ES2784480A1 - RESOLUTION SYSTEM OF RIDDLES, RIDDLES AND ENIGMAS BASED ON VOICE RECOGNITION (Machine-translation by Google Translate, not legally binding) - Google Patents

Abstract

The object of this invention is a system for solving riddles, puzzles and enigmas based on voice recognition that comprises integrative and linguistic software of process (1) that works with algorithms implemented in an electronic device such as computer, server, tablet, mobile, smart speakers, new hardware, etc. and linked, through an interface, with voice recognition computer services, accessible through interconnected communication networks, that is, a web service hosted on the internet (4) or cloud, the electronic device being connected internally or externally with different physical elements that enable the development of its function. The system has a loudspeaker (2), earphone or audio reproduction device, microphone or audio capture element (3) and, optionally, a storage medium (5). The software can be an additional element of the type module, application, app or extra functionality of the software that makes the device work, without incorporating new hardware. (Machine-translation by Google Translate, not legally binding)

Description

DESCRIPTION

RESOLUTION SYSTEM OF RIDDLES, RIDDLES AND ENIGMAS

BASED ON VOICE RECOGNITION

Object of the invention

The present invention refers to a system for solving riddles, puzzles and enigmas based on a voice recognition interface, presenting technical characteristics that implement improvements in different applications of the new personal devices.

Technical sector

The field of the art of this invention corresponds to the processing and / or generation of digital data with the intervention of voice recognition technology (VUI).

State of the art

New information technologies have implemented the so-called voice recognition system, VUI (Voice User Interface), which allows a user to interact with an electronic device equipped with the corresponding software using the voice as the only tool. To do this, the VUI technology recognizes the user's voice according to the parameters it has implemented, allows its entry into the system, decodes and processes it, and transmits a response using voice codes to which other elements of voice can be added. response based on a variety of codes, eg alphabetic, graphic or visual.

The VUI interface, which had a first activation in an advanced computerization environment, is already present in different products and services that are marketed to the general public, implemented in communication devices such as “smartphones”, control devices that allow activating remote home heating or smart speakers.

Given the great diversity of applications and target audience, the design of a User Voice Interface (IVU) must combine different fields of knowledge or disciplines, obviously implementing computer science, but also linguistics, ,,

to the user's ability to reason, interpret and understand.

At present and especially in voice interfaces aimed at a general public and installed in devices for standardized use such as smartphones, tablets, etc. The voice interface implemented, acting bi-directionally with the user, is always the questioned party, that is, the user makes a request and the interface, based on the software with which it is linked, facilitates the response.

The applicant is not aware of the existence of a bidirectional voice interface communication system between a device and a user in which the interface is the questioning party and the user the resolving party.

Object of the invention

Thus, this invention refers to a system for solving riddles, riddles and enigmas that comprises integrative and linguistic software that works with algorithms implemented in an electronic device and linked, through an interface, with computerized voice recognition services accessible through communication networks between computers, that is to say, the Internet, this electronic device being interconnected internally or externally with different elements that enable the development of its function.

According to its statement, the system aims to pose a question, enigma or puzzle to the user, who emits a spoken answer that, through voice recognition, the system analyzes and evaluates linguistically to determine to what degree it is correct. The result of this evaluation is presented to the user in a visual, auditory and / or tactile way, but in an intuitive way for him.

The objective of this invention is not a simple question-answer type interaction between a machine and a user, which, as has been commented, is usually the type in which the user poses the question to the machine seeking an answer that satisfies their expectations. An example of this type of communication is that carried out through Internet search engines or from smartphones that have what can be called virtual assistants.

The system claimed changes this approach as the machine asks the user a question in an intercom based on voice recognition, that is, ,,, animal, place, object, food, sport, etc. The system has the option of issuing tracks (audios, signals, ...) at the user's request or automatically when the user does not get the correct answer on the first attempt.

This approach is valid for specific and specific questions or to configure a set of concatenated and conceptually related or unrelated questions, to build a game, a thematic or informative collection, for example, reiterating the previous process on various concepts subject to classification .

Obviously, the system software is programmable to adapt to different user targets, for example, segmented by age, training or personal preferences, and its purpose can be merely entertainment, informative, training as didactic and / or educational material or to determine the operation of a toy, device or the like.

Description of the drawings

In order to facilitate the understanding of the innovation claimed herein, a sheet with some drawings is attached, which must be analyzed and considered solely by way of example and without any limiting or restrictive character.

Figure 1.- Schematic view of the elements that make up the system

Figure 2.- Schematic view of the phases of the process that the system executes.

Preferred embodiment of the invention

According to these drawings, the object of this invention is a system for solving riddles, puzzles and enigmas based on a voice recognition interface, in which physical elements and integrative and linguistic software intervene.

Figure 1 details the different elements that participate in the system, specifically a process software (1) implemented in an electronic device such as computer, server, tablet, mobile, smart speakers, etc. The electronic device has Internet connectivity (4), either directly or through an external module connected to it. The most important task of the process software (1) is to process the voice response, obtained in text format, and compare it linguistically with the correct response (from ,,

result of this comparison, intuitively for the user.

The electronic device that supports the process software (1) is connected with different elements, in particular a speaker (2), earphone, or audio reproduction device that reproduces the audio in which the question is posed to the user, although it can also be formulated visually, and in turn informs the user of the degree of correctness of his answer, also reproducing clues to help the person to find out the riddle, enigma or riddle.

Said electronic device is also connected to a microphone or audio capture element (3) to capture the user's spoken response.

At the construction level, the electronic device integrates all these elements, counting, for example, with a loudspeaker, but alternatively some of these physical elements or all of them can be interconnected external modules.

In turn, the software consists of an additional element, for example, a module, application, app or extra functionality of the software that makes the device work, in case it already has its own different functionality.

The system has an Internet connection (4) or cloud in which a web service is hosted that receives the user's spoken response, in some digital audio format, and that, through voice recognition, identifies the words spoken, in the format of text, optionally having a storage medium (5).

In addition, the audios that are reproduced may be contained in said medium, or come from the Internet.

The voice recording can also be stored in this storage medium (5) to later be sent to the Internet (4) or a computer network for the recognition of the words it contains.

Figure 2 shows a diagram of the different phases of the process that executes the system for solving riddles, puzzles and enigmas based on voice recognition, identifying the different elements involved in it.

,.

An audio is played on a loudspeaker (2) or the question of the concept to be found is indicated on a display device.

If this is carried out using audio, it comes from a storage medium (5), connected to the electronic device that supports the process software (1) or it is reproduced directly from an audio server hosted on the Internet (4) or cloud, or online computer network.

b) Waiting time (optional) (T).

After the approach, time is allowed for the user to think about the answer.

c) Audio recording and management

During a period of time, the audio present in the microphone or audio capture element (3) is recorded, to be stored in a storage medium (5) or sent directly to the next step (online).

d) Voice recognition.

1. Intercommunication between the system with the web service on the Internet (4) or cloud for voice recognition "speech to text" or acronym ST, that is, the first calls the second.

2. The audio is transmitted to the web service for voice recognition, which receives it as recorded in phase c) or receives it online, that is, as the recording is made, always in a digital format.

3. The process software (1) receives from the web service on the Internet (4) or cloud the result of the voice recognition, that is, the words contained in the recording that has been sent to it, and receives them through a sequence of words in text format.

e) Response treatment.

1. Once the process software (1) receives the sequence of words, in text format, returned by the web service on the Internet (4) or cloud, according to phase d), it performs a comparative linguistic intervention (C) with the expected response (according to the specific criteria of each application or product for which this system is intended).

.

(1) proceeds to communicate to the user the result of the Comparative Intervention (C).

2.1. outputting other audio through the speaker (2).

2.2. by means of a visual signal emitted by a display device, graphic interface or by pilot lights (if the system is implemented in some non-conventional electronic device)

2.3. by means of some tactile element or even Braille keyboard.

It is not considered necessary to make this description more extensive for any person skilled in the art to understand the scope of the invention and the advantages derived from it. The materials, shape, size and arrangement of the elements will be susceptible to variation as long as this does not imply an alteration in the essentiality of the invention. The terms in which this report has been written should always be taken in a broad and non-limiting sense.

Claims (3)

CLAIMS 1a System for solving riddles, puzzles and enigmas based on voice recognition, essentially characterized in that it comprises integrative and linguistic process software (1) that works with algorithms implemented in an electronic device and linked, through an interface, with computer services of voice recognition, accessible through communication networks, that is, a web service hosted on the Internet (4) or cloud, the electronic device being interconnected internally or externally with different elements that enable the development of its function.2a System for solving riddles , puzzles and enigmas based on voice recognition, according to the claim, essentially characterized in that the electronic device is of the type computer, server, tablet, mobile, smart speakers, new hardware, etc. being the process software (1) the one in charge of directing the whole process. 3rd System for solving riddles, puzzles and enigmas based on voice recognition, according to claim, essentially characterized in that the electronic device that supports the process software ( 1) is linked to a loudspeaker (2), headphone or audio reproduction device, a microphone or audio capture element (3) to capture the user's spoken response and, optionally, a storage medium (5) .4a System for solving riddles, puzzles and enigmas based on voice recognition, according to claim 1, essentially characterized in that when the electronic device integrates the elements, the software consists of an additional element of the type module, application, app or extra functionality of the software that makes the device work 5th Process that executes the system of solving riddles, puzzles and riddles based on speech recognition, characterized essentially in that it comprises the following phases) Proposal of the riddle, enigma or riddle by Playing an audio on the loudspeaker (2) from the storage medium (5) connected to the electronic device that supports the process software (1) or by reproduction Direct from an Internet audio server (4) or online computer network or Visualization on a visual device of the question of the concept to be found out. .c) Recording and management of the audio present in a microphone or audio capture element (3) Storing the recorded audio on a storage medium (5) or Sending the recorded audio to phase d) directly (online) .d) Voice recognition. 1. Intercommunication of the system with a web service on the Internet (4) or in the cloud for speech recognition "speech to text" or STT acronym. 2. Streaming the audio to the web service in a digital audio format online O well with the recording made in phase c). 3. Reception, by the process software (1), of the result of the speech recognition by means of a sequence of words in text format, returned by the web service. e) Response treatment. 1. Linguistic comparative intervention (C) of the process software (1) between the sequence of words in text format received, with the expected response (according to the specific criteria of each application or product for which this system is intended). 2. Communication to the user of the result of the comparative intervention (C) based on the degree of success or failure of the response (R) 2.1. outputting other audio through the speaker (2). 2.2. by means of a visual signal emitted by a display device, graphic interface or by pilot lights (if the system is implemented in some non-conventional electronic device) 2.3. by means of some tactile element or even Braille keyboard.