KR20190143210A - Apparatus and method for providing private search pattern guide - Google Patents

Abstract

The present invention relates to an apparatus for providing a personal search pattern guide and a method thereof, capable of providing a personalized search pattern guide by using speaker voice authentication. The apparatus for providing a personal search pattern guide comprises: an input unit for receiving speaker voice; an activation word identification unit for identifying an activation word by processing the input speaker voice; a communications unit for transmitting a personal search pattern guide to a multimedia device; and a control unit for controlling the input unit, the activation word identification unit, and the communications unit, wherein the control unit controls the activation word identification unit to identify whether the input speaker voice is an activation word when the speaker voice is input, performs speaker authentication corresponding to the speaker voice when the speaker voice is the activation word, acquires personal profile information of the authenticated speaker when the speaker authentication is completed, generates a personal search pattern guide based on the acquired personal profile information, and controls the communications unit to transmit the generated personal search pattern guide to the multimedia device.

Description

Apparatus and method for providing a personal search pattern guide {APPARATUS AND METHOD FOR PROVIDING PRIVATE SEARCH PATTERN GUIDE}

The present invention relates to a personal search pattern guide providing apparatus, and more particularly, to a personal search pattern guide providing apparatus and method that can provide a personalized search pattern guide using speaker voice authentication.

In general, natural language processing (NLP) refers to a technology for converting a human language into a mechanical form through various analysis methods so that a computer can understand it, and then, a technology for forming a morpheme for human interpretation Also includes.

Natural language processing, a subfield of artificial intelligence, is a technological field derived from the breakdown of human language analysis and understanding after attempts to create artificial intelligence in the 1960s. The study of linguistic engineering, artificial intelligence, and computational linguistics May include a field.

In addition, natural language means a language such as Korean or English that has been used for communication occurring naturally over a long time in the past, rather than a man-made language like a programming language.

On the other hand, a device that provides a search guide on the screen of a multimedia device such as a TV, in the case of text search, provides a function of increasing the convenience of the search by providing recommendation words and related words as the search progresses.

In addition, when the search guide providing apparatus is capable of natural language processing, a voice search function may be provided. In the case of the voice search, the convenience of the search is improved by providing a microphone display or a caller guide for searching.

However, since the existing search guide providing device does not provide a personalized search pattern guide in case of text search or voice search, the search success rate is very low and it is not easy to promote products and services using the personal search pattern guide. There were problems.

Therefore, there is a demand for development of a personal search pattern guide providing apparatus capable of providing a personalized personal search pattern guide in the future to increase a search success rate and to provide a product and service promotion using the personal search pattern guide.

The present invention obtains the personal profile information of the authenticated speaker by performing the speaker authentication corresponding to the speaker voice, and generates and provides a personal search pattern guide based on the obtained personal profile information, thereby increasing the voice search success rate and personal search pattern guide. To provide a personal search pattern guide providing apparatus, method and system that can provide products and services promotion using the.

The technical problems to be achieved in the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned above will be clearly understood by those skilled in the art from the following description. Could be.

In order to solve the above technical problem, the personal search pattern guide providing apparatus according to an embodiment of the present invention, an input unit for receiving a speaker voice, and a start word identification unit for processing the input speaker voice to identify the starting word; And a communication unit for transmitting the personal search pattern guide to the multimedia device, an input unit, a starting word identification unit, and a control unit controlling the communication unit, wherein the control unit identifies whether the input speaker voice is a starting word when the speaker voice is input. Control the identification unit so that the user's voice is activated, and if the speaker's voice is the user's voice, the speaker's authentication corresponding to the speaker's voice is performed, and when the speaker's authentication is completed, the personal profile information of the authenticated speaker is obtained, and personal search is performed based on the acquired personal profile information. Create a pattern guide, and control the communication unit to transmit the generated personal search pattern guide to the multimedia device Can.

Here, when performing the speaker authentication corresponding to the speaker voice, the control unit controls the communication unit to transmit a speaker voice signal and a speaker authentication request signal for the speaker voice corresponding to the starting word to the server, and transmits to the speaker authentication request from the server. It may receive the speaker authentication information for.

In addition, when performing speaker authentication corresponding to the speaker voice, the controller may directly compare the speaker voice signal corresponding to the starting word with the speaker voice signal registered in advance, and perform speaker authentication, and extract speaker authentication information. .

The controller may control the communication unit to transmit the speaker's authentication information and the personal profile information request signal to the server when acquiring the authenticated speaker's personal profile information, and obtain the speaker's personal profile information received from the server. have.

In addition, when acquiring the personal profile information of the authenticated speaker, the controller may obtain personal profile information corresponding to the authenticated speaker from the personal profile information table previously stored in the storage unit based on the speaker's authentication information.

Next, when generating the personal search pattern guide based on the acquired personal profile information, the controller extracts a plurality of voice search keywords from the obtained personal profile information, classifies the extracted plurality of voice search keywords by item, and A personal search pattern guide having a plurality of voice search keywords classified by stars may be generated.

Here, when the plurality of voice search keywords are extracted from the acquired personal profile information, the controller selects the voice search keywords according to at least one extraction reference rate among the keyword search frequency, popularity, latestness, exposure time, and voice search success rate. Can be extracted.

The controller may further include a channel name item, a channel number item, a content name item, a content genre item, a person name item, a search engine name item, when the extracted voice search keywords are classified by item. The search term may be classified into at least one item.

In some cases, when extracting a plurality of voice search keywords from the acquired personal profile information, the controller may analyze a voice characteristic of the speaker and extract a voice search keyword corresponding to the analyzed voice characteristic from the personal profile information. .

In another case, when extracting a plurality of voice search keywords from the obtained personal profile information, the controller analyzes the speaker's voice characteristics to first extract a voice search keyword corresponding to the voice characteristics analyzed from the personal profile information. Among the first extracted voice search keywords, the voice search keywords may be secondly extracted according to at least one extraction reference rate among the search frequency, popularity, latestness, exposure time, and voice search success rate for the voice search keywords.

Next, when the controller generates the personal search pattern guide based on the acquired personal profile information, the controller recommends at least one of recommended content, recommended advertisement, recommended voice search keyword, and recommended new service promotion based on the obtained personal profile information. May be collected and a personal search pattern guide including the collected recommended information may be generated.

Here, when generating the personal search pattern guide based on the obtained personal profile information, the controller displays a first area for displaying a voice search keyword classified into a plurality of items, a second area for displaying recommendation information, and a recommendation advertisement. A personal search pattern guide including at least one of a third region and a fourth region displaying a guide message may be generated.

On the other hand, the personal search pattern guide providing system according to an embodiment of the present invention, the personal search pattern guide providing apparatus for authenticating the input speaker voice and generates a personal information pattern guide based on the personal profile information of the authenticated speaker, A multimedia device that is communicatively connected to the search pattern guide providing device and displays a personal search pattern guide received from the personal search pattern guide providing device, and that is connected to the personal search pattern guide providing device and that communicates with the personal search pattern guide providing device. And a server for providing personal profile information of the personal information pattern guide providing apparatus. The apparatus for providing a personal search pattern guide may identify whether the input speaker voice is a starting word when the speaker voice is input, and the speaker authentication corresponding to the speaker voice when the speaker voice is the starting word. When the speaker authentication is completed, the authorized speaker The acquired profile information, generates individual pattern search guide based on the acquired personal profile information and may send the generated guide pattern to search personal multimedia device.

On the other hand, the method for providing a personal search pattern guide according to an embodiment of the present invention, the step of receiving a speaker voice, checking whether the input speaker voice is a starting word, and if the speaker voice is a starting word, it corresponds to the speaker voice Performing the speaker authentication, checking whether the speaker authentication is completed, acquiring the personal profile information of the authenticated speaker when the speaker authentication is completed, and a personal search pattern based on the obtained personal profile information Generating the guide, and transmitting the generated personal search pattern guide.

Meanwhile, an embodiment of the present invention may further provide a computer readable program for executing any one of the methods of providing the personal search pattern guide and a recording medium on which the program is recorded.

The apparatus, method and system for providing a personal search pattern guide according to at least one embodiment of the present invention configured as described above may obtain personal profile information of an authenticated speaker by performing speaker authentication corresponding to a speaker voice, By creating and providing a personal search pattern guide based on personal profile information, it is possible to increase the voice search success rate and provide a product and service promotion using the personal search pattern guide.

That is, the present invention can increase the search success rate by personalizing the search pattern by using the speaker profile information through speaker authentication and providing an optimal search pattern guide on the TV screen, and real-time of the personalized search pattern guide through speaker authentication. Providing product advertisement and service promotion can be provided through the provision.

In addition, the present invention can induce a user to search the revenue contribution content, to induce specific home IoT control, to provide a predetermined new service promotion, advertisement of the relevant affiliated companies such as restaurants It may be provided, or a popular search term may be provided for the convenience of search, or a search pattern may be induced to analyze the search failure cases and reflect the same, thereby increasing the search success rate.

The effects obtainable in the present invention are not limited to the above-mentioned effects, and other effects not mentioned above may be clearly understood by those skilled in the art from the following description. will be.

1 is a schematic diagram illustrating a system for providing a personal search pattern guide according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating an apparatus for providing a personal search pattern guide of FIG. 1.
FIG. 3 is a diagram illustrating a personal search pattern guide displayed on the multimedia device of FIG. 1.
4 is a diagram for describing a voice search keyword region of the personal search pattern guide of FIG. 3.
5 to 9 are flowcharts illustrating a method for providing a personal search pattern guide according to an embodiment of the present invention.

Hereinafter, an apparatus and various methods to which embodiments of the present invention are applied will be described in more detail with reference to the accompanying drawings. The suffixes "module" and "unit" for components used in the following description are given or used in consideration of ease of specification, and do not have distinct meanings or roles from each other.

In the above description, all elements constituting the embodiments of the present invention are described as being combined or operating in combination, but the present invention is not necessarily limited to the embodiments. That is, within the scope of the present invention, all of the components may be selectively operated in combination with one or more. In addition, although all of the components may be implemented in one independent hardware, each or all of the components may be selectively combined to perform some or all functions combined in one or a plurality of hardware. It may be implemented as a computer program having a. Codes and code segments constituting the computer program may be easily inferred by those skilled in the art. Such a computer program may be stored in a computer readable storage medium and read and executed by a computer, thereby implementing embodiments of the present invention. The storage medium of the computer program may include a magnetic recording medium, an optical recording medium, a carrier wave medium, and the like.

In the description of the embodiments, in the case of being described as being formed at "up (up) or down (down)", "before (front) or back (back)" of each component, "up (up) or down (Below) ”and“ before (before) or after (behind) ”include both in which two components are formed in direct contact with each other or one or more other components are disposed between the two components.

In addition, the terms "comprise", "comprise" or "having" described above mean that the corresponding component may be included, unless otherwise stated, and thus excludes other components. It should be construed that it may further include other components instead. All terms, including technical and scientific terms, have the same meanings as commonly understood by one of ordinary skill in the art unless otherwise defined. Terms commonly used, such as terms defined in a dictionary, should be interpreted to coincide with the contextual meaning of the related art, and shall not be construed in an ideal or excessively formal sense unless explicitly defined in the present invention.

In addition, in describing the component of this invention, terms, such as 1st, 2nd, A, B, (a), (b), can be used. These terms are only for distinguishing the components from other components, and the nature, order or order of the components are not limited by the terms. If a component is described as being "connected", "coupled" or "connected" to another component, that component may be directly connected to or connected to that other component, but there may be another configuration between each component. It is to be understood that the elements may be "connected", "coupled" or "connected".

In the following description of the present invention, when it is determined that the subject matter of the present invention may be unnecessarily obscured by those skilled in the art with respect to the related well-known technology, the detailed description thereof will be omitted.

The apparatus for providing a personal search pattern guide of the present invention is an interactive service apparatus capable of processing natural language, and is generally referred to as a speech recognition speaker, and may also be referred to as an artificial intelligence speaker, an AI speaker, an artificial intelligence assistant, or the like.

One example of the personal search pattern guide providing apparatus may be a chat bot. Chat bot is literally a compound word of 'chatting' and 'robot', which can mean a robot talking like a person. The chatbot may be a home device such as Google Home, Amazon Echo, or Siri, manufactured and sold by Google, Amazon, Apple, etc., or may be an enterprise device that responds to customers.

In some cases, the personal search pattern guide providing apparatus may include a mobile phone, a smart phone, a laptop computer, a digital broadcasting terminal, a personal digital assistant, a portable multimedia player (PMP), a navigation device, and a slate PC. (slate PC), tablet PC (tablet PC), ultrabook, wearable device (e.g., smartwatch, smart glass, head mounted display) It may also be a mobile terminal including the.

In another case, the personal search pattern guide providing apparatus may be applied to a fixed terminal such as a digital TV, a desktop computer, a digital signage, or the like.

1 is a schematic diagram illustrating a system for providing a personal search pattern guide according to an embodiment of the present invention.

As shown in FIG. 1, the personal search pattern guide providing system of the present invention may include a personal search pattern guide providing apparatus 300, a multimedia apparatus 100, and a server 200.

Here, the apparatus 300 for providing a personal search pattern guide may authenticate a speaker voice that is input and connected to the multimedia apparatus 100 and the server 200 and generate a personal information pattern guide based on personal profile information of the authenticated speaker. Can be.

The multimedia apparatus 100 may be connected to the personal search pattern guide providing apparatus 300 and display the personal search pattern guide received from the personal search pattern guide providing apparatus 300.

For example, the multimedia apparatus 100 may be a network TV, an HBBTV, a smart TV, or the like, and may be applicable to a smartphone in some cases.

Subsequently, the server 200 may be communicatively connected to the personal search pattern guide providing apparatus 300, and may provide the speaker's personal profile information according to a request of the personal search pattern guide providing apparatus 300.

In this manner, in the personal search pattern guide providing system configured, the personal search pattern guide providing apparatus 300 identifies whether the input speaker voice is a starting word when a speaker voice is input, and identifies the speaker voice if the speaker voice is a starting word. The corresponding speaker authentication is performed, and when the speaker authentication is completed, the personal profile information of the authenticated speaker is obtained, a personal search pattern guide is generated based on the obtained personal profile information, and the personal search pattern guide is generated. ) Can be sent.

In another embodiment, in the system of the present invention, the search pattern guide providing apparatus 300 performs a speaker classification corresponding to the speaker voice when the speaker voice is input and performs a personal search corresponding to the classified speaker when the speaker classification is completed. The pattern guide may be generated and the generated personal search pattern guide may be transmitted to the multimedia apparatus 100.

In addition, the search pattern guide providing apparatus 300 may classify the speaker classification into at least one of gender, age group, mood state, health condition, and family member when performing speaker classification corresponding to the speaker voice. But is not limited thereto.

For example, you can classify gender, age group, mood, and health status by information contained in voice such as frequency, amplitude of voice, and the number of family members by checking the number of different voices input through multimedia device or server. You can check.

In some cases, the search pattern guide providing apparatus 300 may classify a speaker corresponding to the speaker voice into a plurality of classification items.

In addition, the search pattern guide providing apparatus 300, when generating a personal search pattern guide corresponding to the classified speaker, extracts a plurality of voice search keywords from the speaker voice, and based on the extracted voice search keywords, personal search pattern guide Can be generated.

Here, when the search pattern guide providing apparatus 300 extracts a plurality of voice search keywords from the speaker's voice, the search pattern guide providing apparatus 300 according to at least one of the search frequency, popularity, recency, exposure time, and voice search success rate of the keyword is selected. A voice search keyword can be extracted.

Then, when the search pattern guide providing apparatus 300 extracts a plurality of voice search keywords from the speaker voice, the voice search keyword is searched from the speaker voice, the search frequency, popularity, the latest degree, An extraction reference rate of at least one of the exposure time and the voice search success rate is calculated, and if the calculated extraction reference rate is less than the preset reference value, the searched voice search keyword is ignored. Search keywords can be extracted.

In addition, when the search pattern guide providing apparatus 300 generates a personal search pattern guide corresponding to the classified speaker, at least one of recommended contents, recommended advertisements, recommended voice search keywords, and recommended new service promotions corresponding to the classified speakers. One recommendation information may be collected, and a personal search pattern guide including the collected recommendation information may be generated.

Here, the search pattern guide providing apparatus 300, when generating a personal search pattern guide corresponding to the classified speaker, the first area to display the voice search keywords classified into a plurality of items, the second to display the recommended information A personal search pattern guide including at least one of an area, a third area for displaying a recommended advertisement, and a fourth area for displaying a guide message may be generated.

As another embodiment, the system of the present invention communicates with the multimedia apparatus 100 displaying the personal search pattern guide, the server 200 providing the personal information pattern guide, and the multimedia apparatus 100 and the server 200. The apparatus may include a search pattern guide providing apparatus 300 which transmits the connected speaker's voice to the server 200 and transmits the personal information pattern guide received from the server 200 to the multimedia apparatus 100.

Here, when the speaker voice is received, the server 200 performs a speaker classification corresponding to the speaker voice. When the speaker classification is completed, the server 200 generates a personal search pattern guide corresponding to the classified speaker, and generates the personal search pattern guide. The search pattern guide providing apparatus 300 may transmit the same.

In addition, when performing the speaker classification corresponding to the speaker's voice, the server 200 may classify the speaker into at least one of gender, age group, mood state, health condition, and family member, but is not limited thereto. It doesn't work.

In some cases, the server 200 may classify a speaker corresponding to the speaker voice into a plurality of classification items.

In addition, when generating the personal search pattern guide corresponding to the classified speaker, the server 200 may extract a plurality of voice search keywords from the speaker voice and generate a personal search pattern guide based on the extracted voice search keyword. have.

Here, when extracting a plurality of voice search keywords from the speaker's voice, the server 200 selects the voice search keyword according to at least one extraction reference rate among the keyword's search frequency, popularity, latestness, exposure time, and voice search success rate. Can be extracted.

When the plurality of voice search keywords are extracted from the speaker's voice, the server 200 searches for the voice search keyword from the speaker's voice, searches for the searched voice search keyword, popularity, latestness, exposure time, and At least one extraction criterion rate of the voice search success rate is calculated, and if the calculated extraction criterion is less than the preset reference value, the searched voice search keyword is ignored. can do.

In addition, when the server 200 generates a personal search pattern guide corresponding to the classified speaker, the server 200 recommends at least one of recommended contents, recommended advertisements, recommended voice search keywords, and recommended new service promotions. Information may be collected and a personal search pattern guide including the collected recommendation information may be generated.

Here, when generating the personal search pattern guide corresponding to the classified speaker, the server 200 includes a first area displaying a voice search keyword classified into a plurality of items, a second area displaying recommendation information, and a recommended advertisement. A personal search pattern guide including at least one of a third area displaying a and a fourth area displaying a guide message may be generated.

Therefore, when a user inputs a voice command by referring to the spoken sentence of the personal search pattern guide displayed on the multimedia apparatus 100, the user can conveniently perform a voice search, a high voice search success rate, User convenience may be provided to receive customized product and service promotions.

As such, the personal search pattern guide providing apparatus 300 may increase the search success rate by personalizing the search pattern by using the speaker profile information through speaker authentication and providing an optimal search pattern guide on the TV screen. Product advertisement and service promotion can be provided through real-time provision of personalized search pattern guides.

FIG. 2 is a block diagram illustrating an apparatus for providing a personal search pattern guide of FIG. 1.

As illustrated in FIG. 2, the apparatus 300 for providing a personal search pattern guide according to the present invention includes an input unit 310 for receiving a speaker voice and a starting word identification unit 320 for identifying a starting word by processing the input speaker voice. ), A communication unit 330 for transmitting the personal search pattern guide to the multimedia device, and an input unit 310, a start word identification unit 320, and a control unit 340 for controlling the communication unit 330.

Here, when the speaker voice is input, the controller 340 controls the start word identification unit 320 to identify whether the input speaker voice is the starting word, and if the speaker voice is the starting word, performs the speaker authentication corresponding to the speaker voice. When the speaker authentication is completed, the communication unit 330 is configured to acquire personal profile information of the authenticated speaker, generate a personal search pattern guide based on the obtained personal profile information, and transmit the generated personal search pattern guide to the multimedia device. Can be controlled.

The controller 340 controls the communication unit 330 to transmit a speaker voice signal and a speaker authentication request signal for the speaker voice corresponding to the starting language to the server when performing speaker authentication corresponding to the speaker voice. The speaker authentication information for the speaker authentication request may be received from the server.

In this case, the personal search pattern guide providing apparatus 300 does not need to additionally place the speaker authentication unit therein and does not need to store additional authentication information in the internal storage, thereby simplifying the internal design configuration and securing memory storage space. It is effective to reduce the production cost.

In some cases, when performing the speaker authentication corresponding to the speaker voice, the controller 340 directly performs a speaker authentication by directly comparing the speaker voice signal corresponding to the starting word with the speaker voice signal registered in advance, and the speaker authentication information. You can also extract

Here, the pre-registered speaker voice signal may be extracted from the speaker voice registration table pre-stored in the storage unit, but is not limited thereto.

In this case, since the personal search pattern guide providing apparatus 300 performs the speaker authentication using the speaker authentication unit therein, the speaker search can be quickly and quickly performed.

Subsequently, when obtaining the personal profile information of the authenticated speaker, the controller 340 controls the communication unit 330 to transmit the speaker's authentication information and the personal profile information request signal to the server, and receives the individual of the speaker received from the server. Profile information can be obtained.

In this case, since the personal search pattern guide providing apparatus 300 does not need to additionally arrange a personal profile collecting unit and does not need to store additional personal profile information in the internal storage, the internal design configuration is simplified and the memory storage space is advantageous. It is effective to reduce the production cost.

In some cases, when acquiring the personal profile information of the authenticated speaker, the controller 340 may acquire personal profile information corresponding to the authenticated speaker from the personal profile information table previously stored in the storage unit based on the speaker's authentication information. It may be.

In this case, since the personal search pattern guide providing apparatus 300 collects personal profile information using an internal personal profile collecting unit, there is an effect of quickly and quickly obtaining personal profile information.

For example, the personal profile information may include identification information of the speaker, viewing environment information of the speaker, viewing history information of the speaker, and search history information of the speaker, but is not limited thereto.

Here, the identification information of the speaker may include, but is not limited to, the age, sex, and residence of the speaker.

The speaker's viewing environment information may include, but is not limited to, preference channel information, volume information, viewing grade information, image mode information, audio mode information, and viewing reservation information.

Next, when generating the personal search pattern guide based on the acquired personal profile information, the controller 340 extracts a plurality of voice search keywords from the obtained personal profile information and classifies the extracted plurality of voice search keywords by items. In addition, a personal search pattern guide having a plurality of voice search keywords classified by items may be generated.

Here, when the plurality of voice search keywords are extracted from the obtained personal profile information, the controller 340 uses the voice based on at least one extraction criterion ratio among the keyword search frequency, popularity, latestness, exposure time, and voice search success rate. Search keywords can be extracted.

That is, the controller 340, when extracting a plurality of voice search keywords from the obtained personal profile information, searches for a voice search keyword from the acquired personal profile information, searches for the searched voice search keywords, popularity, and the latest. Also, at least one extraction reference rate of the exposure time and the voice search success rate is calculated. If the calculated extraction reference rate is less than the preset reference value, the searched voice search keyword is ignored. One voice search keyword can be extracted.

Herein, when ignoring the searched voice search keyword, the controller 340 searches for the searched voice search keyword if the search frequency, popularity, recency, exposure time, and extraction reference rate for the voice search success rate are all less than a predetermined reference value. One voice search keyword can be ignored.

In addition, when the searched voice search keyword is extracted, the controller 340 sets the searched voice search keyword to at least one of a search frequency, popularity, latestness, exposure time, and an extraction reference rate for the voice search success rate. If the reference value is higher than or equal to, the searched voice search keyword may be extracted.

In addition, the controller 340, when classifying the extracted plurality of voice search keywords by item, the extracted voice search keyword is a channel name item, a channel number item, a content name item, a content genre item, a person name item, a search engine name. The item may be classified into at least one of the item and the search word item.

Here, the voice search keywords may be classified one by one, but may be classified by multiple items in some cases.

Next, when classifying the extracted plurality of voice search keywords by item, if the extracted plurality of voice search keywords are classified by item, the controller 340 determines the priority of the voice search keywords by each item and determines the priority. According to the priority, voice search keywords may be arranged for each item.

Here, when determining the priority of the voice search keywords for each item, the controller 340 may determine the priority based on the search frequency, popularity, latestness, exposure time, and voice search success rate for the voice search keyword. have.

In some cases, the controller 340, when determining the priority of the voice search keywords for each item, the search frequency ranking item, the popularity ranking item, the latest ranking item, the exposure time ranking item, The first priority is determined according to a preset priority item among the voice search success rate rank items. If there is a voice search keyword having the same determined first priority, the voice rate is determined according to the calculation rate for the rank item including the voice search keyword. Secondary priority may also be determined.

As another case, the controller 340, when extracting a plurality of voice search keywords from the obtained personal profile information, analyzes the speaker's voice characteristics and extracts a voice search keyword corresponding to the voice characteristics analyzed from the personal profile information. can do.

For example, the speaker's voice characteristic may be at least one of a speaker's age, gender, and health condition, but is not limited thereto.

Here, the controller 340 controls the communication unit 330 to transmit the speaker voice signal and the speaker voice property request signal to the server when analyzing the speaker voice property, and the speaker voice property information of the speaker voice signal from the server. When receiving, the voice characteristic of the speaker may be analyzed based on the received speaker voice characteristic information.

As another case, the controller 340, when extracting a plurality of voice search keywords from the obtained personal profile information, analyzes the speaker's voice characteristics to obtain a voice search keyword corresponding to the voice characteristics analyzed from the personal profile information. Among the extracted voice search keywords, the voice search keywords may be secondly extracted according to at least one extraction criterion among search frequency, popularity, recency, exposure time, and voice search success rate. It may be.

For example, the speaker's voice characteristic may be at least one of a speaker's age, gender, and health condition, but is not limited thereto.

Here, the controller 340, when secondly extracting the voice search keywords from the first extracted voice search keywords, search frequency, popularity, latestness, exposure time, and voice search for the first extracted voice search keywords. At least one of the success rates is calculated, and if the extracted reference rate is less than the predetermined reference value, the first extracted voice search keyword is ignored. Tea can be extracted.

At this time, the controller 340, when ignoring the first extracted voice search keyword, the first extracted voice search keyword is less than the predetermined reference value for the search frequency, popularity, recency, exposure time, and voice search success rate , The searched voice search keyword can be ignored.

In addition, when the second extracted voice search keyword is secondly extracted, the controller 340 extracts the first extracted voice search keyword from at least one of a search frequency, popularity, recency, exposure time, and extraction reference rate for the voice search success rate. If one is equal to or more than a preset reference value, the first extracted voice search keyword may be secondly extracted.

Next, when generating the personal search pattern guide based on the acquired personal profile information, the controller 340 based on the obtained personal profile information, at least one of recommended content, recommended advertisement, recommended voice search keyword, and recommended new service promotion. Collect recommendation information of, and generate a personal search pattern guide including the collected recommendation information.

In addition, when generating the personal search pattern guide based on the obtained personal profile information, the controller 340 may include a first area displaying a voice search keyword classified into a plurality of items, a second area displaying recommendation information, and a recommendation. A personal search pattern guide including at least one of a third area displaying an advertisement and a fourth area displaying a guide message may be generated.

For example, the first area of the personal search pattern guide may include a channel name item display area including a channel name voice search keyword and a representative spoken sentence, a channel number item display area including a channel number voice search keyword and a representative spoken sentence, and a content name voice. A content name item display area including a search keyword and a representative spoken sentence, a content genre item display area including a content genre voice search keyword and a representative spoken sentence, a person name item display area including a mixed voice search keyword and a representative spoken sentence, A search engine name item display area including a search engine name voice search keyword and a representative spoken sentence, and a search term item display area including a search word voice search keyword and a representative spoken sentence may be included.

The third region of the personal search pattern guide may display advertisements related to recommendation information displayed in the second region.

Subsequently, the fourth region of the personal search pattern guide may include a guide message and a list of previous spoken sentence history.

Next, the communication unit 330 may include one or more modules that enable wireless communication between the personal search pattern guide providing apparatus 300 and an external server or between the personal search pattern guide providing apparatus 300 and the multimedia apparatus. have.

The communication unit 330 may include at least one of a broadcast receiving module, a mobile communication module, a wireless internet module, a short range communication module, and a location information module.

The input unit 310 may include a camera or an image input unit for inputting an image signal, a microphone for inputting an audio signal, an audio input unit, and a user input unit 123 for receiving information from a user.

Here, the voice data or the image data collected by the input unit 310 may be analyzed and processed as a user's control command.

In addition, the personal search pattern guide providing apparatus 300 may further include a sensing unit, an output unit, an interface unit, a memory, and a power supply unit.

The sensing unit may include one or more sensors for sensing at least one of information in the personal search pattern guide providing apparatus 300, surrounding environment information surrounding the personal search pattern guide providing apparatus 300, and user information.

For example, the sensing unit may include a proximity sensor, an illumination sensor, a touch sensor, an acceleration sensor, a magnetic sensor, a gravity sensor, G-sensor, Gyroscope Sensor, Motion Sensor, RGB Sensor, Infrared Sensor, Infrared Sensor, Finger Scan Sensor, Ultrasonic Sensor, Optical Sensor , Microphones, battery gauges, environmental sensors (e.g. barometers, hygrometers, thermometers, radiation sensors, heat sensors, gas sensors, etc.), chemical sensors (e.g. electronic noses, Health care sensors, biometric sensors, etc.).

The output unit may be configured to generate an output related to visual, auditory, or tactile, and may include at least one of a display unit, an audio output unit, a hap tip module, and an optical output unit.

Subsequently, the interface unit serves as a path to various types of external devices connected to the personal search pattern guide providing apparatus 300.

The interface unit 160 connects a device equipped with a wired / wireless headset port, an external charger port, a wired / wireless data port, a memory card port, and an identification module. It may include at least one of a port, an audio input / output (I / O) port, a video input / output (I / O) port, and an earphone port.

In addition, the memory stores data supporting various functions of the personal search pattern guide providing apparatus 300.

Memory. A plurality of application programs (applications or applications) driven by the personal search pattern guide providing apparatus 300, data, and instructions for the operation of the personal search pattern guide providing apparatus 300 may be stored.

At least some of these application programs may be downloaded from an external server via wireless communication.

In addition, the application program is stored in a memory and installed on the personal search pattern guide providing apparatus 300, and driven to perform an operation (or function) of the personal search pattern guide providing apparatus 300 by the controller 340. Can be.

The controller 340 of the personal search pattern guide providing apparatus 300 generally controls the overall operation of the personal search pattern guide providing apparatus 300 in addition to an operation related to an application program.

The control unit 340 of the apparatus 300 for providing a personal search pattern guide may process signals, data, information, etc. input or output through the above-described components, or run an application program stored in a memory, thereby providing information or functions appropriate to a user. Can be provided or processed.

In addition, the power supply unit, under the control of the controller 340, receives power from the outside and the power from the inside to supply power to each component included in the personal search pattern guide providing apparatus 300.

Such a power supply includes a battery, which may be an internal battery or a replaceable battery.

As another embodiment, the apparatus 300 for providing a personal search pattern guide according to the present invention may include an input unit for receiving a speaker voice, a communication unit for transmitting a personal search pattern guide to a multimedia device, and a control unit for controlling the input unit and the communication unit. Can be.

Here, when the speaker voice is input, the controller performs a speaker classification corresponding to the speaker voice, and when the speaker classification is completed, generates a personal search pattern guide corresponding to the classified speaker, and converts the generated personal search pattern guide into the multimedia device. The communication unit can be controlled to transmit.

The controller may classify the speaker into at least one of gender, age group, mood state, health condition, and family member when performing speaker classification corresponding to the speaker voice, but is not limited thereto. .

For example, gender, age group, mood state, and health status can be classified using information included in the voice such as frequency and amplitude of the voice, and the number of different voices input through the multimedia device or the server can be used to check the family members. You can check the number.

In addition, the controller may classify a speaker corresponding to the speaker voice into a plurality of classification items.

In addition, when generating a personal search pattern guide corresponding to the classified speaker, the controller may extract a plurality of voice search keywords from the speaker voice and generate a personal search pattern guide based on the extracted voice search keyword.

Here, when the plurality of voice search keywords are extracted from the speaker's voice, the controller may extract the voice search keywords according to at least one extraction reference rate among the keyword's search frequency, popularity, latestness, exposure time, and voice search success rate. have.

The controller, when extracting a plurality of voice search keywords from the speaker's voice, searches for the voice search keyword from the speaker's voice, searches for the searched voice search keyword, popularity, latestness, exposure time, and voice search success rate. The extracted reference rate may be calculated, and if the calculated extraction reference rate is less than the preset reference value, the searched voice search keyword may be ignored, and if the calculated extraction reference rate is greater than or equal to the preset reference value, the searched voice search keyword may be extracted. .

In addition, the controller, when generating a personal search pattern guide corresponding to the classified speaker, collects the recommendation information of at least one of recommended content, recommended advertising, recommended voice search keywords, recommended new service promotions corresponding to the classified speakers. In addition, a personal search pattern guide including the collected recommendation information may be generated.

Herein, when generating the personal search pattern guide corresponding to the classified speaker, the control unit may display a first area displaying a voice search keyword classified into a plurality of items, a second area displaying recommendation information, and a recommendation advertisement. The personal search pattern guide including at least one of the third area and the fourth area displaying the guide message may be generated.

As described above, the present invention obtains the personal profile information of the authenticated speaker by performing speaker authentication corresponding to the speaker voice, and generates and provides a personal search pattern guide based on the obtained personal profile information, thereby increasing the voice search success rate. Promote products and services using personal search pattern guides.

That is, the present invention can increase the search success rate by personalizing the search pattern by using the speaker profile information through speaker authentication and providing an optimal search pattern guide on the TV screen, and real-time of the personalized search pattern guide through speaker authentication. Providing product advertisement and service promotion can be provided through the provision.

In addition, the present invention can induce a user to search the revenue contribution content, to induce specific home IoT control, to provide a predetermined new service promotion, advertisement of the relevant affiliated companies such as restaurants It may be provided, or a popular search term may be provided for the convenience of search, or a search pattern may be induced to analyze the search failure cases and reflect the same, thereby increasing the search success rate.

3 is a diagram illustrating a personal search pattern guide displayed on the multimedia apparatus of FIG. 1, and FIG. 4 is a diagram for describing a voice search keyword region of the personal search pattern guide of FIG. 3.

As illustrated in FIG. 3, the present invention may generate a personal search pattern guide 400 based on the obtained personal profile information and display the personal search pattern guide 400 on the display screen 110 of the multimedia apparatus 100.

For example, the personal search pattern guide 400 may include a first area 410 displaying a voice search keyword classified into a plurality of items, a second area 420 displaying recommended information, and a third displaying a recommended advertisement. The area 430 and the fourth area 440 displaying the guide message may be included, but are not limited thereto.

As illustrated in FIG. 4, the first area 410 of the personal search pattern guide 400 includes a plurality of items 412, voice search keywords 414 corresponding to each item, and each voice keyword. It may include a corresponding spoken sentence 416.

The reason is that by providing the voice search keyword and its spoken sentence together for each item, the user can easily and quickly recognize and perform the voice search in various fields, thereby providing improved user convenience and increasing the search success rate. have.

For example, the channel name item display area 412-1 may include a channel name voice search keyword 414 and a representative spoken sentence 416, and the channel number item display area 412-2 may include a channel number voice search. The keyword 414 and the representative spoken sentence 416 may be included, and the content name item search area 412-3 may include the content name voice search keyword 414 and the representative spoken sentence 416.

The content genre item display area 412-4 may include a content genre voice search keyword 414 and a representative spoken sentence 416, and the person name item display area 412-5 may include a person voice search keyword. 414 and a representative spoken sentence 416, and the search engine name item display area 412-6 may include a search engine name voice search keyword 414 and a representative spoken sentence 416. The search term item display region 412-7 may include a search term voice search keyword 414 and a representative spoken sentence 416.

In addition, the third area 430 of the personal search pattern guide 400 may display an advertisement related to recommendation information displayed on the second area 420.

The reason is that through recommendation information displayed in the second area 420 and related advertisements displayed in the third area 430, the user can be encouraged to search for the sales contribution content. This is because sales contribution can be increased.

In some cases, the third region 430 of the personal search pattern guide 400 may display an advertisement that is not related to the recommendation information of the second region 420.

The reason is that the recommendation information displayed in the second area 420 and other irrelevant advertisements displayed in the third area 430 may induce a user to search contents of various fields, thereby promoting a product or service. This is because it can increase sales contribution to the company.

In addition, the fourth area 440 of the personal search pattern guide 400 may include a guide message and a list of previous spoken sentence history.

The reason is that the user can quickly and easily perform a voice search based on the guide message and the previous spoken sentence, thereby providing improved user convenience and increasing the search success rate.

Meanwhile, when generating a personal search pattern guide, the present invention extracts a plurality of voice search keywords from the obtained personal profile information, classifies the extracted plurality of voice search keywords by item, and generates a plurality of voices classified by items. A personal search pattern guide with search keywords can be created.

In the present invention, when extracting a plurality of voice search keywords from the acquired personal profile information, the voice search keyword is searched from the acquired personal profile information, the search frequency, popularity, the latest degree, An extraction reference rate of at least one of the exposure time and the voice search success rate is calculated, and if the calculated extraction reference rate is less than the preset reference value, the searched voice search keyword is ignored. Search keywords can be extracted.

As such, the reason for extracting the voice search keyword is to provide a voice search keyword that can be optimized for an individual user and increase a search success rate.

Herein, in the present invention, when the searched voice search keyword is ignored, the searched voice search keyword is a searched voice if the search reference rate, popularity, recency, exposure time, and extraction reference rate for the voice search success rate are all less than a predetermined reference value. You can ignore the search keyword.

The reason is that by removing the voice search keywords that are unnecessary for the user or having low voice search success rates, only the voice search keywords optimized for the user can be provided to increase the voice search success rates.

In some cases, when the number of searched voice search keywords is small, the searched voice search keyword is performed when at least one of the search frequency, popularity, recency, exposure time, and extraction reference rate for the voice search success rate is less than a preset reference value. Can be ignored.

The reason is to provide a user with a minimum voice search keyword so that voice search can be performed easily and conveniently.

In the present invention, when the searched voice search keyword is extracted, the searched voice search keyword is at least one of a reference criterion for the search frequency, popularity, latestness, exposure time, and voice search success rate. In this case, the searched voice search keyword can be extracted.

In addition, the present invention, when classifying the extracted plurality of voice search keywords by item, the extracted voice search keywords, channel name item, channel number item, content name item, content genre item, person name item, search engine name item, The search term may be classified into at least one item.

The reason for this is that voice search keywords are categorized for each item and provided to the user, whereby the user can easily and conveniently perform voice search in various fields.

Next, when classifying the extracted plurality of voice search keywords by item, if the extracted plurality of voice search keywords are classified by item, the priority of the voice search keywords by each item is determined, and the determined priority According to each item, voice search keywords can be arranged.

The reason is to provide an optimized voice search keyword to the user to perform a voice search easily and conveniently and to increase the voice search success rate.

Here, when determining the priority of the voice search keywords for each item, the present invention may determine the priority based on the search frequency, popularity, latestness, exposure time, and voice search success rate for the voice search keywords.

In some cases, the present invention, when determining the priority of the voice search keywords for each item, the search frequency ranking item, the popularity ranking item, the latest ranking item, the exposure time ranking item, and the voice for the voice search keyword Among the search success rate ranking items, the first priority is determined according to a preset priority item. If there is a voice search keyword having the same determined first priority, the second order is determined according to the calculation rate for the ranking item including the voice search keyword. You can also determine the priority.

The reason is to provide the user with the most optimized voice search keyword to perform voice search easily and conveniently and to increase the voice search success rate.

As another case, the present invention, when extracting a plurality of voice search keywords from the acquired personal profile information, it is possible to analyze the speaker's voice characteristics, and extract a voice search keyword corresponding to the voice characteristics analyzed from the personal profile information. have.

The reason for this is to provide the user with the most optimized voice search keyword to perform the voice search easily and conveniently.

As another case, the present invention, when extracting a plurality of voice search keywords from the obtained personal profile information, by first analyzing the voice characteristics of the speaker to extract the voice search keywords corresponding to the voice characteristics analyzed from the personal profile information Among the first extracted voice search keywords, the voice search keywords may be secondly extracted according to at least one extraction reference rate among the search frequency, popularity, latestness, exposure time, and voice search success rate for the voice search keywords. .

The reason for this is to provide the user with the most optimized voice search keyword to perform the voice search and increase the voice search success rate easily and conveniently.

Meanwhile, when the personal search pattern guide is generated based on the acquired personal profile information, the present invention recommends at least one of recommended content, recommended advertisement, recommended voice search keyword, and recommended new service promotion based on the obtained personal profile information. Information may be collected and a personal search pattern guide including the collected recommended information may be generated.

5 to 9 are flowcharts illustrating a method for providing a personal search pattern guide according to an embodiment of the present invention.

5 to 9, the apparatus for providing a personal search pattern guide according to the present invention may first receive a speaker voice such as a start word (S100).

Next, the present invention, it is possible to determine whether the input speaker voice is a start word (S200).

Subsequently, when the speaker voice is the active word, the speaker authentication corresponding to the speaker voice may be performed (S300).

Here, the present invention, when performing the speaker authentication corresponding to the speaker voice, transmits a speaker voice signal and a speaker authentication request signal for the speaker voice corresponding to the starting word to the server, the speaker authentication for the speaker authentication request from the server Receives information and may perform speaker authentication based on the received speaker authentication information.

In some cases, when the speaker authentication corresponding to the speaker voice is performed, the present invention performs speaker authentication by directly comparing the speaker voice signal corresponding to the starting word with a speaker voice signal registered in advance, and extracts speaker authentication information. In addition, the speaker authentication may be performed based on the extracted speaker authentication information.

Here, the speaker voice signal registered in advance may be extracted from the speaker voice registration table stored in advance in the storage unit.

Then, the present invention, it can be confirmed whether the speaker authentication is completed (S400).

Next, when the speaker authentication is completed, the present invention may obtain personal profile information of the authenticated speaker (S500).

Herein, when acquiring the personal profile information of the authenticated speaker, the present invention may transmit the speaker's authentication information and the personal profile information request signal to the server, and obtain the speaker's personal profile information received from the server.

In some cases, when acquiring the personal profile information of the authenticated speaker, the present invention may acquire personal profile information corresponding to the authenticated speaker from the personal profile information table previously stored in the storage unit based on the speaker's authentication information. .

For example, the personal profile information may include identification information of the speaker, viewing environment information of the speaker, viewing history information of the speaker, and search history information of the speaker.

Subsequently, the present invention may generate a personal search pattern guide based on the obtained personal profile information (S600).

In addition, the present invention may transmit the generated personal search pattern guide (S700).

As illustrated in FIG. 6, the generating of the personal search pattern guide based on the obtained personal profile information (S600) may perform the following steps.

That is, when the personal profile information is obtained, a plurality of voice search keywords may be extracted from the obtained personal profile information (S610).

In operation S620, the extracted plurality of voice search keywords may be classified by item.

Next, the present invention can generate a personal search pattern guide having a plurality of voice search keywords classified by item (S630).

Here, as an example, as shown in FIG. 7, when extracting a plurality of voice search keywords from the obtained personal profile information, the present invention searches for a voice search keyword from the obtained personal profile information (S612). ).

Then, the present invention calculates at least one extraction reference rate among the search frequency, popularity, latestness, exposure time, and voice search success rate for the searched voice search keyword (S614).

Next, the present invention checks whether the calculated extraction reference ratio is equal to or greater than a preset reference value (S616).

Here, the present invention extracts the searched voice search keyword if the calculated extraction reference ratio is equal to or greater than a preset reference value (S618).

In the present invention, if the calculated extraction reference ratio is less than the preset reference value, the searched voice search keyword can be ignored (S619).

In another embodiment, as shown in FIG. 8, when extracting a plurality of voice search keywords from the acquired personal profile information, the present invention analyzes the speaker's voice characteristics and applies the voice characteristics analyzed from the personal profile information. Corresponding voice search keywords may be extracted.

That is, in the present invention, when analyzing the speaker's voice characteristic, the speaker voice signal and the speaker voice characteristic request signal may first be transmitted to the server (S622).

In the present invention, the speaker voice characteristic information of the speaker voice signal may be received from the server (S626).

Next, the present invention may analyze the speaker's voice characteristic based on the received speaker voice characteristic information (S626).

Subsequently, the present invention may extract a voice search keyword corresponding to the voice characteristic analyzed from the personal profile information (S628).

In some cases, when analyzing the speaker's voice characteristics, the present invention may analyze the speaker's voice characteristics by itself without a server request and extract a voice search keyword corresponding to the voice characteristics analyzed from the personal profile information. .

In another embodiment, as shown in FIG. 9, when extracting a plurality of voice search keywords from the obtained personal profile information, the voice characteristic analyzed from the personal profile information is first analyzed by analyzing the speaker's voice characteristics. The voice search keyword corresponding to the first step is extracted, and among the first extracted voice search keywords, the voice search keyword is searched according to at least one extraction criterion rate among search frequency, popularity, recency, exposure time, and voice search success rate. The voice search keyword may be extracted secondarily.

That is, according to the present invention, the speaker voice signal and the speaker voice characteristic request signal may first be transmitted to the server (S631).

In the present invention, the speaker voice characteristic information of the speaker voice signal can be received from the server (S632).

Next, according to the present invention, the speaker's voice characteristic may be analyzed based on the received speaker voice characteristic information (S633).

Subsequently, the present invention may first extract a voice search keyword corresponding to the voice characteristic analyzed from the personal profile information (S634).

The present invention calculates at least one extraction reference rate among the search frequency, popularity, latestness, exposure time, and voice search success rate for the first extracted voice search keyword (S635).

Next, the present invention checks whether the calculated extraction reference ratio is equal to or greater than the preset reference value (S636).

Here, in the present invention, if the calculated extraction reference ratio is equal to or more than the preset reference value, the searched voice search keyword is secondarily extracted (S637).

The present invention may ignore the searched voice search keyword if the calculated extraction reference ratio is less than the preset reference value (S638).

Meanwhile, in FIG. 6, in step S620 of extracting the plurality of extracted voice search keywords by item, when the extracted plurality of voice search keywords are classified by item, the priority of the voice search keywords is determined by each item. The voice search keywords may be arranged for each item according to the determined priority.

In one embodiment, when determining the priority of the voice search keywords for each item, the present invention prioritizes the priority based on the frequency, popularity, recency, exposure time, and voice success rate of the voice search keywords. You can decide.

The reason is to provide an optimized voice search keyword to the user to perform a voice search easily and conveniently and to increase the voice search success rate.

In another embodiment, the present invention, when determining the priority of the voice search keywords for each item, the search frequency ranking item, the popularity ranking item, the latest ranking item, the exposure time ranking item for the voice search keyword, and The first priority is determined according to a preset priority item among the voice search success rate ranking items. If there are voice search keywords having the same determined first priority, the first priority is determined according to the calculation rate for the rank item including the voice search keyword. The car priority may be determined.

The reason is to provide the user with the most optimized voice search keyword to perform voice search easily and conveniently and to increase the voice search success rate.

In addition, as shown in Figure 6 of the present invention, the step of generating a personal search pattern guide based on the obtained personal profile information (S630), based on the obtained personal profile information, recommended content, recommended ads, recommended voice search keywords, recommended new At least one recommendation information of the service promotion may be collected, and a personal search pattern guide including the collected recommendation information may be generated.

Here, the generating of the personal search pattern guide based on the obtained personal profile information (S630) may include: a first region displaying a voice search keyword classified into a plurality of items, a second region displaying recommendation information, and a recommendation advertisement. The personal search pattern guide including at least one of the third region to be displayed and the fourth region to display the guide message may be generated.

The reason for including the first region is that by providing the voice search keyword and its spoken sentence together for each item, the user can easily and quickly recognize and perform the voice search in various fields, thereby providing improved user convenience and a search success rate. Can increase.

In addition, the reason for including the second and third areas may include a recommendation information displayed in the second area and a recommendation advertisement displayed in the third area, thereby inducing a user to search for sales contribution content. This is because the company can increase its sales contribution to.

In addition, the reason for including the fourth region is that the user can easily and quickly perform a voice search based on the guide message and the previous spoken sentence, thereby providing improved user convenience and increasing the search success rate.

In another embodiment, the apparatus for providing a personal search pattern guide according to the present invention, when receiving a speaker voice, performs speaker classification corresponding to the input speaker voice, checks whether speaker classification is completed, and then performs speaker classification. Upon completion, a personal search pattern guide corresponding to the classified speaker may be generated and the generated personal search pattern guide may be transmitted.

For example, the apparatus for providing a personal search pattern guide according to the present invention may classify the speaker into at least one of gender, age group, mood state, health condition, and family member.

For example, you can classify gender, age group, mood, and health status by information contained in voice such as frequency, amplitude of voice, and the number of family members by checking the number of different voices input through multimedia device or server. You can check.

In addition, in the apparatus for providing a personal search pattern guide, speakers corresponding to the speaker voice may be superimposed on a plurality of classification items.

The apparatus for providing a search pattern guide may extract a plurality of voice search keywords from the speaker voice and generate a personal search pattern guide based on the extracted voice search keyword when generating a personal search pattern guide corresponding to the classified speaker. Can be.

Here, when the search pattern guide providing apparatus extracts a plurality of voice search keywords from the speaker's voice, the voice search keyword is determined according to at least one extraction reference rate among the keyword's search frequency, popularity, latestness, exposure time, and voice search success rate. Can be extracted.

When the search pattern guide providing apparatus extracts a plurality of voice search keywords from the speaker's voice, the voice search keyword is searched from the speaker's voice, and the search frequency, popularity, latestness, exposure time, And extracting a reference rate of at least one of the voice search success rates, and disregarding the searched voice search keyword if the calculated extraction reference rate is less than the preset reference value, and retrieving the searched voice search keyword if the calculated extraction reference rate is greater than or equal to the preset reference value. Can be extracted.

In addition, the search pattern guide providing apparatus, when generating a personal search pattern guide corresponding to the classified speakers, at least one of the recommended content, recommended advertisements, recommended voice search keywords, recommended new service promotions corresponding to the classified speakers The recommendation information may be collected, and a personal search pattern guide including the collected recommendation information may be generated.

Here, the search pattern guide providing apparatus, when generating a personal search pattern guide corresponding to the classified speaker, a first area for displaying a voice search keyword classified into a plurality of items, a second area for displaying recommendation information, and a recommendation A personal search pattern guide including at least one of a third area displaying an advertisement and a fourth area displaying a guide message may be generated.

As another embodiment, in the personal search pattern guide providing system of the present invention, when the speaker voice is input from the personal search pattern guide device, the server performs speaker classification corresponding to the input speaker voice, and speaker classification is completed. When the speaker classification is completed, the personal search pattern guide corresponding to the classified speaker may be generated, and the generated personal search pattern guide may be transmitted to the personal search pattern guide device.

Here, the personal search pattern guide device may transmit the input speaker voice to the server and transmit the personal information pattern guide received from the server to the multimedia device.

For example, when performing speaker classification, the server of the present invention may classify the speaker classification into at least one of sex, age group, mood state, health condition, and family member.

For example, gender, age group, mood state, and health status can be classified using information included in the voice such as frequency and amplitude of the voice, and the number of different voices input through the multimedia device or the server can be used to check the family members. You can check the number.

In addition, the server may be classified by the speaker corresponding to the speaker voice superimposed on a plurality of classification items.

In addition, when generating a personal search pattern guide corresponding to the classified speaker, the server may extract a plurality of voice search keywords from the speaker voice and generate a personal search pattern guide based on the extracted voice search keyword.

Here, when extracting a plurality of voice search keywords from the speaker's voice, the server may extract the voice search keywords according to at least one extraction reference rate among the keyword's search frequency, popularity, latestness, exposure time, and voice search success rate. have.

When the server extracts a plurality of voice search keywords from the speaker's voice, the server searches the voice search keyword from the speaker's voice, and the frequency, popularity, recency, exposure time, and voice search success rate of the searched voice search keyword. The extracted reference rate may be calculated, and if the calculated extraction reference rate is less than the preset reference value, the searched voice search keyword may be ignored, and if the calculated extraction reference rate is greater than or equal to the preset reference value, the searched voice search keyword may be extracted. .

In addition, when the server generates a personal search pattern guide corresponding to the classified speaker, the server collects recommendation information of at least one of recommended content, recommended advertisement, recommended voice search keyword, and recommended new service promotion corresponding to the classified speaker. In addition, a personal search pattern guide including the collected recommendation information may be generated.

Here, when generating the personal search pattern guide corresponding to the classified speaker, the server displays a first area displaying a voice search keyword classified into a plurality of items, a second area displaying recommendation information, and a recommendation advertisement. The personal search pattern guide including at least one of the third area and the fourth area displaying the guide message may be generated.

As described above, the present invention obtains the personal profile information of the authenticated speaker by performing speaker authentication corresponding to the speaker voice, and generates and provides a personal search pattern guide based on the obtained personal profile information, thereby increasing the voice search success rate. Promote products and services using personal search pattern guides.

That is, the present invention can increase the search success rate by personalizing the search pattern by using the speaker profile information through speaker authentication and providing an optimal search pattern guide on the TV screen, and real-time of the personalized search pattern guide through speaker authentication. Providing product advertisement and service promotion can be provided through the provision.

In addition, the present invention can induce a user to search the revenue contribution content, to induce specific home IoT control, to provide a predetermined new service promotion, advertisement of the relevant affiliated companies such as restaurants It may be provided, or a popular search term may be provided for the convenience of search, or a search pattern may be induced to analyze the search failure cases and reflect the same, thereby increasing the search success rate.

Various embodiments described herein may be implemented in a recording medium readable by a computer or similar device using, for example, software, hardware or a combination thereof.

According to a hardware implementation, the embodiments described herein include application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), and the like. It may be implemented using at least one of processors, controllers, micro-controllers, microprocessors, and electrical units for performing the functions. It may be implemented by the controller 180.

In a software implementation, embodiments such as procedures or functions may be implemented with separate software modules to perform at least one function or operation. The software code may be implemented by a software application written in a suitable programming language. In addition, the software code may be stored in the memory 150 and loaded and executed by the controller 180.

In the above-described embodiment, the apparatus for providing a personal search pattern guide may include one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), and field programs. It can be realized by a possible gate array (FPGA), controller, microcontroller, microprocessor or other electronic component.

The method according to the embodiment described above may be stored in a computer-readable recording medium that is produced as a program for execution on a computer, and examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape It may also be implemented in the form of a floppy disk, optical data storage device.

The computer readable recording medium can be distributed over network coupled computer systems so that the computer readable code is stored and executed in a distributed fashion. In addition, functional programs, codes, and code segments for implementing the above-described method may be easily inferred by programmers in the art to which the embodiments belong.

It is apparent to those skilled in the art that the present invention can be embodied in other specific forms without departing from the spirit and essential features of the present invention.

Accordingly, the above detailed description should not be construed as limiting in all aspects and should be considered as illustrative. The scope of the invention should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent scope of the invention are included in the scope of the invention.

100: multimedia device
200: server
300: device for providing a personal search pattern guide
310: input unit
320: starting word identification unit
330: communication unit
340: control unit

Claims (37)

In the device for providing a personal search pattern guide that is connected to the multimedia device and the server,
An input unit for receiving a speaker voice;
A start word identification unit for processing the input speaker voice to identify a start word;
A communication unit for transmitting a personal search pattern guide to the multimedia device; And,
A control unit for controlling the input unit, a start word identification unit, and a communication unit,
The control unit,
When the speaker voice is input, the starter language identification unit is controlled to identify whether the input speaker voice is a starting word, and when the speaker voice is a starting word, a speaker authentication corresponding to the speaker voice is performed, and the speaker authentication is completed. Control the communication unit to obtain personal profile information of the authenticated speaker, generate a personal search pattern guide based on the obtained personal profile information, and transmit the generated personal search pattern guide to the multimedia apparatus. Personal search pattern guide providing device. The method of claim 1, wherein the control unit,
When performing speaker authentication corresponding to the speaker voice, controlling the communication unit to transmit a speaker voice signal and a speaker authentication request signal for the speaker voice corresponding to the starting word to the server, and the speaker authentication request from the server. Personal search pattern guide providing apparatus for receiving the speaker authentication information for. The method of claim 1, wherein the control unit,
When the speaker authentication corresponding to the speaker voice is performed, the speaker authentication is performed by directly comparing the speaker voice signal corresponding to the starting word with a speaker voice signal registered in advance, and extracting speaker authentication information. Search pattern guide providing device. The method of claim 1, wherein the control unit,
When acquiring the personal profile information of the authenticated speaker, the personal search pattern which obtains personal profile information corresponding to the authenticated speaker from a personal profile information table previously stored in a storage unit based on the authentication information of the speaker. Guide provision device. The method of claim 1, wherein the personal profile information,
And a speaker's identification information, a speaker's viewing environment information, a speaker's viewing history information, and a speaker's search history information. The method of claim 5, wherein the identification information of the speaker,
Personal search pattern guide providing apparatus comprising the speaker's age, gender, and residential area. According to claim 5, The viewing environment information of the speaker,
The personal search pattern guide providing apparatus comprising preferred channel information, volume information, audience rating information, image mode information, audio mode information, and viewing reservation information. The method of claim 1, wherein the control unit,
When generating a personal search pattern guide based on the acquired personal profile information, a plurality of voice search keywords are extracted from the obtained personal profile information, the extracted plurality of voice search keywords are classified by item, and each item And a personal search pattern guide having a plurality of classified voice search keywords. The method of claim 8, wherein the control unit,
When extracting a plurality of voice search keywords from the obtained personal profile information, the voice search keywords are extracted according to at least one extraction reference rate among the keyword's search frequency, popularity, latestness, exposure time, and voice search success rate. Personal search pattern guide providing device. The method of claim 9, wherein the control unit,
When extracting a plurality of voice search keywords from the acquired personal profile information, a voice search keyword is searched from the obtained personal profile information, and the search frequency, popularity, latestness, exposure time, And extracting a reference rate of at least one of a voice search success rate, and disregarding the searched voice search keyword if the calculated extraction reference rate is less than a preset reference value, and if the calculated extraction reference rate is greater than or equal to a preset reference value, Personal search pattern guide providing device, characterized in that for extracting a voice search keyword. The method of claim 8, wherein the control unit,
When classifying the extracted plurality of voice search keywords by item, the extracted voice search keywords are selected from among a channel name item, a channel number item, a content name item, a content genre item, a person name item, a search engine name item, and a search word item. Personal search pattern guide providing apparatus characterized in that it is classified into at least one item. The method of claim 11, wherein the voice search keyword,
Personal search pattern guide providing apparatus, characterized in that the plurality of items are classified in duplicate. The method of claim 8, wherein the control unit,
When classifying the extracted plurality of voice search keywords by item, if the extracted plurality of voice search keywords are classified by item, the priority of the voice search keywords is determined for each item and according to the determined priority. Personal search pattern guide providing apparatus characterized by arranging voice search keywords for each item. The method of claim 8, wherein the control unit,
When extracting a plurality of voice search keywords from the obtained personal profile information, the voice characteristic of the speaker is analyzed, and a voice search keyword corresponding to the analyzed voice characteristic is extracted from the personal profile information. Search pattern guide providing device. The method of claim 14, wherein the speaker's voice characteristics,
Personal search pattern guide providing apparatus, characterized in that at least one of the speaker's age, gender and health status. The method of claim 8, wherein the control unit,
When extracting a plurality of voice search keywords from the obtained personal profile information, the voice characteristic of the speaker is analyzed to first extract a voice search keyword corresponding to the analyzed voice characteristic from the personal profile information,
Among the first extracted voice search keywords, second extraction of the voice search keyword is performed based on at least one extraction criterion rate among the search frequency, popularity, latestness, exposure time, and voice search success rate for the voice search keyword. Personal search pattern guide providing device characterized in that. The method of claim 16, wherein the control unit,
When extracting the second voice search keywords from the first extracted voice search keywords, at least one of the search frequency, popularity, latestness, exposure time, and voice search success rate for the first extracted voice search keywords. An extraction reference rate is calculated, and if the calculated extraction reference rate is less than a predetermined reference value, the first extracted voice search keyword is ignored. Personal search pattern guide providing device, characterized in that. The method of claim 1, wherein the control unit,
When generating a personal search pattern guide based on the acquired personal profile information, collecting at least one recommendation information of recommended content, recommended advertisement, recommended voice search keyword, recommended new service promotion, and the like based on the obtained personal profile information. And generating a personal search pattern guide including the collected recommended information. The method of claim 1, wherein the control unit,
When generating a personal search pattern guide based on the obtained personal profile information, a first area displaying a voice search keyword classified into a plurality of items, a second area displaying recommendation information, and a third area displaying recommendation advertisements And a personal search pattern guide including at least one of a fourth area displaying a guide message. In the device for providing a personal search pattern guide that is connected to the multimedia device,
An input unit for receiving a speaker voice;
A communication unit for transmitting a personal search pattern guide to the multimedia device; And,
A control unit for controlling the input unit and the communication unit,
The control unit,
When the speaker voice is input, a speaker classification corresponding to the speaker voice is performed, and when the speaker classification is completed, a personal search pattern guide corresponding to the classified speaker is generated, and the generated personal search pattern guide is used for the multimedia apparatus. Personal search pattern guide providing device characterized in that for controlling the communication unit to transmit to. The method of claim 20, wherein the control unit,
When the speaker classification corresponding to the speaker voice is performed, the speaker classification is classified into at least one of gender, age group, mood state, health state, and family member. The method of claim 21, wherein the control unit,
And a speaker corresponding to the speaker voice is classified and superimposed on a plurality of classification items. The method of claim 20, wherein the control unit,
When generating a personal search pattern guide corresponding to the classified speaker, a plurality of voice search keywords are extracted from the speaker voice, and a personal search pattern guide is generated based on the extracted voice search keywords.
When extracting a plurality of voice search keywords from the speaker's voice, a voice search keyword is extracted according to at least one extraction reference rate of the keyword's search frequency, popularity, latestness, exposure time, and voice search success rate. Search pattern guide providing device. The method of claim 23, wherein the control unit,
When extracting a plurality of voice search keywords from the speaker's voice, a voice search keyword is searched from the speaker's voice, and at least one of a search frequency, popularity, recency, exposure time, and voice search success rate for the searched voice search keyword is obtained. Calculating any one extraction reference rate, and if the calculated extraction reference rate is less than a predetermined reference value, ignores the searched voice search keyword; Personal search pattern guide providing device, characterized in that. The method of claim 20, wherein the control unit,
When generating a personal search pattern guide corresponding to the categorized speaker, collecting recommendation information of at least one of recommended content, recommended advertisement, recommended voice search keyword, and recommended new service promotion corresponding to the categorized speaker; Apparatus for providing a personal search pattern guide, characterized in that for generating a personal search pattern guide including the collected recommended information. The method of claim 20, wherein the control unit,
When generating a personal search pattern guide corresponding to the classified speaker, a first area displaying a voice search keyword classified into a plurality of items, a second area displaying recommendation information, a third area displaying a recommendation advertisement, And generating a personal search pattern guide including at least one of the fourth areas displaying the guide message. A personal search pattern guide providing apparatus for authenticating an input speaker voice and generating a personal information pattern guide based on the authenticated speaker's personal profile information;
A multimedia device communicatively connected to the personal search pattern guide providing apparatus and displaying a personal search pattern guide received from the personal search pattern guide providing apparatus; And,
A server that is communicatively connected to the personal search pattern guide providing apparatus and provides personal profile information of the speaker according to a request of the personal search pattern guide providing apparatus,
The personal search pattern guide providing apparatus,
When the speaker voice is input, it is identified whether the input speaker voice is a starting word, and if the speaker voice is a starting word, a speaker authentication corresponding to the speaker voice is performed. When the speaker authentication is completed, the individual of the authenticated speaker is completed. And obtaining profile information, generating a personal search pattern guide based on the obtained personal profile information, and transmitting the generated personal search pattern guide to the multimedia apparatus. A multimedia device displaying a personal search pattern guide;
A server providing the personal information pattern guide; And,
And a search pattern guide providing device configured to transmit a speaker voice, which is connected in communication with the multimedia apparatus and a server, to the server, and to transmit the personal information pattern guide received from the server to the multimedia apparatus.
The server,
When the speaker voice is received, a speaker classification corresponding to the speaker voice is performed, and when the speaker classification is completed, a personal search pattern guide corresponding to the classified speaker is generated, and the generated personal search pattern guide is converted into the search pattern. The personal search pattern guide providing system, characterized in that for controlling the communication unit to transmit to a guide providing device. The method of claim 28, wherein the server,
When the speaker classification corresponding to the speaker voice is performed, the speaker classification is classified into at least one of gender, age group, mood state, health state, and family member. The method of claim 28, wherein the server,
And a speaker corresponding to the speaker voice is classified and superimposed on a plurality of classification items. The method of claim 28, wherein the server,
When generating a personal search pattern guide corresponding to the classified speaker, a plurality of voice search keywords are extracted from the speaker voice, and a personal search pattern guide is generated based on the extracted voice search keywords.
When extracting a plurality of voice search keywords from the speaker's voice, a voice search keyword is extracted according to at least one extraction reference rate of the keyword's search frequency, popularity, latestness, exposure time, and voice search success rate. Search pattern guide providing system. The server of claim 31, wherein the server comprises:
When extracting a plurality of voice search keywords from the speaker's voice, a voice search keyword is searched from the speaker's voice, and at least one of a search frequency, popularity, recency, exposure time, and voice search success rate for the searched voice search keyword is obtained. Calculating any one extraction reference rate, and if the calculated extraction reference rate is less than a predetermined reference value, ignores the searched voice search keyword; Personal search pattern guide providing system, characterized in that. The method of claim 28, wherein the server,
When generating a personal search pattern guide corresponding to the categorized speaker, collecting recommendation information of at least one of recommended content, recommended advertisement, recommended voice search keyword, and recommended new service promotion corresponding to the categorized speaker; Personal search pattern guide providing system, characterized in that for generating a personal search pattern guide including the collected recommended information. The method of claim 28, wherein the server,
When generating a personal search pattern guide corresponding to the classified speaker, a first area displaying a voice search keyword classified into a plurality of items, a second area displaying recommendation information, a third area displaying a recommendation advertisement, And generating a personal search pattern guide including at least one of the fourth areas displaying the guide message. A method for providing a personal search pattern guide of a device that provides a personal search pattern guide that is connected to a multimedia device and a server.
Receiving a speaker voice;
Checking whether the input speaker voice is a spoken word;
Performing speaker authentication corresponding to the speaker voice if the speaker voice is a starting word;
Confirming whether the speaker authentication is completed;
Acquiring personal profile information of the authenticated speaker when the speaker authentication is completed;
Generating a personal search pattern guide based on the obtained personal profile information; And,
The personal search pattern guide providing method comprising the step of transmitting the generated personal search pattern guide. A method for providing a personal search pattern guide of a device that provides a personal search pattern guide that is connected to a multimedia device and a server.
Receiving a speaker voice;
Performing a speaker classification corresponding to the input speaker voice;
Confirming whether the speaker classification is completed;
Generating a personal search pattern guide corresponding to the classified speakers when the speaker classification is completed; And,
The personal search pattern guide providing method comprising the step of transmitting the generated personal search pattern guide. A computer-readable recording medium having recorded thereon a program for executing the method according to any one of claims 35 to 36.

Images