JP2012068910A - Information processor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an information processor for reading aloud information acquired from an information provision server after removing unnecessary information to be read aloud.SOLUTION: The information processor includes: communication means for accessing a server for providing information and acquiring information from the server; acquisition means for analyzing the information acquired by the communication means to acquire at least one utterance data and acquiring identification information of a speaker, information that shows an image of the speaker, and utterance content from the respective utterance data; display means for acquiring image data of the speaker from the information that shows the image of the speaker and displaying it together with the identification information of the speaker; sentence creation means for analyzing the utterance content and removing unnecessary information to create sentences for voice synthesis; and notification means for notifying a user of the sentences created by the sentence creation means by using voice synthesis.

Description

  The embodiment of the present invention displays navigation information for driving assistance to a vehicle driver, converts text information from the information providing server into speech, outputs it, and synchronizes the speech with speech to read the text. The present invention relates to an information processing apparatus that uses image information of a speaking user or a user who is a speaking target as display means.

  2. Description of the Related Art Conventionally, there is a navigation device that supports driving to a destination, and navigation information is displayed on a display such as a liquid crystal panel provided in the vehicle. In recent years, there is also a device that improves the driver's visibility by providing a head-up display (hereinafter referred to as HUD) that displays navigation information on the windshield of the vehicle.

  Recently, it has become possible to collect various information in real time and to write information on the Internet by using services on the Internet using information communication devices such as mobile phones and personal computers. As an example of such a communication service, for example, “Twitter” (Twitter) is generally known, a user writes a short article called “tweet”, and other users read or write the remarks. You can reply to the remarks.

  That is, “Twitter” is a service that delivers short messages in real time, and can be received using a mobile phone or a PC (personal computer), and is widely used worldwide. In the above service, in addition to the sentences (speakers) written by the speaker himself, other senders registered by the speaker himself can be seen in time series together with his / her speech. In addition, there is a function of quoting a comment written by another speaker or writing a reply to a certain speaker's comment.

  Since the number of characters that can be transmitted in the above service is limited, a dedicated rule is defined so as to advance the conversation with a short speech. In addition, the information indicating the user who has spoken or the user who is the subject of the speech is also very important information in the “Twitter” service, and the user-defined ID and image data (icon) indicating the user are displayed together with the text. Is done.

  In addition, there is a request to display information collected in real time on the vehicle display while driving, but displaying the collected information on the vehicle display increases the time it takes to watch the display screen. It hinders and is dangerous. In the case of a mail service, the content can be understood without paying attention to the screen by reading out the content of the text by using a speech synthesis means.

  However, in the case of the “Twitter” service, the content of the text contains the user ID, abbreviations such as search keywords, and identifiers for accessing other information. There is a problem that it becomes difficult. In particular, the user ID uses a lot of characters and symbols that cannot be read out by speech synthesis, and is inappropriate as a target to be read out by speech synthesis.

JP-A-11-134166 JP 2010-71656 A

  The problem to be solved by the present invention is to analyze information acquired from an information providing server, and to convey information about a user who has made a statement, a user who is to speak, and the contents of a sentence without diverting the driver's attention from driving To provide an apparatus.

  The information processing apparatus according to the embodiment accesses a server for providing information, obtains information from the server, and obtains one or more utterance data by analyzing the information obtained by the communication means, And from each utterance data, the identification information of the utterer, the information indicating the image of the utterer, and the acquisition means for acquiring the content of the utterance; Display means for displaying together with the identification information of the person, sentence creation means for analyzing the content of the utterance, removing unnecessary information and creating a sentence for speech synthesis, and sentence created by the sentence creation means by speech synthesis An informing means for informing.

1 is a block diagram showing an overall configuration of an information processing apparatus according to an embodiment. Explanatory drawing which shows an example of exchange with the server for information provision. The perspective view which shows the example which attached the information processing apparatus to the vehicle. Explanatory drawing which shows the example which displayed the server information acquired with the communication means with the personal computer. Explanatory drawing which shows the example of a display of server information, and audio | voice alerting | reporting. Explanatory drawing which shows the 2nd example of a display of server information and audio | voice alerting | reporting. Explanatory drawing which shows the 3rd example of a display of a server information, and audio | voice alerting | reporting. Explanatory drawing which shows the 4th example of a display of a server information, and audio | voice alerting | reporting. Explanatory drawing which shows the example which displayed the acquired server information by HUD.

  Hereinafter, an information processing apparatus according to an embodiment will be described in detail with reference to the drawings. In addition, in each figure, the same code | symbol is attached | subjected about the same location.

  FIG. 1 is a block diagram illustrating a configuration of an information processing apparatus according to an embodiment, and illustrates an information processing apparatus for a vehicle. The vehicle information processing apparatus may have an information processing unit related to navigation or an audio function for listening to music or radio, but is omitted because it is not a main part of this embodiment.

  In FIG. 1, an information processing apparatus 10 records a CPU 11 that executes a program, a memory 12 that temporarily stores programs and data, a ROM 13 that holds programs, a map data, a dictionary for speech synthesis, and phoneme data. Calculation means based on phoneme data, recording means 14 such as HDD and flash memory, display means 15 for displaying navigation and music information on a liquid crystal screen, input means 16 for inputting user instructions using buttons and touch panel It comprises voice output means 17 for converting the generated digital voice synthesis data into an analog signal and outputting it, and communication means 18 for communicating with an information providing server 20 provided outside the vehicle by a system such as LTE or 3G line. .

  The display means 15 displays information, and a liquid crystal display or HUD provided in the vehicle is used. The input means 16 detects an input from an operation button (not shown) provided on the vehicle, and inputs various instructions by an operation of a driver or the like. The input means 16 may be a touch panel type that touches the display of the display means 15.

  The audio output means 17 further includes an audio amplifier and a speaker 171 (FIG. 3), and notifies the audio from a speaker attached inside the vehicle, for example. In the following description, processing the voice synthesis data and notifying from the speaker will be referred to as “reading a sentence”.

  In the present embodiment, an example is shown in which each element in FIG. 1 is connected by a bus and embodied in a single housing. However, one or more functions are provided in another device and connected by wire or wirelessly. A configuration realized in cooperation with other devices is also conceivable.

  In addition, the CPU has a high capability at present and can be realized as software without using a dedicated LSI or the like. Therefore, in the embodiment, a method realized by software is described, but a method of replacing one or more functions with hardware such as LSI and adding it to the configuration of FIG. 1 is also conceivable.

  FIG. 2 is an explanatory diagram illustrating an example of information exchange between the information processing apparatus 10 and the information providing server 20. The information acquisition uses the same method as that performed by the PC program. That is, the information providing server 20 (hereinafter simply referred to as a server) is a server included in a communication service system on the Internet, and can be accessed by communication means such as an LTE or 3G line. In the present embodiment, the communication service system will be described using a system called “Twitter” developed by Twitter in the United States.

  The software having the configuration of the present embodiment accesses the server 20 using a predetermined URL. At the same time, the information processing apparatus 10 transmits information such as the user ID, password, and the number of necessary utterances (N) to the server 20. The server 20 performs authentication with the user ID and password, and if the authentication result is correct, the server 20 transmits the requested information to the information processing apparatus 10 provided in the vehicle.

  The server 20 creates structured format data such as XML or JSON as information to be transmitted. An item indicating one utterance (one piece of data shown in FIG. 2) includes a utterance ID, a uttered user ID, information (URL) indicating an image of the uttered user, a utterance date, a utterance content, and a utterance content. The information such as the ID of the original message is described in accordance with a predetermined tag, and these items are information in a format in which the required number (N) of items is stored.

  The program operating on the information processing apparatus 10 analyzes the received data based on the TAG included therein, acquires one or more utterance data, and holds it in the recording unit 14. Next, each piece of utterance data is analyzed, and for each piece of utterance data, information such as the utterer's ID, URL indicating the utterer's image, utterance date and time, utterance content, and citation information is acquired and recorded in the recording means 14 . Therefore, the CPU 11 and the recording unit 14 constitute an acquisition unit that acquires message data and the like. The voice output unit 17 has a function of a sentence creation unit that analyzes the content of a statement, removes unnecessary information, and creates a sentence for speech synthesis.

  FIG. 3 is a perspective view showing a configuration when the information processing apparatus 10 is attached to a vehicle and information is displayed on the display means 15. The display means 15 displays information, and a liquid crystal display 151 provided in the vehicle or a HUD is used. The liquid crystal display 151 displays information such as navigation information, music playback information, and air conditioner settings. The HUD is a projector disposed at a position corresponding to the driver's seat on the dashboard of the vehicle, for example, and projects an image on the windshield FG in front of the driver's seat. A speaker 171 is provided near the liquid crystal display 151.

  Further, as shown in FIG. 3, a start button 161 and a stop button 162 that can be operated by the driver are provided in the vehicle. When the start button 161 is pressed, the application is started and access to the server 20 is started. The access is stopped by pressing a stop button 162. Alternatively, a touch panel type operation button may be displayed on the liquid crystal display 151 so that the same function as the start button 161 and the stop button 162 can be executed. The start button 161 and the stop button 162 constitute part of the input means 16.

  FIG. 4 shows an example when information of the “Twitter” service is displayed on the screen of the personal computer. In the example, only one writing is described, but actually, a plurality of such writings are displayed in time series.

  Fig. 4 (a) shows that "tenki", the speaker, said, "A seismic earthquake with a maximum seismic intensity of 3M occurred off the southeast of Shiretaru Island at around 15:38 on March 18," URL of related information, and classification It is the figure which showed the example which wrote the hash tag for. In FIG. 4A, in addition to the speaker icon 41 and the speaker ID 42, a URL (Uniform Resource Locator) 43 indicating related information described in http: //, and the genre of the content of the message starting with # A hash tag 44 indicating a theme and a content 50 of a message called a tweet are shown.

  FIG. 4B is a diagram illustrating an example in which the speaker ID_123 has remarked “How are you” with respect to ID_XYZ. The symbol (45) of @ is a symbol indicating a message addressed to ID_XYZ.

  FIG. 4C is a diagram showing an example in which the speaker ID_123 directly quotes the content of the speech of the speaker ID_XYZ “here, the 3rd summer day continues”. The two arrow marks 46 are symbols indicating quotations from other users.

  FIG. 4D is a diagram showing an example in which the content of the speaker ID_123 is quoted as “Today it is hot” and “Tokyo is also hot”. The symbol 47 of RT is a symbol indicating citation of other utterance contents. However, unlike the symbol 46 of FIG. 4C, the symbol 47 of RT is used when not only citation but also utterance with respect to citation.

  By the way, since the information shown in FIG. 4 includes a user ID, an abbreviation such as a search keyword, an identifier for accessing other information, etc., the text is read as it is by using speech synthesis means. However, it is difficult to understand the contents. In particular, the user ID uses a lot of characters and symbols that cannot be read out by speech synthesis, and requires a method of changing to speech.

  For this reason, this embodiment is characterized in that the information acquired from the server 20 is analyzed, and the user who made the statement, the user who is the subject of the statement, and the content of the sentence are conveyed without diverting the driver's attention from driving. There is. This will be specifically described below.

  FIG. 5 is an explanatory diagram showing a display example of an image displayed on the display unit 15 by processing the server information acquired by the communication unit 18 and contents read out by speech synthesis. In FIG. 5, the navigation image 30 is displayed and the server information 40 is displayed superimposed on the navigation image 30. As the navigation image 30, an example is shown in which an arrow for guiding the traveling direction of the vehicle is displayed. The server information 40 includes, for example, an image data (icon) 41 of a speaker and an ID 42 which is identification information of the speaker. Further, in FIG. 5, for the sake of convenience, the content of notification by voice is shown in a dotted frame 50.

  In the example shown in FIG. 5, an example in which a speaker's icon 41 and a speaker's ID 42 are displayed for the content that a specific speaker has spoken is shown. Various are also conceivable. Furthermore, in this example, the server information 40 is displayed superimposed on the navigation image 30, but may be displayed superimposed on a music or radio player screen, or the server information 40 may be displayed alone.

  That is, in the embodiment, based on the analysis result of the utterance data acquired from the server 20, the utterance user ID and the user image (icon) are displayed on the display unit 15, and the utterance content information is further analyzed. Control what is read and what is displayed on the display screen.

  The contents of the statement are analyzed in the following procedure. First, the content of a statement is divided into a plurality of data using symbols such as “,” “”. Next, it is checked whether each divided data includes a predetermined special symbol or special character, for example, http: //, @, #, RT, QT, etc. The following processing is performed according to the character.

  In the case of http: //, it shows information for acquiring related information, and it is not information suitable for reading, so data including http: // is deleted. In the case of @, a message to the user having the following characters as an ID is shown, and this ID information is deleted for use as display data. Also, the characters following the # indicate keywords used for the search, and are not information suitable for reading, so data including # is deleted. RT and QT are symbols indicating that the following sentences are citations. In this case, not only the characters RT and QT are deleted, but also the data after RT and QT is replaced with the data before RT and QT. Read ahead of the data.

  Even for data not including the special symbols, symbols inappropriate for reading, such as “”, {}, (), etc. are deleted. In this way, it becomes easy to listen to the server information by making a rule for reading out the content that has been spoken and deleting a portion unnecessary for reading to create a reading sentence.

  In the case of Fig. 4 (a), the content of the remark is "At about 15:38 on the 18th, an earthquake with a maximum seismic intensity of 3M occurred off the southeast of Etorofu Island. (Http: //www.tenki/index.html) #tenki “#Saigai”, but after applying the above rule, as shown in FIG. 5, a reading sentence 50 reads, “A seismic intensity of 3M occurred off the southeast of Teppetsu Island at around 15:38 on March 18,” Is sent to the speech synthesis module to create speech data and output it from the speech output means 17. The display unit 15 displays the speaker image data (icon) 41 and the speaker ID 42. The speaker icon 41 and the speaker ID 42 are displayed in synchronization with the time from the start of speech synthesis speech to the end of speech.

  If the same person continues to speak, the icon and ID may be temporarily deleted, and the icon and ID of the same person may be displayed after a certain time interval. In this way, the driver can be explicitly notified that it is another statement.

  As described above, according to the embodiment, the information collected from the information providing server 20 can be converted into sound and output, and information that is not necessary to be read out such as IDs and symbols is omitted and read out. Easy to understand.

  Hereinafter, another display example of the server information (the speaker icon 41 and the speaker ID 42) and an example of voice notification will be described with reference to FIGS. 6 to 8 show a case where the server information is displayed alone on the display means.

  As shown in FIG. 4B, when the speaker's speech is directed toward a person having a specific ID, the content of the speech is “@ID_XYZ, how are you”? As shown in FIG. 6, the text reads “How are you?” Further, ID_XYZ included in the content of the speech is handled as the ID of the person who handles the speech. As a result, as shown in FIG. 6, by displaying in combination with the icon and ID of the speaker, and an icon (for example, an arrow) indicating that the speech is for a specific person, it is easy to understand who to whom. It becomes possible to do.

  When the content of the ID_XYZ statement is quoted as shown in FIG. 4 (c), after the above rule adaptation, as shown in FIG. . Also, ID_123, which is the ID of the quoted user, an arrow mark indicating the quote, the icon of the user who made the quoted statement, and the user ID (ID_XYZ) are displayed on the screen. This makes it easy to understand who quoted who said.

  As shown in Fig. 4 (d), when you quote another person's remarks and speak against them, the remarks are "Tokyo is hot RT @ ID_123 It's hot today" After the rule is applied, the data is treated as two data, “Tokyo is too hot” which is a statement of ID_A10 and “Today is also hot” which is a statement of ID_123. Also, the reading order is changed, and as shown in FIG. 8A, the ID_123 ID is first displayed on the screen, and “Today is hot today” is read out by voice synthesis. After the completion of reading, as shown in FIG. 8B, the ID_A10 icon and ID, an arrow indicating the message to ID_123, and ID_123 are displayed on the screen, and “Tokyo is too hot” is read out by voice synthesis.

  By presenting the remark information in this way, the driver can easily grasp the content even with complicated remarks such as remarks made by others.

  FIG. 9 shows an example in which the server information 40 of FIG. 6 is displayed on the windshield FG of the vehicle using the HUD. As the server information 40, for example, a caller icon and a caller ID are displayed. At the same time, the caller information 50 is notified by voice. When the HUD is used, the server information 40 is displayed so as to overlap the driver's field of view (actual scene). For this reason, the server information 40 is displayed at a position lower than the position of the driver's line of sight so as not to hinder driving.

  As described above, according to the embodiment of the present invention, the speech data acquired from the server is analyzed, and information that cannot be understood even if it is read out is deleted from the speech content, so that the content read out can be easily understood. be able to. Also, not only the image of the speaker and the ID, but also the ID of the other party, the symbol for the person, and the citation symbol are displayed on the screen, making it easy to understand content that is difficult to convey by voice alone. It becomes possible to do. In addition, in the case of utterances to quotes, the order of reading is changed so that the flow of the story can be understood.

  The present invention is not limited to the above description, and various modifications can be made without departing from the scope of the claims.

10 ... Information processing apparatus 11 ... CPU
12 ... Memory 13 ... ROM
14 ... Recording means 15 ... Display means 16 ... Input means 17 ... Audio output means 18 ... Communication means 20 ... Information providing server

Claims (9)

Communication means for accessing a server for providing information and obtaining information from the server;
An acquisition means for analyzing the information acquired by the communication means to acquire one or more utterance data, and acquiring information indicating the identification information of the utterer and an image of the utterer, and the utterance content from each utterance data; ,
Display means for obtaining the image data of the speaker from the information indicating the image of the speaker, and displaying it together with the identification information of the speaker;
Analyzing the content of the statement, removing unnecessary information and creating a sentence for speech synthesis;
Informing means for informing the sentence created by the sentence creating means by speech synthesis;
An information processing apparatus comprising:   The information processing apparatus according to claim 1, wherein the display unit displays the identification information of the speaker and the image data of the speaker over the navigation information or other information including a music player screen.   The display means includes a head-up display that projects and displays an image on a windshield of a vehicle, and projects and displays the identification information of the speaker and the image data of the speaker on the windshield. The information processing apparatus described.   The information processing apparatus according to claim 1, wherein the identification information of the speaker and the image data of the speaker are displayed in synchronization with a time from the start of notification of the speech synthesis output to the end of notification.   When the same person's speech continues, the identification information of the speaker and the image data of the speaker are once deleted, and after a certain time interval, the identification information of the speaker and the image data of the speaker are newly updated. The information processing apparatus according to claim 1, wherein the information processing apparatus displays the information in synchronization with the notification of the speech synthesis output. The sentence creation means, when removing the unnecessary information, if it is determined that the utterance content is addressed to a person having specific identification information, deletes the person identification information and creates a speech synthesis sentence,
2. The information processing apparatus according to claim 1, wherein the display means displays the identification information of the person, a symbol indicating a speech to a specific person, the identification information of the speaker, and the image data of the speaker. . When the acquisition unit analyzes the acquired statement and determines that the content of the statement is a quote from another person, the acquisition unit acquires identification information of the original speaker and information indicating the image of the speaker. ,
The display means displays the identification information of the cited speaker, a symbol indicating the quotation, identification information of the original speaker, and image data of the original speaker. The information processing apparatus according to claim 1.   The sentence creation means, when removing the unnecessary information, if it is determined that the utterance content is uttered in the quoted content of the other person's utterance content, the speech synthesis text is extracted from the quoted utterance content. The information processing apparatus according to claim 1, wherein the information processing apparatus is informed and notified by voice synthesis.   The information processing apparatus according to claim 1, wherein the sentence creating unit discriminates at least a URL for acquiring related information, a hash tag indicating a keyword, and a quotation mark, and removes it as unnecessary information to be read out.

Images