CN-116052333-B - Intelligent voice prompt method and intelligent voice robot

CN116052333BCN 116052333 BCN116052333 BCN 116052333BCN-116052333-B

Abstract

The invention provides an intelligent voice prompt method and an intelligent voice robot, wherein the method comprises the steps of starting a safety control process of the intelligent voice robot when detecting that the current environment meets the preset trigger condition of the intelligent voice robot; the method comprises the steps of obtaining basic warning text from a pre-established warning information database, synthesizing warning information prompt voice by utilizing the basic warning text, playing the warning information prompt voice, displaying a local two-dimensional code for scanning and identifying the people entering and exiting in the public place, and synchronously collecting safety management information corresponding to any person entering and exiting in the public place. According to the method provided by the invention, the information transmission of code scanning execution is changed into a mode of 'listening' of human ears, so that the consumption of repeated same prompts in a manual supervision link is reduced to the greatest extent, the manual frequent prompts are not needed, and the workload of supervision executors is reduced while the safety management and control is improved.

Inventors

ZHANG YUCHENG
SUN LIYUE
LI DEGANG

Assignees

乐播新瑞(北京)科技有限公司

Dates

Publication Date: 20260505
Application Date: 20220408

Claims (7)

1. An intelligent voice prompt method applied to at least one intelligent voice robot, wherein the intelligent voice robot is deployed in a plurality of different types of public places, the method comprising: the intelligent voice robot is provided with two or more sensing components, different environmental elements trigger different sensing components and further different sensing components trigger and start different safety control processes of the intelligent voice robot, the types of the sensing components at least comprise an infrared sensor and a carbon dioxide sensor, the corresponding safety control processes are started when the infrared sensor detects that surrounding people exist, and the corresponding safety control processes are started when the carbon dioxide sensor detects that the surrounding carbon dioxide concentration changes and indicates that the quantity of surrounding people changes; acquiring a basic warning text from a warning information database which is established in advance according to the safety management requirements of the multi-level administrative management area, and synthesizing warning information prompt voice by utilizing the basic warning text; playing the warning information prompt voice; the local two-dimensional code is displayed for scanning and identifying the personnel entering and exiting the public place, and is matched uniformly and dynamically managed according to the safety management requirement of the deployment site of the intelligent voice robot; The method comprises the steps of synchronously collecting safety management information corresponding to any person entering and exiting in a public place, identifying target environment elements triggering and starting the safety management process and element types corresponding to the target environment elements, determining an information collection mode according to the element types corresponding to the target environment elements, synchronously collecting the safety management information corresponding to any person entering and exiting in the public place by utilizing the information collection mode, starting an information collection window capable of collecting basic information corresponding to the person entering and exiting in the public place if the person entering and exiting comprises an old user, a teenager user and/or a child user, synchronously collecting the safety management information corresponding to any person entering and exiting in the public place by utilizing the information collection window, wherein the information collection window of an intelligent voice robot is an image interaction window, a voice interaction window or a man-machine operation window, and synchronously collecting the safety management information corresponding to any person entering and exiting in the public place by utilizing a local two-dimensional code through scanning code identification if the person entering and exiting in the public place comprises an adult user.
2. The method of claim 1, wherein the sensing element comprises at least one of an ultrasonic sensor, a weight sensor, a video camera, a timer, a counter, a temperature and humidity sensor, a MIC microphone for recording sound, and a MINIPAD display for interaction between a user and the intelligent voice robot.
3. The method according to claim 1, wherein determining an information collection manner according to the element category corresponding to the target environmental element, so as to synchronously collect security management information corresponding to any person entering or exiting the public place by using the information collection manner includes: And if the access personnel comprise adult users, synchronously acquiring safety management information corresponding to any access personnel in the public place by utilizing the local two-dimensional code.
4. The method according to claim 1, wherein the method further comprises, before obtaining a basic warning text from a warning information database previously established according to the safety management requirements of the multi-level administrative area and synthesizing warning information to prompt voice using the basic warning text: Collecting the safety management requirements of the multi-level administrative areas, and generating basic warning texts corresponding to various public places and used for warning voice broadcasting according to the safety management requirements of each administrative area so as to establish a matching system of a safety propaganda execution working database and the existing administrative division jurisdiction; The language intonation data corresponding to each administrative management area are collected in advance, at least one virtual host for voice broadcasting is trained by utilizing the language intonation data, and the voice structure corresponding to the virtual host can optimize multi-language broadcasting along with technical upgrading.
5. The method of claim 4, wherein the obtaining basic warning text from a warning information database previously established according to the safety management requirements of the multi-level administrative area, and synthesizing warning information-prompting voices using the basic warning text, comprises: Acquiring the geographic position of the intelligent voice robot according to a positioning device arranged in the intelligent voice robot, identifying the location type corresponding to the geographic position of the intelligent voice robot, and selecting a basic warning text matched with the administrative management area and the location type of the intelligent voice robot from the warning information database; Synthesizing the basic warning text into warning information to prompt voice by using a text-to-voice (TTS) technology so as to enable the administrative area to match with a virtual host for voice broadcasting, or, And designating any one virtual host to record the basic warning text in response to an operation instruction of the operation end.
6. The method of claim 5, wherein after the playing the alert message alert voice, the method further comprises: Acquiring a new security management requirement for updating the administrative management area in real time, and updating a basic warning text in the warning information database according to the new security management requirement; and generating new warning information prompt voice by using the updated basic warning text.
7. An intelligent voice robot for performing the intelligent voice prompt method of any one of claims 1-6, the intelligent voice robot deployed in a plurality of different types of public places, the intelligent voice robot comprising: The detection module is used for starting the safety control process of the intelligent voice robot when detecting that the current environment meets the preset triggering condition of the intelligent voice robot; The voice synthesis module is used for obtaining basic warning texts from a pre-established warning information database, and synthesizing warning information to prompt voice by utilizing the basic warning texts; The playing module is used for playing the warning information prompt voice; The display module is used for displaying the local two-dimensional code so as to enable the personnel entering and exiting the public place to scan and identify; the local two-dimensional code is uniformly matched and dynamically managed by the safety management requirement of the deployment site of the intelligent voice robot; And the information acquisition module is used for synchronously acquiring the safety management information corresponding to any person entering or exiting in the public place.

Description

Intelligent voice prompt method and intelligent voice robot Technical Field The invention relates to the technical field of intelligent robots, in particular to an intelligent voice prompt method and an intelligent voice robot. Background The two-dimensional code is a graph which is distributed on a plane (in a two-dimensional direction) according to a certain rule by using a certain specific geometric figure, is alternately black and white, records data symbol information, has a certain verification function, an automatic identification function on information of different rows and processes graph rotation change points. The traditional information presentation and data acquisition not only require a lot of manpower and material resources to be input, but also have low efficiency, so that certain management pressure is brought, and a method for reducing the manpower cost while simultaneously meeting the safety management is needed. Disclosure of Invention The present invention has been made in view of the above problems, and has as its object to provide an intelligent voice prompt method and an intelligent voice robot that overcome or at least partially solve the above problems. According to a first aspect of the present invention, there is provided an intelligent voice prompt method applied to at least one intelligent voice robot deployed in a plurality of different types of public places, the method comprising: when the current environment is detected to meet the preset triggering condition of the intelligent voice robot, starting the safety control process of the intelligent voice robot; Acquiring a basic warning text from a pre-established warning information database, and synthesizing warning information prompt voice by using the basic warning text; playing the warning information prompt voice; Displaying a local two-dimensional code for scanning and identifying the personnel entering and exiting in the public place, wherein the local two-dimensional code is uniformly matched and dynamically managed by the safety management requirement of the deployment site of the intelligent voice robot; and synchronously collecting safety management information corresponding to any person entering or exiting in the public place, wherein the safety management information comprises the information of the person entering or exiting in the public place. Optionally, the intelligent voice robot is provided with at least one sensing component, when detecting that the current environment meets the preset triggering condition of the intelligent voice robot, starting the safety control process of the intelligent voice robot, including: And detecting at least one environmental element in the current environment to trigger the induction component arranged in the intelligent voice robot, and triggering and starting the safety control process of the intelligent voice robot by the induction component. Optionally, the sensing components comprise at least one of an infrared sensor, an ultrasonic sensor, a weight sensor, a video camera, a timer, a counter, a temperature and humidity sensor, a carbon dioxide sensor, a MIC microphone for recording sound and a MINIPAD display screen for interaction between a user and the intelligent voice robot. Optionally, the detecting that at least one environmental element in the current environment triggers the sensing component disposed in the intelligent voice robot, and the triggering by the sensing component starts the safety control process of the intelligent voice robot, including: the intelligent voice robot is provided with two or more sensing components, different environmental elements trigger different sensing components, and then different sensing components trigger and start different safety control processes of the intelligent voice robot. Optionally, the synchronously collecting the security management information corresponding to any person entering or exiting the public place includes: identifying a target environment element triggering the starting of the security management and control process and an element category corresponding to the target environment element; and determining an information acquisition mode according to the element category corresponding to the target environment element, so as to synchronously acquire the safety management information corresponding to any person entering or exiting in the public place by utilizing the information acquisition mode. Optionally, determining an information collection mode according to the element category corresponding to the target environmental element, so as to synchronously collect the security management information corresponding to any person entering or exiting the public place by using the information collection mode includes: if the access personnel comprise adult users, synchronously acquiring safety management information corresponding to any access personnel in the public place by utilizing the local two-dimensiona