Document generation device, document generation method, and program for generating document

Abstract

To provide a document generation device, a document generation method, and a program for generating a document by which a user is allowed to input easily.SOLUTION: A document generation device includes: an analysis unit 25 of a document analysis unit 22 containing a document generation unit 22f which generates a document according to a result of analysis of text data converted from a voice signal spoken by a speaker, a key word extracting unit 22e which extracts a key word from the text data according to the results of the analysis, and an additional information generation unit 22g which generates additional information to be added to the document on the basis of at least one of the document and the key word; and a message generation unit 23 which generates a message according to the document and the additional information.SELECTED DRAWING: Figure 7

Description

[Technical field]

[0001] The present application belongs to the technical field of a document generation device, a document generation method, and a program for a document generation device. [Background technology]

[0002] A device for sending e-mail while driving a vehicle, which is an example of a moving body, has been developed. For example, the following Patent Document 1 discloses an e-mail sending system using an in-vehicle terminal that stores fixed e-mail phrases received from a mobile communication terminal in a fixed e-mail phrase storage unit, and selects one of the fixed e-mail phrases stored in the fixed e-mail phrase storage unit and sends it to the mobile communication terminal in response to a request to send e-mail, and a mobile communication terminal that sends the generated fixed e-mail phrase to the in-vehicle terminal, receives the fixed e-mail phrases sent from the in-vehicle terminal, generates an outgoing e-mail in an e-mail sending unit based on the received fixed e-mail phrase, and sends it to a mail server. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2006-33377 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, the technology described in Patent Document 1 requires the user to press a button to select an email to send while driving, which is not convenient for the user. Also, the user must select or search for information related to the content they want to send and input it.

[0005] The present application has been made in consideration of the above-mentioned problems, and one example of an object of the application is to provide a document generation device or the like that allows a user to easily perform input. [Means for solving the problem]

[0006] In order to solve the above problem, the invention described in claim 1 is characterized by comprising a document generation unit that generates a document according to a result of analyzing text data converted from a voice signal spoken by a speaker, an extraction unit that extracts keywords from the text data according to the result of the analysis, an additional information generation unit that generates additional information to be added to the document based on at least one of the document and the keywords, and a message generation unit that generates a message according to the document and the additional information.

[0007] The invention described in claim 6 is characterized by including a document generation step of generating a document according to a result of analyzing text data converted from a voice signal spoken by a speaker, an extraction step of extracting keywords from the text data according to the result of the analysis, an additional information generation step of generating additional information to be added to the document based on at least one of the document and the keywords, and a message generation step of generating a message according to the document and the additional information. [Brief description of the drawings]

[0008] [Figure 1] 1 is a block diagram showing an example of a schematic configuration of a document generation device according to an embodiment. [Diagram 2] 1 is a block diagram showing an example of a schematic configuration of a document generation device according to an embodiment; [Diagram 3] 3 is a schematic diagram showing an example of an address database constructed in a storage unit of FIG. 2; [Figure 4] 3 is a schematic diagram showing an example of a keyword database constructed in a storage unit of FIG. 2; [Diagram 5] 3 is a schematic diagram showing an example of an additional information database constructed in the storage unit of FIG. 2; [Figure 6] 3 is a block diagram showing an example of a functional block of the document generation device of FIG. 2. [Figure 7] 7 is a block diagram showing an example of a functional block of a text analysis unit in FIG. 6. [Figure 8]4 is a flowchart showing an example of an operation of the document generation device according to the embodiment. [Figure 9] 1 is a schematic diagram showing an example of what is said by a speaker and a generated message; FIG. [Figure 10] 9 is a flowchart showing an example of a subroutine for analyzing the morphological analysis result of FIG. 8. [Figure 11] 9 is a flowchart showing an example of a message generation subroutine of FIG. 8. [Figure 12] 1 is a schematic diagram showing an example of what is said by a speaker and a generated message; FIG. [Figure 13] 1 is a schematic diagram showing an example of what is said by a speaker and a generated message; FIG. [Figure 14] 1 is a schematic diagram showing an example of what is said by a speaker and a generated message; FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] An embodiment of the present application will be described with reference to Fig. 1. Fig. 1 is a block diagram showing an example of a schematic configuration of a document generation device according to an embodiment.

[0010] As shown in FIG. 1, the document generation device 10 includes a document generation unit 10a, an extraction unit 10b, an additional information generation unit 10c, and a message generation unit 10d that generates a message based on the document and the additional information.

[0011] In this configuration, the document generator 10a generates a document in accordance with the results of analyzing text data converted from a voice signal uttered by a speaker.

[0012] Here, examples of speakers include users of moving objects such as vehicles, motorcycles, aircraft, and ships.

[0013] An example of a process for converting a voice signal into text data is a voice recognition process that extracts what is being said as text data, and examples of recognition techniques include statistical methods, dynamic time warping, and hidden Markov models.

[0014] An example of the analysis of text data is a natural language processing technique such as morphological analysis, etc. An example of the results of analyzing text data is a result of breaking down a document into morphemes (which may be words or phrases) that are the smallest units that have meaning in language, by morphological analysis, etc., and determining the parts of speech of the morphemes.

[0015] Examples of documents include the keyword "late", the standard phrase "I will be late" for the keyword "late", the keyword "current location" and the standard phrase "I will pass by here now" for the keyword "I am here now".

[0016] In this configuration, the extraction unit 10b extracts keywords from the text data according to the analysis result.

[0017] Here, examples of extracting keywords from text data depending on the results of analysis include extraction of keywords that mean sending, such as "send," "send," and "contact" (examples of output keywords), extraction of keywords that mean display, such as "display" and "show" (examples of output keywords), extraction of keywords that mean email destinations such as people's names and company names, and output destinations such as the display destination of a "display," extraction of keywords such as "late" and "lateness" to elicit the standard phrase "I will be late," extraction of keywords to obtain additional information, etc.

[0018] The additional information generating unit 10c generates additional information to be added to a document based on at least one of the document and the keywords.

[0019] Examples of additional information include map information (latitude, longitude) for the keyword "current location," road information for the keyword "traffic jam," weather information for the current location and route for weather-related keywords such as "rain" and "snow," arrival time information for the standard phrase "will be delayed," and map information (latitude, longitude) for the standard phrase "will be passing by here now."

[0020] The message generating unit 10d generates a message according to the document and the additional information.

[0021] Examples of messages include a message that includes a map of the current location in a document when the keyword "current location" is present, a message that includes the document "map display" that shows a link to a map of the current location, a document that includes the document "traffic jam from XX km" when the keyword "traffic jam" is present, and a document that says "please wait at the east exit of XX station" when the keyword "wait" is present.

[0022] As described above, according to the operation of the document generation device 10 according to the embodiment, words uttered by a speaker can be complemented to generate a natural message. EXAMPLES

[0023] [1. Overview of the document generation device's configuration and functions] (1.1 Overview of the document generation system and its functions)

[0024] Next, a specific example corresponding to the above-described embodiment will be described with reference to Figures 2 to 5. Note that the example described below is an example in which the present application is applied to a document generation device.

[0025] Fig. 2 is a block diagram showing an example of a schematic configuration of a document generation device according to an embodiment. Fig. 3 is a schematic diagram showing an example of an address database built in a storage unit. Fig. 4 is a schematic diagram showing an example of a keyword database built in a storage unit. Fig. 5 is a schematic diagram showing an example of an additional information database built in a storage unit.

[0026] 2, the document generation device 10 according to the embodiment includes an input unit 11 for receiving input from a user, a storage unit 12 for storing programs for controlling the document generation device 10, a communication unit 13 for transmitting and receiving data to and from the outside of the document generation device 10, a sensor unit 14 for detecting the state of a mobile object used by the user, an output unit 15 for outputting processing results, a system control unit 16 for controlling the document generation device 10, and an input / output interface unit 17. The system control unit 16 and the input / output interface unit 17 are connected via a system bus 18.

[0027] The input unit 11 has a microphone that converts the voice of a speaker into an electric signal, a touch pad with a position input function, and the like. The portion with the position input function is composed of elements that realize, for example, a capacitance type, a resistive film type, and the like. The input unit 11 acquires, by means of the position input function, position information of the surface of the input unit 11 that is in contact with or in proximity to a user's finger, in pixel units of a predetermined resolution. The input unit 11 may be a touch panel with a display function and a position input function.

[0028] The input unit 11 receives voice from the user, and receives input of a destination and the like from the user.

[0029] The storage unit 12 is composed of, for example, a silicon disk drive. The storage unit 12 stores various programs for controlling the document generation device 10. The various programs include an operating system and a program for sending e-mail. The various programs may be acquired via a network such as a wireless communication network, or may be recorded on a recording medium such as a CD (Compact Disc) or a DVD (Digital Versatile Disc) and read via a drive device.

[0030] The storage unit 12 also includes an address database that stores email address information, a keyword database that stores keywords and fixed phrases, and an additional information database that stores additional information to be added to documents. The storage unit 12 also includes a dictionary database for performing morpheme analysis. The storage unit 12 also includes a map database.

[0031] In addition, an output database that stores keywords related to output such as transmission and display is constructed in the storage unit 12. For example, the output database stores keywords such as "contact", "transmission", "email", and "display".

[0032] 3, the address database stores email addresses in association with personal names, company names, place names, etc. Addresses can be input to the address database by obtaining an address book of a smartphone or the like through communication, by directly inputting an address into an in-vehicle system including the document generation device 10, or by obtaining an address book on a cloud on a network through the communication unit 13.

[0033] As shown in Fig. 4, the keyword database stores fixed phrases in association with keywords. Each fixed phrase is assigned a fixed phrase number.

[0034] In addition, in FIG. 4, in the case of a keyword that causes a message including a location, such as "wait," to be input, a template is prepared that indicates where to insert the location word, such as "*."

[0035] In addition, the input of fixed phrases to the keyword database may be registered from an external device such as a personal computer or a smartphone.

[0036] Furthermore, when performing morpheme analysis of the speech recognition results and treating the results as keywords, a combination of a verb stem and a conjugated verb ending may be treated as a keyword. For example, in the case of "okureru" (to be late), a word combining the stem "oku" and the conjugated verb ending "re, re, reru, reru, rere, rero" becomes a keyword. Also, a combination of morphemes with different parts of speech may be treated as a keyword. For example, for "mattete" (please wait), "matte" becomes an independent verb, "te" becomes a particle, a conjunction particle, and "te" becomes a non-independent verb. For example, for "ite" (please wait), "i" becomes an independent verb, "te" becomes a particle, a conjunction particle.

[0037] As shown in Fig. 5, the additional information database stores additional information in association with keywords or fixed phrases. Note that the additional information may be associated with a combination of keywords and fixed phrases.

[0038] The additional information may be registered in the additional information database from an external device such as a personal computer or a smartphone. The additional information is generated using information from the sensor unit 14, time information, a map database, etc. In the additional information database, text / messages related to the additional information may be dynamically registered as fixed phrases. In addition, in the additional information database, the sentences / messages that handle additional information are statically stored in advance. In addition, there may be a plurality of additional information databases depending on the types of additional information.

[0039] The communication unit 13 is connected to a network such as the Internet via wireless communication and controls the state of communication with the outside.

[0040] The sensor unit 14 has a GPS (Global Positioning System) sensor and is located in a satellite orbit. The document generation device 10 receives navigation radio waves from GPS satellites and detects the position, altitude, etc. of the mobile object on which the document generation device 10 is installed. The sensor unit 14 is also connected to various sensors of the mobile object (for example, a sensor that detects changes in the liquid level due to tilt, a vehicle speed pulse, an acceleration sensor, and a gyro sensor) and acquires mobile object information such as the speed, acceleration, tilt, mileage, and engine RPM of the mobile object. The sensor unit 14 is an example of a current location acquisition unit that acquires the current location.

[0041] The output unit 15 is composed of a speaker that outputs sound, a liquid crystal display element or an EL (Electro Luminescence) element that displays the generated document, etc. When the display function of the output unit 15 is a head-up display, the output unit 15 has a projection means and a screen means (windshield, lens part of glasses, etc.) that displays the image projected from the projection means.

[0042] The system control unit 16 includes, for example, a CPU (Central Processing Unit) 16a and a RO The system control unit 16 has a ROM 16b, a RAM 16c, and a read only memory (ROM) 16b. The system control unit 16 has a CPU 16a which reads out and executes various programs stored in the ROM 16b, the RAM 16c, and the storage unit 12. The system control unit 16 performs voice recognition, analyzes documents, generates messages, and calculates a moving route for a moving object based on information on a current location and a received destination.

[0043] The document generation device 10 also has an internal clock (not shown).

[0044] (1.2 Functional blocks of the document generation device) Next, the functional blocks of the document generation device 10 will be described with reference to FIGS. Fig. 6 is a block diagram showing an example of functional blocks of the document generation device 10. Fig. 7 is a block diagram showing an example of functional blocks of the document analysis unit 22.

[0045] 6, document generation device 10 has a voice recognition unit 21 that converts voice data acquired by input unit 11 into text data, a document analysis unit 22 that analyzes the text data, and a message generation unit 23 that generates a message to be output to output unit 15. Note that voice recognition unit 21, document analysis unit 22, and message generation unit 23 are realized by system control unit 16.

[0046] Message generator 23 (an example of message generator 10d) creates a fixed phrase in accordance with the analysis result of document analyzer 22. Message generator 23 adds morphologically analyzed text to the selected fixed phrase, or adds a fixed phrase including additional information.

[0047] The document analysis unit 22 performs morphological analysis of the text data by referring to the dictionary database, and performs address analysis, keyword analysis for selecting fixed phrases, analysis for additional information, etc. on the analysis results. The document analysis unit 22 is an example of the document generation unit 10a, the extraction unit 10b, and the additional information generation unit 10c.

[0048] 7, the document analysis unit 22 includes a morphological analysis unit 22a, an output keyword extraction unit 22b, an output destination extraction unit 22c, an output determination unit 22d, a keyword extraction unit 22e, a document generation unit 22f, and an additional information generation unit 22g. The keyword extraction unit 22e, the document generation unit 22f, and the additional information generation unit 22g form an analysis unit 25.

[0049] The morpheme analysis unit 22a performs a morpheme analysis on the text data converted by the speech recognition unit 21, breaks it down into morphemes, and determines parts of speech and the like.

[0050] The output keyword extraction unit 22b (an example of the extraction unit 10b) has an output database (the storage unit 12). The output keyword extraction unit 22b refers to the output database and extracts words that mean output, such as transmission and display, from the decomposed morphemes.

[0051] The destination extraction unit 22c (an example of the extraction unit 10b) has an address database (storage unit 12). The destination extraction unit 22c refers to the address database and extracts personal names, company names, place names, etc. from the decomposed morphemes. Next, the destination extraction unit 22c refers to the address database and extracts email addresses corresponding to the personal names, company names, place names, etc.

[0052] The output determination unit 22d determines whether or not to output the generated message based on the output keyword extraction unit 22b and the output destination extraction unit 22c. For example, the output determination unit 22d determines to output the message if it can extract a word meaning output and a destination email address.

[0053] The analysis unit 25 includes a keyword extraction unit 22e, a document generation unit 22f, an additional information generation unit 22g, a keyword database (storage unit 12), and an additional information database (storage unit 12).

[0054] The keyword extraction unit 22e (an example of the extraction unit 10b) refers to a keyword database and extracts keywords from the decomposed morphemes. For example, the keyword extraction unit 22e extracts keywords corresponding to fixed phrases. The keyword extraction unit 22e may also refer to an additional information database and extract keywords from the decomposed morphemes. For example, the keyword extraction unit 22e extracts keywords corresponding to additional information.

[0055] The document generating unit 22f (an example of the document generating unit 10a) refers to a keyword database, extracts a fixed phrase corresponding to the keyword extracted by the keyword extracting unit 22e, and generates a document. The document generating unit 22f may generate a document by combining morphemes from the decomposed morphemes.

[0056] The additional information generating unit 22g (an example of the additional information generating unit 10c) refers to the additional information database, extracts additional information corresponding to the keywords extracted by the keyword extracting unit 22e, and generates additional information. The additional information generating unit 22g also extracts additional information corresponding to the document generated by the document generating unit 22f, and generates additional information. The additional information generating unit 22g also adds the current location as additional information based on the sensor unit 14, or calculates the arrival time and adds the arrival time as additional information.

[0057] The message generating section 23 generates a message based on the results of the output destination extracting section 22c, the results of the document generating section 22f, and the results of the additional information generating section 22g.

[0058] Based on the result of the determination by output determination section 22d, output section 15 outputs the message generated by message generation section 23 to an output destination.

[0059] [2. Operation of the document generation device] (2.1 Example of the operation of the document generation device) The operation of the document generation device according to the embodiment will be described with reference to FIGS.

[0060] Fig. 8 is a flowchart showing an example of the operation of the document generation device 10 according to the embodiment. Fig. 9 is a schematic diagram showing an example of the contents of a speaker's utterance and a generated message. Fig. 10 is a flowchart showing an example of a subroutine for analyzing the morpheme analysis result in Fig. 8. Fig. 11 is a flowchart showing an example of a subroutine for generating a message in Fig. 8. Figs. 12 to 14 are schematic diagrams showing an example of the contents of a speaker's utterance and a generated message.

[0061] 8, the document generation device 10 receives a voice input (step S1). Specifically, the input unit 11 receives a voice spoken by a user (speaker) using a mobile object.

[0062] The document generation device 10 may receive an input of a destination, acquire a current location from the sensor unit 14, and calculate a route to the destination.

[0063] Next, the document generation device 10 converts the voice signal into text data by voice recognition (step S2). Specifically, the system control unit 16 (voice recognition unit 21) converts the voice signal into text data. As shown in Fig. 9, the system control unit 16 obtains the voice recognition result: "Please inform Tanaka of my current location."

[0064] Next, the document generation device 10 performs morpheme analysis on the text data (step S3). Specifically, the system control unit 16 (morpheme analysis unit 22a) performs morpheme analysis on the text data to break it down into morphemes. As shown in Fig. 9, the system control unit 16 obtains morphemes such as "Tanaka", "ni", "current location", "wo", "contact", "shi", "toi", and "te" as a result of the morpheme analysis.

[0065] Next, the document generation device 10 analyzes the morpheme analysis result (step S4). Specifically, the system control unit 16 (output keyword extraction unit 22b, output destination extraction unit 22c, output determination unit 22d, and analysis unit 25) analyzes the morpheme analysis result of the morpheme analysis unit 22a. The analysis of the morpheme analysis result will be described in detail in the subroutine for analyzing the morpheme analysis result.

[0066] Next, the document generation device 10 judges whether or not to generate a message (step S5). Specifically, the system control unit 16 judges whether or not to generate a message based on a message generation flag as a return of the subroutine for analyzing the morphological analysis result.

[0067] In this way, the document generation device 10 functions as an example of an output determination section that determines whether or not to output the message based on the result of the analysis.

[0068] When a message is to be generated (step S5; YES), the document generation device 10 generates the message (step S6). Specifically, as shown in Fig. 9, the system control unit 16 (message generation unit 23) sets the email address to "tanaka@···c.ne.jp" and generates the email content (an example of a message) by adding, as additional information, a document "display map" that links to map information showing the current location to the document "I am passing through here now" (an example of a document). Note that, as additional information, only the map may be displayed below the document "I am passing through here now."

[0069] In this manner, the document generation device 10 functions as an example of a message generation unit that generates a message according to the document and the additional information.

[0070] Next, the document generation device 10 outputs the message (step S7). Specifically, the output unit 15 transmits the generated message via the communication unit 13 based on the email address. The output unit 15 may display the generated message on a display of the document generation device 10.

[0071] In this way, the document generation device 10 functions as an example of an output section that outputs the message to the output destination based on the determination result of the output determination section.

[0072] If a message is not to be generated (step S5; NO), the document generation device 10 ends the process.

[0073] (2.2 Subroutine for analyzing morphological analysis results) Next, the subroutine for analyzing the results of morphological analysis will be described with reference to FIG.

[0074] 10, the document generation device 10 acquires the morphological analysis result (step S10). Specifically, the system control unit 16 (document analysis unit 22) acquires the processing result of step S3.

[0075] Next, the document generation device 10 judges whether or not a keyword meaning transmission is present (step S11). Specifically, the system control unit 16 (output keyword extraction unit 22b) refers to the output database of the storage unit 12, extracts words meaning transmission such as "contact", "send", and "email" from the decomposed morphemes, and if extracted, judges that a keyword meaning transmission is present. In the example of Fig. 9, since the morpheme "contact" is present, the system control unit 16 judges that a keyword meaning transmission is present.

[0076] In this way, the document generation device 10 functions as an example of an extraction unit that extracts keywords from the text data according to the analysis result. Also, the document generation device 10 functions as an example of an output determination unit that determines whether or not to output the message based on the analysis result.

[0077] If a keyword meaning transmission is present (step S11; YES), the document generation device 10 judges whether or not name information of the output destination is present (step S12). Specifically, the system control unit 16 (output destination extraction unit 22c) refers to the address database (one example of the output destination database) in the storage unit 12, and judges whether or not information corresponding to "name" in the address database is present among the resolved morphemes. In the example of FIG. 9, since there is a morpheme "Tanaka", the system control unit 16 judges that name information of the output destination is present.

[0078] In this way, the document generation device 10 functions as an example of an output destination extraction unit that extracts the output destination from an output destination database in which the output destinations of the message are registered, according to the result of the analysis.

[0079] In this way, the document generation device 10 functions as an example of an extraction unit that extracts keywords from the text data according to the analysis result. Also, the document generation device 10 functions as an example of an output determination unit that determines whether or not to output the message based on the analysis result.

[0080] If the name information of the output destination exists (step S12; YES), the document generation device 10 judges whether or not a matching keyword exists (step S13). Specifically, the system control unit 16 (keyword extraction unit 22e) refers to the keyword database in the storage unit 12 and judges whether or not the decomposed morphemes include a morpheme that matches a keyword in the keyword database. In the example of Fig. 9, since there is a morpheme "current location", the system control unit 16 judges that a matching keyword exists.

[0081] In this way, the document generation device 10 functions as an example of an extraction unit that extracts keywords from the text data according to the analysis result. Also, the document generation device 10 functions as an example of an output determination unit that determines whether or not to output the message based on the analysis result.

[0082] If there is no keyword meaning transmission (step S11; NO), if there is no name information of the output destination (step S12; NO), or if there is no matching keyword (step S13; NO), the document generation device 10 sets a message non-generation flag (step S14). Specifically, the system control unit 16 sets an area for a flag for message generation in the RAM 16c, and sets the flag to "0".

[0083] If a matching keyword exists (step S13; YES), the document generation device 10 acquires address information and fixed phrase information (step S15). Specifically, the system control unit 16 (output destination extraction unit 22c) refers to the address database in the storage unit 12 and acquires an email address as address information. In the example of FIG. 9, the system control unit 16 acquires email address information "tanaka@···c.ne.jp" from the address database based on the name information "Tanaka". In addition, the system control unit 16 (keyword extraction unit 22e) acquires fixed phrase information by referring to the keyword database in the storage unit 12. In the example of FIG. 9, the system control unit 16 acquires the fixed phrase "I am passing by here now" from the keyword database based on the keyword "current location" and generates a document.

[0084] In this way, the document generation device 10 functions as an example of a document generation unit that generates a document in accordance with the result of analyzing text data converted from a voice signal uttered by a speaker.

[0085] Next, the document generating device 10 judges whether or not there is a keyword for the additional information (step S16). Specifically, the system control unit 16 (additional information generating unit 22g) refers to the additional information database in the storage unit 12 and judges whether or not there is a keyword for the additional information or a fixed phrase number corresponding to the fixed phrase acquired in step S15.

[0086] In this way, the document generation device 10 functions as an example of an extraction unit that extracts keywords from the text data according to the analysis result.

[0087] If there are keywords or the like for the additional information (step S16; YES), the document generation device 10 acquires the additional information and the fixed phrase information for the additional information (step S17). The system control unit 16 (additional information generation unit 22g) refers to the additional information database in the storage unit 12 to acquire the additional information corresponding to the keyword for the additional information and the additional information corresponding to the fixed phrase number. In the example of FIG. 9, the system control unit 16 acquires the item of map information as the additional information from the additional information database based on the fixed phrase number corresponding to "current location". The system control unit 16 also acquires the fixed phrase information ("display map") corresponding to the additional information "map information". The system control unit 16 sets a flag indicating that there is additional information.

[0088] In this way, the document generation device 10 functions as an example of an additional information generation unit that generates additional information to be added to the document based on at least one of the document and the keywords. The document generation device 10 also functions as an example of an additional information generation unit that acquires information related to the current location and generates the additional information including the information related to the current location based on at least one of the document and the keywords.

[0089] Next, the document generation device 10 sets a message generation flag (step S18). Specifically, the system control unit 16 sets an area for a flag for message generation in the RAM 16c, and sets the flag to "1".

[0090] If there is no keyword or the like for additional information (step S16; NO), a message generation flag is set (step S18). Then, the system control unit 16 sets a flag indicating that there is no additional information.

[0091] When the subroutine ends, the value of the flag is held and the document generation device 10 performs the process of step S5.

[0092] (2.3 Message Generation Subroutines) Next, the message generation subroutine will be described with reference to FIG.

[0093] 11, the document generation device 10 sets the acquired address information (step S20). Specifically, the system control unit 16 sets an email address for the email software.

[0094] Next, the document generation device 10 acquires phrases other than keywords and additional information-related phrases (step S21). For example, in the example of FIG. 9, the system control unit 16 (message generation unit 23) acquires morphemes other than the keyword "Tanaka", the output keyword "contact", and the keyword "current location". Then, the system control unit 16 extracts morphemes that can be used in the message. Note that in the example of FIG. 9, it may be possible that there are no words that can be used in the message excluding these keywords.

[0095] Next, the document generation device 10 generates a basic message from the keywords, phrases other than those related to additional information, and the standard phrase (step S22). For example, in the example of FIG. 9, the system control unit 16 (message generation unit 23) generates a basic message from the standard phrase "I am passing through here now."

[0096] Next, the document generation device 10 judges whether or not to acquire additional information, etc. (step S23). Specifically, if a flag indicating the presence of additional information is set in step S16, the system control unit 16 (message generation unit 23) judges to acquire additional information, etc.

[0097] When it is determined that additional information etc. is to be acquired (step S23; YES), the document generation device 10 adds the additional information etc. to the basic message (step S24). Specifically, the system control unit 16 (message generation unit 23) generates a message by adding the additional information related to the document "display map" and map information (latitude, longitude) to the basic message.

[0098] If it is not determined to acquire additional information, etc. (step S23; NO), the document generation device 10 proceeds to step S7 without adding additional information. For example, as shown in Fig. 12, the speech recognition result "Send an email to Tanaka that I will be 10 minutes late" is an example of no keyword corresponding to the additional information. Note that "email" is an output keyword, "late" is a keyword related to a fixed phrase, "Tanaka" is name information, and "10" and "minutes" are examples of phrases other than those related to additional information.

[0099] Next, other voice recognition results will be described with reference to FIGS. 13 and 14. FIG.

[0100] As shown in FIG. 13, "email" is a keyword meaning sending, "Tanaka" is a keyword for the name information of the output destination, "delay" is a keyword for extracting a fixed phrase, and "traffic jam" is a keyword for additional information.

[0101] In step S17, the document generation device 10 acquires the current location from the sensor unit 14 based on the keyword "traffic jam" for additional information, and acquires traffic jam information via the communication unit 13 based on the route information to the destination. Then, the document generation device 10 generates a document for additional information, a fixed phrase "traffic jam 2 km from XX on Kannana Dori" from the traffic jam information and the current location information. Here, "XX" is the current location.

[0102] The document generation device 10 generates a message of the mail content as shown in FIG.

[0103] In this way, the document generation device 10 functions as an example of an additional information generation unit that generates the additional information including information relating to the route from the current location to the destination.

[0104] As shown in FIG. 14, "send" is a keyword meaning send, "Tanaka" is a keyword for the name information of the output destination, "wait" is a keyword for extracting a fixed phrase, and "station" and "wait" are keywords for additional information.

[0105] In step S17, the document generation device 10 acquires map information about the vicinity of the station from the keywords for the additional information.

[0106] The document generation device 10 generates a message of the mail content as shown in FIG.

[0107] As described above, according to the operation of the embodiment, the words uttered by the speaker can be complemented with additional information to generate a natural message. Also, it becomes easier for the speaker to create documents.

[0108] In addition, when the current location is obtained, information related to the current location is obtained, and the additional information including the information related to the current location is generated based on at least one of a document and a keyword, by adding information about the current location, it is possible to complement the information to be communicated to the other party and convey accurate information.

[0109] When generating additional information including information from the current location to the destination, for example, traffic congestion information, arrival time, and weather information can be obtained as information from the current location to the destination (on the route) and added to the message, making it easier for the speaker to create documents without having to take the trouble of searching for traffic congestion or weather information.

[0110] Furthermore, when an output destination is extracted based on the analysis results from an output destination database (for example, an address database) in which message output destinations are registered, there is no need for the speaker to input the output destination, making operation easier for the speaker.

[0111] Based on the analysis result, it is determined whether or not to output a message, and when the message is output to the output destination based on the determination result, it is not necessary for the speaker to input the output destination, which facilitates the speaker's operation. [Explanation of symbols]

[0112] 10: Document generation device 10a: Document generation unit 10b: Extraction part 10c: Additional information generation unit 10d: Message generation section 11: Input section 14: Sensor section 15: Output section 16: System control unit (document generation unit, extraction unit, additional information generation unit, message generation unit) 21: Voice recognition unit 22: Document Analysis Section 22a: Morphological analysis section 22b: Output keyword extraction section 22c: Output destination extraction part 22e: Keyword extraction section 22f: Document generation section 22g: Additional information generation unit 23: Message generation unit

Claims

[Claim 1] a first acquisition unit that acquires text data obtained by converting a voice uttered by a speaker through voice recognition; an extraction unit that extracts keywords from the text data; A second acquisition unit that acquires fixed phrase information corresponding to the keyword; an additional information generating unit that generates additional information corresponding to at least one of the fixed phrase information and the keyword from an additional information database that stores additional information; a message generating unit that generates a message based on the template information and the additional information; A document generation device comprising:

Images