TWI408675B - Food processor with emotion recognition ability - Google Patents

Abstract

A food processor with emotion recognition ability is disclosed, which comprises: an emotion recognition module and a food processing module. The emotion recognition module is capable of receiving sound signals so as to identify an emotion containing in the received sound signals. The food processing module is capable of producing food products with a taste corresponding to the emotion recognition result of the emotion recognition module.

Description

Food manufacturing device combined with semantic recognition function

The present invention relates to a food manufacturing device incorporating a semantic recognition function, and more particularly to a manufacturing device capable of determining a user's voice signal to produce a food having a corresponding taste.

Press, semantic or speech recognition systems have been widely used in a variety of different technical fields, such as telephone voice systems, input devices, media interaction devices, and the like.

For the conventional patent, for example, the Republic of China Invention Patent Bulletin No. 517221 "Voice Recognition System" is used to receive a speech signal and output an output word corresponding to the voice signal to provide a voice capable of recognizing multiple languages. Identify the system to increase the applicable ethnicity of the call center telephone voice system.

As for the "voice recognition method and system" of Announcement No. 574684, which comprises receiving information reflecting the voice, determining at least one rough classification of the received information, classifying the received information according to the determined coarse classification, selecting a model according to the classification of the received information, and Using the selected model and receiving information to identify speech, to improve the chimeric training, the hidden Markov model may not be able to perform speech recognition in a non-matching channel environment as well as mixed training.

Another example is Announcement No. 219993 "Independent Timed Speech Recognition System", which mainly uses a microphone to convert a voice signal into an analog level signal, and amplifies it with an amplifier, and then converts the analog voice signal into a string by an analog-to-digital converter. The digital signal is sequenced, and the serial digital signal is converted into a parallel digital signal, and the digital processor performs the pre-processing of the parallel digital signal, feature point extraction and speech endpoint detection to obtain a multi-level fixed Point linear prediction coefficient. In the training process, this multi-level fixed-point linear prediction coefficient will be stored as a reference sample. In the identification process, this multi-level fixed-point linear prediction coefficient will be corrected by the symmetry method. The comparison method is compared with the reference sample to obtain an output of the identification result.

Another example is the publication No. I269192 "Speech Emotional Classification System", which mainly includes a domain-independent and specific semantics-based emotional rule database establishment procedure and an emotion classification module; it is based on the induction of emotional psychology. Factoring, and focusing on the semantic label, using the automatic rule generation technology of data exploration, the sentence is transformed into a vector space and an emotional classification module is trained to classify the emotions expressed by the sentence. The case can be used in the original human-computer communication interface. Increasing the emotional communication dimension, through the detection of the user's emotional response, assists in the lack of other communication interfaces, and can replace the rigid interface of the computer system to facilitate the more natural communication interface design.

Another example is Announcement No. 508564 "A Speech Recognition Method and System", which mainly discloses a method and system for simultaneously performing speech recognition, timbre, and vocal emotion judgment processing.

In addition, in the prior U.S. patents, there are also a number of technical means related to semantic judgments, such as detecting the response to the human body by detecting pulse, heart rate and respiratory rate. Lie detection system.

However, in the conventional patents or various consumer products currently on the market, no semantic or speech recognition function is implemented in the food manufacturing equipment, so that the user can obtain the corresponding technical means of the food through the voice interaction.

In view of the lack of the prior art, the present invention proposes a food manufacturing apparatus incorporating a semantic recognition function for determining a user's voice signal to produce a food having a corresponding taste.

In order to achieve the above object, the present invention provides a food manufacturing device incorporating a semantic recognition function, comprising a semantic module and a food manufacturing module, the speech recognition module for receiving an audio signal and identifying the audio signal. In the mood, the food manufacturing module can produce a food having a corresponding taste according to the voice recognition result.

In order to enable your review committee to have a better understanding and recognition of the structural purpose and efficacy of the present invention, the detailed description is as follows.

The technical means and efficacy of the present invention for achieving the object will be described below with reference to the accompanying drawings, and the embodiments listed in the following drawings are only for the purpose of explanation, and are to be understood by the reviewing committee, but the technical means of the present invention are not Limited to the listed figures.

Please refer to the schematic diagram of the first embodiment of the present invention shown in the first embodiment. The food manufacturing device 10 with the semantic recognition function provided by the present invention mainly includes a semantic recognition module 11 and a food manufacturing module 12, which The food manufacturing module 12 includes a food supply unit 121 from which at least one food item such as chocolate, candy, cake, biscuit, beverage can be supplied. The semantic recognition module 11 is configured to receive an audio signal and recognize the emotions included in the audio signal. The recognition manner can be various, and the volume can be detected through a volume, a sound speed, a tone, or by detecting a pulse or a heartbeat of the user. The number of breaths and the like determine the emotional response of the human body; the function of the semantic recognition module 11 is to create a food corresponding to the taste, such as sweetness, sourness, bitterness, and spicy, from the food manufacturing module 12 according to the user's emotion at the time. One of taste, cool taste, etc. or any combination thereof.

Taking chocolate as an example, when the user feels happy and emotionally speaking to the food manufacturing device 10: "I love you", "I miss you", "I love you", "LOVE", regardless of the use of Chinese, English or any language, either a word or a word, or a whole sentence, because the tone is soft and emotional, so the semantic recognition module 11 can recognize that the user is in a state of pleasure. The food supply unit 121 can be controlled to supply a chocolate having a taste of sweetness to the food producing device 10. If the user disgustedly said to the food manufacturing device 10: "I hate you", "I hate you", "I hate you", "HATE", whether using Chinese, English or any language, or a If the tone is stiff and has no feelings, the semantic recognition module 11 can recognize that the user is in a state of inferiority, and can control the food supply unit 121 to supply a taste. The food manufacturing device 10 is delivered for bitter or odorless chocolate. Therefore, when different users speak different sentences in different emotional states, foods having different tastes, including chocolate, biscuits, candy, cakes, and beverages, can be obtained.

Referring to the second embodiment of the present invention, the food manufacturing device 20 includes a semantic recognition module 21, a voice recognition module 22 and a food manufacturing module 23, and the food manufacturing module 23 includes A food supply unit 231 and a character forming unit 232, the function of the semantic recognition module 21 and the achievable functions are the same as those of the semantic recognition module 11 in the first embodiment, which will not be described herein. The difference is that a voice recognition module 22 is provided, and the food manufacturing module 23 includes a food supply unit 231 and a character forming unit 232. The voice recognition module 22 is configured to receive an audio signal and identify the sound signal. At least one food can be supplied by the food supply unit 231, and the character forming unit 232 can form at least one character on the food supplied by the food supply unit 231. The character forming unit 232 can form a plurality of characters, and the character forming unit 232 can be an imprinting device, such as a word die, which can form a text having a different height difference from the surface of the food on the surface of the food, for example, formed. The character forming unit 232 can be a carving device such as a cutter, and can form a character on the surface of the food or cut the food into a character shape. Further, the character forming unit 232 can also be a The drawing device is configured to draw characters on the surface of the food, for example, through a tool similar to a cream squeezing nozzle, extruding raw materials such as chocolate, syrup, cream, etc. on the food, and then passing the drying device to make the soft chocolate and syrup extruded. Or the cream can be quickly solidified and combined with food; for example, the drawing device directly extrudes raw materials such as chocolate, syrup, cream, etc. into words. Character-related data such as fonts and text sizes are stored in the character forming unit 232, or the related data can be stored in one of the independently set databases.

According to the above-mentioned food manufacturing device 20 provided by the present invention, the food type having the characters can be produced in different manners, as shown in the third embodiment, which is drawn on the chocolate 60A to depict the font 61A; The embodiment shown in Fig. 3B is formed by engraving a font 61B on the chocolate 60B; in the embodiment shown in Fig. 3C, the chocolate 60C has a convex font 61C which can be formed by engraving. Alternatively, the fluid chocolate or confectionery material may be equal to the chocolate 60C depicting the font, and after the font is hardened, it is integrated with the chocolate; or as in the embodiment shown in the third D, the chocolate 60D is directly formed into a text type. The font can be engraved in an engraving manner, or the font can be drawn from the fluid chocolate or confectionery material, and then sent out to the food manufacturing device 10 after being hardened, and the formed fonts can be separated one by one (as shown in the third D diagram). Embodiments) may also be partially connected as a whole.

According to the embodiment shown in the second figure, when the user happily reads the food manufacturing device 20 provided by the present invention one by one: "L, O, V, E", the tone should be soft and affectionate. The semantic recognition module 21 recognizes that the user is in a state of pleasing mood, and the voice recognition module 22 receives the voice signal sent by the user and recognizes that it is "L, O, V, E". The letter, that is, the food supply unit 231 can be controlled to supply a piece of chocolate having a taste of sweetness to the character forming unit 232, and the letter forming unit 232 can form the letters "L, O, V, E" on the surface of the chocolate or The sweet chocolate having a character shape is molded and sent out to the food producing apparatus 20. If the user disgustedly reads the food manufacturing device 20 provided by the present invention one by one: "H, A, T, E" (hate, hate), the tone should be stiff and unfeeling, and the voice recognition The module 22 receives the sound signal and recognizes the four letters "H, A, T, E", and then the semantic recognition module 21 recognizes that the user is in a state of inferiority, and can control the food supply unit 231 to supply a piece of music. The taste is bitter or odorless chocolate to the character forming unit 232, and the letter forming unit 232 prints the four letters "H, A, T, E" on the chocolate surface or forms a bitter or odorless chocolate having a letter shape. Further, the food producing apparatus 20 is sent out, and the user can obtain a bitter or odorless chocolate having four letters of "HATE" printed on the surface. By analogy, when different users speak different sentences in different emotional states, they can obtain foods with different characters and different tastes. Similarly, in addition to the English font, the food manufacturing apparatus 20 of the present invention can also recognize Chinese speech. For example, when the user says "I hate you" to the food manufacturing apparatus 20 in Chinese, the semantic recognition can be performed by the semantic expression. The group 21 recognizes that the user is in a state of inferiority, and the voice recognition module 22 receives the voice signal and recognizes the four Chinese characters "I hate you", and can control the food supply unit 231 to supply a taste to bitterness. Or the odorless chocolate to the character forming unit 232, the character forming unit 232 prints the four Chinese characters "I hate you" on the chocolate surface or forms a bitter or odorless chocolate having a text shape, and then sends the food manufacturing device. 20, the user can get the bitter or odorless chocolate printed on the surface with "I hate you". By analogy, when different users speak different sentences in different emotional states, they can obtain foods with different characters and different tastes. It should be noted that the recognition order of the semantic recognition module 21 and the speech recognition module 22 is limited and may be performed simultaneously. In addition, in order to match different emotions, in addition to the text, the corresponding punctuation marks or geometric patterns may be additionally used, and the related punctuation marks or geometric patterns may be stored in the text along with text-related data such as font, text size, text color, and text arrangement. The molding unit 232 is stored in a database of independent settings.

In addition to the above embodiments in which individual letters are read by the user, the speech recognition module 22 of the present invention also has the function of recognizing sentences, for example, when the user utters a sentence of "I LOVE YOU", the speech recognition The module 22 can correctly recognize three English words "I", "LOVE" and "YOU" in the sentence, that is, equivalent to eight English letters; a piece of chocolate is supplied from the food supply unit 231 to the character forming unit 232. At the same time, the character forming unit 232 molds three English words "I", "LOVE" and "YOU" on the surface of the chocolate by embossing, engraving or drawing, or molding a chocolate having a character shape, and then delivering the food. In the device 20, the user can obtain a chocolate having an "I LOVE YOU" letter or a font on the surface.

Please refer to the fourth embodiment of the present invention. The food manufacturing device 30 includes a machine 31. The machine 31 is provided with a microphone 32, a display device 33, an input device 34 and an outlet 35. The display device 33 is a screen. The input device 34 can be a physical keyboard or a touch screen keyboard integrated with the display device 33. A semantic recognition module 36 and a voice are disposed in the machine 31. An identification module 37 and a food manufacturing module 38. The food manufacturing module 38 includes a food supply unit 381 and a character forming unit 382. When the user speaks to the microphone 32 in front of the machine 31, it is said: When I love you, the voice signal can be received by the microphone 32, and the signal is sent to the semantic recognition module 36 and the voice recognition module 37 for semantic and voice recognition, and then the display device 33 displays the semantic recognition module 36 and The recognition result of the voice recognition module 37, as shown in the figure, displays the font, food type, mouth position and quantity formed on the surface of the food on the display device 33, and can also display the text size, Word and text color arrangement, etc. of content words, may be set, or the display device 33 may display the food analog produced the appearance of the image.

When the food information such as the content and taste displayed by the display device 33 is correct, the user can confirm the content through the input device 34, and then the food manufacturing module 38 manufactures and delivers the food to the outlet 35, and the user A sweet chocolate 60E having three Chinese characters "I love you" can be obtained; if the food information displayed by the display device 33 is incorrect, the user can modify the input device 34, for example, due to the user volume. Insufficient, inaccurate pronunciation and the like cause the semantic recognition module 36 to misjudge the user's emotions and cause the food taste to be wrong, or the speech recognition module 37 recognizes the error, so that the content of the sentence is not required by the user; in addition, since the user can modify the food Information, so you can increase the selection items, such as the number of foods, the arrangement of the text, the size and shape of the food, etc. The user can modify the type of food, the content of the food on the surface of the food, the taste of the food and the quantity of the food, etc. The food is then manufactured and delivered by the food manufacturing module 38.

In addition, the user can directly modify or design the desired word content, font, taste and quantity through the input device 34, and display the food information by the display device 33, and if the modification is needed, the input device is used again. 34 is modified until the user is satisfied, and the food manufacturing module 38 manufactures and delivers the food, thereby providing the user with different choices of manufacturing methods, and improving human-computer interaction.

In summary, the food manufacturing device provided by the present invention combined with the semantic recognition function can determine that the user's voice signal produces a food having a corresponding taste or character, and it must be emphasized that the general food vending machine can only sell the standard food. The present invention can supply foods corresponding to tastes according to user emotions, and can produce foods having different characters, that is, foods having different appearances according to user needs, so that users can purchase foods in an interactive manner, thereby increasing consumer interest and willingness. .

However, the above description is only for the embodiments of the present invention, and the scope of the invention is not limited thereto. That is to say, the equivalent changes and modifications made by the applicant in accordance with the scope of the patent application of the present invention should still fall within the scope of the patent of the present invention. I would like to ask your review committee to give a clear explanation and pray for it.

10, 20, 30‧ ‧ food manufacturing equipment

11, 21 ‧ ‧ semantic recognition module

12, 23‧‧‧Food Manufacturing Module

121, 231‧‧‧Food Supply Unit

232‧‧‧Text Forming Unit

22‧‧‧Voice recognition module

31‧‧‧ machine

32‧‧‧Microphone

33‧‧‧Display device

34‧‧‧ Input device

35‧‧‧Export

36‧‧‧Speech Identification Module

37‧‧‧Voice recognition module

38‧‧‧Food manufacturing module

381‧‧‧Food Supply Unit

382‧‧‧Text Forming Unit

60A, 60B, 60C, 60D, 60E‧‧‧ chocolate

61A, 61B, 61C‧‧‧ font

The first figure is a schematic diagram of the architecture of the first embodiment of the present invention.

The second figure is a schematic diagram of the architecture of the second embodiment of the present invention.

The third to third D drawings are schematic views of different food aspects presented by the present invention.

The fourth figure is a schematic diagram of the architecture of the third embodiment of the present invention.

10. . . Food manufacturing device

11. . . Semantic recognition module

12. . . Food manufacturing module

121. . . Food supply unit

Claims (28)

A food manufacturing device incorporating a semantic recognition function includes: a semantic recognition module for receiving an audio signal and identifying an emotion included in the audio signal; a food manufacturing module, the food manufacturing module According to the semantic recognition result, a food having a corresponding taste is produced. The food manufacturing device according to the first aspect of the invention, wherein the taste produced by the food manufacturing module comprises one of sweetness, sourness, bitterness, spicy taste, and coolness, or any mixture thereof. The food manufacturing device of claim 1, wherein the voice recognition module further comprises a voice recognition module, wherein the voice recognition module is configured to receive the voice signal and identify the content of the voice signal. . The food manufacturing device according to the third aspect of the invention, wherein the food manufacturing module is configured to manufacture a food having a corresponding character according to the voice recognition result. The food manufacturing device according to the third aspect of the invention, wherein the content of the sentence recognized by the speech recognition module includes characters and words. The food manufacturing device according to the third aspect of the invention, wherein the food manufacturing module comprises: a food supply unit for supplying at least one food; a text forming unit, the character forming The unit forms at least one character on the food supplied by the food supply unit. The food manufacturing device according to claim 6, wherein the character forming unit is an imprinting device, and the imprinting device is used for imprinting on the surface of the food and molding on the surface of the food. The surface of the food has different heights and drops. The food manufacturing device according to the sixth aspect of the invention, wherein the character forming unit is an engraving device for engraving characters on the surface of the food. The food manufacturing device according to the sixth aspect of the invention, wherein the character forming unit is a drawing device for drawing characters on the surface of the food. The food manufacturing device according to the sixth aspect of the invention, wherein the character forming unit further shapes the food into a letter shape. The food manufacturing device according to claim 10, wherein the character forming unit is an engraving device for engraving the food into a character shape. The food manufacturing device according to claim 10, wherein the character forming unit is a drawing device for drawing a food having a character shape. The food manufacturing device according to the sixth aspect of the invention, wherein the character forming unit is further capable of forming a punctuation mark or a geometric pattern. The food manufacturing device of claim 1, wherein the display device is configured to display food taste, food type and food quantity produced by the food manufacturing module. . The food manufacturing device of claim 14, wherein the input device is configured to provide a user with input of food taste, food type and food quantity. The food manufacturing device according to claim 15 , wherein the input device is combined with the display device as a touch screen. The food manufacturing device according to the fifteenth aspect of the invention, wherein the input device is electrically connected to the food manufacturing module, and the food manufacturing module manufactures a corresponding taste according to the information input by the user. , type and quantity of food. The food manufacturing device of claim 14, wherein the display device further displays the words recognized by the speech recognition module. The food manufacturing device according to claim 18, wherein the display device further displays a word content including a font, a text size, a text color, and a text arrangement. The food manufacturing device according to claim 18, further comprising an input device for providing a user input sentence. The food manufacturing device according to claim 20, wherein the input device is combined with the display device as a touch screen. The food manufacturing device according to claim 20, wherein the input device is electrically connected to the food manufacturing module, and the food manufacturing module creates a corresponding sentence according to the information input by the user. Food. The food manufacturing device according to claim 14, wherein the display device further displays a simulated appearance image of the manufactured food. The food manufacturing device according to claim 1, wherein the food manufacturing device further comprises an input device for providing a user with input of food taste. The food manufacturing device according to claim 24, wherein the input device is further capable of inputting a food type and a quantity of food. The food manufacturing device according to claim 24, wherein the input device is electrically connected to the food manufacturing module, and the food manufacturing module manufactures corresponding text according to the information input by the user. Food. The food manufacturing device according to claim 3, further comprising a database for storing at least one font, at least one text size, and at least one text color. The food manufacturing device according to the first aspect of the invention, wherein the food manufacturing module comprises a chocolate, a candy, a beverage, a cake or a biscuit.