the dotted frame 21.
  • the dotted frame 21 is shown for convenience of explanation, but it is not actually displayed.
  • the receiving unit 101 receives the input text “Tell me about fortune” and the user information constellation: Gemini, blood type: O type
  • the input keyword “fortune” is acquired from the input text.
  • the search unit 102 searches for several question sentence candidates using the input keyword “fortune” as a key. Further, the question information candidates are narrowed down by changing the combination of user information (see step S106 in FIG. 2). For example, the search unit 102 performs a search using a combination of “Gemini”, “O type”, and “Gemini, O type”. Depending on the combination of user information, question sentence candidates may not be linked. In that case, of course, question sentence candidates cannot be narrowed down.
  • FIG. 8 is a specific example of the truth table database 104 used in the dialogue screen of FIG. As shown in FIG. 7, the truth table database 104 stores “fortune of Gemini”, “O-type fortune”, and “O-shaped fortune of Gemini” together with each search keyword. The truth table database 104 is used to enable the interaction shown in FIG.
  • the user can use the other search keywords to perform a replay process without using the user information.
  • the search process is performed.
  • FIG. 9 is a diagram showing a specific example of the dialogue screen and a specific example of the truth table database 104 in order to explain the preferable case.
  • FIG. 9A shows an example of the dialogue screen.
  • the user has input “Tell me how to operate terminal B” as an input sentence (balloon u4).
  • terminal A is registered as the user information (dotted line frame u41).
  • the search unit 102 of the dialog server 100 performs a search using the input keyword “terminal B” and “operation method”, and then uses the user information.
  • a search using “terminal A” is performed (FIG. 2, S105, S106).
  • the truth table database 104 of the dialogue server 100 stores only the search keywords “terminal B” and “operation method” in association with “operation method of terminal B” (FIG. 9B). )).
  • the search unit 102 can determine that there is no need to further perform a search using the user information. Therefore, the search part 102 can determine one question sentence candidate, without performing step S106 of FIG.
  • the dialogue server 100 further transmits an answer about “the operation method of the terminal B” to the user terminal 200 (balloon s4). Therefore, the number of conversations can be reduced.
  • the search unit 102 determines a question sentence candidate corresponding to the input keyword.
  • all of the plurality are provided to the user terminal 200 as question sentence candidates.
  • FIG. 10 is a diagram showing a specific example of the dialogue screen and a specific example of the truth table database 104 when performing the processing.
  • FIG. 10A shows a specific example of the dialogue screen.
  • the user has input “Tell me how to operate terminal B” as an input sentence (balloon u5).
  • the user terminal 200 the user terminal: terminal A, gender: male, and Japanese are registered as user information (dotted line frame u51).
  • FIG. 10B shows the storage contents of the search keyword and question sentence candidate in the truth table database 104.
  • the search unit 102 of the dialogue server 100 searches for the user keyword after performing a search using the “operation method” of the input keyword.
  • the search unit 102 can determine more appropriate user information by selecting a combination of an input keyword and user information that completely matches the search keyword in the truth table database 104. .
  • the dialogue server 100 transmits “Japanese terminal A operation method” to the user terminal 200 as a question sentence candidate (speech balloon s5).
  • the dialogue server 100 is a dialogue server that responds to a search result based on an input by a user, and the receiving unit 101 acquires an input keyword from the user terminal 200 operated by the user and a user associated with the user. Receive information.
  • the truth table database 104 stores one or a plurality of search keywords and question sentence candidates (corresponding to response candidates) in association with each other, and the search unit 102 receives input keywords and user information from the truth table database 104. Search for response candidates corresponding to.
  • the response unit 103 transmits the response candidates searched by the search unit 102 to the user terminal 200.
  • the number of dialogues with the user terminal 200 can be reduced by using the user information. Therefore, an efficient search is possible for the user. Furthermore, for the dialogue server 100, it is possible to reduce the hardware load of the control unit that controls the processing operation by reducing the number of dialogues. Furthermore, network traffic can be suppressed.
  • the user information is transmitted from the user terminal 200, but is not limited thereto.
  • User information such as user attribute information or registration information is registered in the dialog server 100 or other servers arranged on the network, and the dialog server 100 may acquire user information therefrom. In that case, it is necessary to associate identification information such as a user ID with user information. Further, the dialogue server 100 needs to acquire a user ID and the like from the user terminal 200 when performing a search.
  • the search unit 102 may perform a search for prompting additional input according to the input keyword and user information. For example, if the question sentence candidates cannot be narrowed down to a predetermined number or less even using the input keyword and user information, the question sentence candidates may be narrowed down by using a return key to prompt further input. .
  • the search unit 102 performs a search based on the input keyword to obtain a plurality of question sentence candidates (response candidates), and among the plurality of question sentence candidates (response candidates). Search for question sentence candidates (response candidates) including user information.
  • the response unit 103 transmits the searched question sentence candidate (response candidate) to the user terminal 200.
  • the search can be efficiently performed by prioritizing it. That is, the user information may include information that is not directly related to the search, such as gender and age. Using such user information does not increase search efficiency and does not contribute to reducing the number of conversations. Therefore, when there are a plurality of pieces of user information, priority is given to those registered in the search database, thereby improving search efficiency and reducing the number of result dialogues.
  • the search unit 102 performs a search using one or a plurality of user information according to a predetermined condition among a plurality of user information.
  • keywords included in the closest question sentence candidate (response candidate), keywords included in all question sentence candidates (response candidates), and question sentence candidates (response candidates) in the top ranking
  • the question sentence candidate such as the keyword and the keyword of the question sentence candidate (response candidate) based on the match type
  • the dialogue server 100 can return a question sentence candidate corresponding to the complete match without returning a response key.
  • the “closest question sentence candidate” is a use that increases the number of matches when a plurality of search keywords associated with the question sentence candidate are compared with a plurality of keywords composed of input keywords and user information.
  • Question sentence candidate corresponding to person information. For example, when there are search keywords A, B, and C associated with the question sentence candidates, and input keyword A and user information B and D, user information B is more user information. : The number of matches is greater than D.
  • the question sentence candidate using the user information: B in this case is the closest question sentence candidate. Therefore, user information B is selected.
  • the highest ranking question sentence candidate means a higher ranking question sentence candidate based on ranking based on browsing frequency. Regardless of the viewing frequency, rankings based on other criteria may be used.
  • the searching unit 102 when the receiving unit 101 receives a negative intention from the user terminal 200 for one question sentence candidate (response candidate), the searching unit 102 does not use the user information used for the search. Try searching again. For example, the search unit 102 acquires other search keywords from the truth table database 104 instead of the user information, and performs a search using the search keywords.
  • the search unit 102 when there are a plurality of pieces of user information, the search unit 102 performs a search by changing the combination of the plurality of pieces of user information and combining them with the input keyword.
  • the number of conversations can be reduced by changing the combination of the plurality of user information and performing a search using the user information and the input keyword with the changed combination. Can be reduced.
  • the search unit 102 includes a keyword group including one or more search keywords registered for each question sentence candidate (response candidate) in the truth table database 104, an input keyword, and one or more uses.
  • One or a plurality of user information is selected so that a keyword group consisting of a combination of user information is completely matched, and a search using the one or a plurality of user information and the input keyword is performed.
  • the search unit 102 completely matches a keyword group consisting of one or a plurality of search keywords registered for each question sentence candidate in the truth table database 104 and a keyword group consisting of the input keywords. When doing so, one or a plurality of user information is not selected.
  • each functional block may be realized by one device physically and / or logically coupled, and two or more devices physically and / or logically separated may be directly and / or indirectly. Specifically, it may be realized by a plurality of these devices connected by a hook (for example, wired and / or wireless).
  • the dialogue server 100 and the user terminal 200 may function as a computer that performs the processing according to the present embodiment.
  • FIG. 11 is a diagram illustrating an example of a hardware configuration of the dialogue server 100 and the user terminal 200 according to the present embodiment.
  • the above-described dialog server 100 and user terminal 200 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like. .
  • the term “apparatus” can be read as a circuit, a device, a unit, or the like.
  • the hardware configuration of the dialog server 100 and the user terminal 200 may be configured to include one or a plurality of the devices illustrated in the figure, or may be configured not to include some devices.
  • Each function in the dialog server 100 and the user terminal 200 is performed by causing the processor 1001 to perform calculations by reading predetermined software (programs) on hardware such as the processor 1001 and the memory 1002, and performing communication by the communication device 1004 and memory. This is realized by controlling data reading and / or writing in the storage 1003 and the storage 1003.
  • the processor 1001 controls the entire computer by operating an operating system, for example.
  • the processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic device, a register, and the like.
  • the search unit 102 or the like may be realized by the processor 1001.
  • the processor 1001 reads programs (program codes), software modules, and data from the storage 1003 and / or the communication device 1004 to the memory 1002, and executes various processes according to these.
  • programs program codes
  • software modules software modules
  • data data from the storage 1003 and / or the communication device 1004 to the memory 1002, and executes various processes according to these.
  • the program a program that causes a computer to execute at least a part of the operations described in the above embodiments is used.
  • the search unit 102 of the dialogue server 100 may be realized by a control program stored in the memory 1002 and operated by the processor 1001, and may be realized similarly for other functional blocks.
  • the above-described various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001.
  • the processor 1001 may be implemented by one or more chips.
  • the program may be transmitted from a network via a telecommunication line.
  • the memory 1002 is a computer-readable recording medium and includes, for example, at least one of ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), and the like. May be.
  • the memory 1002 may be called a register, a cache, a main memory (main storage device), or the like.
  • the memory 1002 can store a program (program code), a software module, and the like that can be executed to implement the wireless communication method according to the embodiment of the present invention.
  • the storage 1003 is a computer-readable recording medium such as an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (for example, a compact disk, a digital versatile disk, a Blu-ray). (Registered trademark) disk, smart card, flash memory (for example, card, stick, key drive), floppy (registered trademark) disk, magnetic strip, and the like.
  • the storage 1003 may be referred to as an auxiliary storage device.
  • the storage medium described above may be, for example, a database, server, or other suitable medium including the memory 1002 and / or the storage 1003.
  • the communication device 1004 is hardware (transmission / reception device) for performing communication between computers via a wired and / or wireless network, and is also referred to as a network device, a network controller, a network card, a communication module, or the like.
  • a network device for example, the reception unit 101 and the response unit 103 described above may be realized by the communication device 1004.
  • the input device 1005 is an input device (for example, a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts an input from the outside.
  • the output device 1006 is an output device (for example, a display, a speaker, an LED lamp, etc.) that performs output to the outside.
  • the input device 1005 and the output device 1006 may have an integrated configuration (for example, a touch panel).
  • each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information.
  • the bus 1007 may be configured with a single bus or may be configured with different buses between apparatuses.
  • the dialogue server 100 and the user terminal 200 include a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), and the like.
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • PLD programmable logic device
  • FPGA field programmable gate array
  • Hardware may be configured, and a part or all of each functional block may be realized by the hardware.
  • the processor 1001 may be implemented by at least one of these hardware.
  • notification of information is not limited to the aspect / embodiment described in this specification, and may be performed by other methods.
  • notification of information includes physical layer signaling (for example, DCI (Downlink Control Information), UCI (Uplink Control Information)), upper layer signaling (for example, RRC (Radio Resource Control) signaling, MAC (Medium Access Control) signaling), It may be implemented by broadcast information (MIB (Master Information Block), SIB (System Information Block)), other signals, or a combination thereof.
  • the RRC signaling may be called an RRC message, and may be, for example, an RRC connection setup (RRC Connection Setup) message, an RRC connection reconfiguration (RRC ConnectionReconfiguration) message, or the like.
  • Each aspect / embodiment described in this specification includes LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER 3G, IMT-Advanced, 4G, 5G, FRA (Future Radio Access), W-CDMA.
  • LTE Long Term Evolution
  • LTE-A Long Term Evolution-Advanced
  • SUPER 3G IMT-Advanced
  • 4G 5G
  • FRA Full Radio Access
  • W-CDMA Wideband
  • GSM registered trademark
  • CDMA2000 Code Division Multiple Access 2000
  • UMB User Mobile Broadband
  • IEEE 802.11 Wi-Fi
  • IEEE 802.16 WiMAX
  • IEEE 802.20 UWB (Ultra-WideBand
  • the present invention may be applied to a Bluetooth (registered trademark), a system using another appropriate system, and / or a next generation system extended based on the system.
  • the input / output information or the like may be stored in a specific location (for example, a memory) or may be managed by a management table. Input / output information and the like can be overwritten, updated, or additionally written. The output information or the like may be deleted. The input information or the like may be transmitted to another device.
  • the determination may be performed by a value represented by 1 bit (0 or 1), may be performed by a true / false value (Boolean: true or false), or may be performed by comparing numerical values (for example, a predetermined value) Comparison with the value).
  • notification of predetermined information is not limited to explicitly performed, but is performed implicitly (for example, notification of the predetermined information is not performed). Also good.
  • software, instructions, etc. may be transmitted / received via a transmission medium.
  • software may use websites, servers, or other devices using wired technology such as coaxial cable, fiber optic cable, twisted pair and digital subscriber line (DSL) and / or wireless technology such as infrared, wireless and microwave.
  • wired technology such as coaxial cable, fiber optic cable, twisted pair and digital subscriber line (DSL) and / or wireless technology such as infrared, wireless and microwave.
  • DSL digital subscriber line
  • wireless technology such as infrared, wireless and microwave.
  • system and “network” used in this specification are used interchangeably.
  • information, parameters, and the like described in this specification may be represented by absolute values, may be represented by relative values from a predetermined value, or may be represented by other corresponding information.
  • the radio resource may be indicated by an index.
  • User terminals can be obtained by those skilled in the art from subscriber stations, mobile units, subscriber units, wireless units, remote units, mobile devices, wireless devices, wireless communication devices, remote devices, mobile subscriber stations, access terminals, mobile terminals, wireless It may also be called terminal, remote terminal, handset, user agent, mobile client, client, or some other appropriate terminology.
  • determining may encompass a wide variety of actions. “Judgment” and “decision” are, for example, judgment, calculation, calculation, processing, derivation, investigating, searching (looking up) (for example, table , Searching in a database or another data structure), considering ascertaining as “determining”, “deciding”, and the like.
  • determination and “determination” include receiving (for example, receiving information), transmitting (for example, transmitting information), input (input), output (output), and access. (accessing) (e.g., accessing data in a memory) may be considered as "determined” or "determined”.
  • determination and “decision” means that “resolving”, “selecting”, “choosing”, “establishing”, and “comparing” are regarded as “determining” and “deciding”. May be included. In other words, “determination” and “determination” may include considering some operation as “determination” and “determination”.
  • connection means any direct or indirect connection or coupling between two or more elements and It can include the presence of one or more intermediate elements between two “connected” or “coupled” elements.
  • the coupling or connection between the elements may be physical, logical, or a combination thereof.
  • the two elements are radio frequency by using one or more wires, cables and / or printed electrical connections, and as some non-limiting and non-inclusive examples
  • electromagnetic energy such as electromagnetic energy having a wavelength in the region, microwave region, and light (both visible and invisible) region, it can be considered to be “connected” or “coupled” to each other.
  • the phrase “based on” does not mean “based only on”, unless expressly specified otherwise. In other words, the phrase “based on” means both “based only on” and “based at least on.”
  • any reference to the element does not generally limit the quantity or order of the elements. These designations can be used herein as a convenient way to distinguish between two or more elements. Thus, a reference to the first and second elements does not mean that only two elements can be employed there, or that in some way the first element must precede the second element.
  • DESCRIPTION OF SYMBOLS 100 Dialog server 101 ... Receiving part 102 ... Search part 103 ... Response part 104 ... Truth table database 105 ... FAQ database 200 ... User terminal 201 ... Key reception part 202 ... User information storage part, 203 ... Communication unit, 204 ... Display unit.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

[Problem] The purpose of the present invention is to provide an interactive server that can reduce the number of interactions in searching. [Solution] An interactive server 100 transmits a search result in response to an input from a user. A reception unit 101 acquires an input keyword from a user terminal 200 operated by the user, and receives user information associated with the user. A truth table database 104 stores one or more search keywords and question sentence candidates in association with each other, and a search unit 102 searches the truth table database 104 for a response candidate corresponding to the input keyword and the user information. A response unit 103 transmits to the user terminal 200 a question sentence candidate searched by the search unit 102.

Description

対話サーバConversation server
　本発明は、入力キーワードに基づいて検索を行う対話サーバに関る。 The present invention relates to a dialog server that performs a search based on an input keyword.
　下記特許文献１には、自然文で記述された質問への回答の出力を制御し、顧客の質問の意図に合致しない回答を選択するリスクを回避することや、回答の絞り込みを効率的に処理するための質問回答制御プログラムについての記載がある。具体的にはこの特許文献１には、ＦＡＱ検索を行う際において、所定件数以上である場合には、逆質問または関連質問を行うことにより、該当件数を絞り込むことについての記載がある。 Patent Document 1 below controls the output of answers to questions written in natural text, avoids the risk of selecting answers that do not match the customer's intent, and efficiently handles the narrowing down of answers There is a description about the question answer control program to do. Specifically, in this Patent Document 1, there is a description about narrowing down the number of cases by performing an inverse question or a related question when the number of cases is equal to or more than a predetermined number when performing a FAQ search.
特開２０１５－３６９４５号公報JP2015-36945A
　しかしながら、適切な逆質問または関連質問を行うことができない場合がある。その場合、対話回数が多くなるという問題がある。 However, there are cases where it is not possible to make appropriate reverse questions or related questions. In that case, there is a problem that the number of dialogues increases.
　そこで、上述の課題を解決するために、本発明は、検索のための対話回数を少なくすることができる対話サーバを提供することを目的とする。 Therefore, in order to solve the above-described problems, an object of the present invention is to provide a dialog server that can reduce the number of dialogs for searching.
　上述の課題を解決するために、本発明の一態様における対話サーバは、ユーザによる入力に基づいて検索結果を応答する対話サーバにおいて、前記ユーザが操作するユーザ端末から入力キーワードを取得するとともに、前記ユーザに関連付けられている利用者情報を取得する取得部と、一または複数の検索キーワードと応答候補とを対応付けて記憶する検索データベースから、前記入力キーワードおよび前記利用者情報に対応する応答候補を検索する検索部と、前記検索部により検索された応答候補を前記ユーザ端末に対して送信する応答部と、を備える。 In order to solve the above-described problem, the dialog server according to one aspect of the present invention acquires an input keyword from a user terminal operated by the user in the dialog server that responds to a search result based on an input by the user, and A response candidate corresponding to the input keyword and the user information is acquired from an acquisition unit that acquires user information associated with the user and a search database that stores one or more search keywords and response candidates in association with each other. A search unit for searching, and a response unit for transmitting response candidates searched by the search unit to the user terminal.
　この構成により、利用者情報を用いた検索を行い、応答候補を絞り込むことができ、対話回数を削減することができる。 With this configuration, it is possible to search using user information, narrow down response candidates, and reduce the number of conversations.
　本発明によれば、対話回数を削減することができる。 According to the present invention, the number of dialogues can be reduced.
本実施形態の対話サーバ１００およびユーザ端末２００の機能構成を示すブロック図である。It is a block diagram which shows the function structure of the dialogue server 100 and user terminal 200 of this embodiment. 対話サーバ１００およびユーザ端末２００の動作を示すシーケンス図である。It is a sequence diagram which shows operation | movement of the dialogue server 100 and the user terminal 200. ユーザ端末２００における対話画面の具体例を示す図である。It is a figure which shows the specific example of the dialogue screen in the user terminal. 真理表データベース１０４の記憶内容を示す図である。It is a figure which shows the memory content of the truth table database 104. FIG. 対話サーバ１００から提示された質問文候補に対してユーザが否定した時の処理を示すシーケンス図である。It is a sequence diagram which shows a process when a user denies with respect to the question sentence candidate shown from the dialogue server 100. 利用者情報を用いて決定した質問文候補が否定された場合の対話画面を示す図である。It is a figure which shows the dialogue screen when the question sentence candidate determined using user information is denied. ユーザ端末２００における対話画面（ほかの例）を示す図である。It is a figure which shows the dialog screen (other example) in the user terminal. 図７の対話画面において用いられる真理表データベース１０４の具体例である。It is a specific example of the truth table database 104 used in the dialog screen of FIG. 利用者情報を使わない場合の対話画面とその真理表データベース１０４を示す図である。It is a figure which shows the dialogue screen when not using user information, and its truth table database. 利用者情報を適宜選択するときの対話画面とその真理表データベース１０４を示す図である。It is a figure which shows the dialog screen and truth table database 104 when selecting user information suitably. 対話サーバ１００のハードウェア構成を示す図である。2 is a diagram illustrating a hardware configuration of a dialog server 100. FIG.
　添付図面を参照しながら本発明の実施形態を説明する。可能な場合には、同一の部分には同一の符号を付して、重複する説明を省略する。 Embodiments of the present invention will be described with reference to the accompanying drawings. Where possible, the same parts are denoted by the same reference numerals, and redundant description is omitted.
　図１は、本実施形態の対話サーバ１００およびユーザ端末２００の機能構成を示すブロック図である。この対話サーバ１００は、ユーザ端末２００から送信された入力キーワードに応じた応答候補を検索して、ユーザ端末２００に送信する装置である。例えば、ＦＡＱ検索システムに用いられる。 FIG. 1 is a block diagram showing functional configurations of the interactive server 100 and the user terminal 200 of the present embodiment. The dialog server 100 is a device that searches for response candidates according to the input keyword transmitted from the user terminal 200 and transmits the response candidate to the user terminal 200. For example, it is used in a FAQ search system.
　対話サーバ１００は、受信部１０１（取得部）、検索部１０２、応答部１０３、真理表データベース１０４およびＦＡＱデータベース１０５を含んで構成されている。また、ユーザ端末２００は、キー受付部２０１、利用者情報記憶部２０２、通信部２０３、および表示部２０４を含んで構成されている。まず、対話サーバ１００の各構成要件について説明する。 The dialogue server 100 includes a reception unit 101 (acquisition unit), a search unit 102, a response unit 103, a truth table database 104, and a FAQ database 105. The user terminal 200 includes a key reception unit 201, a user information storage unit 202, a communication unit 203, and a display unit 204. First, each component of the dialogue server 100 will be described.
　受信部１０１は、ユーザ端末２００から送信される入力文章を受信して、入力キーワードを取得する部分である。 The receiving unit 101 is a part that receives an input sentence transmitted from the user terminal 200 and acquires an input keyword.
　検索部１０２は、入力キーワードに基づいて真理表データベース１０４を検索して、応答候補を取得する部分である。本実施形態では、応答候補は、例えば、ＦＡＱ検索システムにおける入力キーワードに対する質問文候補である。さらに検索部１０２は、ユーザ端末２００から送信された利用者情報を用いて、応答候補をさらに絞り込む検索を行う。なお、検索部１０２は、利用者情報に代えて、応答候補を絞り込むための検索キーワードを利用頻度などに基づいて選択して、聞き返しキーとして真理表データベース１０４から取得してもよい。 The search unit 102 is a part that searches the truth table database 104 based on the input keyword and obtains response candidates. In the present embodiment, the response candidates are, for example, question sentence candidates for input keywords in the FAQ search system. Further, the search unit 102 uses the user information transmitted from the user terminal 200 to perform a search for further narrowing down the response candidates. Note that instead of the user information, the search unit 102 may select a search keyword for narrowing down response candidates based on the usage frequency or the like, and acquire the search keyword from the truth table database 104 as a replay key.
　応答部１０３は、検索部１０２により検索された応答候補または聞き返しキーをユーザ端末２００に送信する部分である。 The response unit 103 is a part that transmits the response candidate or the return key searched by the search unit 102 to the user terminal 200.
　真理表データベース１０４は、一または複数の検索キーワードと、応答候補である質問文候補とを対応付けて記憶している。真理表データベース１０４は、ＦＡＱデータベース１０５の質問文候補に基づいて、対話サーバ１００の管理者により作成される。なお、対話サーバ１００は、形態素解析を行う情報処理部を備え、その情報処理部が、ＦＡＱデータベース１０５を参照して自動的に質問文候補から検索キーワードを抽出し、真理表データベース１０４を構築してもよい。なお、真理表データベースの検索キーワードの組合せは、質問文候補を一意に決定可能にするために質問文候補ごとに異なるキーワードが設定されていることが好ましい。 The truth table database 104 stores one or a plurality of search keywords and question sentence candidates that are response candidates in association with each other. The truth table database 104 is created by the administrator of the dialogue server 100 based on the question sentence candidates in the FAQ database 105. The dialogue server 100 includes an information processing unit that performs morphological analysis. The information processing unit automatically extracts a search keyword from a question sentence candidate with reference to the FAQ database 105, and constructs a truth table database 104. May be. In addition, as for the combination of search keywords in the truth table database, it is preferable that a different keyword is set for each question sentence candidate so that the question sentence candidate can be uniquely determined.
　ＦＡＱデータベース１０５は、質問文とその回答を対応付けて記憶している。なお、質問文および質問文候補とは、ユーザが希望する質問文またはその候補である。例えば、「端末の操作方法」などの文章である。本実施形態において、質問文として決定前の状態では質問文候補と称しているが、その内容は変わるものではない。 The FAQ database 105 stores a question sentence and its answer in association with each other. The question sentence and the question sentence candidate are a question sentence desired by the user or a candidate thereof. For example, a sentence such as “terminal operation method”. In the present embodiment, the question sentence is referred to as a question sentence candidate in a state before being determined, but the content is not changed.
　回答は、その質問文に対する回答である。例えば、質問文候補が、操作方法に関する場合、その操作方法に関する情報である。なお、回答を文章で示してもよいし、操作方法を記述する外部サーバへのリンク先としてもよい。なお、真理表データベース１０４とＦＡＱデータベース１０５とを一つのデータベースとして構築してもよい。 The answer is an answer to the question text. For example, when a question sentence candidate is related to an operation method, the information is related to the operation method. The answer may be shown in text, or may be a link destination to an external server describing the operation method. The truth table database 104 and the FAQ database 105 may be constructed as one database.
　つぎに、ユーザ端末２００の構成要件について説明する。 Next, configuration requirements of the user terminal 200 will be described.
　キー受付部２０１は、ユーザにより操作されることにより、入力文章を受け付ける部分である。 The key receiving unit 201 is a part that receives an input sentence when operated by a user.
　利用者情報記憶部２０２は、ユーザ端末２００の利用者情報を記憶する部分である。利用者情報とは、例えば、ユーザ端末２００の機種名、機種識別子、ユーザの性別・特性、ユーザの住所、端末の使用言語などの設定情報などである。いわゆる利用者情報は、ユーザまたはユーザ端末２００を識別する識別情報、またはその特性、設定または属性を示す情報である。これら情報は、ユーザにより設定されてもよいし、端末に事前に設定されてもよい。 The user information storage unit 202 is a part that stores user information of the user terminal 200. The user information is, for example, setting information such as the model name of the user terminal 200, the model identifier, the user's gender / characteristics, the user's address, and the language used by the terminal. The so-called user information is identification information for identifying the user or the user terminal 200, or information indicating characteristics, settings, or attributes thereof. Such information may be set by the user or may be set in advance in the terminal.
　通信部２０３は、ユーザにより入力された入力文章、聞き返しに対する肯定・否定の指示および利用者情報を対話サーバ１００に送信する部分である。また、対話サーバ１００から質問文候補または聞き返しキーワードを受信する部分である。 The communication unit 203 is a part that transmits the input text input by the user, the affirmative / negative instruction for the answer and the user information to the dialogue server 100. In addition, it is a part that receives a question sentence candidate or a question keyword from the dialogue server 100.
　表示部２０４は、ユーザにより入力された入力文章、質問文候補、または聞き返しキーワードを対話形式で表示する部分である。すなわち、表示部２０４は、対話サーバ１００との間における対話画面を表示する部分である。 The display unit 204 is a part that displays an input sentence, a question sentence candidate, or a query keyword input by the user in an interactive format. That is, the display unit 204 is a part that displays a dialogue screen with the dialogue server 100.
　つぎに、このように構成された対話サーバ１００およびユーザ端末２００の動作について説明する。図２は、その動作を示すシーケンス図である。 Next, operations of the dialog server 100 and the user terminal 200 configured as described above will be described. FIG. 2 is a sequence diagram showing the operation.
　ユーザ端末２００において、キー受付部２０１は、ユーザから入力文章を受け付け（Ｓ１０１）、通信部２０３は、利用者情報記憶部２０２から利用者情報を抽出し（Ｓ１０２）、入力文章および利用者情報を対話サーバ１００に送信する（Ｓ１０３）。 In the user terminal 200, the key receiving unit 201 receives an input sentence from the user (S101), the communication unit 203 extracts user information from the user information storage unit 202 (S102), and inputs the input sentence and the user information. It transmits to the dialogue server 100 (S103).
　対話サーバ１００において、受信部１０１は、ユーザ端末２００から送信された入力文章および利用者情報を受信する。受信部１０１は、入力文章から入力キーワードを抽出し、入力内容を認識する（Ｓ１０４）。 In the dialogue server 100, the receiving unit 101 receives the input text and user information transmitted from the user terminal 200. The receiving unit 101 extracts an input keyword from the input sentence and recognizes the input content (S104).
　検索部１０２は、抽出した入力キーワードに基づいて真理表データベース１０４に対する検索処理を行い、一または複数の質問文候補を抽出する（Ｓ１０５）。検索部１０２は、抽出した質問文候補が複数あった場合には、ステップＳ１０３で取得した利用者情報と、抽出した複数の質問文候補のそれぞれの検索キーワードとを比較する（Ｓ１０６）。比較対象となる利用者情報は、一つでもよいし、複数でもよい。また、後述する通り、複数の利用者情報の組み合わせを変えて比較してもよい。また、検索に用いられる利用者情報として、検索キーワードとして真理表データベース１０４に記述されているものを優先することが好ましい。 The search unit 102 performs a search process on the truth table database 104 based on the extracted input keyword, and extracts one or a plurality of question sentence candidates (S105). When there are a plurality of extracted question sentence candidates, the search unit 102 compares the user information acquired in step S103 with each search keyword of the extracted plurality of question sentence candidates (S106). One or more pieces of user information may be compared. Further, as will be described later, a combination of a plurality of pieces of user information may be changed for comparison. Moreover, it is preferable to give priority to the user information used for the search that is described in the truth table database 104 as a search keyword.
　検索部１０２は、比較の結果、当該利用者情報と一致する検索キーワードに対応付けられている質問文候補を決定する（Ｓ１０７）。なお、検索部１０２は、利用者情報を用いても質問文候補が複数、残った場合には、そのすべてを質問文候補として決定してもよいし、真理表データベース１０４における検索キーワードとの一致の程度（キーワードの一致数）に基づいて一の質問文候補を決定してもよい。 The search unit 102 determines the question sentence candidate associated with the search keyword that matches the user information as a result of the comparison (S107). If a plurality of question sentence candidates remain even if the user information is used, the search unit 102 may determine all of them as question sentence candidates or match the search keywords in the truth table database 104. One question sentence candidate may be determined based on the degree of (number of keyword matches).
　応答部１０３は、決定した質問文候補をユーザ端末２００に送信する。ユーザ端末２００において、ユーザは質問文候補に対して肯定・否定の意図を指示する。本実施形態では、ユーザは肯定指示をすると、ユーザ端末２００は、その旨を対話サーバ１００に送信する（Ｓ１０８）。 The response unit 103 transmits the determined question sentence candidate to the user terminal 200. In the user terminal 200, the user instructs an intention of affirmation / negative for the question sentence candidate. In the present embodiment, when the user gives an affirmative instruction, the user terminal 200 transmits a message to that effect to the dialogue server 100 (S108).
　対話サーバ１００において、検索部１０２は、ユーザ端末２００から肯定指示を受けた質問文候補に対応する回答をＦＡＱデータベース１０５から取得する（Ｓ１０９）。応答部１０３は、質問文（質問文候補）およびその回答をユーザ端末２００に送信する（Ｓ１１０）。 In the dialogue server 100, the search unit 102 acquires an answer corresponding to the question sentence candidate that has received an affirmative instruction from the user terminal 200 from the FAQ database 105 (S109). The response unit 103 transmits the question sentence (question sentence candidate) and the answer to the user terminal 200 (S110).
　このようにユーザ端末２００から送信される利用者情報を用いることで不必要な対話をすることなく質問文候補を絞り込むことができ、対話回数を削減することができる。 Thus, by using the user information transmitted from the user terminal 200, the question sentence candidates can be narrowed down without an unnecessary dialogue, and the number of dialogues can be reduced.
　つぎに、上記処理におけるユーザ端末２００の対話画面の具体例について説明する。図３は、ユーザ端末２００における対話画面の具体例を示す図である。図３に示すとおり、吹き出しｕ１は、ユーザがキー受付部２０１を操作することで入力した入力文章を示す。点線枠ｕ１１は、利用者情報記憶部２０２に記憶されている利用者情報を示す。ここでは、利用者情報として、利用端末：端末Ａ、性別：男性が記憶されている。なお、点線枠ｕ１１は、説明の便宜上、明示したが、実際の対話画面には表示されない。吹き出しｓ２は、対話サーバ１００において検索された質問文候補を示す。 Next, a specific example of the dialogue screen of the user terminal 200 in the above process will be described. FIG. 3 is a diagram illustrating a specific example of an interactive screen on the user terminal 200. As illustrated in FIG. 3, the balloon u <b> 1 indicates an input sentence input by the user operating the key receiving unit 201. A dotted frame u11 indicates user information stored in the user information storage unit 202. Here, the user terminal: terminal A and gender: male are stored as user information. The dotted frame u11 is clearly shown for convenience of explanation, but is not displayed on the actual dialogue screen. A balloon s2 indicates a question sentence candidate searched in the dialogue server 100.
　対話サーバ１００において、受信部１０１は、吹き出しｕ１で示される入力文章を受信し、その入力文章から、入力キーワードとして「操作方法」を抽出する（図２のＳ１０４に相当）。検索部１０２は、「操作方法」に基づいて検索を行い、質問文候補を取得する（図２のＳ１０５に相当）。 In the dialogue server 100, the receiving unit 101 receives the input sentence indicated by the balloon u1, and extracts “operation method” as an input keyword from the input sentence (corresponding to S104 in FIG. 2). The search unit 102 performs a search based on the “operation method” and acquires a question sentence candidate (corresponding to S105 in FIG. 2).
　一方、図４に示されるとおり真理表データベース１０４には、質問文候補と検索キーワードとが対応付けて記憶されている。図４に示されるとおり、質問文候補「端末Ａの操作方法」には、検索キーワード「端末Ａ」「操作方法」が対応付けられている。また、「端末Ｂの操作方法」には、「端末Ｂ」「操作方法」が対応付けられている。また、「ＰＣの操作方法」には、「ＰＣ」「操作方法」が対応付けられている。なお、真理表データベース１０４は、当然に他の質問文候補およびその検索キーワードを記憶している。 On the other hand, as shown in FIG. 4, the truth table database 104 stores question sentence candidates and search keywords in association with each other. As shown in FIG. 4, the search keyword “terminal A” and “operation method” are associated with the question sentence candidate “operation method of terminal A”. Further, “terminal B” and “operation method” are associated with “operation method of terminal B”. “PC operation method” is associated with “PC” and “operation method”. The truth table database 104 naturally stores other question sentence candidates and their search keywords.
　そして、検索部１０２は、検索キーワード「操作方法」をキーにして、真理表データベース１０４を検索して、質問文候補「端末Ａの操作方法」、「端末Ｂの操作方法」、および「ＰＣの操作方法」を抽出する（図２のＳ１０５）。 Then, the search unit 102 searches the truth table database 104 using the search keyword “operation method” as a key, and asks question sentence candidates “operation method of terminal A”, “operation method of terminal B”, and “PC The “operation method” is extracted (S105 in FIG. 2).
　さらに、検索部１０２は、利用者情報を用いて、質問文候補を絞り込む。ここでは、検索部１０２は利用者情報と各質問文候補の検索キーワードとを比較し（図２のＳ１０６）、利用者情報：端末Ａを含む「端末Ａの操作方法」を質問文候補として、決定する（図２のＳ１０７）。 Further, the search unit 102 narrows down question sentence candidates using the user information. Here, the search unit 102 compares the user information and the search keyword of each question sentence candidate (S106 in FIG. 2), and uses the user information: “method of operating terminal A” including terminal A as a question sentence candidate. Determine (S107 in FIG. 2).
　応答部１０３は、検索部１０２が抽出した質問文候補を含んだメッセージを生成して、送信処理を行う。具体的には、吹き出しｓ２に記載される通り、『「端末Ａの操作方法」についての回答を表示しますか？』のメッセージを生成し、ユーザ端末２００に送信する。ユーザ端末２００は、その対話画面にそのメッセージを表示する。 The response unit 103 generates a message including the question sentence candidate extracted by the search unit 102 and performs transmission processing. Specifically, as described in the balloon s2, “Do you want to display an answer to“ How to operate terminal A ”?” Is generated and transmitted to the user terminal 200. The user terminal 200 displays the message on the dialog screen.
　従来においては質問文候補を絞り込む際に、検索キーワードを用いて、ユーザに聞き返しを行うことにより、徐々に質問文候補を絞り込んでいたが、利用者情報を用いることで、その聞き返し処理を省略することができる。 In the past, when narrowing down the question sentence candidates, the question sentence candidates were gradually narrowed down by using the search keyword to ask the user. be able to.
　つぎに、対話サーバ１００から提示された質問文候補に対してユーザが否定した時の処理について説明する。図５は、その動作を示すシーケンス図である。ステップＳ１０１～Ｓ１０７までは図２と同じである。 Next, processing when the user denies the question sentence candidate presented from the dialogue server 100 will be described. FIG. 5 is a sequence diagram showing the operation. Steps S101 to S107 are the same as those in FIG.
　対話サーバ１００において、応答部１０３が質問文候補を送信し、受信部１０１がユーザ端末２００から否定指示を受信すると（Ｓ１０８ａ）、検索部１０２は、否定指示された質問文候補に含まれている利用者情報に代えて、真理表データベース１０４から一の検索キーワードを聞き返しキーとして取得する（Ｓ１１２）。聞き返しキーとしての選択は、上述したとおり、真理表データベース１０４における利用頻度などに基づいて決定される。 In the dialogue server 100, when the response unit 103 transmits a question sentence candidate and the reception unit 101 receives a negative instruction from the user terminal 200 (S108a), the search unit 102 is included in the question sentence candidate that has been instructed negatively. Instead of the user information, one search keyword is acquired as a return key from the truth table database 104 (S112). As described above, the selection as the answer key is determined based on the usage frequency in the truth table database 104.
　対話サーバ１００において、検索部１０２は、聞き返しキーとして選択した一の検索キーワードを含んだ質問文候補を決定する（Ｓ１１３）。応答部１０３は、質問文候補をユーザ端末２００に送信する。ユーザ端末２００において、表示部２０４は、その質問文候補を表示し、キー受付部２０１は、その質問文候補に対して肯定・否定の指示をユーザから受け付ける。 In the dialogue server 100, the search unit 102 determines a question sentence candidate including the one search keyword selected as the answer key (S113). The response unit 103 transmits the question sentence candidate to the user terminal 200. In the user terminal 200, the display unit 204 displays the question sentence candidate, and the key reception unit 201 receives an affirmative / negative instruction for the question sentence candidate from the user.
　これにより、利用者情報を用いなくても質問文候補を絞り込むことができる。なお、上述説明では、検索キーワード（聞き返しキーワード）を用いて聞き返し処理を行っているが、聞き返しキーワードに代えて、さらに別の利用者情報を用いて質問文候補を絞り込むようにしてもよい。 This makes it possible to narrow down question sentence candidates without using user information. In the above description, the query process is performed using the search keyword (listen keyword), but the question sentence candidates may be narrowed down using another user information instead of the query keyword.
　図６は、上述の処理における対話画面を示す図である。吹き出しｕ３は、ユーザが入力した入力文章である。上述したのと同様に、点線枠ｕ３１は、ユーザ端末２００に記憶されている利用者情報である。 FIG. 6 is a diagram showing an interactive screen in the above-described processing. A balloon u3 is an input sentence input by the user. As described above, the dotted frame u31 is user information stored in the user terminal 200.
　対話サーバ１００は、ユーザ端末２００から入力文章および利用者情報を受信すると、利用者情報を用いて「端末Ａの操作方法」を質問文候補として決定し、それを送信する。図６においては、対話サーバ１００は、『「端末Ａの操作方法」についての回答を表示しますか？』のメッセージを生成し、送信する。 When the dialogue server 100 receives the input text and the user information from the user terminal 200, the dialogue server 100 determines the “operation method of the terminal A” as a question text candidate using the user information and transmits it. In FIG. 6, the dialogue server 100 displays an answer about “How to operate terminal A”? ] Message is generated and sent.
　ユーザ端末２００においては、その質問文候補の否定操作を行い、否定指示を対話サーバ１００に送信する。対話画面では、吹き出しｕ３２で示される通り「いいえ」と表示される。 The user terminal 200 performs a negative operation on the question sentence candidate and transmits a negative instruction to the dialogue server 100. On the dialog screen, “No” is displayed as indicated by the balloon u32.
　対話サーバ１００において、受信部１０１が質問文候補「端末Ａの操作方法」の否定の旨を受信し、検索部１０２は、利用者情報：端末Ａが否定されたと判断する。 In the dialogue server 100, the receiving unit 101 receives a negative message question “terminal A operation method”, and the search unit 102 determines that the user information: terminal A is denied.
　よって、検索部１０２は、利用者情報：端末Ａを検索キーワードから除外し、新たな別の検索キーワードを真理表データベース１０４から抽出し、その検索キーワードに基づいた検索を行う。図６では、検索部１０２は、「端末Ｂ」を検索キーワードとして選択し、これを聞き返しキーワードとしてユーザ端末２００に送信する。 Therefore, the search unit 102 excludes the user information: terminal A from the search keyword, extracts another new search keyword from the truth table database 104, and performs a search based on the search keyword. In FIG. 6, the search unit 102 selects “terminal B” as a search keyword, and transmits it to the user terminal 200 as a return keyword.
　利用者情報を用いて決定した質問文候補がユーザに否定された場合は、その利用者情報が不適切であることが想定される。したがって、そのような場合においては、利用者情報を用いずに検索を行うことが、対話回数削減につながる。 When the question sentence candidate determined using the user information is denied by the user, it is assumed that the user information is inappropriate. Therefore, in such a case, searching without using user information leads to a reduction in the number of conversations.
　なお、図６においては、取得済みキーとして、端末Ａ（利用者情報）、操作方法（通常）と表記されている。取得済みキーは、検索に用いられたキーワードを示しており、その括弧は、キーワードの出所元を示している。この表記を対話画面に表示することで、ユーザは、どのようなキーワードが用いられた検索結果であるかを知ることができ、その検索結果を正確に理解することができる。 In FIG. 6, terminal A (user information) and operation method (normal) are shown as acquired keys. The acquired key indicates the keyword used for the search, and the parentheses indicate the origin of the keyword. By displaying this notation on the dialogue screen, the user can know what keyword is used as the search result, and can accurately understand the search result.
　つぎに、利用者情報を組み合わせて検索する対話サーバ１００の処理における変形例について説明する。図７は、ユーザ端末２００における対話画面（ほかの例）を示す図である。ユーザ端末２００は、点線枠２１で示す通り、利用者情報として星座：ふたご座、血液型０型を記憶している。なお、上述と同様に、説明の便宜上、点線枠２１を示しているが、実際には表示されない。 Next, a description will be given of a modification in the processing of the dialogue server 100 that searches by combining user information. FIG. 7 is a diagram showing an interactive screen (another example) on the user terminal 200. The user terminal 200 stores constellation: Gemini and blood type 0 as user information, as indicated by the dotted frame 21. As described above, the dotted frame 21 is shown for convenience of explanation, but it is not actually displayed.
　対話サーバ１０において、受信部１０１が、入力文章「運勢を教えて」とともに、利用者情報の星座：ふたご座、血液型：Ｏ型を受信すると、まず入力文章から入力キーワード「運勢」を取得する。検索部１０２は、入力キーワード「運勢」をキーにして、いくつかの質問文候補を検索する。さらに、利用者情報を相互に組み合わせを変えて、質問文候補を絞り込む（図２のステップＳ１０６参照）。例えば、検索部１０２は、「ふたご座」、「Ｏ型」、「ふたご座、Ｏ型」の組合せで検索を行う。なお、利用者情報の組合せによっては、質問文候補の紐付けがなされていない場合がある。その場合には、当然に質問文候補を絞り込むことができない。 In the dialogue server 10, when the receiving unit 101 receives the input text “Tell me about fortune” and the user information constellation: Gemini, blood type: O type, first, the input keyword “fortune” is acquired from the input text. . The search unit 102 searches for several question sentence candidates using the input keyword “fortune” as a key. Further, the question information candidates are narrowed down by changing the combination of user information (see step S106 in FIG. 2). For example, the search unit 102 performs a search using a combination of “Gemini”, “O type”, and “Gemini, O type”. Depending on the combination of user information, question sentence candidates may not be linked. In that case, of course, question sentence candidates cannot be narrowed down.
　図７の例では、以下の質問文候補に絞り込む。 In the example of Fig. 7, we narrow down to the following question sentence candidates.
・ふたご座の運勢
・Ｏ型の運勢
・ふたご座のＯ型の運勢
ユーザは、これら質問文候補からその適否について指示することで、対話サーバ１００はその指示に応じた質問文及びその回答をユーザに提示することができる。 -Gemini Fortune-O-type Fortune-Gemini O-type Fortune User instructs the question text candidates from the question sentence candidates, so that the dialogue server 100 gives the user a question sentence corresponding to the instruction and its answer. Can be presented.
　図８は、図７の対話画面において用いられる真理表データベース１０４の具体例である。図７に示される通り、真理表データベース１０４には、「ふたご座の運勢」「Ｏ型の運勢」「ふたご座のＯ型の運勢」が、それぞれの検索キーワードとともに記憶されている。真理表データベース１０４を用いて図７に示される対話を可能にする。 FIG. 8 is a specific example of the truth table database 104 used in the dialogue screen of FIG. As shown in FIG. 7, the truth table database 104 stores “fortune of Gemini”, “O-type fortune”, and “O-shaped fortune of Gemini” together with each search keyword. The truth table database 104 is used to enable the interaction shown in FIG.
　なお、これら利用者情報の組合せから得られたそれぞれの質問文候補に対して、ユーザから否定されると、これら利用者情報を用いることなく、他の検索キーワードを用いて聞き返し処理などをすることで検索処理が行われる。 In addition, if the user denies each question sentence candidate obtained from the combination of the user information, the user can use the other search keywords to perform a replay process without using the user information. The search process is performed.
　つぎに、入力キーワードと真理表データベース１０４における検索キーワードとの関係に基づいて利用者情報を使わない場合が好適な場合がある。図９は、その好適な事例を説明するために、対話画面の具体例と、真理表データベース１０４の具体例を示す図である。 Next, it may be preferable that user information is not used based on the relationship between the input keyword and the search keyword in the truth table database 104. FIG. 9 is a diagram showing a specific example of the dialogue screen and a specific example of the truth table database 104 in order to explain the preferable case.
　図９（ａ）は、対話画面の例である。図に示される通り、ユーザは、入力文章として、「端末Ｂの操作方法を教えて」と入力している（吹き出しｕ４）。なお、利用者情報として、利用端末：端末Ａが登録されている（点線枠ｕ４１）。図２を参照すると、利用者情報を用いる検索を実行するため、対話サーバ１００の検索部１０２は、入力キーワード「端末Ｂ」、および「操作方法」を使って検索を行い、その後、利用者情報「端末Ａ」を用いた検索を行う（図２　Ｓ１０５，Ｓ１０６）。 FIG. 9A shows an example of the dialogue screen. As shown in the figure, the user has input “Tell me how to operate terminal B” as an input sentence (balloon u4). Note that the user terminal: terminal A is registered as the user information (dotted line frame u41). Referring to FIG. 2, in order to execute a search using user information, the search unit 102 of the dialog server 100 performs a search using the input keyword “terminal B” and “operation method”, and then uses the user information. A search using “terminal A” is performed (FIG. 2, S105, S106).
　しかしながら、本例示においては、対話サーバ１００の真理表データベース１０４は、検索キーワード「端末Ｂ」「操作方法」のみを、「端末Ｂの操作方法」に対応付けて記憶している（図９（ｂ））。 However, in this example, the truth table database 104 of the dialogue server 100 stores only the search keywords “terminal B” and “operation method” in association with “operation method of terminal B” (FIG. 9B). )).
　よって、入力キーワードと、検索キーワードとが完全一致しており、検索部１０２は、利用者情報を用いた検索をさらに行う必要性がないと判断できる。したがって、検索部１０２は、図２のステップＳ１０６を行うことなく、一の質問文候補を決定することができる。 Therefore, the input keyword and the search keyword completely match, and the search unit 102 can determine that there is no need to further perform a search using the user information. Therefore, the search part 102 can determine one question sentence candidate, without performing step S106 of FIG.
　図９（ａ）では、さらに対話サーバ１００は「端末Ｂの操作方法」についての回答をユーザ端末２００に送信している（吹き出しｓ４）。よって、対話回数を削減することができる。 In FIG. 9 (a), the dialogue server 100 further transmits an answer about “the operation method of the terminal B” to the user terminal 200 (balloon s4). Therefore, the number of conversations can be reduced.
　したがって、入力キーワードと、検索キーワードとが完全一致している場合には、利用者情報を用いてさらに絞り込む必要はなく、検索部１０２は、その入力キーワードに対応する質問文候補を決定する。なお、質問文候補が複数ある場合には、その複数すべてを質問文候補としてユーザ端末２００に提供する。 Therefore, when the input keyword and the search keyword completely match, it is not necessary to further narrow down using the user information, and the search unit 102 determines a question sentence candidate corresponding to the input keyword. In addition, when there are a plurality of question sentence candidates, all of the plurality are provided to the user terminal 200 as question sentence candidates.
　つぎに、真理表データベース１０４における検索キーワードと完全一致させるように入力キーワードおよび利用者情報を組み合わせて、質問文候補を決定するときの処理について説明する。 Next, processing for determining a question sentence candidate by combining an input keyword and user information so as to completely match a search keyword in the truth table database 104 will be described.
　図１０は、その処理を行うときの対話画面の具体例および真理表データベース１０４の具体例を示す図である。 FIG. 10 is a diagram showing a specific example of the dialogue screen and a specific example of the truth table database 104 when performing the processing.
　図１０（ａ）は、対話画面の具体例を示す。図に示される通り、ユーザは、入力文章として「端末Ｂの操作方法を教えて」を入力している（吹き出しｕ５）。ユーザ端末２００には、利用者情報として、利用端末：端末Ａ、性別：男、：日本語が登録されている（点線枠ｕ５１）。 FIG. 10A shows a specific example of the dialogue screen. As shown in the figure, the user has input “Tell me how to operate terminal B” as an input sentence (balloon u5). In the user terminal 200, the user terminal: terminal A, gender: male, and Japanese are registered as user information (dotted line frame u51).
　一方、図１０（ｂ）は、真理表データベース１０４における検索キーワードと質問文候補との記憶内容を示す。図１０（ｂ）に示される検索キーワードと完全一致させるために、対話サーバ１００の検索部１０２は、入力キーワードの「操作方法」で検索した後に、利用者情報を用いた検索を行うために、利用端末：端末Ａ、言語：日本語を選択する。 On the other hand, FIG. 10B shows the storage contents of the search keyword and question sentence candidate in the truth table database 104. In order to completely match the search keyword shown in FIG. 10B, the search unit 102 of the dialogue server 100 searches for the user keyword after performing a search using the “operation method” of the input keyword. Use terminal: Terminal A, Language: Japanese is selected.
　このように対話サーバ１００において、検索部１０２は、真理表データベース１０４における検索キーワードと完全一致する入力キーワードおよび利用者情報の組み合わせを選択することで、より適切な利用者情報を決定することができる。 As described above, in the dialog server 100, the search unit 102 can determine more appropriate user information by selecting a combination of an input keyword and user information that completely matches the search keyword in the truth table database 104. .
　図１０（ａ）の例では、対話サーバ１００は、「日本語による端末Ａの操作方法」を質問文候補としてユーザ端末２００に送信している（吹き出しｓ５）。 In the example of FIG. 10 (a), the dialogue server 100 transmits “Japanese terminal A operation method” to the user terminal 200 as a question sentence candidate (speech balloon s5).
　つぎに、本実施形態の対話サーバ１００の作用効果について説明する。この対話サーバ１００は、ユーザによる入力に基づいて検索結果を応答する対話サーバであり、受信部１０１は、ユーザが操作するユーザ端末２００から入力キーワードを取得するとともに、ユーザに関連付けられている利用者情報を受信する。 Next, operational effects of the dialogue server 100 of the present embodiment will be described. The dialogue server 100 is a dialogue server that responds to a search result based on an input by a user, and the receiving unit 101 acquires an input keyword from the user terminal 200 operated by the user and a user associated with the user. Receive information.
　真理表データベース１０４は、一または複数の検索キーワードと質問文候補（応答候補に相当）とを対応付けて記憶しておき、検索部１０２は、この真理表データベース１０４から、入力キーワードおよび利用者情報に対応する応答候補を検索する。 The truth table database 104 stores one or a plurality of search keywords and question sentence candidates (corresponding to response candidates) in association with each other, and the search unit 102 receives input keywords and user information from the truth table database 104. Search for response candidates corresponding to.
　応答部１０３は、検索部１０２により検索された応答候補をユーザ端末２００に対して送信する。 The response unit 103 transmits the response candidates searched by the search unit 102 to the user terminal 200.
　この対話サーバ１００によれば、利用者情報を用いることで、ユーザ端末２００との間の対話回数を削減することができる。したがって、ユーザにとって効率的な検索を可能にする。さらに、対話サーバ１００にとっても、対話回数を削減することで、処理動作を制御する制御部などのハードウエア負荷を軽減することができる。さらに、ネットワークトラフィックを抑えることができる。 According to this dialogue server 100, the number of dialogues with the user terminal 200 can be reduced by using the user information. Therefore, an efficient search is possible for the user. Furthermore, for the dialogue server 100, it is possible to reduce the hardware load of the control unit that controls the processing operation by reducing the number of dialogues. Furthermore, network traffic can be suppressed.
　上記説明では、利用者情報は、ユーザ端末２００から送信されることになっているが、それに限るものではない。ユーザの属性情報または登録情報などの利用者情報を対話サーバ１００またはそのほかネットワーク上に配置されるサーバに登録されおり、対話サーバ１００は、そこから利用者情報として取得してもよい。その場合、ユーザＩＤなどの識別情報と利用者情報との対応付けをしておく必要がある。また、対話サーバ１００は、検索を行う際において、ユーザＩＤ等をユーザ端末２００から取得する必要がある。 In the above description, the user information is transmitted from the user terminal 200, but is not limited thereto. User information such as user attribute information or registration information is registered in the dialog server 100 or other servers arranged on the network, and the dialog server 100 may acquire user information therefrom. In that case, it is necessary to associate identification information such as a user ID with user information. Further, the dialogue server 100 needs to acquire a user ID and the like from the user terminal 200 when performing a search.
　対話サーバ１００において、検索部１０２は、入力キーワードおよび利用者情報に応じて追加入力を促すための検索を行ってもよい。例えば、入力キーワードおよび利用者情報を用いても質問文候補を所定数以下に絞り込むことができない場合には、さらに追加入力を促すため、聞き返しキーを用いて質問文候補を絞り込むようにしてもよい。 In the interactive server 100, the search unit 102 may perform a search for prompting additional input according to the input keyword and user information. For example, if the question sentence candidates cannot be narrowed down to a predetermined number or less even using the input keyword and user information, the question sentence candidates may be narrowed down by using a return key to prompt further input. .
　また、本実施形態の対話サーバ１００において、検索部１０２は、入力キーワードに基づいて検索を行って複数の質問文候補（応答候補）を得て、当該複数の質問文候補（応答候補）のうち利用者情報を含む質問文候補（応答候補）を検索する。応答部１０３は、検索した質問文候補（応答候補）をユーザ端末２００に送信する。 In the interactive server 100 of the present embodiment, the search unit 102 performs a search based on the input keyword to obtain a plurality of question sentence candidates (response candidates), and among the plurality of question sentence candidates (response candidates). Search for question sentence candidates (response candidates) including user information. The response unit 103 transmits the searched question sentence candidate (response candidate) to the user terminal 200.
　この対話サーバ１００によると、真理表データベース１０４に利用者情報と同じキーワードが登録されている場合には、それを優先させることで、検索を効率的に行うことができる。すなわち、利用者情報には、性別、年齢など、検索には直接関連性のない情報が含まれている場合がある。そのような利用者情報を用いても検索効率は上がることはなく、対話回数削減に寄与しない。したがって、複数の利用者情報がある場合には、検索データベースに登録されているものを優先させることで、検索効率を向上させ、結果対話回数を削減することができる。 According to the dialog server 100, when the same keyword as the user information is registered in the truth table database 104, the search can be efficiently performed by prioritizing it. That is, the user information may include information that is not directly related to the search, such as gender and age. Using such user information does not increase search efficiency and does not contribute to reducing the number of conversations. Therefore, when there are a plurality of pieces of user information, priority is given to those registered in the search database, thereby improving search efficiency and reducing the number of result dialogues.
　対話サーバ１００において、検索部１０２は、複数の利用者情報のうち、予め定められた条件にしたがった一または複数の利用者情報を用いて検索を行う。 In the interactive server 100, the search unit 102 performs a search using one or a plurality of user information according to a predetermined condition among a plurality of user information.
　予め定められた条件として、最も近い質問文候補（応答候補）に含まれているキーワード、全ての質問文候補（応答候補）に含まれているキーワード、ランキング上位の質問文候補（応答候補）のキーワード、マッチ種別にもとづいた質問文候補（応答候補）のキーワードなど、質問文候補（応答候補）に応じて利用者情報を切替えることで、対話回数の削減を向上させることができる。 As predetermined conditions, keywords included in the closest question sentence candidate (response candidate), keywords included in all question sentence candidates (response candidates), and question sentence candidates (response candidates) in the top ranking By switching the user information according to the question sentence candidate (response candidate) such as the keyword and the keyword of the question sentence candidate (response candidate) based on the match type, the number of conversations can be reduced.
　「全ての質問文候補」に含まれている利用者情報を選択する場合には、入力キーワードおよび利用者情報と、真理表データベース１０４の検索キーワードとが完全マッチとなる、利用者情報を選択するのがよい。完全マッチとは、真理表データベース１０４の各質問文に対応付けられている一または複数の検索キーワードと、入力キーワードおよび利用者情報とが、過不足なく、一致している状態をいう。 When selecting user information included in “all question sentence candidates”, user information that matches the input keyword and user information with the search keyword of the truth table database 104 is selected. It is good. The complete match is a state in which one or a plurality of search keywords associated with each question sentence in the truth table database 104, the input keyword, and the user information match with each other without excess or deficiency.
　完全マッチとなる利用者情報を選択した場合には、対話サーバ１００は、聞き返しキーを返信することなく、その完全マッチに対応した質問文候補を返信することができる。 When user information that is a perfect match is selected, the dialogue server 100 can return a question sentence candidate corresponding to the complete match without returning a response key.
　なお、検索キーワードが過剰となる利用者情報を選択する、すなわち、利用者情報および入力キーワードが、検索キーワードより少ない状態（不足マッチ）となる利用者情報を選択することも、質問文候補を絞り込む上で、技術的意義がある。したがって、完全マッチ以外に不足マッチとなる利用者情報を選択することも考えられる。 It is also possible to select user information that has excessive search keywords, that is, to select user information that has less user information and input keywords than the search keyword (insufficient match). Above, it has technical significance. Therefore, it is also conceivable to select user information that is a shortage match other than a perfect match.
　「最も近い質問文候補」とは、質問文候補に対応付けられている複数の検索キーワードと、入力キーワードおよび利用者情報とからなる複数のキーワードとを比較した場合、その一致数が多くなる利用者情報に対応する質問文候補である。例えば、質問文候補に対応付けられている検索キーワード：Ａ、Ｂ、Ｃであり、入力キーワード：Ａ、利用者情報：Ｂ、Ｄとあった場合、利用者情報：Ｂのほうが、利用者情報：Ｄより、その一致数が多くなる。この場合における利用者情報：Ｂを用いた質問文候補が、最も近い質問文候補である。よって、利用者情報：Ｂが選択される。 The “closest question sentence candidate” is a use that increases the number of matches when a plurality of search keywords associated with the question sentence candidate are compared with a plurality of keywords composed of input keywords and user information. Question sentence candidate corresponding to person information. For example, when there are search keywords A, B, and C associated with the question sentence candidates, and input keyword A and user information B and D, user information B is more user information. : The number of matches is greater than D. The question sentence candidate using the user information: B in this case is the closest question sentence candidate. Therefore, user information B is selected.
　「ランキング上位の質問文候補」とは、閲覧頻度に基づいたランキングなどに基づいた上位の質問文候補をいう。閲覧頻度にかかわらず、他の基準でのランキングでもよい。 “The highest ranking question sentence candidate” means a higher ranking question sentence candidate based on ranking based on browsing frequency. Regardless of the viewing frequency, rankings based on other criteria may be used.
　対話サーバ１００において、受信部１０１は、ユーザ端末２００から、一の質問文候補（応答候補）に対して否定の意図を受信すると、検索部１０２は、その検索に用いた利用者情報を用いずに検索をやり直す。例えば、検索部１０２は、利用者情報に代えて、他の検索キーワードを真理表データベース１０４から取得し、その検索キーワードを用いた検索を行う。 In the interactive server 100, when the receiving unit 101 receives a negative intention from the user terminal 200 for one question sentence candidate (response candidate), the searching unit 102 does not use the user information used for the search. Try searching again. For example, the search unit 102 acquires other search keywords from the truth table database 104 instead of the user information, and performs a search using the search keywords.
　この構成により、利用者情報を用いた検索により取得した応答候補がユーザに否定された場合には、その利用者情報はその検索に対しては不適切であると考えられる。したがって、その場合には、利用者情報を除外し、検索をやり直すことで、適切な検索を行うとともに、結果的に、対話回数削減を向上させることができる。 With this configuration, when a response candidate obtained by a search using user information is denied by the user, the user information is considered inappropriate for the search. Therefore, in this case, by excluding the user information and performing the search again, an appropriate search can be performed and, as a result, the reduction in the number of dialogs can be improved.
　また、対話サーバ１００において、検索部１０２は、利用者情報が複数あった場合には、当該複数の利用者情報の組合せを変えて、入力キーワードと組み合わせて、それぞれの検索を行う。 In the interactive server 100, when there are a plurality of pieces of user information, the search unit 102 performs a search by changing the combination of the plurality of pieces of user information and combining them with the input keyword.
　この構成により、複数の利用者情報がある場合には、当該複数の利用者情報の組合せを変えて、組合せを変えた利用者情報と入力キーワードとを用いて検索を行うことで、対話回数を削減することができる。 With this configuration, when there is a plurality of user information, the number of conversations can be reduced by changing the combination of the plurality of user information and performing a search using the user information and the input keyword with the changed combination. Can be reduced.
　また、対話サーバ１００において、検索部１０２は、真理表データベース１０４における質問文候補（応答候補）ごとに登録されている一または複数の検索キーワードからなるキーワード群と、入力キーワードおよび一または複数の利用者情報の組合せからなるキーワード群と、が完全一致するように、一または複数の利用者情報を選択し、当該一または複数の利用者情報と前記入力キーワードとを用いた検索を行う。 In the dialogue server 100, the search unit 102 includes a keyword group including one or more search keywords registered for each question sentence candidate (response candidate) in the truth table database 104, an input keyword, and one or more uses. One or a plurality of user information is selected so that a keyword group consisting of a combination of user information is completely matched, and a search using the one or a plurality of user information and the input keyword is performed.
　この構成により、入力キーワードと検索キーワードとが完全に一致する質問文候補がない場合には、完全に一致するように利用者情報を選択することで、効率的な検索を可能にする。すなわち、過不足なく、完全に一致する検索キーワードに対応する質問文候補は、ユーザが望んだ検索結果である可能性が高く、効率的な検索を可能にする。 ∙ With this configuration, when there is no question sentence candidate whose input keyword and search keyword completely match, it is possible to perform efficient search by selecting user information so as to match completely. That is, there is a high possibility that the question sentence candidate corresponding to the completely matched search keyword without excess or deficiency is a search result desired by the user, and enables efficient search.
　また、対話サーバ１００において、検索部１０２は、真理表データベース１０４における質問文候補ごとに登録されている一または複数の検索キーワードからなるキーワード群と、前記入力キーワードからなるキーワード群と、が完全一致する場合には、一または複数の利用者情報を選択しない。 In the dialogue server 100, the search unit 102 completely matches a keyword group consisting of one or a plurality of search keywords registered for each question sentence candidate in the truth table database 104 and a keyword group consisting of the input keywords. When doing so, one or a plurality of user information is not selected.
　この構成によれば、入力キーワードのみが検索キーワードと完全に一致する場合には、利用者情報を選択する必要がない。したがって、効率的な検索を可能にする。 According to this configuration, when only the input keyword matches the search keyword completely, there is no need to select user information. Therefore, an efficient search is possible.
　上記実施の形態の説明に用いたブロック図は、機能単位のブロックを示している。これらの機能ブロック（構成部）は、ハードウェア及び／又はソフトウェアの任意の組み合わせによって実現される。また、各機能ブロックの実現手段は特に限定されない。すなわち、各機能ブロックは、物理的及び／又は論理的に結合した１つの装置により実現されてもよいし、物理的及び／又は論理的に分離した２つ以上の装置を直接的及び／又は間接的に (例えば、有線及び／又は無線)で接続し、これら複数の装置により実現されてもよい。 The block diagram used in the description of the above embodiment shows functional unit blocks. These functional blocks (components) are realized by any combination of hardware and / or software. Further, the means for realizing each functional block is not particularly limited. That is, each functional block may be realized by one device physically and / or logically coupled, and two or more devices physically and / or logically separated may be directly and / or indirectly. Specifically, it may be realized by a plurality of these devices connected by a hook (for example, wired and / or wireless).
　例えば、本発明の一実施の形態における対話サーバ１００およびユーザ端末２００などは、本実施形態の処理を行うコンピュータとして機能してもよい。図１１は、本実施形態に係る対話サーバ１００およびユーザ端末２００のハードウェア構成の一例を示す図である。上述の対話サーバ１００およびユーザ端末２００は、物理的には、プロセッサ１００１、メモリ１００２、ストレージ１００３、通信装置１００４、入力装置１００５、出力装置１００６、バス１００７などを含むコンピュータ装置として構成されてもよい。 For example, the dialogue server 100 and the user terminal 200 according to an embodiment of the present invention may function as a computer that performs the processing according to the present embodiment. FIG. 11 is a diagram illustrating an example of a hardware configuration of the dialogue server 100 and the user terminal 200 according to the present embodiment. The above-described dialog server 100 and user terminal 200 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like. .
　なお、以下の説明では、「装置」という文言は、回路、デバイス、ユニットなどに読み替えることができる。対話サーバ１００およびユーザ端末２００のハードウェア構成は、図に示した各装置を１つ又は複数含むように構成されてもよいし、一部の装置を含まずに構成されてもよい。 In the following description, the term “apparatus” can be read as a circuit, a device, a unit, or the like. The hardware configuration of the dialog server 100 and the user terminal 200 may be configured to include one or a plurality of the devices illustrated in the figure, or may be configured not to include some devices.
　対話サーバ１００およびユーザ端末２００における各機能は、プロセッサ１００１、メモリ１００２などのハードウェア上に所定のソフトウェア（プログラム）を読み込ませることで、プロセッサ１００１が演算を行い、通信装置１００４による通信や、メモリ１００２及びストレージ１００３におけるデータの読み出し及び／又は書き込みを制御することで実現される。 Each function in the dialog server 100 and the user terminal 200 is performed by causing the processor 1001 to perform calculations by reading predetermined software (programs) on hardware such as the processor 1001 and the memory 1002, and performing communication by the communication device 1004 and memory. This is realized by controlling data reading and / or writing in the storage 1003 and the storage 1003.
　プロセッサ１００１は、例えば、オペレーティングシステムを動作させてコンピュータ全体を制御する。プロセッサ１００１は、周辺装置とのインターフェース、制御装置、演算装置、レジスタなどを含む中央処理装置（ＣＰＵ：Central　Processing　Unit）で構成されてもよい。例えば、検索部１０２などは、プロセッサ１００１で実現されてもよい。 The processor 1001 controls the entire computer by operating an operating system, for example. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic device, a register, and the like. For example, the search unit 102 or the like may be realized by the processor 1001.
　また、プロセッサ１００１は、プログラム（プログラムコード）、ソフトウェアモジュールやデータを、ストレージ１００３及び／又は通信装置１００４からメモリ１００２に読み出し、これらに従って各種の処理を実行する。プログラムとしては、上述の実施の形態で説明した動作の少なくとも一部をコンピュータに実行させるプログラムが用いられる。例えば、対話サーバ１００の検索部１０２は、メモリ１００２に格納され、プロセッサ１００１で動作する制御プログラムによって実現されてもよく、他の機能ブロックについても同様に実現されてもよい。上述の各種処理は、１つのプロセッサ１００１で実行される旨を説明してきたが、２以上のプロセッサ１００１により同時又は逐次に実行されてもよい。プロセッサ１００１は、１以上のチップで実装されてもよい。なお、プログラムは、電気通信回線を介してネットワークから送信されても良い。 Further, the processor 1001 reads programs (program codes), software modules, and data from the storage 1003 and / or the communication device 1004 to the memory 1002, and executes various processes according to these. As the program, a program that causes a computer to execute at least a part of the operations described in the above embodiments is used. For example, the search unit 102 of the dialogue server 100 may be realized by a control program stored in the memory 1002 and operated by the processor 1001, and may be realized similarly for other functional blocks. Although the above-described various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. Note that the program may be transmitted from a network via a telecommunication line.
　メモリ１００２は、コンピュータ読み取り可能な記録媒体であり、例えば、ＲＯＭ（Read　Only　Memory）、ＥＰＲＯＭ（Erasable　Programmable　ＲＯＭ）、ＥＥＰＲＯＭ（Electrically Erasable Programmable ＲＯＭ）、ＲＡＭ（Random　Access　Memory）などの少なくとも１つで構成されてもよい。メモリ１００２は、レジスタ、キャッシュ、メインメモリ（主記憶装置）などと呼ばれてもよい。メモリ１００２は、本発明の一実施の形態に係る無線通信方法を実施するために実行可能なプログラム（プログラムコード）、ソフトウェアモジュールなどを保存することができる。 The memory 1002 is a computer-readable recording medium and includes, for example, at least one of ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), and the like. May be. The memory 1002 may be called a register, a cache, a main memory (main storage device), or the like. The memory 1002 can store a program (program code), a software module, and the like that can be executed to implement the wireless communication method according to the embodiment of the present invention.
　ストレージ１００３は、コンピュータ読み取り可能な記録媒体であり、例えば、ＣＤ－ＲＯＭ（Compact　Disc　ＲＯＭ）などの光ディスク、ハードディスクドライブ、フレキシブルディスク、光磁気ディスク(例えば、コンパクトディスク、デジタル多用途ディスク、Ｂｌｕ－ｒａｙ（登録商標）ディスク)、スマートカード、フラッシュメモリ(例えば、カード、スティック、キードライブ)、フロッピー（登録商標）ディスク、磁気ストリップなどの少なくとも１つで構成されてもよい。ストレージ１００３は、補助記憶装置と呼ばれてもよい。上述の記憶媒体は、例えば、メモリ１００２及び／又はストレージ１００３を含むデータベース、サーバその他の適切な媒体であってもよい。 The storage 1003 is a computer-readable recording medium such as an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (for example, a compact disk, a digital versatile disk, a Blu-ray). (Registered trademark) disk, smart card, flash memory (for example, card, stick, key drive), floppy (registered trademark) disk, magnetic strip, and the like. The storage 1003 may be referred to as an auxiliary storage device. The storage medium described above may be, for example, a database, server, or other suitable medium including the memory 1002 and / or the storage 1003.
　通信装置１００４は、有線及び／又は無線ネットワークを介してコンピュータ間の通信を行うためのハードウェア（送受信デバイス）であり、例えばネットワークデバイス、ネットワークコントローラ、ネットワークカード、通信モジュールなどともいう。例えば、上述の　受信部１０１および応答部１０３などは、通信装置１００４で実現されてもよい。 The communication device 1004 is hardware (transmission / reception device) for performing communication between computers via a wired and / or wireless network, and is also referred to as a network device, a network controller, a network card, a communication module, or the like. For example, the reception unit 101 and the response unit 103 described above may be realized by the communication device 1004.
　入力装置１００５は、外部からの入力を受け付ける入力デバイス（例えば、キーボード、マウス、マイクロフォン、スイッチ、ボタン、センサなど）である。出力装置１００６は、外部への出力を実施する出力デバイス（例えば、ディスプレイ、スピーカー、LEDランプなど）である。なお、入力装置１００５及び出力装置１００６は、一体となった構成（例えば、タッチパネル）であってもよい。 The input device 1005 is an input device (for example, a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts an input from the outside. The output device 1006 is an output device (for example, a display, a speaker, an LED lamp, etc.) that performs output to the outside. The input device 1005 and the output device 1006 may have an integrated configuration (for example, a touch panel).
　また、プロセッサ１００１やメモリ１００２などの各装置は、情報を通信するためのバス１００７で接続される。バス１００７は、単一のバスで構成されてもよいし、装置間で異なるバスで構成されてもよい。 Also, each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information. The bus 1007 may be configured with a single bus or may be configured with different buses between apparatuses.
　また、対話サーバ１００およびユーザ端末２００は、マイクロプロセッサ、デジタル信号プロセッサ（ＤＳＰ：Digital　Signal　Processor）、ＡＳＩＣ（Application　Specific　Integrated　Circuit）、ＰＬＤ（Programmable　Logic　Device）、ＦＰＧＡ（Field　Programmable　Gate　Array）などのハードウェアを含んで構成されてもよく、当該ハードウェアにより、各機能ブロックの一部又は全てが実現されてもよい。例えば、プロセッサ１００１は、これらのハードウェアの少なくとも１つで実装されてもよい。 The dialogue server 100 and the user terminal 200 include a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), and the like. Hardware may be configured, and a part or all of each functional block may be realized by the hardware. For example, the processor 1001 may be implemented by at least one of these hardware.
　以上、本実施形態について詳細に説明したが、当業者にとっては、本実施形態が本明細書中に説明した実施形態に限定されるものではないということは明らかである。本実施形態は、特許請求の範囲の記載により定まる本発明の趣旨及び範囲を逸脱することなく修正及び変更態様として実施することができる。したがって、本明細書の記載は、例示説明を目的とするものであり、本実施形態に対して何ら制限的な意味を有するものではない。 As mentioned above, although this embodiment was described in detail, it is clear for those skilled in the art that this embodiment is not limited to embodiment described in this specification. The present embodiment can be implemented as a modification and change without departing from the spirit and scope of the present invention defined by the description of the scope of claims. Therefore, the description of the present specification is for illustrative purposes and does not have any limiting meaning to the present embodiment.
　情報の通知は、本明細書で説明した態様／実施形態に限られず、他の方法で行われてもよい。例えば、情報の通知は、物理レイヤシグナリング（例えば、ＤＣＩ（Downlink　Control　Information）、ＵＣＩ（Uplink　Control　Information））、上位レイヤシグナリング（例えば、ＲＲＣ（Radio　Resource　Control）シグナリング、ＭＡＣ（Medium　Access　Control）シグナリング、報知情報（ＭＩＢ（Master　Information　Block）、ＳＩＢ（System　Information　Block）））、その他の信号又はこれらの組み合わせによって実施されてもよい。また、ＲＲＣシグナリングは、ＲＲＣメッセージと呼ばれてもよく、例えば、ＲＲＣ接続セットアップ（RRC Connection Setup）メッセージ、ＲＲＣ接続再構成（RRC ConnectionReconfiguration）メッセージなどであってもよい。 The notification of information is not limited to the aspect / embodiment described in this specification, and may be performed by other methods. For example, notification of information includes physical layer signaling (for example, DCI (Downlink Control Information), UCI (Uplink Control Information)), upper layer signaling (for example, RRC (Radio Resource Control) signaling, MAC (Medium Access Control) signaling), It may be implemented by broadcast information (MIB (Master Information Block), SIB (System Information Block)), other signals, or a combination thereof. Further, the RRC signaling may be called an RRC message, and may be, for example, an RRC connection setup (RRC Connection Setup) message, an RRC connection reconfiguration (RRC ConnectionReconfiguration) message, or the like.
　本明細書で説明した各態様／実施形態は、ＬＴＥ（Long　Term　Evolution）、ＬＴＥ－Ａ（LTE-Advanced）、ＳＵＰＥＲ　３Ｇ、ＩＭＴ－Ａｄｖａｎｃｅｄ、４Ｇ、５Ｇ、ＦＲＡ（Future　Radio　Access）、Ｗ－ＣＤＭＡ（登録商標）、ＧＳＭ（登録商標）、ＣＤＭＡ２０００、ＵＭＢ（Ultra　Mobile　Broadband）、ＩＥＥＥ　８０２．１１（Ｗｉ－Ｆｉ）、ＩＥＥＥ　８０２．１６（ＷｉＭＡＸ）、ＩＥＥＥ　８０２．２０、ＵＷＢ（Ultra-WideBand）、Ｂｌｕｅｔｏｏｔｈ（登録商標）、その他の適切なシステムを利用するシステム及び／又はこれらに基づいて拡張された次世代システムに適用されてもよい。 Each aspect / embodiment described in this specification includes LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER 3G, IMT-Advanced, 4G, 5G, FRA (Future Radio Access), W-CDMA. (Registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, UWB (Ultra-WideBand), The present invention may be applied to a Bluetooth (registered trademark), a system using another appropriate system, and / or a next generation system extended based on the system.
　本明細書で説明した各態様／実施形態の処理手順、シーケンス、フローチャートなどは、矛盾の無い限り、順序を入れ替えてもよい。例えば、本明細書で説明した方法については、例示的な順序で様々なステップの要素を提示しており、提示した特定の順序に限定されない。 The processing procedures, sequences, flowcharts and the like of each aspect / embodiment described in this specification may be switched in order as long as there is no contradiction. For example, the methods described herein present the elements of the various steps in an exemplary order and are not limited to the specific order presented.
　入出力された情報等は特定の場所(例えば、メモリ)に保存されてもよいし、管理テーブルで管理してもよい。入出力される情報等は、上書き、更新、または追記され得る。出力された情報等は削除されてもよい。入力された情報等は他の装置へ送信されてもよい。 The input / output information or the like may be stored in a specific location (for example, a memory) or may be managed by a management table. Input / output information and the like can be overwritten, updated, or additionally written. The output information or the like may be deleted. The input information or the like may be transmitted to another device.
　判定は、１ビットで表される値（０か１か）によって行われてもよいし、真偽値（Boolean：trueまたはfalse）によって行われてもよいし、数値の比較（例えば、所定の値との比較）によって行われてもよい。 The determination may be performed by a value represented by 1 bit (0 or 1), may be performed by a true / false value (Boolean: true or false), or may be performed by comparing numerical values (for example, a predetermined value) Comparison with the value).
　本明細書で説明した各態様／実施形態は単独で用いてもよいし、組み合わせて用いてもよいし、実行に伴って切り替えて用いてもよい。また、所定の情報の通知（例えば、「Ｘであること」の通知）は、明示的に行うものに限られず、暗黙的（例えば、当該所定の情報の通知を行わない）ことによって行われてもよい。 Each aspect / embodiment described in this specification may be used alone, in combination, or may be switched according to execution. In addition, notification of predetermined information (for example, notification of being “X”) is not limited to explicitly performed, but is performed implicitly (for example, notification of the predetermined information is not performed). Also good.
　ソフトウェアは、ソフトウェア、ファームウェア、ミドルウェア、マイクロコード、ハードウェア記述言語と呼ばれるか、他の名称で呼ばれるかを問わず、命令、命令セット、コード、コードセグメント、プログラムコード、プログラム、サブプログラム、ソフトウェアモジュール、アプリケーション、ソフトウェアアプリケーション、ソフトウェアパッケージ、ルーチン、サブルーチン、オブジェクト、実行可能ファイル、実行スレッド、手順、機能などを意味するよう広く解釈されるべきである。 Software, whether it is called software, firmware, middleware, microcode, hardware description language, or other names, instructions, instruction sets, code, code segments, program codes, programs, subprograms, software modules , Applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, etc. should be interpreted broadly.
　また、ソフトウェア、命令などは、伝送媒体を介して送受信されてもよい。例えば、ソフトウェアが、同軸ケーブル、光ファイバケーブル、ツイストペア及びデジタル加入者回線（ＤＳＬ）などの有線技術及び／又は赤外線、無線及びマイクロ波などの無線技術を使用してウェブサイト、サーバ、又は他のリモートソースから送信される場合、これらの有線技術及び／又は無線技術は、伝送媒体の定義内に含まれる。 Further, software, instructions, etc. may be transmitted / received via a transmission medium. For example, software may use websites, servers, or other devices using wired technology such as coaxial cable, fiber optic cable, twisted pair and digital subscriber line (DSL) and / or wireless technology such as infrared, wireless and microwave. When transmitted from a remote source, these wired and / or wireless technologies are included within the definition of transmission media.
　本明細書で説明した情報、信号などは、様々な異なる技術のいずれかを使用して表されてもよい。例えば、上記の説明全体に渡って言及され得るデータ、命令、コマンド、情報、信号、ビット、シンボル、チップなどは、電圧、電流、電磁波、磁界若しくは磁性粒子、光場若しくは光子、又はこれらの任意の組み合わせによって表されてもよい。 The information, signals, etc. described herein may be represented using any of a variety of different technologies. For example, data, commands, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description are voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, light fields or photons, or any of these May be represented by a combination of
　なお、本明細書で説明した用語及び／又は本明細書の理解に必要な用語については、同一の又は類似する意味を有する用語と置き換えてもよい。 Note that the terms described in this specification and / or terms necessary for understanding this specification may be replaced with terms having the same or similar meaning.
　本明細書で使用する「システム」および「ネットワーク」という用語は、互換的に使用される。 The terms “system” and “network” used in this specification are used interchangeably.
　また、本明細書で説明した情報、パラメータなどは、絶対値で表されてもよいし、所定の値からの相対値で表されてもよいし、対応する別の情報で表されてもよい。例えば、無線リソースはインデックスで指示されるものであってもよい。 In addition, information, parameters, and the like described in this specification may be represented by absolute values, may be represented by relative values from a predetermined value, or may be represented by other corresponding information. . For example, the radio resource may be indicated by an index.
　上述したパラメータに使用する名称はいかなる点においても限定的なものではない。さらに、これらのパラメータを使用する数式等は、本明細書で明示的に開示したものと異なる場合もある。様々なチャネル（例えば、ＰＵＣＣＨ、ＰＤＣＣＨなど）及び情報要素（例えば、ＴＰＣなど）は、あらゆる好適な名称によって識別できるので、これらの様々なチャネル及び情報要素に割り当てている様々な名称は、いかなる点においても限定的なものではない。 The names used for the above parameters are not limited in any way. Further, mathematical formulas and the like that use these parameters may differ from those explicitly disclosed herein. Since various channels (eg, PUCCH, PDCCH, etc.) and information elements (eg, TPC, etc.) can be identified by any suitable name, the various names assigned to these various channels and information elements are However, it is not limited.
　ユーザ端末は、当業者によって、加入者局、モバイルユニット、加入者ユニット、ワイヤレスユニット、リモートユニット、モバイルデバイス、ワイヤレスデバイス、ワイヤレス通信デバイス、リモートデバイス、モバイル加入者局、アクセス端末、モバイル端末、ワイヤレス端末、リモート端末、ハンドセット、ユーザエージェント、モバイルクライアント、クライアント、またはいくつかの他の適切な用語で呼ばれる場合もある。 User terminals can be obtained by those skilled in the art from subscriber stations, mobile units, subscriber units, wireless units, remote units, mobile devices, wireless devices, wireless communication devices, remote devices, mobile subscriber stations, access terminals, mobile terminals, wireless It may also be called terminal, remote terminal, handset, user agent, mobile client, client, or some other appropriate terminology.
　本明細書で使用する「判断(determining)」、「決定(determining)」という用語は、多種多様な動作を包含する場合がある。「判断」、「決定」は、例えば、判定(judging)、計算(calculating)、算出(computing)、処理(processing)、導出(deriving)、調査(investigating)、探索(looking up)（例えば、テーブル、データベースまたは別のデータ構造での探索）、確認(ascertaining)した事を「判断」「決定」したとみなす事などを含み得る。また、「判断」、「決定」は、受信(receiving)（例えば、情報を受信すること）、送信(transmitting)(例えば、情報を送信すること)、入力(input)、出力(output)、アクセス(accessing)（例えば、メモリ中のデータにアクセスすること）した事を「判断」「決定」したとみなす事などを含み得る。また、「判断」、「決定」は、解決(resolving)、選択(selecting)、選定(choosing)、確立(establishing)、比較(comparing)などした事を「判断」「決定」したとみなす事を含み得る。つまり、「判断」「決定」は、何らかの動作を「判断」「決定」したとみなす事を含み得る。 As used herein, the terms “determining” and “determining” may encompass a wide variety of actions. “Judgment” and “decision” are, for example, judgment, calculation, calculation, processing, derivation, investigating, searching (looking up) (for example, table , Searching in a database or another data structure), considering ascertaining as “determining”, “deciding”, and the like. In addition, “determination” and “determination” include receiving (for example, receiving information), transmitting (for example, transmitting information), input (input), output (output), and access. (accessing) (e.g., accessing data in a memory) may be considered as "determined" or "determined". In addition, “determination” and “decision” means that “resolving”, “selecting”, “choosing”, “establishing”, and “comparing” are regarded as “determining” and “deciding”. May be included. In other words, “determination” and “determination” may include considering some operation as “determination” and “determination”.
　「接続された(connected)」、「結合された(coupled)」という用語、又はこれらのあらゆる変形は、２又はそれ以上の要素間の直接的又は間接的なあらゆる接続又は結合を意味し、互いに「接続」又は「結合」された２つの要素間に１又はそれ以上の中間要素が存在することを含むことができる。要素間の結合又は接続は、物理的なものであっても、論理的なものであっても、或いはこれらの組み合わせであってもよい。本明細書で使用する場合、２つの要素は、１又はそれ以上の電線、ケーブル及び／又はプリント電気接続を使用することにより、並びにいくつかの非限定的かつ非包括的な例として、無線周波数領域、マイクロ波領域及び光（可視及び不可視の両方）領域の波長を有する電磁エネルギーなどの電磁エネルギーを使用することにより、互いに「接続」又は「結合」されると考えることができる。 The terms “connected”, “coupled”, or any variation thereof, means any direct or indirect connection or coupling between two or more elements and It can include the presence of one or more intermediate elements between two “connected” or “coupled” elements. The coupling or connection between the elements may be physical, logical, or a combination thereof. As used herein, the two elements are radio frequency by using one or more wires, cables and / or printed electrical connections, and as some non-limiting and non-inclusive examples By using electromagnetic energy, such as electromagnetic energy having a wavelength in the region, microwave region, and light (both visible and invisible) region, it can be considered to be “connected” or “coupled” to each other.
　本明細書で使用する「に基づいて」という記載は、別段に明記されていない限り、「のみに基づいて」を意味しない。言い換えれば、「に基づいて」という記載は、「のみに基づいて」と「に少なくとも基づいて」の両方を意味する。 As used herein, the phrase “based on” does not mean “based only on”, unless expressly specified otherwise. In other words, the phrase “based on” means both “based only on” and “based at least on.”
　本明細書で「第１の」、「第２の」などの呼称を使用した場合においては、その要素へのいかなる参照も、それらの要素の量または順序を全般的に限定するものではない。これらの呼称は、２つ以上の要素間を区別する便利な方法として本明細書で使用され得る。したがって、第１および第２の要素への参照は、２つの要素のみがそこで採用され得ること、または何らかの形で第１の要素が第２の要素に先行しなければならないことを意味しない。 In the present specification, when a designation such as “first” or “second” is used, any reference to the element does not generally limit the quantity or order of the elements. These designations can be used herein as a convenient way to distinguish between two or more elements. Thus, a reference to the first and second elements does not mean that only two elements can be employed there, or that in some way the first element must precede the second element.
　「含む（include）」、「含んでいる（including）」、およびそれらの変形が、本明細書あるいは特許請求の範囲で使用されている限り、これら用語は、用語「備える(comprising)」と同様に、包括的であることが意図される。さらに、本明細書あるいは特許請求の範囲において使用されている用語「または（or）」は、排他的論理和ではないことが意図される。 These terms are similar to the term “comprising” as long as “include”, “including” and variations thereof are used herein or in the claims. It is intended to be comprehensive. Furthermore, the term “or” as used herein or in the claims is not intended to be an exclusive OR.
　本明細書において、文脈または技術的に明らかに1つのみしか存在しない装置である場合以外は、複数の装置をも含むものとする。 In this specification, a plurality of devices are also included unless there is only one device that is clearly present in context or technically.
１００…対話サーバ、１０１…受信部、１０２…検索部、１０３…応答部、１０４…真理表データベース、１０５…ＦＡＱデータベース、２００…ユーザ端末、２０１…キー受付部、２０２…利用者情報記憶部、２０３…通信部、２０４…表示部。
 
 

  DESCRIPTION OF SYMBOLS 100 ... Dialog server 101 ... Receiving part 102 ... Search part 103 ... Response part 104 ... Truth table database 105 ... FAQ database 200 ... User terminal 201 ... Key reception part 202 ... User information storage part, 203 ... Communication unit, 204 ... Display unit.



Claims (7)

  1. 　ユーザによる入力に基づいて検索結果を応答する対話サーバにおいて、
    　前記ユーザが操作するユーザ端末から入力キーワードを取得するとともに、前記ユーザに関連付けられている利用者情報を取得する取得部と、
    　一または複数の検索キーワードと応答候補とを対応付けて記憶する検索データベースから、前記入力キーワードおよび前記利用者情報に対応する応答候補を検索する検索部と、　前記検索部により検索された応答候補を前記ユーザ端末に対して送信する応答部と、
    を備える対話サーバ。     In a dialog server that responds to search results based on user input,
    An acquisition unit that acquires an input keyword from a user terminal operated by the user and acquires user information associated with the user;
    A search unit that searches for a response candidate corresponding to the input keyword and the user information from a search database that stores one or a plurality of search keywords and response candidates in association with each other, and a response candidate searched by the search unit A response unit for transmitting to the user terminal;
    A dialogue server comprising:
  2. 　前記検索部は、入力キーワードに基づいて検索を行って複数の応答候補を得て、当該複数の応答候補のうち前記利用者情報を含む応答候補を検索し、
    　前記応答部は、前記応答候補を送信する、請求項１に記載の対話サーバ。     The search unit performs a search based on an input keyword to obtain a plurality of response candidates, searches for response candidates including the user information among the plurality of response candidates,
    The dialogue server according to claim 1, wherein the response unit transmits the response candidate.
  3. 　前記検索部は、複数の利用者情報のうち、予め定められた条件にしたがった一または複数の利用者情報を用いて検索を行う、請求項１または２に記載の対話サーバ。 The interactive server according to claim 1 or 2, wherein the search unit performs a search using one or a plurality of pieces of user information in accordance with a predetermined condition among a plurality of pieces of user information.
  4. 　前記取得部は、前記ユーザ端末から、前記応答候補に対して否定の意図を受信すると、　前記検索部は、前記利用者情報を用いずに、他の検索キーワードを用いて応答候補の検索を行う
    　請求項１～３のいずれか一項に記載の対話サーバ。     When the acquisition unit receives a negative intention for the response candidate from the user terminal, the search unit searches for a response candidate using another search keyword without using the user information. The dialogue server according to any one of claims 1 to 3.
  5. 　前記検索部は、
    　前記利用者情報が複数あった場合には、当該複数の利用者情報の組合せを変えて検索を行う、請求項１～４のいずれか一項に記載の対話サーバ。     The search unit
    The interactive server according to any one of claims 1 to 4, wherein when there are a plurality of pieces of user information, a search is performed by changing a combination of the plurality of pieces of user information.
  6. 　前記検索部は、
    　前記検索データベースにおける応答候補ごとに登録されている一または複数の検索キーワードからなるキーワード群と、前記入力キーワードおよび一または複数の利用者情報の組合せからなるキーワード群と、が完全一致するように、一または複数の利用者情報を選択し、当該一または複数の利用者情報と前記入力キーワードとを用いた検索を行う、
    請求項１～５のいずれか一項に記載の対話サーバ。     The search unit
    The keyword group consisting of one or more search keywords registered for each response candidate in the search database and the keyword group consisting of a combination of the input keyword and one or more user information are completely matched. Selecting one or more user information and performing a search using the one or more user information and the input keyword;
    The interactive server according to any one of claims 1 to 5.
  7. 　前記検索部は、
    　前記検索データベースにおける応答候補ごとに登録されている一または複数の検索キーワードからなるキーワード群と、前記入力キーワードからなるキーワード群と、が完全一致する場合には、一または複数の利用者情報を選択しない、
    請求項６に記載の対話サーバ。
     

          The search unit
    If the keyword group consisting of one or more search keywords registered for each response candidate in the search database and the keyword group consisting of the input keywords completely match, select one or more user information do not do,
    The dialogue server according to claim 6.


PCT/JP2019/014169 2018-05-08 2019-03-29 Interactive server WO2019216054A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2020518184A JP6975323B2 (en) 2018-05-08 2019-03-29 Dialogue server

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2018089828 2018-05-08
JP2018-089828 2018-05-08

Publications (1)

Publication Number Publication Date
WO2019216054A1 true WO2019216054A1 (en) 2019-11-14

Family

ID=68467132

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2019/014169 WO2019216054A1 (en) 2018-05-08 2019-03-29 Interactive server

Country Status (2)

Country Link
JP (1) JP6975323B2 (en)
WO (1) WO2019216054A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7447612B2 (en) 2020-03-27 2024-03-12 サクサ株式会社 FAQ providing device and FAQ providing program
JP7485940B2 (en) 2020-08-27 2024-05-17 富士通株式会社 Search control program, search control method, and search control device

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH10283362A (en) * 1997-04-02 1998-10-23 Casio Comput Co Ltd Portable information terminal and storage medium
JP2011060218A (en) * 2009-09-14 2011-03-24 Nec Corp Reply system
JP2016081401A (en) * 2014-10-21 2016-05-16 株式会社日立製作所 Information search presentation apparatus and information search presentation method

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH10283362A (en) * 1997-04-02 1998-10-23 Casio Comput Co Ltd Portable information terminal and storage medium
JP2011060218A (en) * 2009-09-14 2011-03-24 Nec Corp Reply system
JP2016081401A (en) * 2014-10-21 2016-05-16 株式会社日立製作所 Information search presentation apparatus and information search presentation method

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7447612B2 (en) 2020-03-27 2024-03-12 サクサ株式会社 FAQ providing device and FAQ providing program
JP7485940B2 (en) 2020-08-27 2024-05-17 富士通株式会社 Search control program, search control method, and search control device

Also Published As

Publication number Publication date
JPWO2019216054A1 (en) 2020-12-17
JP6975323B2 (en) 2021-12-01

Similar Documents

Publication Publication Date Title
JP6802364B2 (en) Dialogue system
JP7166350B2 (en) dialogue device
WO2019202788A1 (en) Dialogue system
WO2019216054A1 (en) Interactive server
WO2019193796A1 (en) Interaction server
US11971977B2 (en) Service providing apparatus
WO2019202787A1 (en) Dialogue system
JP7087095B2 (en) Dialogue information generator
JP7043593B2 (en) Dialogue server
WO2020235136A1 (en) Interactive system
US11604831B2 (en) Interactive device
WO2019187463A1 (en) Dialogue server
US11430440B2 (en) Dialog device
US20220300519A1 (en) Re-ranking device
WO2019211967A1 (en) Dialogue device

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19799246

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020518184

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19799246

Country of ref document: EP

Kind code of ref document: A1