KR20150073235A - Method for making road guide contents based on own voice and Navigation service system implemented the same - Google Patents

Abstract

The present invention relates to a method for producing voice road guide information based on the own voice running on a navigation service system comprising: a step of receiving road guide content recorded information directly recorded by a user with own voices from a user terminal; a step of determining whether an error exists in the road guide content recorded information; a step of generating voice road guide information based on the road guide content recorded information if an error does not exist in the road guide content recorded information; and a step of transmitting voice road guide information to the user terminal.

Description

TECHNICAL FIELD [0001] The present invention relates to a navigation service system in which voice information is generated,

The present invention relates to a navigation service system in which voice guidance information is produced and a method for producing the same, and more particularly, to a navigation service system in which a voice guidance information system And more particularly, to a navigation service system in which voice route guidance information production method and method are implemented.

As the number of cars increases, traffic congestion is getting worse around the city. In Korea, congestion costs account for about one-third of total transportation costs, and congestion is serious. A car navigation service system has been proposed as a way to solve these problems and provide a more safe and comfortable driving environment to the driver. In terms of efficiency and accuracy, the car navigation service system helps the driver to navigate to the destination, so most vehicles are equipped with navigation terminals.

In addition to functioning to display only the position of the vehicle, the navigation terminal utilizes the rapidly developing semiconductor and computer technology, and various functions such as optimal route calculation, route guidance, traffic related information and additional service information are added. In many countries, the use of navigation terminals is expanding as a multidimensional traffic information network that simultaneously transmits spatial information and real-time information using various information media. In addition, the technology is being developed so that the navigation terminal can perform a multimedia system function in the vehicle.

Meanwhile, mobile network operators are providing navigation functions while introducing 3G / 4G smartphones. In Korea, SK Telecom's T-MAP, KT's Ole Navi, and Rock and Roll's Nationwide Navigator Kim Gisa have registered their navigation apps for smartphones in the App Store. Navigation devices that are built in or externally attached to a car are inconvenient for users to upgrade periodically, but navigation apps installed on smartphones are convenient because they are automatically upgraded.

As the navigation terminal or the smart phone performs functions as an integrated information terminal beyond the function of a simple car navigation device, it is necessary to design navigation contents as well as the navigation contents according to the taste and personality of the user.

Patent Registration No. 10-1225430 (Registered on January 1, 2013)

SUMMARY OF THE INVENTION The present invention has been made in view of the above background, and it is an object of the present invention to provide a method and apparatus for generating voice guide information based on a self-voice that satisfies a user's individuality and taste, And to provide a navigation service system.

It is another object of the present invention to provide a navigation service system in which a voice guidance information is generated by a voice of a self-voice, and the voice guidance information is generated as a gift to friends.

It is still another object of the present invention to provide a navigation service system in which a voice guidance information is recorded by a voice of a person and is publicly available to the general public for free or for a fee and is commercially available.

According to an aspect of the present invention, there is provided a method for generating voice guide information on a voice of a user, the method comprising: receiving voice guidance content recorded by a user directly from a user terminal; The method comprising the steps of: determining whether there is an error in the guidance content recording information; generating voice guidance information based on the guidance content recording information when there is no error in the guidance content recording information; And transmitting the information to the user terminal.

In the method of generating voice guide information on the basis of the additional feature of the present invention, when there is an error in the voice guidance content recording information, Further comprising the step of receiving route guidance content recording information of the first portion being retransmitted from the user terminal and determining again whether or not there is an error in the route guidance content recording information of the received first portion .

In the method of generating voice guide information based on a self voice according to a further aspect of the present invention, the step of determining whether or not an error exists in the voice guidance content recording information includes performing syllable restoration on the voice guidance content recording information, Generating a result string by performing morpheme analysis on the restored character string, and determining whether an error exists based on a result of determining whether the result character string is the same as the guidance content do.

The navigation service system according to the present invention includes a navigation contents recording information receiver for receiving navigation contents recording information recorded by a user directly from a user terminal, An error judging unit for judging whether or not there is an error in the recording information of the route guidance content; and an error judgment unit for judging whether or not there is an error in the route guidance content recording information, A voice guidance information generating unit for generating the guidance information, and a voice guidance information processing unit for transmitting the voice guidance information to the user terminal.

In the navigation service system in which the voice voice guidance information generation method according to a further aspect of the present invention is implemented, if there is an error in the voice guidance content recording information as a result of the determination by the error determination unit, And a retransmission request unit for requesting retransmission of the route guidance content recording information of the first part, which is transmitted from the user terminal, and the error determination unit determines whether there is an error in the route guidance content recording information of the first part retransmitted from the user terminal .

As described above, according to the present invention, it is possible to create and use a route guidance voice through a navigation service system in which a method for producing voice guidance information based on self-voice and a method for manufacturing the same, thereby enabling navigation terminals and smartphone users to You can get directions by voice.

In addition, by downloading the navigation app from the App Store and getting directions recorded from various people's voices, the same voice can be more focused than when used on a navigation device or smartphone.

In addition, it is possible to automatically determine whether or not there is an error in recorded voice guidance content recorded in the voice of the user, thereby generating the voice guidance information, thereby preventing the wrong route guidance due to the recording result in which the error exists .

Also, you can record the route guidance voice with your own voice and present it to the acquaintances as a gift. In this case, a grandchild or a granddaughter can present it as a gift for grandparents or grandmothers.

In addition, a voice guidance voice can be recorded with his / her own voice and publicly available to the public for free or for a fee.

1 is a block diagram of a voice-based voice guidance information production system according to the present invention.
2 is a diagram for explaining a process of generating voice guidance information according to the present invention.
FIG. 3 is an exemplary diagram for explaining a process of determining whether there is an error in the recorded contents of the guidance content according to the present invention.
FIG. 4 is an exemplary view for explaining a method of dividing recorded contents of road-guidance contents according to the present invention.
FIG. 5 is a diagram for explaining a process of generating voice guidance information by combining voice guidance contents recording information according to the present invention.
FIG. 6 is an exemplary diagram illustrating a process in which voice route guidance information generated in the navigation service system according to the present invention is disclosed and shared with other users.
7 is an exemplary diagram illustrating a hash tag assigned to voice guidance information according to the present invention.
8 is a diagram for explaining a process of generating new voice guidance information by combining registered voice guidance information according to the present invention.
9 is a flowchart for explaining a method of generating voice guide information based on a self-voice according to the present invention.
FIG. 10 is a block diagram of a navigation service system in which a method for producing voice guide information based on a self-voice according to the present invention is implemented.

The terms first, second, etc. in this specification may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component.

The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the term "comprising " is intended to designate the presence of stated features, integers, steps, operations, elements, parts, or combinations thereof, and may include one or more other features, And does not preclude the presence or addition of one or more other elements, components, components, parts, or combinations thereof.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Reference will now be made in detail to the present embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the like elements throughout.

In this specification, a method of sounding and recording the guidance content is exemplified as being implemented in a user terminal, but the present invention is not limited to this, and may be implemented by a method of recording in a recording room or a method of recording directly using a PC. Since the configuration of the recording room is already well known, a detailed description thereof will be omitted.

The voice-based voice guidance information production system according to the present invention can be implemented by including first and second user terminals 100 and 120 and a navigation service system 150, as shown in FIG.

1, a method for generating voice route guidance information based on a voice of a user of a first user terminal 100 will be described. In the present invention, the first and second user terminals 100 and 120 may be various devices for guiding a route, for example, a navigation terminal, a smart phone, a PDA, a notebook, a portable terminal, It is used to include meaning.

Referring to FIG. 1, a user can record a guidance content in the first user terminal 100 and record the navigation content. For example, the content of the directions may be, for example, "turn left in front of 100 meters", "turn right in front of two hundred meters", "ten kilometers to your destination", "slow down" It can be a word, a syllable, or a word-by-word text such as 'right turn', 'is', 'meter', 'bag', 'cloth' The navigation information recorded by the user at the first user terminal 100 is transmitted to the navigation service system 150.

The user can generate the voice file recorded by using the device having the recording function such as a smart phone, and then transmit the voice file to the navigation service system 150. [ As another example, the user can create a recording file using the recording device of the recording room and provide the recording file to the navigation service system 150. Hereinafter, in the embodiment of the present invention, a voice file in which the user has recorded the guidance content in the first user terminal 100 is expressed by the term guidance content recording information.

The navigation service system 150 transmits data for traffic guidance to the first and second user terminals 100 and 120 or updates the settings of the navigation functions mounted on the first and second user terminals 100 and 120 (E. G., A server). ≪ / RTI > According to an embodiment of the present invention, the navigation service system 150 may combine the navigation content recording information to generate all the navigation announcements.

The navigation service system 150 may determine whether the guidance content recording information is correct. For example, the navigation service system 150 may determine whether the voice pronounced by the user is suitable for guiding the route, or whether there is no guiding content recorded by the user in error. For example, it can be assumed that the tenth guiding content in the first guiding content exists in the guiding content. The user can generate the guidance content recording information by sequentially sounding the contents of the first guidance content to the tenth guidance content. The navigation service system 150 may determine an error of the guidance content recording information, such as whether or not the incorrectly pronounced content exists in the guidance content, whether there is content that may confuse the user, and the like. This error determination method will be described later.

As another example, the manufacturer can directly listen to the guidance content recording information and detect whether there is an error. The navigation service system 150 may be configured to receive the error detection information directly detected by the manufacturer and process the error of the guidance content recording information.

If there is an error in the route guidance content recording information, the navigation service system 150 may request the first user terminal 100 to retransmit the route guidance content recording information in which the error exists. The navigation service system 150 may transmit to the first user terminal 100 information indicating the presence of an error in the route guidance content recorded in the route guidance content recording information, It is possible to retransmit the guidance content recording information re-recorded only for the guidance content. For example, when a portion where an error exists can be corrected using the guidance content recording information, the navigation service system 150 does not request the first user terminal 100 to retransmit the guidance content recording information, You can also automatically correct errors.

If there is no error in the route guidance content recording information, the navigation service system 150 generates the audio route guidance information based on the route guidance content recording information. The navigation service system 150 edits the route guidance content recording information and combines them to suit various situations to generate the audio route guidance information. For example, if ten sentences are recorded as the guidance content recording information, the ten sentences can be combined to generate voice guidance information that can be generated in various guidance situations. The method of generating the voice guidance information will be described later.

The navigation service system 150 may transmit the voice route guidance information to the first user terminal 100. [ The navigation service system 150 may directly transmit the voice guidance information to the first user terminal 100, but may also transmit the voice guidance information to the first user terminal 100 using another network device as an intermediary have.

The navigation service system 150 may register the voice guidance information and download the registered voice guidance information at the request of the second user terminal 120. [ For example, the navigation service system 150 can register voice route guidance information generated through communication with a server providing an app service included in an internal configuration or a mobile app store operated by, for example, Apple or Google. The registered voice route guidance information may be installed in the second user terminal 120 and used as voice information for route guidance.

The user can transmit the voice route guidance information generated based on the voice of the user based on the network service implemented between the user terminals so that other users can download and use the voice route guidance information. For example, based on a network service such as the navigation service system 150 or a social network service (SNS), voice guidance information generated based on the user's voice can be transmitted to the acquaintance.

Hereinafter, a method for generating voice route guidance information based on the user's own voice will be described in detail.

First, a process of generating voice guidance information according to the present invention will be described with reference to FIG. The number of the guiding content recorded information exemplarily shown in Fig. 2 and the number of voice guiding information generated in combination may be changed to arbitrary. For example, the route guidance content recording information 200 may include the first route guidance content recording information 200-1 to the tenth guidance content recording information 200-10. The navigation service system transmits the first guidance content recording information 200-1 to the tenth guidance content recording information 200-10 included in the guidance content recording information 200 to a voice combination Apparatus can be combined to generate more than ten voice guidance information 250. [ In addition, it may be used to generate a plurality of voice guidance information 250 by dividing one piece of presentation information of the presentation contents (for example, the first presentation content 200-1).

For example, the first guidance content recording information 200-1 may be 'right turn in front of a hundred meters' and the tenth guidance content recording information 200-10 may be 'decelerate speed'. In such a case, the first guidance content recording information 200-1 and the tenth guidance content recording information 200-10 are combined and 'turn right in front of a hundred meters. Slow down the speed 'can be generated.

As another example, it is also possible to use one piece of guiding content recording information 200 to generate a plurality of pieces of voice guiding information. Suppose that the first way-announcement content recording information 200-1 is 'turn right in front of a hundred meters'. In this case, the first guidance content information 200-1 can be divided and used to generate other voice guidance information such as 'back', 'meter', 'right turn', and 'right'.

For example, 'back', 'meter', 'ahead', 'is' is used to generate the information contained in the first guidance content recording information 200-1 to generate' And extracted. In order to divide the first guidance content recording information 200-1, a process of restoring a syllable and analyzing morphemes is required. This process may be performed together with a process of analyzing whether there is an error in the guidance content recording information 200. [ A method of dividing the guidance content recording information by analyzing morpheme by restoring the syllable and determining whether or not there is an error in the guidance content recording information will be described later.

The process of determining whether or not an error exists in the recorded contents of the guidance content according to the present invention will be described with reference to FIG. By detecting an error included in the route guidance content recording information 300 and correcting the error, erroneous route guidance audio information is stored in the user terminal, thereby preventing the user terminal from performing the wrong route guidance.

Referring to FIG. 3, the navigation service system 150 may decompress the syllable (S 310) by analyzing the guidance content recording information and calculate the resultant character string through morphological analysis on the restored character string 320. The navigation service system 150 compares the calculated result string with the guidance content to determine whether or not it is different from the guidance content and determine whether there is an error in the guidance content recording information 300. [ Hereinafter, a method for restoring a syllable and analyzing a morpheme will be described in detail in the embodiment of the present invention.

In Korean, phonological fluctuations can occur within a single morpheme or between a morpheme and a morpheme. Therefore, a syllable restoration process is needed to reverse the applied phonological fluctuation in the speech recognition process to the original spoken sentence. For example, if there is a route guidance content 'Set destination to Busan', the information generated by the route guidance content recording information 300 is actually pronounced and ' Can be recognized as such. In this case, according to the syllable restoration rule, the recognized recorded information is restored to 'Set', 'Restore', 'Restore' to 'Busan', 'Restore to Busan' Can be generated. In addition, the restoration character string 320 may additionally detect whether the restoration character string 320 is a grammatically correct word or phrase through the morphological analysis 330.

For example, the phrase 'path' may be pronounced 'flag', and a restored string 320 of 'restored' or 'path' may be generated. In this case, it is possible to judge whether the restoration string 320 is a word with a grammatical error through morphological analysis 330. In the case of 'path', 'path' is recognized as a noun and ' And is recognized as a grammatically correct word, but '??' To '?' Are grammatically classified as unregistered words and can be recognized as incorrect words. In this case, 'path' can be determined as an accurate result string 340 through morphological analysis 330.

The syllable restoration and morphological analysis may be performed to generate the final result character string 350 based on the guiding content recording information 300. The resulting string 340 may then be compared 350 to determine whether an error exists. For example, suppose that the route guidance content is 'turn right in front of a hundred meters' and the result character string 340 generated based on the route guidance content recording information 300 is 'left before 100 meters'. In this case, since the result character string 340 of the route guidance content is not the same as the result character string of the route guidance content, it can be determined that an error exists in the route guidance content recording information 300. Through the error determination process, the navigation service system can recognize the route guidance content in which the error exists in the route guidance content recording information 300.

The navigation service system 150 may request the user terminal to re-record the route guidance content in which the error exists and transmit the re-recorded route guide content again. The navigation service system 150 may determine whether there is an error again based on the recorded information of the guidance contents re-recorded at the user terminal.

The navigation service system 150 can correct the error information of the route guidance content recorded on the basis of the record information when the route guidance content record information that can be edited by editing is included in the route guidance content record information. For example, suppose that an error occurs by pronouncing 'turn right' as 'left turn' as described above. In this case, the navigation service system 150 may determine whether there is a final result string recognized as " right turn " If there is a final result string recognized as a 'right turn', the record information in which the end result string is recognized as 'left turn' is deleted and the recorded information corresponding to the end result string recognized as 'right turn' .

A method of dividing the recorded contents of the road guidance content according to the present invention will be described with reference to FIG. 4 is an example of a method of dividing a recorded sentence. In the method of dividing a recorded sentence according to various methods other than the method disclosed in FIG. 4, a recorded sentence includes a plurality of syllables Lt; / RTI >

Referring to FIG. 4, the navigation service system may preferentially perform syllable restoration and morphological analysis based on the guidance content recording information to generate a resultant character string. Based on the result string, the guidance content recording information can be separated into a word or syllable unit. It is possible to divide the route guidance content recording information for each word or syllable unit by analyzing the segment of the result string and the guidance content recording information.

If it is assumed that the route guidance content recording information is 'right turn in front of a hundred meters', the first route guidance content information is divided into 'back' 400, 'meter 410', 'ahead 420' Right turn 430 ", and " 440 " can be used to generate other voice guidance information. For example, 'Meter (410)' combines words such as' two hundred meters', 'three hundred meters', and' four hundred meters' in combination with syllables such as' two hundred, '' three hundred, Can be used to generate.

By using this method, even if the user does not record the entire voice guidance information, that is, even if only a part of the guidance content recording information is transmitted, the entire voice guidance information can be generated by combining a part of the guidance content recording information. That is, it is possible to synthesize the voice guidance information in various ways in order to generate the entire voice guidance information naturally by combining the voice guidance content recording information.

The process of generating the voice guidance information by combining the voice guidance content recording information according to the present invention will be described with reference to FIG. FIG. 5 shows a method of generating voice guidance information by naturally combining the guidance contents recording information. The method of generating the voice guidance information by combining the voice guidance contents recording information disclosed in FIG. 5 on the basis of the synthesis engine 500 may be combined with the voice guidance contents recording information through various other methods, Information can be generated.

Referring to FIG. 5, the navigation service system may generate voice guidance information by naturally combining the guidance contents recording information using the synthesis engine 500. The segmented tracked content recording information is recorded in different voice levels and different voice contexts, so that there may be awkwardness when continuously connecting them. In order to naturally connect them, it is necessary to convert the pitch of the sound into a similar range (520) and to transform the tone color similarly (540).

The synthesis engine 500 may perform the tone pitch transformation 520 and the tone adjustment 540 in the vibration range of the recorded voice. Negative height transform 520 may occur in the scales spectrum. After performing a short time fourier transform (STFT), which is a wave-shaped sample, the spectrum is divided into several regions, and each region of the spectrum is changed in size so that the scaling elements coincide with the negative height transformation 520. For example, after the STFT (Short Time Fourier Transform) is performed on the first and second route guidance recorded information, the scale factor may be adjusted to coincide with the negative height transformation.

The spectral shape near each harmonic can remain unchanged. Since the voice information is received from the same user, the tone color adjustment 540 may not be performed, but if tone color adjustment 540 is additionally performed, the tone color adjustment may be performed by varying the amplitude of each harmonic. As another example, you can modify the voice file itself and create and apply the resulting file. That is, the modified voice file can be used as the final file.

A process in which voice route guidance information generated in the navigation service system according to the present invention is disclosed and shared with other users will be described with reference to FIG. The voice guidance information generated by the first user terminal 600 is registered in the navigation service system 650 and the other second user terminals 620 share the voice guidance information registered through the navigation service system 650 can do.

For example, the user can set whether or not to share voice guidance information generated in her voice. If the user does not share the voice guidance information, the voice guidance information generated by the first user terminal 600 can be prevented from being used by others through the private setting. On the other hand, if the user wishes to share the voice guidance information, the voice guidance information generated by the first user terminal 600 can be registered to be used by others through the public setting.

The user can transmit voice guidance information generated by her voice to another second user terminal 620. For example, the son can transmit the voice guidance information generated by her voice to the user terminal of the father, or the voice guidance information generated by the granddaughter using the voice of the grandfather to the user terminal of the grandfather.

The voice guidance information may be mapped and stored in a hash tag (HASH TAG) 605 in various ways. The hash tag (HASH TAG) 605 may be an identifier generated to represent the contents of the voice guidance information. Based on the hash tag (HASH TAG) 605, users of the second user terminal 620 can quickly search for voice guidance information having a tone color desired by the user, and download and use the voice guidance information.

A process of allocating and registering a hash tag (HASH TAG) in the voice guidance information according to the present invention will be described with reference to FIG. A method for mapping a hash tag (HASH TAG) by analyzing the voice guidance information in Fig. 7 will be described. In order to map the hash tag assigned to the voice route guidance information, information on the sex, age, and the area of origin of the user can be obtained from the user terminal.

For example, suppose that a man using thirty standard words living in Seoul area generates first voice guidance information 710. The first voice guidance information 710 may be mapped to a hash tag of 30 units, male, and standard word. As another example, let us suppose that a woman who writes twenty Kyodo dialects living in Busan region generates second voice guidance information 720. The second voice guidance information 720 may be mapped to a hash tag called a twos, a female, a Kyodo dialect. Such HASH TAG information can be used for searching and downloading the voice guidance information registered by the user by another user terminal.

According to an embodiment of the present invention, another method of generating a hash tag (HASH TAG) is to analyze the registered voice route guidance information without receiving the additional information directly from the user registering the voice guidance information, It is also possible to use a method of directly generating a tag (HASH TAG). For example, the age of the user who generated the voice guidance information by classifying the registered voice based on the voice analysis algorithm as male or female, and measuring the degree of aging of the voice based on the recorded voice Can be estimated. Also, by analyzing the intonation of the recorded voice, it is possible to classify the local voice such as whether the voice is in Seoul area, Gyeongsang area or Jeolla province area.

The classification of the registered voice guidance information by assigning a hash tag (HASH TAG) to the registered voice guidance information based on the sex, age, and regional characteristics is one example. That is, a hash tag (HASH TAG) may be added to the registered voice route guidance information based on various information other than sex, age, and regional characteristics, and such an embodiment may also be included in the scope of the present invention. Based on the classified hash tag (HASH TAG), voice guidance information registered by another user terminal can be easily searched.

A process of generating new voice guidance information by combining a plurality of registered voice guidance information according to the present invention will be described with reference to FIG. For example, the first voice guidance information 810 and the second voice guidance information 820 may be registered in the navigation service device. The user terminal may receive the first voice guidance information 810 and the second voice guidance information 810.

The user terminal can perform the guidance by combining the downloaded first voice guidance information 810 and the second voice guidance information 820. For example, the user terminal may select either the first voice guidance information 810 or the second voice guidance information 820 when performing the guidance. As another example, different voice guidance information may be reproduced according to the operation time.

For example, in the morning and at night, the first voice guidance information recorded in the voice of the Highton can be used to make the driver more alert when driving. Conversely, at the time of the morning and after the night, the second voice guidance information recorded with a calm voice may be set to be reproduced for the guidance of the road. As another example, when the operation time is long and the certain operation time has elapsed, the voice used for the guidance of the road from the first voice guidance information to the second voice guidance information may be set differently, have.

The method for producing voice guide information based on a self voice according to the present invention will be described with reference to FIG. The navigation service system receives the guidance content recording information from the user terminal (step S900). For example, when the user terminal is a smartphone, the navigation app can be executed to generate the guidance content recording information. The navigation app works in conjunction with the recording function of the smartphone, so that the user can record the voice pronounced the navigation contents. For example, if you launch the navigation app and launch the roadtrip content recording function, your smartphone's screen may display navigation content. The sentence displayed in the route guidance content may allow the current user to identify the content to be pronounced in a manner that the color changes or the shape changes, and the user terminal can perform recording according to the displayed route guidance content. The user terminal can transmit the generated navigation content to the navigation service system by pronouncing the navigation content.

The navigation service system determines whether there is an error in the guidance content recording information (step S910). For example, as described above, after generating a result string through syllable restoration and morphological analysis for the guidance information of the guidance content, the generated result string is compared with the guidance information to determine an error occurred in the guidance information of the guidance content can do.

As another example, the manufacturer can directly listen to the guidance content recording information and detect whether there is an error. The navigation service system can receive the error detection information and determine the error of the guidance content recording information.

If there is an error in the route guidance content recording information, the user terminal requests a retransmission of the route guidance content recording information (step S920). If it is determined in step S910 that there is an error in the guidance content recording information, the user terminal may request retransmission of the guidance content recording information. The navigation service system may request the user terminal to transmit the re-recorded guidance content recording information only for the guidance content determined to be in error.

According to another embodiment of the present invention, when there is an error in the guidance content recording information, if the navigation service system determines that it is possible to correct the error with the guidance content recording information, It may not request retransmission. The redirected navigation content recording information may again be searched by the navigation service system to see if an error exists.

If there is no error in the route guidance content recording information, the navigation service system generates the audio route guidance information based on the route guidance content recording information (step S930). The navigation service system may use the route guidance content recording information as it is, the route guidance content recording information may be combined, the route guidance content recording information may be divided into syllable or word segment, May be generated. The generated voice guidance information is transmitted to the user terminal (step S940).

The generated voice route guidance information based on the route guidance content recording information is transmitted to the user terminal so that the actual user terminal can be used in performing the route guidance. The generated voice route guidance information can be registered in the navigation service system (step S950).

Voice guidance information may be registered in the navigation service system when the user agrees to use voice guidance information recorded in her voice with other users. The voice route guidance information is provided with HASH TAG information for identifying the characteristic of the voice route guidance information and is classified on the basis of the provided HASH TAG information so that the voice route guidance information is registered in the navigation service system .

10, the navigation service system according to the present invention includes a navigation contents recording information receiving unit 1000, an error determination unit 1010, a re-transmission request unit 1010, A voice guidance information generating unit 1030, a voice guidance information processing unit 1040, and a processor 1050. The voice guidance information generating unit 1030, Each component of the navigation service system can be implemented to perform the operations of the navigation service system described in Figs. 1 to 9 described above. Each component of the navigation service system can perform, for example, the following operations.

The route guidance content recording information receiving unit 1000 receives route guidance content recording information recorded by a user directly from a user terminal. The error determination unit 1010 determines whether there is an error in the received guidance content recording information. If the error determination unit 1010 determines that there is an error in the guidance content recording information, the retransmission request unit 1020 requests the user terminal to retransmit the guidance content recording information of the first part in which an error exists do.

For example, the error determination unit 1010 determines whether there is an error in the guidance content recording information of the first portion retransmitted from the user terminal. If there is an error in the guidance content recording information, the error determination unit 1010 edits the guidance content recording information to determine whether or not the guidance content recording information of the part where the error exists can be corrected, If the error can be corrected, the navigation contents recording information is edited to correct the error.

The error determination unit 1010 generates a restoration character string by performing a syllable restoration on the guidance content recording information, performs morphological analysis on the restoration character string to generate a result character string, and determines whether the result character string is the same as the guidance content Based on the result of the determination of whether or not there is an error.

If the error determination unit 1010 determines that there is no error in the voice guidance content recording information as a result of the determination by the error determination unit 1010, the voice path guide information generation unit 1030 generates voice path guidance information based on the voice guidance content recording information. The voice route guidance information may be generated by combining the route guidance content recording information or may be generated by combining the divided route guidance content recording information by dividing the route guidance content recording information into syllable or word units.

The voice path guide information processing unit 1040 transmits the voice path guide information to the user terminal. The voice path guide information processing unit 1040 allocates a hash tag assigned to the voice path guide information generated by the voice path guide information generation unit 1030 and transmits the voice path information based on the hash tag (HASH TAG) And to classify and register the guide information.

The processor 1050 receives the operation of the route guidance content recording information receiving unit 1000, the error determining unit 1010, the retransmission request unit 1020, the voice route guidance information generating unit 1030 and the voice route guidance information processing unit 1040 And the like.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the scope of the invention as defined by the appended claims. Accordingly, the true scope of the present invention should be determined only by the appended claims.

Claims (14)

A method of generating a self-voice-based voice guidance information that is executed in a navigation service system,
The method comprising: receiving route guidance content recording information recorded by a user in a voice of the user;
Determining whether there is an error in the road guidance content recording information;
Generating voice guidance information based on the voice guidance content recording information when there is no error in the voice guidance content recording information; And
Transmitting the voice guidance information to a user terminal;
Based voice guidance information generation method.
The method according to claim 1,
If there is an error in the guidance content recorded information, it requests retransmission of the guidance content recording information of the first part in which an error exists, receives the guidance content recording information of the first part retransmitted in the response Determining again whether or not there is an error in the navigation information of the received portion of the first portion;
Based voice guidance information generation method.
The method according to claim 1,
Determining whether or not the guidance content recording information of the part where the error exists can be corrected by editing the guidance content recording information if an error exists in the guidance content recording information;
If the error can be corrected, correcting the error by editing the guidance content recording information;
If the error can not be corrected, request retransmission of the guidance content recording information of the first part in which the error exists, receive the guidance content recording information of the first part retransmitted in the response, Re-determining whether there is an error in the guidance content recording information of the first portion;
Based voice guidance information generation method.
The method according to claim 1, wherein the step of determining whether there is an error in the road-
Generating a restoration character string by performing syllable restoration on the guidance content recording information;
Performing a morphological analysis on the restored character string to generate a result character string; And
Determining whether there is an error based on a result of determining whether the result character string is identical to the navigation contents;
Based voice guidance information generation method.
The voice guidance system according to claim 4,
Wherein the generated voice guidance information is generated by combining the voice guidance content recording information or the divided voice guidance content recording information by dividing the voice guidance content recording information into syllable or word units.
The method as claimed in claim 1, wherein the self-voice-
Further comprising the step of registering the voice guidance information in the navigation service system,
Wherein the voice guidance information is assigned a hash tag and is registered in the navigation service system based on the hash tag,
Wherein the method comprises the steps of:
The method of claim 6,
The navigation service system includes a plurality of voice guidance information classified and registered based on the hash tag,
The method of claim 1,
Transmitting a plurality of voice guidance information selected by the user to the user terminal;
Based voice guidance information generation method.
It is a navigation service system that allows users to create their own navigation contents with their own voices.
A route guidance content recording information receiving unit for receiving route guidance content recording information recorded by a user directly from a user terminal in a voice of a user;
An error determination unit for determining whether or not there is an error in the received guidance content recording information;
A voice guidance information generating unit for generating voice guidance information based on the guidance information of the recorded contents when the error determination unit does not have an error in the recorded voice guidance information; And
A voice guidance information processing unit for transmitting the voice guidance information to the user terminal;
And a navigation service system.
The navigation system according to claim 8,
Further comprising a retransmission request unit for requesting retransmission of the guidance content recording information of the first part in which an error exists in the user terminal if there is an error in the guidance content recording information as a result of the determination by the error determination unit ,
The error determination unit may determine whether there is an error in the guidance content recording information of the first portion retransmitted from the user terminal,
The navigation system comprising:
The method of claim 8,
If there is an error in the guidance content recording information, the error determination unit determines whether or not the guidance content recording information of the portion where the error exists can be corrected by editing the guidance content recording information, Correcting the error by editing the guidance content recording information,
The navigation system comprising:
The system according to claim 8,
Generating a restoration character string by performing syllable restoration on the guidance content recording information,
Performing a morphological analysis on the restored character string to generate a result character string,
Determining whether there is an error based on a result of determining whether the result character string is identical to the navigation content,
The navigation system comprising:
The method according to claim 11,
Generating the navigation information by combining the navigation information of the navigation contents, or combining the navigation information of the divided contents by dividing the information of the navigation contents into syllables or phrases,
The navigation system comprising:
The voice guidance system according to claim 8,
Assigning a hash tag to the voice guidance information generated by the voice guidance information generation unit and classifying and registering the voice guidance information based on the hash tag,
The navigation system comprising:
14. The method of claim 13,
The navigation service system includes a plurality of voice guidance information classified and registered based on the hash tag,
The voice guidance information processing unit,
Transmitting a plurality of voice route guidance information selected by the user to the user terminal,
The navigation system comprising:

Images