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

Abstract

This invention provides a document generation device, a document generation method, and a program for the document generation device that are easy for users to input data into. [Solution] The document generation device includes a document analysis unit 22 which includes a document generation unit 22f that generates a document according to the results of analyzing text data converted from speech signals uttered by a speaker, a keyword extraction unit 22e that extracts keywords from the text data according to the results of the analysis, and an additional information generation unit 22g 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 23 which generates a message according to the document and the additional information.

Description

Technical Field

[0001] This application belongs to the technical field of document generation devices, document generation methods, and programs for document generation devices.

Background Art

[0002] During the driving of a vehicle, which is an example of a moving body, a device for sending emails has been developed. For example, in Patent Document 1 below, email templates received from a mobile communication terminal are stored in an email template storage unit, and in response to an email sending request, one of the email templates stored in the email template storage unit is selected and sent to the mobile communication terminal. There is also disclosed a mobile communication terminal that sends the generated email template to the in-vehicle terminal, receives the email template sent from the in-vehicle terminal, generates a sending email based on the received email template at the email sending unit, and sends it to the email server.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the technology described in Patent Document 1 above, it is necessary to press a button to select a sending email during driving, which is not easy for the user to input. Also, it is necessary to select or search for and input information related to the content to be sent.

[0005] Therefore, this application has been made in view of the above problems, and an example of the problem is to provide a document generation device and the like that are easy for the user to input.

Means for Solving the Problems

[0006] To solve the above problems, the invention described in claim 1 is characterized by comprising: a document generation unit that generates a document according to the results of analyzing text data converted from speech signals uttered by a speaker; an extraction unit that extracts keywords from the text data according to the results 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] Furthermore, the invention described in claim 6 is characterized by including a document generation step of generating a document in accordance with the results of analyzing text data converted from speech signals uttered by a speaker; an extraction step of extracting keywords from the text data in accordance with the results 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 in accordance with the document and the additional information. [Brief explanation of the drawing]

[0008] [Figure 1] This is a block diagram showing an example of the schematic configuration of a document generation device according to an embodiment. [Figure 2] This is a block diagram showing an example of the outline configuration of a document generation device according to the embodiment. [Figure 3] Figure 2 is a schematic diagram showing an example of an address database constructed in the memory unit. [Figure 4] Figure 2 is a schematic diagram showing an example of a keyword database constructed in the memory unit. [Figure 5] Figure 2 is a schematic diagram showing an example of an additional information database constructed in the memory unit. [Figure 6] Figure 2 is a block diagram showing an example of the functional blocks of a document generation device. [Figure 7] Figure 6 is a block diagram showing an example of a functional block in the text analysis unit. [Figure 8]This flowchart shows an example of the operation of the document generation device according to the embodiment. [Figure 9] This is a schematic diagram showing an example of what the speaker said and the resulting message. [Figure 10] This flowchart shows an example of a subroutine for analyzing the morphological analysis results shown in Figure 8. [Figure 11] Figure 8 is a flowchart showing an example of a subroutine for generating messages. [Figure 12] This is a schematic diagram showing an example of what the speaker said and the resulting message. [Figure 13] This is a schematic diagram showing an example of what the speaker said and the resulting message. [Figure 14] This is a schematic diagram showing an example of what the speaker said and the resulting message. [Modes for carrying out the invention]

[0009] The embodiments for carrying out this application will be described with reference to Figure 1. Figure 1 is a block diagram showing an example of the schematic configuration of a document generation device according to the embodiment.

[0010] As shown in Figure 1, the document generation device 10 is configured to include 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 according to the document and the additional information.

[0011] In this configuration, the document generation unit 10a generates a document according to the results of analyzing the text data converted from the speech signal uttered by the speaker.

[0012] Examples of speakers include users of vehicles, motorcycles, aircraft, ships, and other forms of transportation.

[0013] Also, as an example of the conversion process from an audio signal to text data, there is a speech recognition process that extracts the spoken content as character data. As an example of recognition technology, there are statistical methods, dynamic time warping, hidden Markov models, and the like.

[0014] Also, as an example of the analysis of text data, there are natural language processing technologies such as morphological analysis. Also, as an example of the result of analyzing text data, there are results such as decomposing a document into morphemes (which may be words or phrases), the smallest units having meaning in a language by morphological analysis, and the result of discriminating the part-of-speech of morphemes.

[0015] Also, as an example of a document, there are set phrases such as "will be late" for the keyword "be late", "will be late" for the keyword "late", "will pass here now" for the keyword "current location", "where I am now".

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

[0017] Here, as an example of extracting keywords from text data according to the analysis result, extraction of keywords meaning transmission such as "send", "send it", "contact" (an example of output keywords), extraction of keywords meaning display such as "display", "show me" (an example of output keywords), extraction of keywords meaning output destinations such as the addressee of an email like a person's name, company name, and the display destination of "display", extraction of keywords such as "be late", "be tardy" to引出 the set phrase "will be late", extraction of keywords for obtaining additional information, and the like.

[0018] The additional information generation unit 10c generates additional information to be added to the 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 "I will be late," and map information (latitude, longitude) for the standard phrase "I am passing here now."

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

[0021] Examples of messages include, if the keyword is "current location," a message that includes a map of the current location, a message that includes a document titled "Map Display" showing a link to the map of the current location, if the keyword is "traffic jam," a document titled "Traffic jam ○km from ○○," and if the keyword is "wait," a document such as "Please wait at the east exit of ○○ Station."

[0022] As described above, according to the operation of the document generation device 10 according to this embodiment, it is possible to generate a natural message by supplementing the words spoken by the speaker. [Examples]

[0023] [1. Overview of Document Generation Device Configuration and Functions] (1.1 Overview of Document Generation Device Configuration and Functions)

[0024] Next, specific embodiments corresponding to the embodiments described above will be explained using Figures 2 to 5. The embodiments described below are examples in which the present invention is applied to a document generation device.

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

[0026] As shown in Figure 2, the document generation device 10 according to this embodiment includes an input unit 11 that receives input from the user, a storage unit 12 that stores programs for controlling the document generation device 10, a communication unit 13 that transmits and receives data to and from the outside of the document generation device 10, a sensor unit 14 that detects the state of the mobile device used by the user, an output unit 15 that outputs processing results, a system control unit 16 that controls 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 includes a microphone that converts the speaker's voice into an electrical signal, a touchpad with a position input function, and the like. The position input function is composed of elements that implement, for example, a capacitive or resistive touch method. The input unit 11 acquires positional information of the surface of the input unit 11 that is in contact with or near the user's finger, etc., in units of pixels with a predetermined resolution. The input unit 11 may also be a touch panel with a display function and a position input function.

[0028] The input unit 11 receives voice input from the user and inputs such as destinations from the user.

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

[0030] Furthermore, the memory unit 12 contains an address database for storing email address information, a keyword database for storing keywords and standard phrases, and an additional information database for storing additional information to be added to documents. The memory unit 12 also contains a dictionary database for performing morphological analysis. Additionally, the memory unit 12 contains a map database.

[0031] Furthermore, the memory unit 12 has an output database that stores keywords related to output such as transmission and display. For example, the output database stores keywords such as "contact," "transmit," "email," and "display."

[0032] As shown in Figure 3, the address database stores email addresses associated with personal names, company names, place names, etc. Addresses can be entered into the address database by obtaining them via communication from an address book on a smartphone or other device, by directly entering them into an in-vehicle system including the document generation device 10, or by obtaining them via the communication unit 13 from an address book on the network cloud.

[0033] As shown in Figure 4, the keyword database stores predefined phrases associated with keywords. Each predefined phrase is assigned a predefined phrase number.

[0034] Furthermore, in Figure 4, for keywords that include a location, such as "wait," a predefined phrase is provided indicating where to insert the location word, such as "*".

[0035] Note that predefined phrases can be entered into the keyword database from external devices such as personal computers or smartphones.

[0036] Furthermore, when performing morphological analysis on speech recognition results and treating the results as keywords, the combination of the verb stem and its conjugation ending may be used as the keyword. For example, in the case of "okureru" (to be late), the keyword is a combination of the stem "ochi" (late) and the conjugation ending "re, re, reru, reru, rere, rero" (lower ichidan conjugation). Additionally, combinations of morphemes from different parts of speech may be used as keywords. For example, in "matte te" (wait), "mat" is an independent verb, "te" is a particle and conjunctive particle, and "te" is a non-independent verb. Similarly, in the case of "ite" (feel), "i" is an independent verb, and "te" is a particle and conjunctive particle.

[0037] As shown in Figure 5, the additional information database stores additional information associated with keywords or standard phrases. Alternatively, additional information may be associated using combinations of keywords and standard phrases.

[0038] Additional information can be registered in the additional information database from external devices such as personal computers or smartphones. Furthermore, the additional information is generated using information from the sensor unit 14, time information, a map database, etc. In addition, text / messages related to the additional information may be dynamically registered as standard text in the additional information database. Furthermore, in an additional information database, documents / messages that handle additional information statically in advance. It may be registered as such. Furthermore, there may be multiple additional information databases depending on the type of additional information.

[0039] The communication unit 13 connects to a network such as the Internet via wireless communication and controls the communication status with the outside world.

[0040] The sensor unit 14 has a GPS (Global Positioning System) sensor and is located in satellite orbit. The document generation device 10 receives navigation signals from GPS satellites and detects the position, altitude, etc., of the mobile object on which it is installed. The sensor unit 14 is connected to various sensors on the mobile object (for example, a sensor that detects changes in liquid level due to tilt, a vehicle speed pulse sensor, an acceleration sensor, and a gyroscope sensor) to acquire mobile object information such as speed, acceleration, tilt, distance traveled, and engine speed. 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, and a liquid crystal display element or EL (Electro-Luminescence) element that displays the generated document. If the display function of the output unit 15 is a head-up display, the output unit 15 has projection means and screen means (windshield, eyeglass lens, 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 RO It has M (Read Only Memory) 16b and RAM (Random Access Memory) 16c. The system control unit 16 reads and executes various programs stored in the ROM 16b, RAM 16c, and memory unit 12 from the CPU 16a. The system control unit 16 performs voice recognition, analyzes documents, generates messages, and calculates the movement route of a moving object based on the current location and accepted destination information.

[0043] Furthermore, the document generation device 10 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 explained using Figures 6 and 7. Figure 6 is a block diagram showing an example of the functional blocks of the document generation device 10. Figure 7 is a block diagram showing an example of the functional blocks of the document analysis unit 22.

[0045] As shown in Figure 6, the document generation device 10 includes a speech recognition unit 21 that converts speech data acquired by the 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 the output unit 15. The speech recognition unit 21, the document analysis unit 22, and the message generation unit 23 are implemented by the system control unit 16.

[0046] The message generation unit 23 (an example of the message generation unit 10d) creates a standard text according to the analysis results of the document analysis unit 22. The message generation unit 23 adds morphologically analyzed text or adds a standard text containing additional information to the selected standard text.

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

[0048] As shown in Figure 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 the analysis unit 25.

[0049] The morphological analysis unit 22a performs morphological analysis on the text data converted by the speech recognition unit 21, decomposes it into morphemes, and determines the part of speech, etc.

[0050] The output keyword extraction unit 22b (an example of the extraction unit 10b) has an output database (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 output destination extraction unit 22c (an example of the extraction unit 10b) has an address database (storage unit 12). The output destination extraction unit 22c refers to the address database and extracts names of people, companies, places, etc. from the decomposed morphemes. Next, the output destination extraction unit 22c refers to the address database and extracts email addresses corresponding to the names of people, companies, places, 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 that means output and the recipient's 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) extracts keywords from the decomposed morphemes by referring to the keyword database. For example, the keyword extraction unit 22e extracts keywords corresponding to standard phrases. Alternatively, the keyword extraction unit 22e may also extract keywords from the decomposed morphemes by referring to the supplementary information database. For example, the keyword extraction unit 22e extracts keywords corresponding to supplementary information.

[0055] The document generation unit 22f (an example of the document generation unit 10a) refers to the keyword database, extracts standard phrases corresponding to the keywords extracted by the keyword extraction unit 22e, and generates a document. Alternatively, the document generation unit 22f may generate a document by combining morphemes from the decomposed morphemes.

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

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

[0058] The output unit 15 outputs the message generated by the message generation unit 23 to the output destination based on the determination result of the output determination unit 22d.

[0059] [2. Operation of the document generation device] (2.1 Example of document generation device operation) The operation of the document generation device according to the embodiment will be explained using Figures 8 to 14.

[0060] Figure 8 is a flowchart showing an example of the operation of the document generation device 10 according to the embodiment. Figure 9 is a schematic diagram showing an example of the content spoken by the speaker and the generated message. Figure 10 is a flowchart showing an example of the subroutine for analyzing the morphological analysis results of Figure 8. Figure 11 is a flowchart showing an example of the subroutine for generating the message of Figure 8. Figures 12 to 14 are schematic diagrams showing an example of the content spoken by the speaker and the generated message.

[0061] As shown in Figure 8, the document generation device 10 accepts voice input (step S1). Specifically, the input unit 11 receives the voice spoken by the user (speaker) using the mobile device.

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

[0063] Next, the document generation device 10 converts the voice signal into text data using speech recognition (step S2). Specifically, the system control unit 16 (speech recognition unit 21) converts the voice signal into text data. As shown in Figure 9, the system control unit 16 obtains the speech recognition result: "Tell Tanaka where I am now".

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

[0065] Next, the document generation device 10 analyzes the morphological analysis results (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 morphological analysis results of the morphological analysis unit 22a. The analysis of the morphological analysis results will be explained in detail in the subroutine for analyzing the morphological analysis results.

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

[0067] Thus, 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 results of the analysis.

[0068] If a message is to be generated (Step S5; YES), the document generation device 10 generates a message (Step S6). Specifically, as shown in Figure 9, the system control unit 16 (message generation unit 23) sets the email address to "tanaka@···c.ne.jp" and generates an email content (example message) that includes "You are currently passing through here." (example document) and, as additional information, adds a document titled "Display Map" which links to map information showing the current location. Alternatively, as additional information, only the map may be displayed below the document "You are currently passing through here."

[0069] Thus, 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 a message (step S7). Specifically, the output unit 15 sends the generated message via the communication unit 13 based on the email address. The output unit 15 may also display the generated message on the display of the document generation device 10.

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

[0072] If no message is generated (step S5; NO), the document generator 10 terminates processing.

[0073] (2.2 Subroutine for analyzing morphological analysis results) Next, we will explain the subroutine for analyzing the morphological analysis results using Figure 10.

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

[0075] Next, the document generation device 10 determines whether or not a keyword meaning "to send" exists (step S11). Specifically, the system control unit 16 (output keyword extraction unit 22b) refers to the output database of the storage unit 12 and extracts words meaning "to send," such as "contact," "send," and "email," from the decomposed morphemes. If it can extract such words, it determines that a keyword meaning "to send" exists. In the example in Figure 9, since the morpheme "contact" exists, the system control unit 16 determines that a keyword meaning "to send" exists.

[0076] Thus, the document generation device 10 functions as an example of an extraction unit that extracts keywords from the text data according to the results of the analysis. Furthermore, 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 results of the analysis.

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

[0078] Thus, 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 that registers the output destinations of the message, according to the results of the analysis.

[0079] Thus, the document generation device 10 functions as an example of an extraction unit that extracts keywords from the text data according to the results of the analysis. Furthermore, 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 results of the analysis.

[0080] If name information for the output destination exists (step S12; YES), the document generation device 10 determines whether 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 determines whether there is a morpheme among the decomposed morphemes that matches a keyword in the keyword database. In the example in Figure 9, there is a morpheme called "current location", so the system control unit 16 determines that a matching keyword exists.

[0081] Thus, the document generation device 10 functions as an example of an extraction unit that extracts keywords from the text data according to the results of the analysis. Furthermore, 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 results of the analysis.

[0082] If there is no keyword indicating transmission (step S11; NO), if there is no name information for the output destination (step S12; NO), or if there is no matching keyword (step S13; NO), the document generation device 10 sets a message not generated flag (step S14). Specifically, the system control unit 16 sets a flag area for message generation in RAM 16c and sets the flag to "0".

[0083] If a matching keyword exists (step S13; YES), the document generation device 10 obtains address information and standard 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 obtains an email address as address information. In the example in Figure 9, the system control unit 16 obtains the email address information "tanaka@···c.ne.jp" from the address database based on the name information "Tanaka". The system control unit 16 (keyword extraction unit 22e) also obtains standard phrase information by referring to the keyword database in the storage unit 12. In the example in Figure 9, the system control unit 16 obtains the standard phrase "You are currently passing through here" from the keyword database based on the keyword "current location" and generates a document.

[0084] Thus, the document generation device 10 functions as an example of a document generation unit that generates a document according to the results of analyzing text data converted from speech signals uttered by a speaker.

[0085] Next, the document generation device 10 determines whether or not keywords for additional information exist (step S16). Specifically, the system control unit 16 (additional information generation unit 22g) refers to the additional information database in the storage unit 12 and determines whether or not keywords for additional information or a standard phrase number corresponding to the standard phrase obtained in step S15 exist.

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

[0087] If keywords for additional information exist (step S16; YES), the document generation device 10 acquires the additional information and standard 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 and acquires additional information corresponding to the keywords for the additional information and additional information corresponding to the standard phrase number. In the example in Figure 9, the system control unit 16 acquires the map information item as additional information from the additional information database based on the standard phrase number corresponding to "current location". The system control unit 16 also acquires standard phrase information ("display map") corresponding to the additional information "map information". The system control unit 16 also sets a flag indicating that additional information exists.

[0088] Thus, the document generation device 10 functions as an example of an additional information generation unit that generates additional information to be added to a document based on at least one of the document and the keywords. Furthermore, 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 a flag area for message generation in RAM 16c and sets the flag to "1".

[0090] Furthermore, if there are no keywords or other information for additional information (step S16; NO), the message generation flag is set (step S18). The system control unit 16 then sets a flag indicating that there is no additional information.

[0091] When the subroutine finishes, the document generator 10 retains the value of the flag and performs the process in step S5.

[0092] (2.3 Subroutine for generating messages) Next, the message generation subroutine will be explained using Figure 11.

[0093] As shown in Figure 11, the document generation device 10 sets the acquired address information (step S20). Specifically, the system control unit 16 sets the email address of the email software.

[0094] Next, the document generation device 10 acquires phrases other than keywords and additional information (step S21). For example, in the example in Figure 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 in Figure 9, it is also possible that there are no words that can be used in the message if these keywords are excluded.

[0095] Next, the document generation device 10 generates a basic message using keywords, phrases other than those related to additional information, and standard phrases (step S22). For example, in the example in Figure 9, the system control unit 16 (message generation unit 23) generates the basic message, which is the standard phrase "You are currently passing through here."

[0096] Next, the document generation device 10 determines whether or not to acquire additional information (step S23). Specifically, if the system control unit 16 (message generation unit 23) has set a flag indicating that additional information exists in step S16, it determines to acquire the additional information.

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

[0098] If the decision is not made to acquire additional information (step S23; NO), the document generation device 10 proceeds to step S7 without adding the additional information. For example, as shown in Figure 12, the speech recognition result "Tell Tanaka I'll be 10 minutes late" is an example where there are no keywords corresponding to additional information. Note that "email" is an output keyword, "late" is a keyword related to the standard phrase, "Tanaka" is name information, and "10" and "minutes" are examples of phrases other than those related to additional information.

[0099] Next, other speech recognition results will be explained using Figures 13 and 14.

[0100] As shown in Figure 13, "email" is the keyword for sending, "Tanaka" is the keyword for the name information of the output destination, "delayed" is the keyword for extracting the standard phrase, and "traffic jam" is the keyword for additional information.

[0101] In step S17, the document generation device 10 obtains the current location from the sensor unit 14 based on the keyword "traffic jam" for additional information, and obtains 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 with the standard phrase "2km traffic jam from XX on Kan-nana Street" for additional information 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 containing email content, as shown in Figure 13.

[0103] Thus, the document generation device 10 functions as an example of an additional information generation unit that generates the additional information, including information about the distance from the current location to the destination.

[0104] As shown in Figure 14, "Send" is the keyword meaning "send", "Tanaka" is the keyword for the name information of the output destination, "Wait" is the keyword for extracting the standard phrase, and "Station" and "Wait" are keywords for additional information.

[0105] In step S17, the document generation device 10 obtains map information of the area around the station from keywords for additional information.

[0106] The document generation device 10 generates a message containing email content, as shown in Figure 14.

[0107] As described above, the operation according to the embodiment allows for the generation of natural-sounding messages by supplementing the words spoken by the speaker with additional information. Furthermore, it makes document creation easier for the speaker.

[0108] Furthermore, when acquiring the current location and information related to the current location, and generating the aforementioned additional information that includes information related to the current location based on at least one of the document and keywords, adding information about the current location allows for the accurate transmission of information by complementing the information to be conveyed to the recipient.

[0109] When generating additional information that includes information about the route from the current location to the destination, it is possible to request and add information about the route from the current location to the destination (such as traffic information, estimated arrival time, and weather information) to the message. This makes it easier for the speaker to create documents without having to search for traffic information or weather information themselves.

[0110] Furthermore, when extracting output destinations from an output destination database (e.g., an address database) based on the analysis results, there is no need to manually input the output destination, making it easier for the speaker to operate.

[0111] Based on the analysis results, a decision is made as to whether or not to output a message. If the message is to be output to the destination based on the decision result, the speaker does not need to input the destination, making operation easier. [Explanation of Symbols]

[0112] 10: Document generation device 10a: Document generation unit 10b: Extraction part 10c: Additional information generation unit 10d: Message generation unit 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: Speech Recognition Unit 22: Document Analysis Department 22a: Morphological analysis section 22b: Output Keyword Extraction Unit 22c: Output destination extraction part 22e: Keyword Extraction Unit 22f: Document Generation Unit 22g: Additional information generation unit 23: Message generation unit

Claims

[Claim 1] A first acquisition unit acquires text data converted from the speech uttered by the speaker by speech recognition, An extraction unit for extracting keywords from the aforementioned text data, A second acquisition unit acquires standard phrase information corresponding to the aforementioned keyword, An additional information generation unit generates additional information corresponding to at least one of the standard phrase information and the keyword from an additional information database that stores additional information, A message generation unit that generates a message based on the aforementioned standard text information and the aforementioned additional information, A document generation device characterized by having the following features.

Images