JP5707346B2 - Information providing apparatus, program thereof, and information providing system - Google Patents

Description

  Embodiments described herein relate generally to an information providing apparatus that outputs an image and sound for advertising a product, a program thereof, and an information providing system.

  There is known a digital signage that displays an advertisement image on a display and informs the public.

JP 2011-210238 A

  Digital signage as described above targets an unspecified number of people for advertising. For this reason, information may not be accurately transmitted to the person who sees the display. In this case, sufficient advertising effect cannot be obtained.

  An object of an embodiment of the present invention is to provide an information providing apparatus, a program therefor, and an information providing system that can accurately convey information to a viewer who sees the display and can obtain a high advertising effect.

An information providing apparatus according to an embodiment of the present invention includes a display unit that displays an advertisement image, a microphone for sound collection, a voice recognition unit that recognizes a voice from sound collected by the microphone, and the voice recognition unit. The number of persons in front of the display means is detected from the voice recognized by the voice recognition means, and the voice of the display means is determined based on the voice with the highest input volume among the voices recognized by the voice recognition means within a predetermined time. Detecting means for detecting an attribute of a person in front ; audio generating means for generating a sound having characteristics related to the number and attributes detected by the detecting means with respect to an image displayed on the display means; Control means for outputting the sound generated by the sound generation means and variably setting the volume of the sound output according to the number detected by the detection means.

The block diagram which shows the structure of one Embodiment. The flowchart which shows operation | movement of one Embodiment. The figure which shows the modification of one Embodiment.

Hereinafter, an embodiment will be described with reference to the drawings.
In FIG. 1, reference numeral 1 denotes a display unit having a display (display means / display device) 2 for displaying an advertisement image 2, a microphone 3 for sound collection, and a speaker 4 for sound output on the front surface. The display unit 1 is installed on a wall surface of a building, a loading platform of a vehicle, or the like for advertising a product. Alternatively, as the display unit 1, a merchandise sales processing device placed on a cash register counter of a store, for example, a customer side display of a POS terminal is used. When the customer side display of the POS terminal is used as the display unit 1, the POS terminal includes the information providing apparatus.

  On the other hand, the control unit 10 includes an image generation unit 11 that generates an advertisement image, a speech recognition unit 12 that recognizes speech from sound collected by the microphone 3, a speech synthesis unit 13 that generates advertisement speech, an image A data input unit 14 for inputting data necessary for voice generation, an operation unit 15 for setting operating conditions, and a network interface 16 are connected. The network interface 16 is connected to the server 21 via the communication network 20.

  The voice recognition unit 12 analyzes the sound collected by the microphone 3 to extract and recognize the voice included in the collected sound. The voice synthesizer 13 synthesizes the voice having the content instructed from the control unit 10. The server 21 transfers the image data necessary for generating the advertisement image and the sound data necessary for generating the advertisement sound to the control unit 10 via the communication network 20.

  The display unit 1, the image generation unit 11, the voice recognition unit 12, the voice synthesis unit 13, the data input unit 14, the operation unit 15, and the network interface 16 generate an advertisement image and voice and inform the public of it. An information providing apparatus for digital signage is configured. The control unit 10, the image generation unit 11, the voice recognition unit 12, the voice synthesis unit 13, the data input unit 14, the operation unit 15, and the network interface 16 are configured by a computer.

The control unit 10 includes the following means (1) to (4) as main functions based on programs stored in the internal memory in advance.
(1) Detection means for detecting the number and attributes of persons (including persons passing in front) in front of the display unit 1 from the voice recognized by the voice recognition unit 12. Specifically, the voice recognized by the voice recognition unit 12 is monitored for a certain period of time, and the number of persons having different characteristics within a certain period of time is detected as the number of people in front of the display unit 1. Of the voices recognized by the voice recognition unit 12 within a certain period of time, the voice with the highest input volume and the age, sex and foreign language stored in the internal memory in advance (English, Chinese, Korean) Etc.) by collating with a plurality of types of voice model data, and analyzing the frequency and speed of the voice recognized by the voice recognition unit 12 and adding the analysis result to the above-mentioned collation result as necessary, The attributes of the person in front of the display unit 1 are elderly people, children, ordinary women (non-aged women), general men (non-aged men), foreigners (English-speaking people, Chinese-speaking people, Korean-speaking people) ).

  (2) Image generation means for generating an advertisement image to be displayed on the display 2 of the display unit 1 together with the image generation unit 11 according to the attribute detected by the detection means.

  (3) Advertisement voice (guidance voice) having contents related to the image displayed on the display 2 of the display unit 1 and having characteristics matched to the number and attributes detected by the detection means, together with the voice synthesis unit 13 Voice generation means for generating. Specifically, multiple types of voice generation data by age, gender, and foreign language (English, Chinese, Korean, etc.) are stored in the internal memory, and the above detection is based on these voice generation data. When the number detected by the means is a certain number (for example, five persons) or more, a sound for listening to an unspecified number of people is generated as a sound having a predetermined characteristic, and the number detected by the detecting means is If the number is less than a certain number, a voice having a feature that matches the attribute detected by the detection means is generated. In other words, if the attribute is less than a certain number, if the attribute is elderly, a slow speed voice for the elderly is generated, and if the attribute is a child, a popular character for the child (such as a manga or TV program) If the attribute is a foreigner, the voice using the vocabulary and expressions of the language that the foreigner uses on a daily basis is generated. Note that these generated sounds have the same contents (advertising contents) except for the characteristics such as speed and voice quality.

  (4) Control means for outputting the sound generated by the sound generation means from a speaker and variably setting the volume of the sound output according to the number detected by the detection means (the number of people in front). Specifically, when the detected number is equal to or greater than the predetermined number, the maximum level volume is set, and when the detected number is less than the predetermined number, the normal level volume is set.

Next, the operation will be described with reference to the flowchart of FIG.
When a person standing in front of the display unit 1 or a person passing in front of the display unit 1 utters sound, the sound is collected by the microphone 3 and analyzed and recognized (step 101). Based on the recognized voice, the number and attributes of people in front of the display unit 1 are detected (step 102). In other words, the number of people is detected as to how many voices with different characteristics exist within a certain period of time, and among the recognized voices, the voices with the largest volume are the elderly, children, general women, general men, foreign countries. It is detected whether it is a person.

  If the number of detected persons is equal to or greater than a certain number (YES in step 103), the volume of the sound output from the speaker 4 is set to the maximum level (step 104). Then, an advertisement image of a product targeting an unspecified number of general publics and sound of contents related to the image are generated, the generated image is displayed on the display 2, and the generated sound is transmitted from the speaker 4. It is emitted at the maximum volume (step 105). In this case, standard speed speech using standard vocabulary and expressions, such as those used in Japanese television and radio, is generated and emitted so that an unspecified number of people can easily listen. In particular, since the loudest sound is emitted from the speaker 4, even in a noisy situation where many people talk with each other in front of the display unit 1, the contents of the advertisement image can be accurately conveyed to the people. Can do.

  If the detected number of persons is less than a certain number (NO in step 103), the volume of the sound output from the speaker 4 is set to a normal level so that the person in front of the display unit 1 does not feel inconvenience. (Step 106). Then, it is determined whether the detected attribute is elderly, child, general female, general male, or foreigner (steps 107, 108, 111, 113, 115, 117).

  If it is an elderly woman (YES in step 107, YES in step 108), an advertisement image of a product targeting the elderly woman and a sound of contents related to the image are generated, and the generated image is displayed on the display 2. While being displayed, the generated voice is emitted from the speaker 4 (step 109). In this case, in order to make it easy for elderly people to listen, while using standard vocabulary and expressions, a voice that does not include a high frequency range as much as possible is generated. Therefore, an elderly woman in front of the display unit 1 can easily and accurately grasp the contents of the advertisement image while viewing the advertisement image of the product of interest.

  If it is an elderly man (YES in step 107, NO in step 108), an advertisement image of a product targeting the elderly man and a sound of contents related to the image are generated, and the generated image is displayed on the display 2. While being displayed, the generated voice is emitted from the speaker 4 (step 110). In this case, in order to make it easy for elderly people to listen, while using standard vocabulary and expressions, a voice that does not include a high frequency range as much as possible is generated. Therefore, an elderly man in front of the display unit 1 can easily and accurately grasp the contents of the advertisement image while looking at the advertisement image of the product of interest.

  If it is a child (YES in step 111), an advertisement image of a product targeting children and families and a sound of contents related to the image are generated, and the generated image is displayed on the display 2 and generated. The generated sound is emitted from the speaker 4 (step 112). In this case, speech that is similar to a popular character (a popular person appearing in a comic or a television program) is generated using simple vocabulary and expressions so that the child can easily understand and be interested. Therefore, a child or a family member in front of the display unit 1 can listen to the content of the advertisement image with interest and interest while watching the advertisement image of the product of interest.

  If it is a general woman (YES in step 113), an advertisement image of a product targeting the general woman and a sound of contents related to the image are generated, and the generated image is displayed and generated on the display 2. The voice is emitted from the speaker 4 (step 114). In this case, while using standard vocabulary and expressions, speech of inflection and speed that strongly appeals to general women is generated. A woman in front of the display unit 1 can easily and accurately grasp the contents of the advertisement image while viewing the advertisement image of the product of interest.

  If it is a general male (NO in step 115), an advertisement image of a product targeting the general male and sound of contents related to the image are generated, and the generated image is displayed and generated on the display 2. The voice is emitted from the speaker 4 (step 116). In this case, while using standard vocabulary and expressions, intonation and speed sounds that generate interest in general men are generated. A man in front of the display unit 1 can easily and accurately grasp the contents of the advertisement image while viewing the advertisement image of the product of interest.

  If it is a foreigner (NO in step 117), an advertisement image of a product targeting the foreigner and a sound of contents related to the image are generated, and the generated image is displayed and generated on the display 2. The voice is emitted from the speaker 4 (step 118). In this case, if the recognized speech language is English, speech using English vocabulary and expressions is generated. If the recognized speech language is Chinese, speech using Chinese vocabulary and expressions is generated. If the recognized speech language is Korean, speech using Korean vocabulary and expressions is generated. Therefore, a foreigner in front of the display unit 1 can easily and accurately grasp the contents of the advertisement image while looking at the advertisement image of the product of interest.

  When the detected attribute is neither an elderly person, a child, a general female, a general male, or a foreigner (NO in each of steps 107, 108, 111, 113, 115, and 117), the detected number of persons is constant. As with more than a few cases, standard speed speech using standard vocabulary and expressions, such as those used in Japanese television and radio, is generated so that an unspecified number of people can easily hear. Emitted (step 105).

  When the output of the image and sound of one advertisement is completed, the processing from step 101 is repeated, and the image and sound of the next advertisement for the person standing in front of the display unit 1 or the person passing by is output again.

  In this way, by generating and uttering sound that matches the attributes of the person in front of the display unit 1, the contents of the advertisement can be accurately conveyed to the person in front of the display unit 1. Therefore, a high advertising effect as digital signage can be obtained.

  In the above embodiment, a display is used as the display means, but a video display projector may be used. Although it is configured to detect English-speaking, Chinese-speaking, and Korean-speaking people as foreigners, it is of course possible to detect people in other language-speaking areas.

  A part of the function and configuration of the information providing apparatus can be provided in an external server. When constructing this system, for example, cloud computing can be used. More specifically, a software provision form called SaaS (software as a service) is suitable. A configuration in the case of using this cloud system is shown in FIG. The information providing system 200 includes a cloud 201, a plurality of terminals 202, a plurality of communication networks 203, and a plurality of servers 204 connected to each other for communication. Each of these terminals 202, communication network 203, and server 204 may be only one. The terminal 202 can communicate with the cloud 201 via the communication network 203. As the terminal 202, the information providing device, various computers such as a desktop type and a notebook type, a mobile phone device, a personal digital assistant (PDA), a smartphone, and the like can be used as appropriate. As the communication network 203, the Internet, a private network, a next generation network (NGN), a mobile network, or the like can be used as appropriate.

  In the image display system 200, at least one of the functions and configurations of the information providing apparatus is provided in the server 204, and the remaining functions and configurations that are not provided in the server 204 are provided in the terminal 202. The functions and configurations provided in the server 204 may be arranged in one server 204 or may be distributed in a plurality of servers 204.

In addition, the said embodiment and modification are shown as an example and are not intending limiting the range of invention. The novel embodiments and modifications can be implemented in various other forms, and various omissions, rewrites, and changes can be made without departing from the spirit of the invention. The scope of the invention is included in the gist of these embodiments and modifications, and is included in the invention described in the claims and the equivalents thereof.
The invention described in the scope of the original claims of the present application will be added below.
[1]
Display means for displaying an advertisement image;
A microphone for sound collection;
Voice recognition means for recognizing voice from sound collected by the microphone;
Detection means for detecting the number of people in front of the display means from the voice recognized by the voice recognition means;
Sound generating means for generating sound related to the image displayed by the display means;
Control means for outputting the sound generated by the sound generation means and variably setting the volume of the sound output according to the number detected by the detection means;
An information providing apparatus comprising:
[2]
The detection means detects the number and attributes of people in front of the display means from the voice recognized by the voice recognition means;
The sound generation unit generates a sound having characteristics related to the number and attributes detected by the detection unit and contents related to the image displayed by the display unit.
The control means sets the volume of the audio output to a maximum level when the number detected by the detection means is equal to or greater than a certain level, and to a normal level when the number is less than a certain number,
[1] The information providing device according to [1].
[3]
When the number detected by the detection means is equal to or greater than the predetermined number, the sound generation means generates a sound related to an image displayed on the display means and to be heard by an unspecified number of people, When the number detected by the detecting means is less than the predetermined number, the sound of the feature is matched with the attribute detected by the detecting means with the contents related to the image displayed on the display means,
[2] The information providing device according to [2].
[4]
The detection means detects elderly people, children, foreigners as the attribute,
When the number detected by the detection means is less than the predetermined number, the voice generation means generates a slow speed voice for the elderly if the attribute detected by the detection means is an elderly person. If the attribute detected by the detection means is a child, a voice by a popular character for the child is generated. If the attribute detected by the detection means is a foreigner, a foreign language for the foreigner is generated. Generate sound by
[3] The information providing apparatus according to [3].
[5]
In an information providing apparatus including display means for displaying an image for advertisement, a microphone for sound collection, and a computer,
In the computer,
A voice recognition function for recognizing voice from sound collected by the microphone;
A detection function for detecting the number of people in front of the display means from the recognized voice;
A sound generation function for generating sound related to an image displayed by the display means;
A control function for outputting the generated sound and variably setting the volume of the sound output according to the detected number;
A program characterized by realizing.
[6]
In an information providing system including an information providing apparatus and a server for displaying an advertisement image,
Sound collection means for collecting sound;
Voice recognition means for recognizing voice from the sound collected by the sound collection means;
Detecting means for detecting the number of people in front of the information providing device from the voice recognized by the voice recognition means;
Sound generating means for generating sound related to an image displayed on the information providing apparatus;
Control means for outputting the sound generated by the sound generation means and variably setting the volume of the sound output according to the number detected by the detection means;
The information providing system is characterized in that the server includes at least one means of each means, and the information providing apparatus includes the remaining means excluding the means included in the server.

  DESCRIPTION OF SYMBOLS 1 ... Display unit, 2 ... Display, 3 ... Microphone, 4 ... Speaker, 10 ... Control part, 11 ... Image generation part, 12 ... Speech recognition part, 13 ... Speech synthesis part, 14 ... Data input part, 15 ... Operation part , 16 ... Network interface, 20 ... Communication network, 21 ... Server

Claims (6)

Display means for displaying an advertisement image;
A microphone for sound collection;
Voice recognition means for recognizing voice from sound collected by the microphone;
The number of persons in front of the display means is detected from the voice recognized by the voice recognition means, and based on the voice having the highest input volume among the voices recognized by the voice recognition means within a predetermined time. Detecting means for detecting an attribute of a person in front of the display means ;
A voice generation unit that generates a voice having characteristics according to the number and attributes detected by the detection unit and the contents related to the image displayed by the display unit;
Control means for outputting the sound generated by the sound generation means and variably setting the volume of the sound output according to the number detected by the detection means;
An information providing apparatus comprising: Before SL control means, claims, characterized in that the number of detected sound volume of the audio output by the detection means is set to the normal level when less than the predetermined number is set to the maximum level when more than a certain number of 1. The information providing apparatus according to 1. When the number detected by the detection means is equal to or greater than the predetermined number, the sound generation means generates a sound related to an image displayed on the display means and to be heard by an unspecified number of people, When the number detected by the detecting means is less than the predetermined number, the sound of the feature is matched with the attribute detected by the detecting means with the contents related to the image displayed on the display means,
The information providing apparatus according to claim 2. The detection means detects elderly people, children, foreigners as the attribute,
When the number detected by the detection means is less than the predetermined number, the voice generation means generates a slow speed voice for the elderly if the attribute detected by the detection means is an elderly person. If the attribute detected by the detection means is a child, a voice by a popular character for the child is generated. If the attribute detected by the detection means is a foreigner, a foreign language for the foreigner is generated. Generate sound by
The information providing apparatus according to claim 2 , wherein the information providing apparatus is an information providing apparatus. In an information providing apparatus including display means for displaying an image for advertisement, a microphone for sound collection, and a computer,
In the computer,
A voice recognition function for recognizing voice from sound collected by the microphone;
The number of persons in front of the display means is detected from the recognized voice, and the display means based on the voice having the highest input volume among the voices recognized by the voice recognition function within a predetermined time. A detection function that detects the attributes of the person in front ,
A voice generation function for generating a voice having features according to the number and attributes detected by the detection function, which are contents related to an image displayed by the display unit;
A control function for outputting the generated sound and variably setting the volume of the sound output according to the detected number;
A program characterized by realizing. In an information providing system including an information providing apparatus and a server for displaying an advertisement image,
Sound collection means for collecting sound;
Voice recognition means for recognizing voice from the sound collected by the sound collection means;
The number of persons in front of the information providing device is detected from the voice recognized by the voice recognition means, and based on the voice having the highest input volume among the voices recognized by the voice recognition means within a predetermined time. Detecting means for detecting an attribute of a person in front of the information providing device ;
A voice generation unit that generates a voice having characteristics according to the number and attributes detected by the detection unit, the content relating to the image displayed by the information providing apparatus;
Control means for outputting the sound generated by the sound generation means and variably setting the volume of the sound output according to the number detected by the detection means;
The information providing system is characterized in that the server includes at least one means of each means, and the information providing apparatus includes the remaining means excluding the means included in the server.

Images