KR101401503B1 - System, Method and Apparatus for Providing Service Based on User Voice - Google Patents

Abstract

A system, method and apparatus for providing a user voice based service are disclosed. A service providing system based on a user voice includes a voice service unit for providing a voice service based on a user voice received from a user terminal and acquiring a user voice received from the user terminal based on a consent from the user terminal, And a service server unit for providing an additional service including a voice consulting service using the user voice acquired by the service providing unit. Accordingly, various additional services such as a consulting service and the like can be provided based on the user voice that can be acquired through the voice service.

Description

TECHNICAL FIELD [0001] The present invention relates to a service providing system, a method,

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a system, a method and an apparatus for providing a service based on a user voice, and is based on voice information of users obtainable through a voice service, The present invention relates to a technology capable of providing services of a service provider.

In general, voice services can encompass a variety of services provided based on automatic voice guidance and user voice. Since voice service is a service based on user's voice, it has been expected that there will be many advantages in terms of convenience and community formation as compared with services based on digital documents. Accordingly, various voice services such as a voice mail service, a voice memo service, an automatic answering service based on voice recognition, a voice search service, a voice information service, and a voice call service are provided.

Nevertheless, voice service is only used to receive spotlight at the time of release without being widely used in comparison with its convenience due to subtle emotional reasons such as the need to communicate with the machine without the other party, and the consciousness of others to follow accordingly. In particular, it is true that the voice service has difficulty in popularizing the service because it does not yet have a link service to cause interest.

In general, it is known that a voice of a person contains information on the status of a speaking person, a psychological state (for example, happiness, disappointment, anger, depressed emotions, etc.) and a physical condition. In addition, voices play a very important role in communication, according to Albert Mehrabian's law, which consists of 38% voice, 35% standard, 20% attitude and 7% speech. In other words, the content of speech is only 7% when communicating, and the most influential factor in communication is the voice of the doctor.

As such, the voice of a person has a great influence on the credibility, liking, or friendliness of the person as well as appearance and personality. Therefore, the voice of a leader with a high social status is suitable for efficient communication Attractive voices need to be constantly developed. From an individual's point of view, they have questions such as how their voices are objectively and how they can appeal to others, and recognize the importance of voices as they do their social lives.

However, in order to develop the user's own voice, it is very rare that practitioners actually practice it because it is possible only through an individual effort or an institute such as a school. Accordingly, it is urgently required to develop a new technology that helps naturally develop voice of a user through voice service and has an interest in voice service to the user.

Korean Patent Publication No. 2003-0064348

The present invention has been made in view of the above circumstances, and it is an object of the present invention to provide a method and apparatus for providing a user service through a consulting service in connection with a voice service, which can help a user improve a voice in a positive direction, Based service providing system, method, and apparatus.

In order to achieve the above object, the present invention provides a system for providing a user voice based service in an aspect. The service providing system based on user voice includes a voice service unit for providing a voice service based on a user voice received from a user terminal and acquiring the received user voice based on a consent from the user terminal; And a service server unit for providing an additional service including a voice consulting service using a user voice acquired by the voice service unit.

The voice service may be at least one of a voice mail service, a voice memo service, a voice mail service, an automatic response service, a voice search service, a voice information service, a voice call service, a voice messenger service and a voice text service.

The voice service unit outputs a guide to the user terminal asking whether or not to agree to the acquisition of the user voice and the provision of the additional service, and when a signal indicating agreement is input from the user terminal, To the server unit.

Wherein the service server section recognizes the contents of the acquired user voice through speech recognition, extracts at least one reference speech information corresponding to the user speech based on the recognized content from the database, Information is compared with user voice to generate analysis information for each voice element, and voice consulting information based on the analysis information can be generated.

The service server unit may separate the user speech for each unit voice including at least one sentence according to the recognized content, and extract reference voice information corresponding to the unit voice from the database. The voice component may include at least one of a voice size, a speech speed, a voice pitch, a pause, and a tone.

Wherein the service server unit receives the user condition information from the user terminal, recognizes the contents of the acquired user voice through speech recognition, and transmits the received user condition information and at least one reference voice corresponding to the recognized content Information can be extracted from the database.

The reference voice information may include voice samples corresponding to the contents of the user voice. Wherein the service server extracts at least one reference speech sample corresponding to the recognized content from the database and compares the extracted speech sample with the spectrum of the acquired user speech to compare the extracted speech sample with the extracted speech sample It is possible to analyze how much difference the sound elements have.

The service server unit may determine at least one analysis criterion based on the contents of the recognized user voice and extract at least one reference voice information corresponding to the determined at least one analysis criterion from the database. The service server unit may generate an exemplary sample voice modulated to match the user voice with the reference voice information based on the analysis information, and provide the generated sample voice to the user terminal.

Wherein the service server unit calculates a match degree of each voice component between the user voice and at least one reference voice information and calculates a match degree for each of the calculated voice components to obtain a total match degree with reference voice information according to at least one analysis criterion .

The additional service may further include a voice ranking service and a contact establishment service based on the obtained user voice. The voice ranking service may calculate a ranking based on the public trust index and the good feeling index for a plurality of user voices acquired from the voice service unit, and transmit the calculated ranking information to the user terminal.

Wherein the contact establishment service registers a plurality of user voices acquired through the voice service unit in a database and provides the user terminals with the user's voice of reason among the user voices registered in the database with the user terminal, And provide the user information corresponding to the user's voice of reason selected in the user terminal. The contact establishment service can provide ranking information calculated by the voice ranking service to the user terminal.

According to another aspect of the present invention, there is provided a method for providing a service based on a user voice. The method of providing a service based on a user voice is a method of providing a service based on a user voice performed by a service server, the method comprising: providing a voice service based on a user voice received from the user terminal; Receiving the acquired user voice from a voice service unit for acquiring the received user voice; And providing the supplementary service including the voice consulting service using the received user voice. The additional service may further include a voice ranking service and a contact establishment service based on the obtained user voice.

The step of providing the supplementary service including the voice consulting service may include recognizing the contents of the acquired user voice through speech recognition; Extracting at least one reference speech information corresponding to the user speech from the database based on the recognized content; Comparing the extracted reference speech information with the user speech to generate analysis information for each speech element; And generating voice consulting information based on the analysis information.

The method of providing a service based on user voice may further include separating the user voice for each unit voice including at least one sentence according to the recognized content. The step of extracting the at least one reference voice information from the database may include extracting reference voice information corresponding to the unit voice from the database.

The method of providing a user voice based service may further include receiving user condition information from the user terminal. Extracting the at least one reference voice information from the database may include extracting the received user condition information and at least one reference voice information corresponding to the recognized content from the database.

The method of providing a service based on the user voice may further include determining an analysis criterion based on the recognized content. The step of extracting the at least one reference voice information from the database may include extracting, from the database, reference voice information corresponding to the determined analysis criterion.

The method of providing a service based on user voice includes the steps of: generating an exemplary sample voice corresponding to the user voice based on the analysis information; And providing the generated exemplary sample voice to the user terminal.

According to another aspect of the present invention, there is provided an apparatus for interworking with a voice service unit for acquiring user voice and providing voice service. The apparatus comprising: a voice recognition unit for acquiring contents of a user voice acquired by the voice service unit through speech recognition; Extracting at least one reference speech information corresponding to a user speech from the database based on the content of the recognized content, comparing the extracted reference speech information with user speech to generate analysis information for each speech element; And a consulting processor for generating voice consulting information based on the analysis information and transmitting the voice consulting information to the user terminal.

As described above, according to the present invention, it is possible to provide various supplementary services on the basis of the user voice that can be acquired through the voice service. For example, a user can receive various voice services such as a voice mailbox service, a voice memo service, a voice mail service, and an automatic answering service, and can receive consultation on voice they speak. A variety of additional services such as contact arrangements can be provided. Thus, the user can evaluate his voice objectively and improve it in a positive direction. In addition, because of this additional service, the user's interest in the voice service itself also increases, which can contribute to the activation of the voice service.

1 is a block diagram illustrating a service system based on a user voice according to a preferred embodiment of the present invention.
2 is a block diagram showing the configuration of a service server unit according to a preferred embodiment of the present invention.
3 is a block diagram showing a detailed configuration of the consulting service unit of the service server unit.
4 is an exemplary diagram illustrating voice consulting information generated by a consulting processing unit and provided to a user terminal.
5 is an exemplary diagram illustrating exemplary ranking information provided by a ranking service unit.
6 is a flowchart illustrating a method of providing a service based on a user voice according to a preferred embodiment of the present invention.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail.

It should be understood, however, that the invention is not intended to be limited to the particular embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.

The terms first, second, etc. 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. And / or < / RTI > includes any combination of a plurality of related listed items or any of a plurality of related listed items.

It is to be understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, . On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it should be understood that there are no other elements in between.

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 this application, the terms "comprises", "having", and the like are intended to specify the presence of stated features, integers, steps, operations, components, parts, or combinations thereof, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the relevant art and are to be interpreted in an ideal or overly formal sense unless explicitly defined in the present application Do not.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In order to facilitate the understanding of the present invention, the same reference numerals are used for the same constituent elements in the drawings and redundant explanations for the same constituent elements are omitted.

1 is a block diagram illustrating a service system based on a user voice according to a preferred embodiment of the present invention.

1, a system 1 for providing a user voice-based service according to a preferred embodiment of the present invention includes a voice service unit 20 and a service server unit 20 interlocked with the user terminal 10 through a communication network 40).

The user terminal 10 may refer to a terminal authenticated by a user account. The user terminal 10 may be a portable terminal such as a Smart Phone, a Tablet Personal Computer, a PDA (Personal Digital Assistance), a notebook or the like, or may be a portable terminal such as a PC or a two- Lt; / RTI > The user terminal may include a call function for receiving a voice service, a web browsing function for receiving a web service, and the like.

The voice service unit 20 may provide the voice service based on the user voice to the user terminal 10. [ The voice service may be at least one of a voice mail service, a voice memo service, a voice mail service, an answering service, a voice search service, a voice information service, a voice call service, a voice messenger service,

The voice service unit 20 can acquire the user voice received from the user terminal 10 through the provision of the voice service and transmit the acquired user voice to the service server unit 30. [ For example, when using an automated answering service that provides weather information, the user may ask, "What is the weather today?" Or, when using the voicemail service, How have you been? Let's meet at Hongdae at 00 o'clock today. ' The voice service section 20 can acquire the inquiry or recording data as a user voice and transmit it to the service server section 30. [

In order to acquire such user voice, the voice service unit 20 outputs a guidance message to the user terminal 10 via voice or screen, informing the user whether or not the user agrees to the acquisition of the user voice, And when a signal indicating that the user agrees to the acquisition of the user's voice is received, the user's voice can be acquired.

If a signal indicating that the user terminal 10 does not agree is received or there is no response, the user's voice may not be acquired. The voice service unit 10 may perform the consent inquiry about acquisition of the user voice as described above before acquiring the user voice, but it may receive the consent in advance through the web page, telephone, or the like.

The service server unit 30 may provide the user terminal 10 with supplementary services such as a voice consulting service, a ranking service, a contact arrangement service, etc., using the user voice transmitted from the voice service unit 20. [ Hereinafter, the detailed configuration and operation of the service server unit 30 according to the preferred embodiment of the present invention will be described.

2 is a block diagram showing the configuration of a service server unit 30 according to a preferred embodiment of the present invention.

2, the service server unit 30 of the user voice-based service providing system 1 includes a consulting service unit 40, a ranking service unit 50, a contact arranging service unit 60, (70). The consulting service unit 40, the ranking service unit 50 and the contact arranging service unit 60 can interoperate with each other as needed for each operation, and can store data in cooperation with the database unit 70 , The data stored in the database unit 70 can be used.

The consulting service unit 40 may receive the user voice acquired from the voice service unit 20 and provide the voice consulting service to the user terminal 10 based on the received user voice.

3 is a block diagram showing a detailed configuration of the consulting service unit 40 of the service server unit 30. As shown in FIG.

3, the consulting service unit 40 includes a communication unit 41, a voice recognition unit 43, an information setting unit 42, a voice analysis unit 45, and a consulting processing unit 47 .

The communication unit 41 may provide a communication interface function for interworking with the voice service unit 20. For example, the communication unit 41 can receive the user voice acquired from the voice service unit 20. [ The communication unit 41 may store the received user voice in the database unit 70 in association with the user's account, and may transmit the received user voice to the voice recognition unit 43. [

The voice recognition unit 43 includes a voice recognition module capable of performing voice recognition, and can acquire the contents of the user voice by recognizing the user voice through voice recognition. For example, the voice recognition unit 43 receives the user voice acquired by the voice service unit 20 from the database unit 70 or the communication unit 41, and acquires the contents of the user voice through speech recognition . The voice recognition unit 43 can store the acquired contents of the user's voice in the database unit 70 or transmit it to the voice analysis unit 45. [

The information setting unit 42 may receive the user condition information of the user from the user terminal 10 and store the inputted user condition information in the database unit 70 in association with the user's account. The information setting unit 42 may display an information setting user interface for receiving user condition information on the user terminal 10 and receive user condition information inputted through the information setting user interface from the user terminal 10 have.

The user condition information may include a user's age, sex, occupation group, and at least one analysis criterion. The information setting user interface may include a graphical interface and a selection / input window for easily inputting items of each user condition information.

The age may be information indicating the age of the user. For example, the age may be information indicating whether the age of the user corresponds to between 10 and 80 generations. The setting for the age group is for teenagers, 20s, ... , But it is also possible to set various sections such as 5 years, 3 years, and 15 years.

The sex may mean information indicating whether the user is male or female. The job group may be information indicating which job group the user belongs to. For example, the job group may indicate which job group the user belongs to, such as a white office, a sales office, a CEO, and the like. The setting of the job group may be variously set according to the execution environment.

The analysis criterion may be information for selecting a reference voice that the user desires to consult. For example, the selection criteria of the analysis criteria may include public confidence, favorability, and the like. That is, the analysis criterion may be information for setting whether the user desires a voice with a credible voice or a voice of a favorable voice. The analysis criterion may be set according to the user's selection through the information setting user interface. However, the analysis unit 45 may analyze the content of the user's voice acquired by the voice recognition unit 43, And then set it.

The voice analysis unit 45 extracts at least one reference voice information corresponding to the user voice extracted by the voice recognition unit 43 from the database unit 70 and compares the extracted reference voice information with the user voice The analysis information for each voice element may be generated and then provided to the consulting information providing unit 47. [ The voice analysis unit 45 analyzes the user voice based on the contents of the user voice and provides the analysis result to the consulting information providing unit 47. The voice analysis unit 45 may store the generated analysis information in the database unit 70. [

The reference voice information may be a file of voice samples having the same content as the contents of the user voice. For example, if the contents of the user's voice are 'What is today's weather?', The voice analysis unit 45 inquires the database unit and reads 'What is today's weather?' Among a plurality of voice samples stored in the database unit. Can be extracted. The voice analyzer 45 analyzes the spectrum of the user voice and the extracted voice samples to detect how much the voice component differs from the voice samples in comparison with the voice samples.

In this case, the voice component may be a voice size, a speech speed, a voice pitch, a pause, a tone, and the like. The voice analyzing unit 45 analyzes the spectrum of the user voice and the voice sample to detect differences in voice size, speech speed, voice pitch, pauses, and tones between two voices, and based on the difference information, As shown in FIG. That is, the voice analysis unit 45 may extract the voice sample file from the database unit 70 and compare the spectrum of the user voice and the voice sample to generate analysis information.

The reference voice information may be reference information for analyzing the contents of the user voice by voice components. The reference information includes, for example, analysis standard information for exemplary speech, such as the average size of an exemplary voice, the number of words (or syllables) per unit time, the duration and timing of voice pitch differences and timing, can do. In this case, the voice analyzer 45 analyzes the spectrum of the user's voice, compares the spectrum of the user's voice with the reference information, and analyzes how much the voice component of the user voice differs from the reference for each voice component Analysis information can be generated. That is, the voice analysis unit 45 may extract the reference information from the database unit 70 and generate analysis information by comparing the user voice spectrum with the reference information.

Meanwhile, the voice analyzing unit 45 may analyze the contents of the user voice to separate the user voice for each unit voice that can be analyzed if the user voice is too long or includes a plurality of sentences.

For example, the voice analyzer 45 analyzes the contents of the user voice to determine whether the contents of the user voice exceed the predetermined reference word count or the number of reference sentences, and determines whether the number of reference words or the number of reference sentences The user's voice may be divided into a predetermined number of words or a unit number of sentences. For example, if the user voice is' Hi? How have you been? Let's meet at Hongdae at 00 o'clock today. ' How are you? "And" Let's meet at Hongdae at 00:00 today. "

In this case, the voice analysis unit 45 extracts corresponding reference voice information for each of the separated unit sounds from the database unit 70, compares each unit voice with the corresponding reference voice information, After generating the information, the unit analysis information can be integrated to generate the final analysis information.

In extracting the reference speech information for analyzing the user's voice, the speech analyzing unit 45 transmits reference speech information for analyzing the user speech according to the user condition information set by the information setting unit 42 to the database unit 70). In this case, the database unit 70 may store a plurality of pieces of reference voice information corresponding to respective voice contents in accordance with various user condition information.

For example, assuming that the age, gender, job group, and analysis standard among the items of the user condition information of the user are '20s,' 'female,' 'salesperson,' and ' Extracts reference voice information corresponding to '20', 'female', 'salesperson', and 'good feeling' among the reference voice information corresponding to the contents of the user voice from the database unit 70, . In this case, the extracted reference voice information may refer to a voice sample or reference information of a voice having a high appeal level as a female salesman in his twenties.

The voice analyzer 45 may automatically discriminate at least one of the analysis criteria according to the contents of the user voice, and may select the reference voice information according to the determined analysis criteria.

For example, if the content of the user voice is 'inquire of today's weather' and the user condition information is set to 20, female, office worker, etc. for each age group, sex, , The voice analysis unit 45 inquires of the predetermined analysis reference table to determine that 'inquire about today's weather' is a voice requiring 'public confidence', and judges that the reference voice information corresponding to 20's, female, office work, Can be extracted from the database unit 70 and used for analysis. The analysis criteria may be plural. For example, the voice analysis unit 45 may extract a plurality of reference voice information from the database unit 70 in order to analyze the user voice by the confidence level and the likelihood.

The analysis reference table may be a table that stores information of corresponding sentences for each analysis criterion. For example, the analysis reference table may store sentences corresponding to public confidence (i.e., sentences requiring public confidence), sentences corresponding to favorability (i.e. sentences requiring favorability), and the like.

Meanwhile, the voice analyzing unit 45 calculates the degree of correspondence between the user voice and the at least one reference voice information for each voice element, calculates the degree of correspondence for each calculated voice element, A total agreement degree may be calculated. At this time, the calculation may include an operation of averaging the degree of agreement for each voice element, an operation of weighting the degree of matching of a specific voice element according to a predetermined standard, and the like.

For example, assuming that the user condition information is a professional female in the twenties and that the analytical standard is 'public confidence', the voice analysis unit 45 receives '20s', 'professions', 'women' And extracts reference voice information corresponding to 'public confidence'. At this time, the voice analysis unit may calculate the degree of correspondence between the user voice and the extracted reference voice information for each voice component according to a predetermined algorithm. The speech analyzing unit can calculate the degree of match for each calculated speech element and calculate the degree of total agreement with the extracted reference speech information. The calculated total degree of coincidence may be expressed as a 'confidence score' of the user's voice. Similarly, the voice analysis unit may calculate the 'goodness index' of the user voice.

The consulting processing unit 47 may generate the voice consulting information based on the analysis information generated by the voice analyzing unit 45 and provide the generated voice consulting information to the user terminal 10. [ The voice consulting information 47 may include analysis result information of the user voice in comparison with the reference voice information, calibration information for calibrating the voice of the user, an exemplary sample voice, and the like.

The consulting processing unit 47 may generate analysis result information indicating an analysis result of the user voice based on the reference voice information based on the analysis information generated by the voice analysis unit 45. [ The analysis result information may include information indicating a difference between the user's voice and the reference voice information by voice element, a total degree of agreement with the reference voice information according to the analysis standard, and the like. The consulting processing unit 47 may generate calibration information for calibrating the user's voice according to the analysis result information. In addition, the consulting processing unit 47 may generate an exemplary sample voice by modulating the user's voice to conform to the reference voice information based on the analysis result information.

When such information is generated, the consulting processing unit 47 may generate the voice consulting information including the generated analysis result information, the calibration information, the best sample voice, and the like, and may transmit the voice consulting information to the user terminal 10.

4 is an exemplary diagram exemplarily showing voice consulting information generated by the consulting processing unit 47 and provided to the user terminal 10. [

As shown in FIG. 4, the voice consulting information (VC) may include analysis result information of the user voice, for example, a 'voice analysis result'. The analysis result information may include information indicating how much the user speech is different for each voice element compared to the reference voice information extracted based on the user condition information.

For example, if it is assumed that the user condition information is '20s' for the age group, 'female' for the sex, 'salesperson' for the job group, and 'public confidence' for the analysis standard, Based on the voice information, it may include comparison information of voice elements such as 'voice size is small by 10%, voice pitch is 15% higher, horse speed is 12% faster, and so on'.

In addition, the analysis result information may include at least one total agreement according to at least one analysis criterion calculated by the voice analysis unit 45. [ The overall degree of match may be a degree of matching with reference voice information according to an analysis criterion. For example, the analysis result information may include a confidence score of a user's voice, a favorability index, and the like.

In addition, the voice consulting information (VC) may include voice calibration information based on the analysis result information. That is, the voice correction information may be information that enables the user's voice to be guided in a direction consistent with the reference voice information based on the analysis result information.

For example, in the example shown in FIG. 4, the voice correction information 'improvement direction' indicates that the user voice is 10% smaller than the voice sample, the voice pitch is 15% higher and the speech is 12% With a big, confident, slightly lower voice, and a slower talk, you'll be a more attractive voice! " And the like.

The voice consulting information (VC) may display an icon (IC) capable of listening to the exemplary voice samples. When the user selects the icon (IC), the exemplary speech sample generated by the consulting processing unit 47 is reproduced.

On the other hand, the ranking service unit 50 may provide a voice ranking service based on user voices acquired from interworking user terminals. For example, the ranking service unit 50 may calculate a ranking based on the public trust index and the good feeling index for a plurality of user voices acquired through the voice service unit 20, and transmit the calculated ranking information to the user terminal . Also, the ranking service unit 50 may display the rank of the user voice corresponding to the user account in the calculated ranking.

5 is an exemplary diagram showing an example of ranking information provided by the ranking service section 50. As shown in FIG.

As shown in FIG. 5, the ranking information provided by the ranking service unit 50 may be displayed on the user terminal 10. FIG. The ranking information may include ranking information based on the credit score of the user's voice and the likelihood score, and overall ranking information among the voices of the users corresponding to the user's selection condition.

For example, if the user is a professional female in his twenties, the ranking service department 50 can determine the user voice based on the confidence index rank 30, favorability rank 51, 45 ", and so on. In addition, the ranking service unit 50 may display a list of public trust ranking, favorability rank ranking, and summation ranking of all user voices corresponding to the above conditions.

Meanwhile, the contact arranging service unit 60 can provide the contact arranging service to the user terminal 10. [ For example, the contact establishment service unit 60 registers a plurality of user voices acquired through the voice service unit 20 in the database unit 70, and transmits the user's voice to the database unit 70 The user terminal 10 can inquire or search for the user's voice of reason among the registered user's voices.

When the user terminal 10 selects a certain user's voice with certainty, the contact establishment service unit 60 can transmit the user information corresponding to the selected user's voice to the user terminal 10. The contact establishment service unit 60 may provide the ranking information calculated by the ranking service unit 50 to the user terminal 10. For example, the contact facilitating service unit 60 may provide the user terminal 10 with rank information about the user's voice of interest, which is inquired or searched by the user terminal 10. [

The service providing system 1 based on the user voice according to the preferred embodiment of the present invention has been described above. According to the user voice-based service providing system 1 according to the preferred embodiment of the present invention, the user can receive various voice services such as voice mail service, voice memo service, voice mail service, You can be consulted about voice, and you can get various additional services such as ranking about your voice, arrange meeting using voice.

Thus, the user can evaluate his voice objectively and improve it in a positive direction. In addition, because of this additional service, the user's interest in the voice service itself also increases, which can contribute to the activation of the voice service.

Hereinafter, a service providing method based on the service providing system 1 will be described.

6 is a flowchart illustrating a method of providing a service based on a user voice according to a preferred embodiment of the present invention.

As shown in FIG. 6, the user accesses the voice service unit 20 through the user terminal 10 and requests voice service (step: S1). The voice service may be a voice mail service, a voice memo service, a voice mail service, an answering service, a voice search service, a voice information service, a voice call service, a voice messenger service,

The voice service unit 20 requests the user terminal 10 to consent to the provision of the user voice acquisition and supplementary services (step S2), and receives a signal from the user terminal 10 indicating that the user agrees to the request (Step S3).

For example, the voice service unit 20 outputs a guidance message to the user terminal via voice or screen to inform the user whether or not they agree to the acquisition of the user voice, and acquires the user voice from the user terminal 10 A signal may be received informing of the agreement. At this time, if a signal indicating that the user terminal 10 does not agree is received or there is no response, the user's voice may not be acquired. On the other hand, the voice service unit 20 may receive consent for provision of the user voice acquisition and additional service in advance through a web page, telephone, or the like.

When the user agreement is completed, the voice service unit 20 acquires the user voice received from the user terminal 10 at the voice service (step 4), and transmits the acquired user voice to the service server unit 30 (Step S5).

Upon receiving the user's voice, the service server unit 30 can acquire the contents of the user's voice by recognizing the user's voice through voice recognition (step S6). On the other hand, the service server unit 30 receives the user condition information of the user from the user terminal 10 and stores the user condition information in the database unit 70 in association with the user account. The user condition information may include a user's age, sex, occupation group, and at least one analysis criterion.

Next, the service server unit 30 can analyze the user voice based on the contents of the acquired user voice (step: S7). For example, the service server unit 30 extracts at least one reference voice information corresponding to the content of the acquired user voice from the database unit 70, compares the extracted reference voice information with the user voice, Analysis information can be generated. The voice component may be a voice size, a speech speed, a voice pitch, a pause, a tone, and the like.

The reference voice information may be a file of voice samples having the same content as the contents of the user voice. For example, if the contents of the user voice are 'What is today's weather?', The service server unit 30 inquires the database unit 70 to search for a plurality of voice samples stored in the database unit 70, How is the weather of today? "Can be extracted. The service server unit 30 may analyze the spectrum of the user speech and the extracted speech samples to detect how the speech components are different from each other, i.e., how much the speech components differ from the speech samples.

The reference voice information may be reference information for analyzing the contents of the user voice by voice components. The reference information includes, for example, analysis standard information for exemplary speech, such as the average size of an exemplary voice, the number of words (or syllables) per unit time, the duration and timing of voice pitch differences and timing, can do. In this case, the service server unit 30 analyzes the spectrum of the user's voice, compares the spectrum of the user's voice with the reference information, and analyzes how much the sound components of the user's voice differ from each other Analysis information can be generated.

If the user's voice is too long or includes a plurality of sentences, the service server unit 30 may analyze the contents of the user's voice and separate the user's voice according to the unit sounds that can be analyzed. In this case, the service server unit 30 extracts corresponding reference voice information for each separated unit voice from the database unit 70, compares each unit voice with the corresponding reference voice information, The unit analysis information can be integrated to generate a final analysis result.

The service server unit 30 may extract standard voice information for analyzing user voice according to preset user condition information from the database unit 70 at the time of extracting the reference voice information for analysis of the user voice. In this case, the database unit 70 may store a plurality of pieces of reference voice information corresponding to respective voice contents in accordance with various user condition information. Also, the service server unit 30 may automatically discriminate at least one of the analysis criteria according to the contents of the user's voice, and may select the reference speech information according to the determined analysis criterion.

The service server unit 30 calculates a match degree of each voice component between the user voice and the at least one reference voice information, calculates the match degree for each calculated voice component, A match degree may be calculated. At this time, the calculation may include an operation of averaging the degree of agreement for each voice element, an operation of weighting the degree of matching of a specific voice element according to a predetermined standard, and the like.

When the analysis of the user voice is completed, the service server unit 30 generates voice consulting information based on the analysis information (step S8), and transmits the generated voice consulting information to the user terminal (step S9) . The voice consulting information may include analysis result information of the user voice in comparison with the reference voice information, calibration information for calibrating the voice of the user, an exemplary sample voice, and the like.

Meanwhile, the service server unit 30 may provide a voice ranking service that provides ranking information based on user voices acquired from interworking user terminals. For example, the service server unit 30 may calculate a ranking based on the public trust index and the likelihood index for the acquired plurality of user voices, and transmit the calculated ranking information to the user terminal 10. Also, the service server unit 30 may display the rank of the user voice corresponding to the user account in the calculated ranking.

In addition, the service server unit 30 may provide the user's terminal 10 with a contact arrangement service based on the user's voice. For example, the service server unit 30 registers a plurality of user voices acquired through the voice service unit in the database unit 70, The user terminal 10 can inquire, search, and listen to user's voice.

The service server unit 30 may transmit user information corresponding to the selected user's voice to the user terminal 10. [ The service server unit 30 may provide the ranking information provided by the ranking service to the user terminal 10 at the time of the contact arrangement service. For example, the service server unit 30 may provide rank information on the user's voice to the user terminal.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it will be understood by those of ordinary skill in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. It will be understood that the invention may be practiced otherwise than as described herein. Accordingly, modifications of the embodiments of the present invention will not depart from the scope of the present invention.

10: User terminal
20: Voice service department
30: Service server
40: Consulting Service Department
41:
42: Information setting section
43:
45: Voice analysis section
47: Consulting Processing Department
50: Ranking Service Department
60: Meeting Service Department
70:

Claims (23)

There is provided a voice service including at least one of a voice mail service, a voice memo service, a voice mail service, an automatic response service, a voice search service, a voice information service, a voice call service, a voice messenger service, And outputting to the user terminal a guidance asking whether or not the user agrees to acquire the user's voice received from the user terminal through the voice service and use it for the supplementary service including the voice consulting service, A voice service unit for acquiring the user voice received from the user terminal during the voice service when a signal indicating acceptance is received in response to the voice service; And
And a service server unit for providing the supplementary service including the voice consulting service including analysis information of the user voice using user voice acquired by the voice service unit,
Wherein the service server unit stores an analysis reference table including sentences requiring trustworthiness corresponding to trustworthiness and favorability, which are items of analysis criteria, and sentences requiring favorability,
Determining whether the content of the user voice is a sentence requiring trustworthiness or a sentence requiring a good impression based on the analysis reference table based on the content of the user voice, Extracting information from the database and calculating a degree of correspondence between the user's voice and the at least one reference voice information for each voice element and calculating a degree of match for each of the calculated voice elements, And a total degree of agreement is calculated based on the user's voice.
delete delete delete 2. The apparatus of claim 1, wherein the service server unit separates the user speech for each unit voice including at least one sentence according to the recognized content, and extracts reference voice information corresponding to the unit voice from the database Based service providing system.
The service providing system according to claim 1, wherein the voice component includes at least one of a voice size, a speech speed, a voice pitch, a pause, and a tone.
delete 2. The method of claim 1, wherein the reference voice information includes voice samples corresponding to contents of the user voice,
Wherein the service server extracts at least one reference speech sample corresponding to the recognized content from the database and compares the extracted speech sample with the spectrum of the acquired user speech to compare the extracted speech sample with the extracted speech sample And analyzing how much the voice components are different from each other.
delete The service providing system according to claim 1,
And generates the best sample voice by modulating the user voice to conform to the reference voice information based on the analysis information, and provides the generated sample voice to the user terminal system.
delete The system of claim 1, wherein the supplementary service further comprises a voice ranking service and a contact establishment service based on the acquired user voice.
13. The method of claim 12, wherein the voice ranking service calculates a ranking based on a public confidence index and a good feeling index for a plurality of user voices acquired from the voice service unit, and transmits the calculated ranking information to the user terminal Wherein the user-voice-based service providing system comprises:
13. The method of claim 12, wherein the contact establishment service registers a plurality of user voices acquired through the voice service unit in a database, and transmits user notes of the user's voice registered in the database to the user terminal, And provides the user information corresponding to the user's voice of the reason selected by the user terminal.
15. The system of claim 14, wherein the contact establishment service provides rank information calculated by the voice ranking service to the user terminal.
A service providing method based on a user voice performed by a service server,
There is provided a voice service including at least one of a voice mail service, a voice memo service, a voice mail service, an automatic response service, a voice search service, a voice information service, a voice call service, a voice messenger service, step;
Outputting, to the user terminal, a guidance inquiring whether the user's voice received from the user terminal is obtained through the voice service and whether the user's voice agrees to use the supplementary service including the voice consulting service;
Acquiring the user's voice received from the user terminal in the voice service when the user terminal receives a signal indicating agreement in response to the guidance;
Storing an analysis reference table including sentences requiring trustworthiness and sentences requiring favorability that correspond respectively to public confidence and favorability, which are items of analysis criteria; And
Providing the supplementary service including the voice consulting service including analysis information of the user voice using the acquired user voice,
Wherein the step of providing the additional service comprises:
Recognizing the contents of the user voice;
Determining whether the content of the user voice is a sentence requiring confidence or a sentence requiring a good impression based on the analysis reference table;
Extracting at least one reference voice information from the database based on the determination;
Calculating a match degree for each of the speech components of the user speech and the at least one reference speech information;
And calculating a degree of match for each of the speech elements calculated to calculate a total degree of agreement with the reference speech information according to at least one analysis criterion. delete delete delete delete delete delete delete

Images