CN113793588A - Intelligent voice prompt method, device, equipment and storage medium - Google Patents
Intelligent voice prompt method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113793588A CN113793588A CN202111083750.6A CN202111083750A CN113793588A CN 113793588 A CN113793588 A CN 113793588A CN 202111083750 A CN202111083750 A CN 202111083750A CN 113793588 A CN113793588 A CN 113793588A
- Authority
- CN
- China
- Prior art keywords
- intelligent voice
- prompt
- rule
- voice prompt
- text
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000003213 activating effect Effects 0.000 claims abstract description 16
- 238000013507 mapping Methods 0.000 claims description 27
- 230000004913 activation Effects 0.000 claims description 4
- 230000003993 interaction Effects 0.000 abstract description 10
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000006855 networking Effects 0.000 description 3
- 208000033748 Device issues Diseases 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000002040 relaxant effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, and discloses an intelligent voice prompt method, an intelligent voice prompt device, intelligent voice prompt equipment and a storage medium, wherein the method comprises the following steps: acquiring current scene information; when the current scene information meets the scene information corresponding to the intelligent voice prompt rule, determining a target intelligent voice prompt rule according to the current scene information; determining a target prompt text according to the target intelligent voice prompt rule and activating an intelligent voice output signal; and carrying out intelligent voice prompt based on the intelligent voice output signal through the target prompt text. Corresponding prompt texts are generated by presetting corresponding intelligent voice prompt rules, and corresponding intelligent voice prompt information is sent to a user under appropriate scene information, so that voice prompt is more intelligent, and human-computer interaction experience is effectively improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an intelligent voice prompt method, an intelligent voice prompt device, intelligent voice prompt equipment and a storage medium.
Background
Far-field voice technology can liberate both hands of people through voice control equipment, and the household appliances are more intelligent, and the digital equipment is more easily used by people. The far-field sound control function of the television can enable a user to get rid of a complex remote controller, and the user can watch a program which the user wants to watch only by speaking the sentence into the television, so that the remote control television is convenient and practical. At present, all smart televisions have far-field voice control functions, one of the core functions of far-field voice control is interrupting awakening, wherein interrupting awakening is that when a television normally plays a program, a user speaks an awakening word, the television receives an awakening command and activates an artificial intelligence engine (AI engine for short), and then the AI engine mutes the television and is attentive to receive the control command. At present, voice interaction mainly comprises that a user actively sends a voice instruction, intelligent equipment such as a television and the like passively receives the voice instruction of the user for response, and the intelligent equipment cannot actively communicate with the user, so that poor human-computer interaction experience is easily caused.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide an intelligent voice prompt method, an intelligent voice prompt device, intelligent voice prompt equipment and a storage medium, and aims to solve the technical problem that in the prior art, intelligent equipment cannot actively communicate with a user, so that the human-computer interaction experience is poor.
In order to achieve the above object, the present invention provides an intelligent voice prompt method, which comprises the following steps:
acquiring current scene information;
when the current scene information meets the scene information corresponding to the intelligent voice prompt rule, determining a target intelligent voice prompt rule according to the current scene information;
determining a target prompt text according to the target intelligent voice prompt rule and activating an intelligent voice output signal;
and carrying out intelligent voice prompt based on the intelligent voice output signal through the target prompt text.
Optionally, a preset rule text mapping relation table is queried according to the target intelligent voice prompt rule, wherein the preset rule text mapping relation table comprises the intelligent voice prompt rule and the corresponding relation of the prompt text;
and determining a target prompt text according to the query result, and activating an intelligent voice output signal.
Optionally, a rule entry request is obtained, and an intelligent voice prompt rule is determined according to the rule entry request;
combining the intelligent voice prompt rule with a text template database to generate a corresponding prompt text;
and generating a preset rule text mapping relation table according to the intelligent voice prompt rule and the prompt text.
Optionally, the obtaining a rule entry request, and determining an intelligent voice prompt rule according to the rule entry request includes:
acquiring a rule input request, and generating a rule input display interface according to the rule input request;
and determining the intelligent voice prompt rules of different scenes according to the rule input display interface.
Optionally, the generating a corresponding prompt text by combining the intelligent voice prompt rule with a text template database includes:
acquiring keywords of the intelligent voice prompt rule;
and combining the keywords with a text template database to generate a corresponding prompt text.
Optionally, the generating a corresponding prompt text according to the combination of the keyword and the text template database includes:
determining candidate text templates of a text template database according to the keywords;
and combining the keywords with the candidate text template to generate a corresponding prompt text.
Optionally, after the performing the intelligent voice prompt based on the intelligent voice output signal through the target prompt text, the method further includes:
acquiring voice information of a target user corresponding to the target prompt text;
determining intention information of a target user according to the voice information;
and outputting an intelligent voice prompt result by responding to the intention information.
In addition, in order to achieve the above object, the present invention further provides an intelligent voice prompt apparatus, including:
the acquisition module is used for acquiring current scene information by voice;
the determining module is used for determining a target intelligent voice prompt rule according to the current scene information when the current scene information meets the scene information corresponding to the intelligent voice prompt rule;
the activation module is used for determining a target prompt text according to the target intelligent voice prompt rule and activating an intelligent voice output signal;
and the voice module is used for carrying out intelligent voice prompt on the basis of the intelligent voice output signal through the target prompt text.
In addition, in order to achieve the above object, the present invention further provides an intelligent voice prompt apparatus, including: a memory, a processor and an intelligent voice prompt program stored on the memory and executable on the processor, the intelligent voice prompt program configured to implement the steps of the intelligent voice prompt method as described above.
In addition, to achieve the above object, the present invention further provides a storage medium, in which an intelligent voice prompt program is stored, and the intelligent voice prompt program, when executed by a processor, implements the steps of the intelligent voice prompt method as described above.
The method comprises the steps of obtaining current scene information; when the current scene information meets the scene information corresponding to the intelligent voice prompt rule, determining a target intelligent voice prompt rule according to the current scene information; determining a target prompt text according to the target intelligent voice prompt rule and activating an intelligent voice output signal; and carrying out intelligent voice prompt based on the intelligent voice output signal through the target prompt text. Corresponding prompt texts are generated by presetting corresponding intelligent voice prompt rules, and corresponding intelligent voice prompt information is sent to a user under appropriate scene information, so that voice prompt is more intelligent, and human-computer interaction experience is effectively improved.
Drawings
FIG. 1 is a schematic structural diagram of an intelligent voice prompt device in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a first embodiment of an intelligent voice prompt method according to the present invention;
FIG. 3 is a flowchart illustrating a second embodiment of an intelligent voice prompt method according to the present invention;
FIG. 4 is a flowchart illustrating a third embodiment of an intelligent voice prompt method according to the present invention;
fig. 5 is a block diagram of an intelligent voice prompt apparatus according to a first embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an intelligent voice prompt device in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the intelligent voice prompt apparatus may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in FIG. 1 does not constitute a limitation of the intelligent voice prompt apparatus and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and a smart voice prompt program.
In the intelligent voice prompt apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 of the intelligent voice prompt device of the present invention may be arranged in the intelligent voice prompt device, and the intelligent voice prompt device calls the intelligent voice prompt program stored in the memory 1005 through the processor 1001 and executes the intelligent voice prompt method provided by the embodiment of the present invention.
An embodiment of the present invention provides an intelligent voice prompting method, and referring to fig. 2, fig. 2 is a schematic flow diagram of a first embodiment of an intelligent voice prompting method according to the present invention.
In this embodiment, the intelligent voice prompt method includes the following steps:
step S10: and acquiring current scene information.
It should be noted that the execution subject in this embodiment may be an intelligent voice prompt device, and may also be other devices that can implement the same or similar functions.
It can be understood that the current scene information may include current time information, device information of the intelligent voice prompt device, weather information of the current day, and the like, which is not limited in this embodiment, where the intelligent voice prompt device may be an intelligent device including a mobile phone, an intelligent television, and the like, and in this embodiment, the intelligent device may be an intelligent television for description.
Step S20: and when the current scene information meets the scene information corresponding to the intelligent voice prompt rule, determining a target intelligent voice prompt rule according to the current scene information.
It should be noted that, the acquired current scene information mainly depends on which scene areas the user applies when setting the corresponding intelligent prompting rule, so that the scene information is acquired for which scene areas, for example, if the intelligent voice prompting rule can prompt for nine morning hours, and is set to perform voice prompting 30 minutes before the morning hours, if the time information corresponding to the acquired current scene information is 8:30, the current scene information satisfies the scene information corresponding to the intelligent voice prompting rule, and therefore, the target intelligent voice prompting rule may perform intelligent voice prompting 30 minutes before the morning hours.
Step S30: and determining a target prompt text according to the target intelligent voice prompt rule, and activating an intelligent voice output signal.
It can be understood that the target prompt text can be voice information for intelligent voice prompt output of the intelligent device, and therefore, a preset rule text mapping relation table can be queried, wherein the preset rule text mapping relation table includes corresponding relations of the intelligent voice prompt rule and the prompt text, so that the target prompt text corresponding to the target intelligent voice prompt rule is obtained, and the intelligent voice output signal is activated.
For example, if the target intelligent voice prompt rule may be to remind people at nine morning hours of work, and the voice prompt is set 30 minutes before work, the target prompt text corresponding to the target intelligent voice prompt rule may be "leave 30 minutes away from work time, please leave the door in time" by querying a preset rule text mapping relation table, so that the intelligent voice output signal is activated when the target prompt text is determined, where the intelligent voice output signal is a signal for performing intelligent voice prompt on the target prompt text.
Step S40: and carrying out intelligent voice prompt based on the intelligent voice output signal through the target prompt text.
It should be understood that the intelligent device issues the corresponding intelligent voice prompt based on the intelligent voice output signal through the target prompt text so as to issue the corresponding prompt information to the user at the appropriate time.
It can be understood that, for example, the target prompt text is "leave 30 minutes away from work time, please go out in time", and the intelligent device performs voice broadcast based on the intelligent voice output signal on "leave 30 minutes away from work time, please go out in time" in the text information corresponding to the target prompt text.
The embodiment obtains the current scene information; when the current scene information meets the scene information corresponding to the intelligent voice prompt rule, determining a target intelligent voice prompt rule according to the current scene information; determining a target prompt text according to the target intelligent voice prompt rule and activating an intelligent voice output signal; and carrying out intelligent voice prompt based on the intelligent voice output signal through the target prompt text. Corresponding prompt texts are generated by presetting corresponding intelligent voice prompt rules, and corresponding intelligent voice prompt information is sent to a user under appropriate scene information, so that voice prompt is more intelligent, and human-computer interaction experience is effectively improved.
Referring to fig. 3, fig. 3 is a flowchart illustrating an intelligent voice prompt method according to a second embodiment of the present invention.
Based on the first embodiment, the intelligent voice prompt method of this embodiment includes, in step S30, further including:
step S301: and inquiring a preset rule text mapping relation table according to the target intelligent voice prompt rule, wherein the preset rule text mapping relation table comprises the intelligent voice prompt rule and the corresponding relation of the prompt text.
It should be understood that the preset rule text mapping relation table may be a correspondence between the intelligent voice prompt rule and the prompt text, and therefore, the preset rule text mapping relation table may be queried to determine whether the target prompt text corresponding to the target intelligent voice prompt rule is involved, so as to obtain a query result.
Further, before querying a preset rule text mapping relation table according to the target intelligent voice prompt rule, the method further includes:
and acquiring a rule input request, and determining an intelligent voice prompt rule according to the rule input request.
It should be noted that the rule entry request may be a request signal for performing the rule entry triggered by the user through the device terminal, and the user may click a button for the rule entry in the specific implementation process.
Further, acquiring a rule entry request, and determining an intelligent voice prompt rule according to the rule entry request, including:
acquiring a rule input request, and generating a rule input display interface according to the rule input request; and determining the intelligent voice prompt rules of different scenes according to the rule input display interface.
It should be understood that the rule entry display interface includes a scene, a prompt date, a prompt content, or other information related to voice prompt, and the present embodiment is not limited thereto, for example, the scene selected on the rule entry display interface may include time prompts such as a special day of a family member and a special anniversary, names or names of members are input in the prompt content, and the prompt date may select a corresponding intelligent voice prompt rule such as seven days before a holiday; or the prompting scene is weather, and the prompting time is the corresponding intelligent voice prompting rule of eight points every day and the like; or the prompted scene is intelligent equipment information, and the method comprises the following steps: under the condition that the electronic cable is loose in connection, the station is not searched all the time after automatic station searching, the user clicks and plays the online video without networking, and as a result, the online video cannot be normally played all the time or the online video is played through intelligent voice prompt rules such as information related to other devices connected with the intelligent device through wifi.
And combining the intelligent voice prompt rule with a text template database to generate a corresponding prompt text.
It can be understood that various prompt text templates are stored in the text template database, and therefore, corresponding prompt texts can be generated by combining the keywords of the obtained intelligent voice prompt rules with various corresponding prompt text templates in the text template database.
Further, the step of combining the intelligent voice prompt rule with a text template database to generate a corresponding prompt text comprises:
acquiring keywords of the intelligent voice prompt rule; and combining the keywords with a text template database to generate a corresponding prompt text.
Further, obtaining keywords of the intelligent voice prompt rule; combining the keywords with a text template database to generate a corresponding prompt text, wherein the prompt text comprises the following steps:
acquiring keywords of the intelligent voice prompt rule; and combining the keywords with a text template database to generate a corresponding prompt text.
It can be understood that the keywords of the intelligent voice prompt rule are set according to a specific scene and prompt information, for example, if a scene about the prompt of the working time is stored in the text template database, the corresponding prompt text template is "away from the working time by minutes", please go out in time ", the working time is set to nine points by the intelligent voice prompt rule, and the prompt is performed 30 minutes in advance, so that the keywords in the scene are 30 minutes, and the corresponding prompt text is" away from the working time by 30 minutes ", please go out in time". Similarly, the user sets the special days of the family members, such as the birthday of father, mother, wife, child, the special days of father, mother, wedding anniversary, valentine's day, and the like, sets the intelligent voice prompt rule which prompts 7 days ahead of the special days, combines the intelligent voice prompt rule with the text template database, and can set the prompt text corresponding to the intelligent voice prompt rule as "the birthday of your mother and 7 days ahead of the wedding anniversary", "a gift list is prepared for you, and how you want to spend the special days? "; or the intelligent device acquires the weather condition of the current day, and actively gives the intelligent voice prompt rule of voice prompt to the user half an hour before the user is on duty, the corresponding prompt text can be combined with the text template database, and the corresponding prompt text can be weather such as raining, typhoon, hail and the like, and people can remember to take an umbrella before going out, and the people pay attention to safety! "; or, the smart machine is connected with the intelligent refrigerator through wifi, and the information feedback of the acquisition of the refrigerator is to the smart machine: for example, the number of days in the refrigerator is the number of days, and the intelligent voice prompt rule for prompting the existing state of food is carried out. The corresponding prompt text may be "food is eaten soon or has been eaten". The food has not been eaten, has been left for days, please check for spoilage as soon as possible ", etc. by combining with the text template database.
It should be understood that, for example, when prompting is performed on the device information of the smart device, for example, after a user automatically searches for a channel in an ATV/DTV channel, the user does not always search for the channel, and the corresponding prompt text may be "please check whether a signal line is connected or a line is changed for trying"; the user clicks to play the online video without networking, the result cannot be played normally all the time, and when the intelligent device detects that the online video is played under the condition of no networking, the corresponding prompt text can be 'no connection of the current network, please connect a wired or wireless network for trial test, and enter a setting-network setting interface for connecting with the network'; when the system detects such abnormal conditions, the corresponding prompt text can be 'possibly loosening the electronic cable, please unplug the electronic cable again for trial test after powering off the television', and the like.
And generating a preset rule text mapping relation table according to the intelligent voice prompt rule and the prompt text.
It should be noted that the preset rule text mapping relationship table may be generated according to the intelligent voice prompt rule, the identifier corresponding to the intelligent voice prompt rule, the prompt text, and the identifier corresponding to the intelligent voice prompt rule, where the identifier of the intelligent voice prompt rule and the identifier of the prompt text may be set by those skilled in the art, and this embodiment does not limit this.
Step S302: and determining a target prompt text according to the query result, and activating an intelligent voice output signal.
It can be understood that if the preset rule text mapping relation table is queried by the target intelligent voice prompt rule to have a corresponding target prompt text, the corresponding target prompt text can be determined, and the intelligent voice output signal is activated.
The embodiment determines the intelligent voice prompt rule according to the rule input request by acquiring the rule input request; combining the intelligent voice prompt rule with a text template database to generate a corresponding prompt text; generating a preset rule text mapping relation table according to the intelligent voice prompt rule and the prompt text to preset a preset rule text mapping relation table, and inquiring the preset rule text mapping relation table according to the target intelligent voice prompt rule; and determining a target prompt text according to the query result, and activating an intelligent voice output signal, thereby effectively improving the accuracy of human-computer interaction experience.
Referring to fig. 4, fig. 4 is a flowchart illustrating an intelligent voice prompt method according to a third embodiment of the present invention.
Based on the foregoing first embodiment of the intelligent voice prompt, after the step S40, the method further includes:
step S501: and acquiring voice information of the target user corresponding to the target prompt text.
It can be understood that, after the smart device sends the voice prompt, the voice assistant in the smart device is turned on, and the voice information of the target user is received by the voice assistant of the smart device, so that the voice information of the target user corresponding to the target prompt text can be obtained, for example, the smart device sends "a birthday away from mom, 7 days later, please prepare a gift in advance", "xiaowei has prepared a gift list for you, how you want to spend this special day? After the language prompt, the voice assistant is turned on, so as to obtain the voice information of "what recommendation" fed back by the target user.
Step S502: and determining intention information of the target user according to the voice information.
It should be understood that the intention information may be the intention of the target user determined by semantic analysis of the voice information, for example, the voice information is "what recommended", and then a gift list prepared by the smart device by the user may be analyzed.
Step S503: and outputting an intelligent voice prompt result by responding to the intention information.
It should be noted that, based on the intention information, the intelligent terminal responds to the intention information to obtain an intelligent voice prompt result, for example, responds to the intention information of the target user, so as to automatically display a related gift list on the interface, and a good place for dinner party, or a route recommendation such as relaxing a nearby scenic spot or self-driving tour.
The embodiment obtains the voice information of the target user corresponding to the target prompt text; determining intention information of a target user according to the voice information; and outputting an intelligent voice prompt result by responding to the intention information, thereby effectively improving the intelligence of human-computer interaction experience.
In addition, an embodiment of the present invention further provides a storage medium, where an intelligent voice prompt program is stored on the storage medium, and the intelligent voice prompt program, when executed by a processor, implements the steps of the intelligent voice prompt method described above.
Since the storage medium adopts all technical solutions of all the embodiments, at least all the beneficial effects brought by the technical solutions of the embodiments are achieved, and no further description is given here.
Referring to fig. 5, fig. 5 is a block diagram of an intelligent voice prompt apparatus according to a first embodiment of the present invention.
As shown in fig. 5, the intelligent voice prompt device provided in the embodiment of the present invention includes:
and the obtaining module 10 is used for obtaining the current scene information through voice.
It can be understood that the current scene information may include current time information, device information of the intelligent voice prompt device, weather information of the current day, and the like, which is not limited in this embodiment, where the intelligent voice prompt device may be an intelligent device including a mobile phone, an intelligent television, and the like, and in this embodiment, the intelligent device may be an intelligent television for description.
And the determining module 20 is configured to determine a target intelligent voice prompt rule according to the current scene information when the current scene information meets the scene information corresponding to the intelligent voice prompt rule.
It should be noted that, the acquired current scene information mainly depends on which scene areas the user applies when setting the corresponding intelligent prompting rule, so that the scene information is acquired for which scene areas, for example, if the intelligent voice prompting rule can prompt for nine morning hours, and is set to perform voice prompting 30 minutes before the morning hours, if the time information corresponding to the acquired current scene information is 8:30, the current scene information satisfies the scene information corresponding to the intelligent voice prompting rule, and therefore, the target intelligent voice prompting rule may perform intelligent voice prompting 30 minutes before the morning hours.
And the activation module 30 is used for determining a target prompt text according to the target intelligent voice prompt rule and activating an intelligent voice output signal.
It can be understood that the target prompt text can be voice information for intelligent voice prompt output of the intelligent device, and therefore, a preset rule text mapping relation table can be queried, wherein the preset rule text mapping relation table includes corresponding relations of the intelligent voice prompt rule and the prompt text, so that the target prompt text corresponding to the target intelligent voice prompt rule is obtained, and the intelligent voice output signal is activated.
For example, if the target intelligent voice prompt rule may be to remind people at nine morning hours of work, and the voice prompt is set 30 minutes before work, the target prompt text corresponding to the target intelligent voice prompt rule may be "leave 30 minutes away from work time, please leave the door in time" by querying a preset rule text mapping relation table, so that the intelligent voice output signal is activated when the target prompt text is determined, where the intelligent voice output signal is a signal for performing intelligent voice prompt on the target prompt text.
And the voice module 40 is used for carrying out intelligent voice prompt on the basis of the intelligent voice output signal through the target prompt text.
It should be understood that the intelligent device issues the corresponding intelligent voice prompt based on the intelligent voice output signal through the target prompt text so as to issue the corresponding prompt information to the user at the appropriate time.
It can be understood that, for example, the target prompt text is "leave 30 minutes away from work time, please go out in time", and the intelligent device performs voice broadcast based on the intelligent voice output signal on "leave 30 minutes away from work time, please go out in time" in the text information corresponding to the target prompt text.
The embodiment obtains the current scene information; when the current scene information meets the scene information corresponding to the intelligent voice prompt rule, determining a target intelligent voice prompt rule according to the current scene information; determining a target prompt text according to the target intelligent voice prompt rule and activating an intelligent voice output signal; and carrying out intelligent voice prompt based on the intelligent voice output signal through the target prompt text. Corresponding prompt texts are generated by presetting corresponding intelligent voice prompt rules, and corresponding intelligent voice prompt information is sent to a user under appropriate scene information, so that voice prompt is more intelligent, and human-computer interaction experience is effectively improved.
In an embodiment, the activation module 30 is further configured to query a preset rule text mapping relationship table according to the target intelligent voice prompt rule, where the preset rule text mapping relationship table includes a corresponding relationship between the intelligent voice prompt rule and the prompt text; and determining a target prompt text according to the query result, and activating an intelligent voice output signal.
In an embodiment, the obtaining module 10 is further configured to obtain a rule entry request, and determine an intelligent voice prompt rule according to the rule entry request; combining the intelligent voice prompt rule with a text template database to generate a corresponding prompt text; and generating a preset rule text mapping relation table according to the intelligent voice prompt rule and the prompt text.
In an embodiment, the obtaining module 10 is further configured to obtain a rule entry request, and generate a rule entry display interface according to the rule entry request; and determining the intelligent voice prompt rules of different scenes according to the rule input display interface.
In an embodiment, the obtaining module 10 is further configured to obtain a keyword of the intelligent voice prompt rule; and combining the keywords with a text template database to generate a corresponding prompt text.
In an embodiment, the obtaining module 10 is further configured to determine a candidate text template of a text template database according to the keyword; and combining the keywords with the candidate text template to generate a corresponding prompt text.
In an embodiment, the determining module 20 is further configured to obtain voice information of a target user corresponding to the target prompt text; determining intention information of a target user according to the voice information; and outputting an intelligent voice prompt result by responding to the intention information.
Other embodiments or specific implementation methods of the intelligent voice prompt device of the present invention may refer to the above embodiments of the methods, and are not described in detail here.
It should be understood that the above is only an example, and the technical solution of the present invention is not limited in any way, and in a specific application, a person skilled in the art may set the technical solution as needed, and the present invention is not limited thereto.
It should be noted that the above-described work flows are only exemplary, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of them to achieve the purpose of the solution of the embodiment according to actual needs, and the present invention is not limited herein.
In addition, the technical details that are not described in detail in this embodiment may refer to the intelligent voice prompt method provided in any embodiment of the present invention, and are not described herein again.
Further, it is to be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g. Read Only Memory (ROM)/RAM, magnetic disk, optical disk), and includes several instructions for enabling a terminal device (e.g. a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. An intelligent voice prompt method is characterized by comprising the following steps:
acquiring current scene information;
when the current scene information meets the scene information corresponding to the intelligent voice prompt rule, determining a target intelligent voice prompt rule according to the current scene information;
determining a target prompt text according to the target intelligent voice prompt rule and activating an intelligent voice output signal;
and carrying out intelligent voice prompt based on the intelligent voice output signal through the target prompt text.
2. The intelligent voice prompt method of claim 1, wherein determining a target prompt text according to the target intelligent voice prompt rule and activating an intelligent voice output signal comprises:
inquiring a preset rule text mapping relation table according to the target intelligent voice prompt rule, wherein the preset rule text mapping relation table comprises the intelligent voice prompt rule and the corresponding relation of the prompt text;
and determining a target prompt text according to the query result, and activating an intelligent voice output signal.
3. The intelligent voice prompt method according to claim 2, wherein before querying a preset rule text mapping relationship table according to the target intelligent voice prompt rule, the method further comprises:
acquiring a rule input request, and determining an intelligent voice prompt rule according to the rule input request;
combining the intelligent voice prompt rule with a text template database to generate a corresponding prompt text;
and generating a preset rule text mapping relation table according to the intelligent voice prompt rule and the prompt text.
4. The intelligent voice prompt method of claim 3, wherein obtaining a rule entry request from which to determine an intelligent voice prompt rule comprises:
acquiring a rule input request, and generating a rule input display interface according to the rule input request;
and determining the intelligent voice prompt rules of different scenes according to the rule input display interface.
5. The intelligent voice prompt method according to claim 3, wherein the generating of the corresponding prompt text according to the combination of the intelligent voice prompt rule and the text template database comprises:
acquiring keywords of the intelligent voice prompt rule;
and combining the keywords with a text template database to generate a corresponding prompt text.
6. The intelligent voice prompt method according to claim 5, wherein the generating of the corresponding prompt text according to the combination of the keyword and the text template database comprises:
determining candidate text templates of a text template database according to the keywords;
and combining the keywords with the candidate text template to generate a corresponding prompt text.
7. The intelligent voice prompt method of any one of claims 1 to 6, wherein after the intelligent voice prompt based on the intelligent voice output signal by the target prompt text, further comprising:
acquiring voice information of a target user corresponding to the target prompt text;
determining intention information of a target user according to the voice information;
and outputting an intelligent voice prompt result by responding to the intention information.
8. An intelligent voice prompt device, characterized in that, intelligent voice prompt device includes:
the acquisition module is used for acquiring current scene information by voice;
the determining module is used for determining a target intelligent voice prompt rule according to the current scene information when the current scene information meets the scene information corresponding to the intelligent voice prompt rule;
the activation module is used for determining a target prompt text according to the target intelligent voice prompt rule and activating an intelligent voice output signal;
and the voice module is used for carrying out intelligent voice prompt on the basis of the intelligent voice output signal through the target prompt text.
9. An intelligent voice prompt device, characterized in that intelligent voice prompt device includes: a memory, a processor, and a smart voice prompt program stored on the memory and executable on the processor, the smart voice prompt program configured to implement the smart voice prompt method of any one of claims 1 to 7.
10. A storage medium having stored thereon an intelligent voice guidance program which, when executed by a processor, implements the intelligent voice guidance method of any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111083750.6A CN113793588A (en) | 2021-09-15 | 2021-09-15 | Intelligent voice prompt method, device, equipment and storage medium |
| PCT/CN2021/140349 WO2023040109A1 (en) | 2021-09-15 | 2021-12-22 | Intelligent speech prompt method and device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111083750.6A CN113793588A (en) | 2021-09-15 | 2021-09-15 | Intelligent voice prompt method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113793588A true CN113793588A (en) | 2021-12-14 |
Family
ID=79183708
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111083750.6A Pending CN113793588A (en) | 2021-09-15 | 2021-09-15 | Intelligent voice prompt method, device, equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113793588A (en) |
| WO (1) | WO2023040109A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023040109A1 (en) * | 2021-09-15 | 2023-03-23 | 深圳创维－Rgb电子有限公司 | Intelligent speech prompt method and device, and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109684443A (en) * | 2018-11-01 | 2019-04-26 | 百度在线网络技术（北京）有限公司 | Intelligent interactive method and device |
| JP2020030814A (en) * | 2018-08-22 | 2020-02-27 | バイドゥ オンライン ネットワーク テクノロジー（ペキン） カンパニー リミテッド | Method and apparatus for processing information |
| CN110929074A (en) * | 2018-08-31 | 2020-03-27 | 长城汽车股份有限公司 | Vehicle-mounted voice broadcasting method and system |
| CN112837671A (en) * | 2020-12-30 | 2021-05-25 | 平安科技（深圳）有限公司 | Intelligent voice prompt method, device and equipment and readable storage medium |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101976304A (en) * | 2010-10-16 | 2011-02-16 | 陈长江 | Intelligent life housekeeper system and method |
| KR102188090B1 (en) * | 2013-12-11 | 2020-12-04 | 엘지전자 주식회사 | A smart home appliance, a method for operating the same and a system for voice recognition using the same |
| US10268491B2 (en) * | 2015-09-04 | 2019-04-23 | Vishal Vadodaria | Intelli-voyage travel |
| CN108536655A (en) * | 2017-12-21 | 2018-09-14 | 广州市讯飞樽鸿信息技术有限公司 | Audio production method and system are read aloud in a kind of displaying based on hand-held intelligent terminal |
| CN109492795A (en) * | 2018-10-11 | 2019-03-19 | 平安科技（深圳）有限公司 | Airport boarding service processing method, device, equipment and medium based on AI |
| CN112420038A (en) * | 2020-10-28 | 2021-02-26 | 深圳创维－Rgb电子有限公司 | Intelligent voice broadcasting method and device capable of self-adapting scene judgment |
| CN112463106A (en) * | 2020-11-12 | 2021-03-09 | 深圳Tcl新技术有限公司 | Voice interaction method, device and equipment based on intelligent screen and storage medium |
| CN113793588A (en) * | 2021-09-15 | 2021-12-14 | 深圳创维－Rgb电子有限公司 | Intelligent voice prompt method, device, equipment and storage medium |
-
2021
- 2021-09-15 CN CN202111083750.6A patent/CN113793588A/en active Pending
- 2021-12-22 WO PCT/CN2021/140349 patent/WO2023040109A1/en unknown
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2020030814A (en) * | 2018-08-22 | 2020-02-27 | バイドゥ オンライン ネットワーク テクノロジー（ペキン） カンパニー リミテッド | Method and apparatus for processing information |
| CN110929074A (en) * | 2018-08-31 | 2020-03-27 | 长城汽车股份有限公司 | Vehicle-mounted voice broadcasting method and system |
| CN109684443A (en) * | 2018-11-01 | 2019-04-26 | 百度在线网络技术（北京）有限公司 | Intelligent interactive method and device |
| CN112837671A (en) * | 2020-12-30 | 2021-05-25 | 平安科技（深圳）有限公司 | Intelligent voice prompt method, device and equipment and readable storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023040109A1 (en) * | 2021-09-15 | 2023-03-23 | 深圳创维－Rgb电子有限公司 | Intelligent speech prompt method and device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023040109A1 (en) | 2023-03-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107370649B (en) | Household appliance control method, system, control terminal and storage medium | |
| US20220221959A1 (en) | Annotations in software applications for invoking dialog system functions | |
| US11688402B2 (en) | Dialog management with multiple modalities | |
| CN106782526B (en) | Voice control method and device | |
| KR102189855B1 (en) | Parameter collection and automatic dialog generation in dialog systems | |
| CN107003999B (en) | System and method for subsequent response to a user's prior natural language input | |
| US20180277115A1 (en) | Generating dialog recommendations for chat information systems based on user interaction and environmental data | |
| CN110046227B (en) | Configuration method, interaction method, device, equipment and storage medium of dialogue system | |
| CN110770694B (en) | Obtaining response information from multiple corpora | |
| TWI511125B (en) | Voice control method, mobile terminal apparatus and voice controlsystem | |
| CN106205615B (en) | Control method and system based on voice interaction | |
| US20150331665A1 (en) | Information provision method using voice recognition function and control method for device | |
| US20170368683A1 (en) | User portrait based skill package recommendation device and method | |
| CN112463106A (en) | Voice interaction method, device and equipment based on intelligent screen and storage medium | |
| KR102360262B1 (en) | Method for generating and pushing integration information, and device, terminal, server and medium thereof | |
| CN111984180B (en) | Terminal screen reading method, device, equipment and computer readable storage medium | |
| CN113793588A (en) | Intelligent voice prompt method, device, equipment and storage medium | |
| CN112383662B (en) | Information display method and device and electronic equipment | |
| CN112306450A (en) | Information processing method and device | |
| CN111933135A (en) | Terminal control method and device, intelligent terminal and computer readable storage medium | |
| CN113678119A (en) | Electronic device for generating natural language response and method thereof | |
| CN115658875A (en) | Data processing method based on chat service and related product | |
| CN113314115A (en) | Voice processing method of terminal equipment, terminal equipment and readable storage medium | |
| US20180336890A1 (en) | Semantic processing method of robot and semantic processing device | |
| CN113421565A (en) | Search method, search device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |