CN107909998B - Voice instruction processing method and device, computer equipment and storage medium - Google Patents

Voice instruction processing method and device, computer equipment and storage medium Download PDF

Info

Publication number
CN107909998B
CN107909998B CN201710969298.0A CN201710969298A CN107909998B CN 107909998 B CN107909998 B CN 107909998B CN 201710969298 A CN201710969298 A CN 201710969298A CN 107909998 B CN107909998 B CN 107909998B
Authority
CN
China
Prior art keywords
instruction
parameters
keywords
voice
semantic
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.)
Active
Application number
CN201710969298.0A
Other languages
Chinese (zh)
Other versions
CN107909998A (en
Inventor
杨晋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Gongjin Electronics Co Ltd
Original Assignee
Chengdu Gongwei Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chengdu Gongwei Technology Co ltd filed Critical Chengdu Gongwei Technology Co ltd
Priority to CN201710969298.0A priority Critical patent/CN107909998B/en
Publication of CN107909998A publication Critical patent/CN107909998A/en
Application granted granted Critical
Publication of CN107909998B publication Critical patent/CN107909998B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/284—Lexical analysis, e.g. tokenisation or collocates
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L2015/088—Word spotting
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223—Execution procedure of a spoken command

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • User Interface Of Digital Computer (AREA)
  • Telephonic Communication Services (AREA)
  • Machine Translation (AREA)

Abstract

The invention relates to a voice instruction processing method, a voice instruction processing device, computer equipment and a storage medium, wherein the method comprises the following steps: receiving a voice instruction uploaded by the intelligent home equipment, and converting the voice instruction into a character instruction; identifying key words in the text instructions; reading a configuration file, wherein the configuration file comprises a plurality of instruction parameters; traversing a plurality of instruction parameters, and matching the instruction parameters with the key words; if the unmatched instruction parameters exist, generating corresponding prompt information according to the unmatched instruction parameters; and receiving a voice command corresponding to the prompt message, and avoiding the user from repeatedly inputting the same voice command. Repeating the step of identifying the key words in the text instructions until all instruction parameters match the corresponding key words; and generating an operation instruction by using a plurality of instruction parameters of the matched keyword word, and executing the operation instruction. Therefore, the friendliness of a man-machine interaction mode can be improved, and the expansibility of the intelligent home system can be improved.

Description

Voice instruction processing method and device, computer equipment and storage medium
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for processing a voice instruction, a computer device, and a storage medium.
Background
With the rapid development of computer technology, the application of natural language human-computer interaction on software systems is more and more extensive. Human-computer interaction by using natural language is more in line with human habits, and brings much convenience to the life of people. For example, a user says "turn on the light", and the smart home system converts the natural language into a command for turning on the light, and then issues the command to complete the operation of turning on the light. However, in some complex instruction scenarios, due to the processing capability of the smart home system, the rigor of natural language, and the like, some conditions of the voice instruction may not be completely recognized by the smart home system.
In the traditional mode, the interaction mode of prompting the user to re-input is not friendly enough, and the efficiency is low. And the interaction mode aiming at the specific scene has low expansibility of the system and cannot adapt to the later-stage requirements of continuous development. How to improve the friendliness of a man-machine interaction mode and improve the expansibility of an intelligent home system becomes a technical problem to be solved at present.
Disclosure of Invention
Therefore, in order to solve the above technical problems, it is necessary to provide a voice instruction processing method, an apparatus, a computer device, and a storage medium, which can improve human-computer interaction friendliness and smart home system extensibility.
A method of voice instruction processing, comprising:
receiving a voice instruction uploaded by intelligent home equipment, and converting the voice instruction into a text instruction;
identifying key words in the text instructions;
reading a configuration file, wherein the configuration file comprises a plurality of instruction parameters;
traversing the instruction parameters, and matching the instruction parameters with the keywords;
if the unmatched instruction parameters exist, generating corresponding prompt information according to the unmatched instruction parameters;
receiving a voice instruction corresponding to the intelligent home equipment and the prompt message, and repeating the step of recognizing the keywords in the character instruction until all instruction parameters are matched with the corresponding keywords;
generating an operation instruction by using a plurality of instruction parameters matched with the keywords, and issuing the operation instruction to the intelligent home equipment so that the intelligent home equipment executes the operation instruction.
In one embodiment, before the step of receiving the voice instruction uploaded by the smart home device, the method further includes:
acquiring a data table corresponding to the configuration file;
displaying the data table, wherein the data table comprises a plurality of instruction parameters and corresponding prompt information;
receiving a modification instruction, and modifying the instruction parameter and the corresponding prompt information according to the modification instruction;
and storing the modified instruction parameters and the corresponding prompt information into the configuration file.
In one embodiment, after the step of identifying the keyword in the text instruction, the method further includes:
reading a semantic word set file, wherein the semantic word set file comprises a plurality of instruction semantic words;
and performing semantic comparison on the keywords and the instruction related semantic words, and converting the keywords into the instruction semantic words if the semantics are the same or similar.
In one embodiment, the voice instruction carries a timestamp, and the method further comprises:
acquiring current system time;
calculating a difference value between the current system time and a timestamp of the voice instruction, and comparing the difference value with a preset timeout duration;
and when the difference is larger than the timeout duration, repeating the step of traversing the plurality of instruction parameters until the operation instruction is executed.
A method of voice instruction processing, comprising:
receiving a voice instruction uploaded by a terminal, and converting the voice instruction into a text instruction;
identifying key words in the text instructions;
reading a configuration file, wherein the configuration file comprises a plurality of instruction parameters;
traversing the instruction parameters, and matching the instruction parameters with the keywords;
if the unmatched instruction parameters exist, generating corresponding prompt information according to the unmatched instruction parameters;
receiving a voice instruction corresponding to the prompt message and uploaded by the terminal, and repeating the step of identifying the keywords in the character instruction until all instruction parameters are matched with the corresponding keywords;
generating an operation instruction by using a plurality of instruction parameters matched with the keywords, and issuing the operation instruction to the intelligent home equipment so that the intelligent home equipment executes the operation instruction.
In one embodiment, before the step of receiving the voice instruction, the method further includes:
acquiring a data table corresponding to the configuration file;
displaying the data table, wherein the data table comprises a plurality of instruction parameters and corresponding prompt information;
receiving a modification instruction, and modifying the instruction parameter and the corresponding prompt information according to the modification instruction;
and storing the modified instruction parameters and the corresponding prompt information into the configuration file.
A voice instruction processing apparatus comprising:
the command receiving module is used for receiving a voice command uploaded by the intelligent household equipment and converting the voice command into a character command;
the matching module is used for identifying key words in the character instruction; reading a configuration file, wherein the configuration file comprises a plurality of instruction parameters; traversing the instruction parameters, and matching the instruction parameters with the keywords;
the information prompt module is used for generating corresponding prompt information according to the unmatched instruction parameters if the unmatched instruction parameters exist;
the instruction receiving module is further used for receiving a voice instruction which is uploaded by the intelligent household equipment and corresponds to the prompt information;
the matching module is further used for repeating the step of identifying the keywords in the character instruction until all instruction parameters are matched with the corresponding keywords;
and the instruction issuing module is used for generating an operation instruction by using the plurality of instruction parameters matched with the keywords and issuing the operation instruction to the intelligent home equipment so that the intelligent home equipment executes the operation instruction.
A voice instruction processing apparatus comprising:
the instruction receiving module is used for receiving a voice instruction uploaded by a terminal and converting the voice instruction into a character instruction;
the matching module is used for identifying key words in the character instruction; reading a configuration file, wherein the configuration file comprises a plurality of instruction parameters; traversing the instruction parameters, and matching the instruction parameters with the keywords;
the information prompt module is used for generating corresponding prompt information according to the unmatched instruction parameters if the unmatched instruction parameters exist;
the instruction receiving module is further used for receiving a voice instruction which is uploaded by the terminal and corresponds to the prompt information;
the matching module is further used for repeating the step of identifying the keywords in the character instruction until all instruction parameters are matched with the corresponding keywords;
the instruction issuing module is used for generating an operation instruction by using the plurality of instruction parameters matched with the keywords and issuing the operation instruction to the intelligent home equipment so that the intelligent home equipment executes the operation instruction.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the above method when executing the program.
A computer-readable storage medium, on which a computer program is stored, characterized in that the program realizes the steps of the above-mentioned method when executed by a processor.
According to the voice instruction processing method, after the server receives the voice instruction uploaded by the intelligent household equipment, the voice instruction is converted into a character instruction; identifying keywords or words in the character instruction; the configuration file is read, the configuration file comprises a plurality of instruction parameters, and a user can modify the configuration file according to the requirement of the user, so that the user can customize parameter information in the configuration file to adapt to the expansion requirement on the intelligent home system in the later period. The server traverses the instruction parameters and matches the instruction parameters with the keywords; if the unmatched instruction parameters exist, the corresponding prompt information is generated according to the unmatched instruction parameters, and the prompt information is generated aiming at the unmatched instruction parameters, so that the user does not need to repeatedly input the previous voice instruction, and only needs to further input the voice instruction corresponding to the prompt information according to the inquiry statement sent by the intelligent household equipment, so that the repeated input of the user is avoided, and the interaction friendliness and efficiency of the user and the intelligent household equipment are improved. Therefore, the friendliness of human-computer interaction can be improved, and the expansibility of the intelligent home system can be improved.
Drawings
FIG. 1 is a diagram of a hardware environment for a method of processing voice commands in one embodiment;
FIG. 2 is a flow diagram of a method for voice command processing in one embodiment;
FIG. 3 is a flow diagram of a method for processing voice commands in one embodiment;
FIG. 4 is a diagram illustrating an internal structure of the apparatus for processing a voice command according to an embodiment;
FIG. 5 is a diagram illustrating an internal structure of the apparatus for processing a voice command according to an embodiment;
FIG. 6 is a diagram showing an internal configuration of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not limiting of the application.
The voice instruction processing method provided in the embodiment of the present application can be applied to the application scenario shown in fig. 1. The smart home devices 102 have a network access function, and may be smart home devices such as an air conditioner, a sound box, a television, and a computer. The server 104, which may be an independent server or a cluster server, is used to implement the voice instruction processing method. The smart home devices 102 are connected to the server 104 through a network. The smart home device 102 receives a voice instruction sent by a user, and sends the voice instruction to the server 104. The server 104 receives the voice command, converts the voice command into a character command and identifies a keyword in the character command; reading a configuration file, wherein the configuration file comprises a plurality of instruction parameters; traversing a plurality of instruction parameters, and matching the instruction parameters with the keywords; if the unmatched instruction parameters exist, generating corresponding prompt information according to the unmatched instruction parameters; the server 104 sends the prompt information to the smart home device 102, and the smart home device 102 sends a voice message corresponding to the prompt information to the user, so that the user does not need to repeatedly input the same voice command. The smart home device 102 receives a voice instruction corresponding to the prompt information, which is input by the user, and sends the voice instruction to the server 104. After receiving the voice command corresponding to the prompt message, the server 104 repeats the step of recognizing the keywords in the text command until all command parameters match the corresponding keywords; the server 104 generates an operation instruction by using the instruction parameters matching the keywords, and issues the operation instruction to the smart home device 102, so that the smart home device 102 executes the operation instruction. The user can improve the friendliness of a man-machine interaction mode by inputting a voice command according to the prompt message, and the expansibility of the intelligent home system can be improved by calling the configuration file.
As shown in FIG. 2, in one embodiment, a method of voice instruction processing is provided. The embodiment is exemplified by applying the method to a server. The method specifically comprises the following steps:
step S202: and receiving a voice instruction uploaded by the intelligent household equipment, and converting the voice instruction into a text instruction.
The voice instruction is a voice instruction corresponding to a natural language message input by a user through the intelligent household equipment. The word instruction is a word instruction which identifies the audio frequency of the voice instruction as corresponding to the text information. Specifically, a user inputs a voice instruction corresponding to a natural language into the intelligent home device, the intelligent home device sends the voice instruction to the server through the network, the server receives the voice instruction uploaded by the intelligent home device through the voice instruction receiving interface, the voice instruction receiving interface is a human-computer interaction interface, and the voice instruction is cached into the voice instruction cache. And after receiving the voice instruction, the server calls a thread in the processing thread pool to convert the voice instruction into a corresponding word instruction.
In one embodiment, the server may perform feature extraction on the voice instruction, recognize feature data of the voice instruction, perform framing processing on the voice instruction according to the acoustic model to obtain a plurality of phonemes, convert the plurality of phonemes obtained through the processing into a character sequence according to a correspondence between candidate words and phonemes in the candidate word library, and adjust the converted character sequence by using the voice model to obtain text information corresponding to the voice instruction, thereby obtaining the text instruction corresponding to the voice instruction.
Step S204: keywords in the text instructions are identified.
Specifically, the server carries out word segmentation processing on the character instruction according to a preset word segmentation mode by calling threads in a processing thread pool, splits the content of the character instruction to obtain characters or words in the character instruction, and matches the characters or words of the voice instruction with preset instruction semantic words; and when the matching is successful, determining the word as a keyword in the voice command. After identifying the keywords in the text instruction, the server checks whether the obtained keywords are legal or not and whether the keywords are a complete instruction or not.
Step S206: a configuration file is read, the configuration file including a plurality of instruction parameters.
The configuration file may be an XML (Extensible Markup Language) configuration file, and the XML configuration file includes instruction parameters, a verification method, and a dialog query. Specifically, the instruction parameter may be parameter information required for executing the instruction, including parameter information such as an instruction subject parameter, an instruction object parameter, an instruction behavior parameter, an instruction condition parameter, and a query statement. For example, the instruction subject parameter may correspond to a main body of an execution instruction, the instruction object parameter may correspond to an item to be executed, the instruction behavior parameter may correspond to a specific operation to be executed, the instruction condition parameter may correspond to a time range for executing the operation, and the like. The user can modify the configuration file according to the own requirements, so that the user can customize the parameter information in the configuration file, and the expansibility of the intelligent home system can be improved.
Step S208: and traversing the instruction parameters, and matching the instruction parameters with the keywords.
Step S210: and if the unmatched instruction parameters exist, generating corresponding prompt information according to the unmatched instruction parameters.
Specifically, the server reads an instruction parameter in the configuration file, wherein the instruction parameter corresponds to prompt information related to the instruction parameter. And circularly traversing the instruction parameters in the configuration file, comparing each instruction parameter with a keyword in the character instruction, and judging whether the keyword is matched with the instruction parameters. And if the keyword is not matched with the corresponding instruction parameter, generating corresponding prompt information according to the instruction parameter which is not matched. The server converts the prompt information into prompt information in a voice form by calling the message sending interface, then sends the prompt information to the intelligent home equipment, and sends voice prompt information to the user through the intelligent home equipment. Because the prompt information is generated aiming at the unmatched instruction parameters, the user does not need to repeatedly input the previous voice instruction, and only needs to further input the voice instruction corresponding to the prompt information according to the inquiry statement sent by the intelligent household equipment, so that the repeated input of the user is avoided, and the friendliness of man-machine interaction is improved.
Step S212: and receiving a voice command corresponding to the prompt message, and repeating the step of identifying the keywords in the character command until all command parameters are matched with the corresponding keywords.
When the voice command input by the user cannot be completely recognized, the keywords in the voice command are verified and matched by calling the configuration file so as to detect whether the voice command input by the user is complete. When the condition that the instruction parameters cannot be matched is detected, the server generates prompt information corresponding to the instruction parameters, sends the prompt information to the intelligent terminal corresponding to the user, and sends query statements corresponding to the prompt information to the user through the intelligent terminal. So that the user inputs the corresponding voice command according to the query sentence, and the step of converting the voice command into the character command is repeatedly executed according to the new voice command until all command parameters can be matched with the corresponding keywords.
For example, the user inputs a voice command of 'no access to the internet', after verification and matching, when matching out the missing command object parameter, that is, "who" is not allowed to access the internet, the smart home device further sends an inquiry sentence "who is restricted from accessing the internet" to the user. Because the query statement is the prompt message generated aiming at the unmatched instruction parameters, the user does not need to repeatedly input the previous voice instruction, and only needs to further input the voice instruction corresponding to the prompt message according to the query statement sent by the intelligent household equipment, so that the repeated input of the user is avoided, and the friendliness of man-machine interaction is improved.
Step S214: and generating an operation instruction by using the plurality of instruction parameters matched with the keywords, and issuing the operation instruction to the intelligent home equipment so that the intelligent home equipment executes the operation instruction.
The server analyzes the plurality of instruction parameters of the matched keywords into executable machine language through the calling instruction analysis interface, and after the corresponding operation instruction is generated, the calling instruction issuing interface issues the operation instruction to the intelligent home equipment, so that the intelligent home equipment executes the operation instruction.
In the embodiment, after receiving the voice instruction uploaded by the intelligent home equipment, the server converts the voice instruction into a text instruction; identifying keywords or words in the character instruction; the configuration file is read, the configuration file comprises a plurality of instruction parameters, and a user can modify the configuration file according to the requirement of the user, so that the user can customize parameter information in the configuration file to adapt to the expansion requirement on the intelligent home system in the later period. The server traverses the instruction parameters and matches the instruction parameters with the keywords; if the unmatched instruction parameters exist, the corresponding prompt information is generated according to the unmatched instruction parameters, and the prompt information is generated aiming at the unmatched instruction parameters, so that the user does not need to repeatedly input the previous voice instruction, and only needs to further input the voice instruction corresponding to the prompt information according to the inquiry statement sent by the intelligent household equipment, so that the repeated input of the user is avoided, and the interaction friendliness and efficiency of the user and the intelligent household equipment are improved. Therefore, the friendliness of human-computer interaction can be improved, and the expansibility of the intelligent home system can be improved.
In one embodiment, prior to the step of receiving the voice instruction, the method further comprises: acquiring a data table corresponding to the configuration file; displaying a data table, wherein the data table comprises a plurality of instruction parameters and corresponding prompt information; receiving a modification instruction, and modifying the instruction parameter and the corresponding prompt information according to the modification instruction; and storing the modified instruction parameters and the corresponding prompt information into a configuration file.
The configuration file may be an XML configuration file that includes instruction parameters, a verification means, and a dialog query. The user or manufacturer can change the parameter information of the configuration file to adapt to the later expansion of the specific language scene.
Specifically, the server converts the XML configuration file into a corresponding data table, and the data table is sent to the intelligent terminal for display, wherein the data table comprises a plurality of instruction parameters and corresponding prompt information. The user or manufacturer can modify the parameter information in the XML configuration file or add the parameter type in the data table. Specifically, a control corresponding to the modification instruction is arranged in the data table modification interface, the server displays the corresponding modification interface after acquiring the modification instruction, and a user or a manufacturer can modify or supplement the parameter information in the data table by clicking the modification control in the data table modification interface. The server stores the modified parameter information in the data table into the XML configuration file, and the expansibility of the intelligent home system can be improved by modifying the parameter information of the configuration file.
For example, if there is an instruction topic of "internet access restriction" in the current XML configuration file, the instruction parameters include "who is restricted from accessing internet" and "time range for internet access restriction". When the user or the manufacturer modifies or supplements the parameter information in the XML configuration file through the data sheet, the internet surfing account number contained in the instruction parameter of 'who is limited to surf the internet' can be modified, and the internet surfing account number can also be increased. The user or manufacturer may also add parameter information, such as adding a "type of internet limited" command parameter. The user or the manufacturer can modify the configuration file according to the requirement of the user or the manufacturer, so that the user can customize the parameter information in the configuration file, and the expansibility of the intelligent home system can be improved.
In one embodiment, after the step of identifying the keyword in the textual instruction, the method further comprises: reading a semantic word set file, wherein the semantic word set file comprises a plurality of instruction semantic words; and performing semantic comparison on the keywords and the instruction related semantic words, and converting the keywords into the instruction semantic words if the semantics are the same or similar.
The semantic word set file comprises a plurality of preset instruction semantic words corresponding to a plurality of instruction parameters such as an instruction subject parameter, an instruction object parameter and an instruction behavior parameter. The semantic word set file can be stored in a file, a database or a cache and acquired from the file, the database or the cache when needed. Specifically, after receiving a voice instruction, the server calls a thread in the processing thread pool to convert the voice instruction into a text instruction, identifies a keyword in the text instruction, reads a semantic word set file, wherein the number of the keyword in the text instruction may be multiple, performs semantic matching comparison between the keyword and a command-related semantic word, and converts the keyword into a command semantic word if the semantics are the same or similar.
Specifically, for example, if the text instruction is "not to surf the internet", the keywords in the text instruction can be identified as "not to surf the internet", "son" and "surf the internet". By semantically comparing the keywords with the instruction-related semantic words, the internet surfing can be matched with the access network and matched with the corresponding instruction subject category parameters. The "not ok" may match the "no go" and match to the corresponding instruction behavior parameters. The son is matched with the corresponding account identification and the instruction object parameter. Therefore, the keywords in the character instruction can be effectively converted into the instruction semantic words, and the machine language which can be identified and executed by the terminal or the equipment is formed.
In one embodiment, the voice instruction carries a time stamp, the method further comprising: acquiring current system time; calculating the difference value between the current system time and the time stamp of the voice instruction, and comparing the difference value with the preset overtime duration; and when the difference value is larger than the preset timeout duration, repeating the step of traversing the plurality of instruction parameters until the operation instruction is executed.
In this embodiment, when no corresponding prompt information is generated or no operation instruction is executed within a preset time period, the step of traversing the plurality of instruction parameters is repeated. Specifically, the timestamp cache stores a timestamp of the voice instruction, and the timestamp is the time when the server receives the voice instruction. The server acquires the current system time in real time, calculates the difference value between the current system time and the time stamp of the voice instruction, and compares the difference value with the preset overtime duration. And when the difference is larger than the preset timeout duration, repeating the step of traversing the plurality of instruction parameters.
For example, after the smart home device sends the query statement corresponding to the prompt message to the user, the user does not further input the corresponding instruction parameter information according to the query statement sent by the terminal within a preset time, and at this time, the situation is overtime. And the server reads the configuration file again, performs loop traversal on the instruction parameters in the configuration file again, and matches the instruction parameters with the keywords in the character instruction. If the unmatched instruction parameters exist, corresponding prompt information is generated according to the unmatched instruction parameters, query sentences corresponding to the prompt information are sent to the user through the intelligent home equipment, the user can input corresponding instruction parameter information according to the query sentences sent by the terminal, the server further executes voice instructions supplemented by the user until the server generates operating instructions capable of being directly executed by utilizing the instruction parameters matched with the keywords, and therefore the server can be ensured to accurately process the voice instructions which the user wants to execute.
In one embodiment, a server receives a new voice instruction uploaded by smart home equipment, wherein the new voice instruction is a voice instruction which is input by a user and is different from a current instruction theme parameter, and the current instruction parameter is an instruction parameter corresponding to a currently executed voice instruction. When a user sends a voice instruction to the terminal, a new voice instruction is sent, and a wrong instruction may be sent to the user or the user wants to jump out the current situation of conversation with the smart home device. The server converts the new voice instruction into a character instruction; identifying key words in the character instruction, and converting the key words into instruction semantic words; and when the instruction parameters in the instruction semantic words are identified to be not matched with the current instruction parameters, reading the configuration file, traversing the instruction parameters in the configuration file, and matching the instruction parameters with the keywords corresponding to the new voice instruction. And if the unmatched instruction parameters exist, generating corresponding prompt information according to the unmatched instruction parameters. And receiving a voice command corresponding to the prompt message, and repeating the step of identifying the keywords in the character command until all command parameters are matched with the corresponding keywords. And generating an operation instruction by using the plurality of instruction parameters matched with the keywords, and issuing the operation instruction to the intelligent home equipment so that the intelligent home equipment executes the operation instruction. And when a new voice command is recognized, jumping out of the current session, so that the interaction between the user and terminals such as the intelligent home system is more flexible.
As shown in FIG. 3, in one embodiment, a method of voice instruction processing is provided. The embodiment is exemplified by applying the method to a server. The method specifically comprises the following steps:
step S302: and receiving a voice instruction uploaded by the terminal, and converting the voice instruction into a text instruction.
The server receives the voice instruction uploaded by the intelligent household equipment through the voice instruction receiving interface, the voice instruction receiving interface is a man-machine interaction interface, and the voice instruction is cached in the voice instruction cache. And after receiving the voice instruction, the server calls a thread in the processing thread pool to convert the voice instruction into a corresponding word instruction.
Step S304: keywords in the text instructions are identified.
Step S306: a configuration file is read, the configuration file including a plurality of instruction parameters.
The configuration file may be an XML (Extensible Markup Language) configuration file, and the XML configuration file includes instruction parameters, a verification method, and a dialog query. Specifically, the instruction parameter may be parameter information required for executing the instruction, including parameter information such as an instruction subject parameter, an instruction object parameter, an instruction behavior parameter, an instruction condition parameter, and a query statement. For example, the instruction subject parameter may correspond to a main body of an execution instruction, the instruction object parameter may correspond to an item to be executed, the instruction behavior parameter may correspond to a specific operation to be executed, the instruction condition parameter may correspond to a time range for executing the operation, and the like. The user can modify the configuration file according to the own requirements, so that the user can customize the parameter information in the configuration file, and the expansibility of the intelligent home system can be improved.
Step S308: and traversing the instruction parameters, and matching the instruction parameters with the keywords.
Step S310: and if the unmatched instruction parameters exist, generating corresponding prompt information according to the unmatched instruction parameters.
Specifically, the server reads an instruction parameter in the configuration file, wherein the instruction parameter corresponds to prompt information related to the instruction parameter. And circularly traversing the instruction parameters in the configuration file, comparing each instruction parameter with a keyword in the character instruction, and judging whether the keyword is matched with the instruction parameters. And if the keyword is not matched with the corresponding instruction parameter, generating corresponding prompt information according to the instruction parameter which is not matched. The server converts the prompt information into prompt information in a voice form by calling the message sending interface, then sends the prompt information to the intelligent home equipment, and sends voice prompt information to the user through the intelligent home equipment.
Step S312: and receiving a voice command corresponding to the prompt message, and repeating the step of identifying the keywords in the character command until all command parameters are matched with the corresponding keywords.
Step S314: and generating an operation instruction by using the plurality of instruction parameters matched with the keywords, and issuing the operation instruction to the intelligent home equipment so that the intelligent home equipment executes the operation instruction.
In this embodiment, the user can input the voice command to the terminal, so that the intelligent home equipment can be remotely controlled. Specifically, after receiving a voice instruction uploaded by a terminal, a server converts the voice instruction into a text instruction; identifying keywords or words in the character instruction; the configuration file is read, the configuration file comprises a plurality of instruction parameters, and a user can modify the configuration file according to the requirement of the user, so that the user can customize parameter information in the configuration file to adapt to the expansion requirement on the intelligent home system in the later period. The server traverses the instruction parameters and matches the instruction parameters with the keywords; if the unmatched instruction parameters exist, the corresponding prompt information is generated according to the unmatched instruction parameters, and the prompt information is generated aiming at the unmatched instruction parameters, so that the user does not need to repeatedly input the previous voice instruction, and only needs to further input the voice instruction corresponding to the prompt information according to the inquiry statement sent by the intelligent household equipment, so that the repeated input of the user is avoided, and the interaction friendliness and efficiency of the user and the intelligent household equipment are improved. Therefore, the friendliness of human-computer interaction can be improved, and the expansibility of the intelligent home system can be improved.
In one embodiment, a user can send voice instructions to a plurality of smart home devices simultaneously by inputting the voice instructions to the terminal. Specifically, after receiving a plurality of voice instructions uploaded by a terminal, a server converts the voice instructions into character instructions; identifying keywords or words in the character instruction; reading a configuration file, wherein the configuration file comprises a plurality of instruction parameters, and the server calls a plurality of threads in a processing thread pool to respectively traverse the instruction parameters and match the instruction parameters with the keywords; if the unmatched instruction parameters exist, the corresponding prompt information is generated according to the unmatched instruction parameters, and the server receives the voice instruction corresponding to the prompt information, so that the user does not need to repeatedly input the same voice instruction. Repeating the step of identifying the keywords in the character command until all command parameters match the corresponding keywords; and generating an operation instruction by using the plurality of instruction parameters matched with the keywords, and issuing the operation instruction to the intelligent home equipment so that the intelligent home equipment executes the operation instruction. The server calls the multiple processing threads and executes the voice instructions concurrently, so that the multiple intelligent household devices can be effectively and remotely controlled at the same time, and convenience is provided for users.
In one embodiment, prior to the step of receiving the voice instruction, the method further comprises: acquiring a data table corresponding to the configuration file; displaying a data table, wherein the data table comprises a plurality of instruction parameters and corresponding prompt information; receiving a modification instruction, and modifying the instruction parameter and the corresponding prompt information according to the modification instruction; and storing the modified instruction parameters and the corresponding prompt information into a configuration file.
The configuration file may be an XML configuration file that includes instruction parameters, a verification means, and a dialog query. The user or manufacturer can change the parameter information of the configuration file to adapt to the later expansion of the specific language scene.
In one embodiment, after the step of identifying the keyword in the textual instruction, the method further comprises: reading a semantic word set file, wherein the semantic word set file comprises a plurality of instruction semantic words; and performing semantic comparison on the keywords and the instruction related semantic words, and converting the keywords into the instruction semantic words if the semantics are the same or similar.
The semantic word set file comprises a plurality of preset instruction semantic words corresponding to a plurality of instruction parameters such as an instruction subject parameter, an instruction object parameter and an instruction behavior parameter. The semantic word set file can be stored in a file, a database or a cache and acquired from the file, the database or the cache when needed. Specifically, after receiving a voice instruction, the server calls a thread in the processing thread pool to convert the voice instruction into a text instruction, identifies a keyword in the text instruction, reads a semantic word set file, wherein the number of the keyword in the text instruction may be multiple, performs semantic matching comparison between the keyword and a command-related semantic word, and converts the keyword into a command semantic word if the semantics are the same or similar.
In one embodiment, the voice instruction carries a time stamp, the method further comprising: acquiring current system time; calculating the difference value between the current system time and the time stamp of the voice instruction, and comparing the difference value with the preset overtime duration; and when the difference value is larger than the preset timeout duration, repeating the step of traversing the plurality of instruction parameters until the operation instruction is executed.
In this embodiment, when no corresponding prompt information is generated or no operation instruction is executed within a preset time period, the step of traversing the plurality of instruction parameters is repeated. Specifically, the timestamp cache stores a timestamp of the voice instruction, and the timestamp is the time when the server receives the voice instruction. The server acquires the current system time in real time, calculates the difference value between the current system time and the time stamp of the voice instruction, and compares the difference value with the preset overtime duration. And when the difference is larger than the preset timeout duration, repeating the step of traversing the plurality of instruction parameters.
In one embodiment, as shown in fig. 4, there is provided a voice instruction processing apparatus including: an instruction receiving module 402, a matching module 404, an information prompting module 406, and an instruction issuing module 408, wherein:
the instruction receiving module 402 is configured to receive a voice instruction uploaded by the smart home device, and convert the voice instruction into a text instruction;
a matching module 404, configured to identify a keyword in the text instruction; the matching module 604 is further configured to read a configuration file, where the configuration file includes a plurality of instruction parameters; traversing a plurality of instruction parameters, and matching the instruction parameters with the keywords;
the information prompt module 406 is configured to generate corresponding prompt information according to the instruction parameters that are not matched if the instruction parameters that are not matched exist;
the instruction receiving module 402 is further configured to receive a voice instruction corresponding to the prompt message; the matching module 604 is further configured to repeat the step of identifying the keywords in the text instruction until all instruction parameters match the corresponding keywords;
the instruction issuing module 408 is configured to generate an operation instruction by using the plurality of instruction parameters matching the keyword, and issue the operation instruction to the smart home device, so that the smart home device executes the operation instruction.
In one embodiment, the matching module 404 is further configured to read a semantic word set file, where the semantic word set file includes a plurality of instruction semantic words; and performing semantic comparison on the keywords and the instruction related semantic words, and converting the keywords into the instruction semantic words if the semantics are the same or similar.
In one embodiment, the system further comprises a change module, configured to obtain a data table corresponding to the configuration file; displaying a data table, wherein the data table comprises a plurality of instruction parameters and corresponding prompt information; receiving a modification instruction, and modifying the instruction parameter and the corresponding prompt information according to the modification instruction; and storing the modified instruction parameters and the corresponding prompt information into a configuration file.
In one embodiment, the system further comprises a timeout processing module, configured to acquire a current system time; calculating the difference value between the current system time and the time stamp of the voice instruction, and comparing the difference value with the preset overtime duration; and when the difference value is larger than the timeout duration, repeating the step of traversing the plurality of instruction parameters until the operation instruction is executed.
In one embodiment, as shown in fig. 5, there is provided a voice instruction processing apparatus including: an instruction receiving module 502, a matching module 504, an information prompting module 506, and an instruction issuing module 508, wherein:
the instruction receiving module 502 is configured to receive a voice instruction uploaded by the terminal, and convert the voice instruction into a text instruction;
a matching module 504, configured to identify a keyword in the text instruction; the matching module 504 is further configured to read a configuration file, where the configuration file includes a plurality of instruction parameters; traversing a plurality of instruction parameters, and matching the instruction parameters with the keywords;
an information prompt module 506, configured to generate corresponding prompt information according to the instruction parameters that are not matched if the instruction parameters that are not matched exist;
the instruction receiving module 502 is further configured to receive a voice instruction corresponding to the prompt message; the matching module 504 is further configured to repeat the step of identifying the keywords in the text instruction until all instruction parameters match the corresponding keywords;
the instruction issuing module 508 is configured to generate an operation instruction by using the multiple instruction parameters matching the keyword, and issue the operation instruction to the smart home device, so that the smart home device executes the operation instruction.
In one embodiment, the matching module 504 is further configured to read a semantic word set file, where the semantic word set file includes a plurality of instruction semantic words; and performing semantic comparison on the keywords and the instruction related semantic words, and converting the keywords into the instruction semantic words if the semantics are the same or similar.
In one embodiment, the system further comprises a change module, configured to obtain a data table corresponding to the configuration file; displaying a data table, wherein the data table comprises a plurality of instruction parameters and corresponding prompt information; receiving a modification instruction, and modifying the instruction parameter and the corresponding prompt information according to the modification instruction; and storing the modified instruction parameters and the corresponding prompt information into a configuration file.
In one embodiment, as shown in FIG. 6, a computer device is provided, which may be a server, for example. The computer device includes a processor, a non-volatile storage medium, an internal memory, and a network interface connected by a system bus. The nonvolatile storage medium of the computer device stores an operating system and a database, and the database can store configuration files, semantic word set files and prompt information corresponding to the instruction parameters. The processor of the computer device is used for providing calculation and control capacity and supporting the operation of the whole server. The computer program, when executed, causes a processor to implement a method of processing voice instructions. The processor of the computer device is configured to provide computing and control capabilities and is configured to perform a method of business field processing. The internal memory provides an environment for running the computer program in the nonvolatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection according to an access network, such as receiving a user voice command and the like sent by the terminal. Those skilled in the art will appreciate that the architecture shown in fig. 6 is a block diagram of only a portion of the architecture associated with the subject application, and does not constitute a limitation on the servers to which the subject application applies, as a particular server may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, which may be a server. The computer device comprises a processor and a memory, said memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of: receiving a voice instruction uploaded by the intelligent home equipment, and converting the voice instruction into a character instruction; identifying key words in the character instruction; reading a configuration file, wherein the configuration file comprises a plurality of instruction parameters; traversing a plurality of instruction parameters, and matching the instruction parameters with the keywords; if the unmatched instruction parameters exist, generating corresponding prompt information according to the unmatched instruction parameters; receiving a voice instruction corresponding to the prompt message and uploaded by the intelligent home equipment, and repeating the step of recognizing the keywords in the character instruction until all instruction parameters are matched with the corresponding keywords; and generating an operation instruction by using the plurality of instruction parameters matched with the keywords, and issuing the operation instruction to the intelligent home equipment so that the intelligent home equipment executes the operation instruction.
In one embodiment, before the step of receiving the voice command uploaded by the smart home device, the method further includes: acquiring a data table corresponding to the configuration file; displaying a data table, wherein the data table comprises a plurality of instruction parameters and corresponding prompt information; receiving a modification instruction, and modifying the instruction parameter and the corresponding prompt information according to the modification instruction; and storing the modified instruction parameters and the corresponding prompt information into a configuration file.
In one embodiment, after the step of identifying the keyword in the text instruction, the method further includes: reading a semantic word set file, wherein the semantic word set file comprises a plurality of instruction semantic words; and performing semantic comparison on the keywords and the instruction related semantic words, and converting the keywords into the instruction semantic words if the semantics are the same or similar.
In one embodiment, the voice command carries a time stamp, and the method further comprises: acquiring current system time; calculating the difference value between the current system time and the time stamp of the voice instruction, and comparing the difference value with the preset overtime duration; and when the difference value is larger than the preset timeout duration, repeating the step of traversing the plurality of instruction parameters until the operation instruction is executed.
In one embodiment, a computer device is provided, which may be a server. The computer device comprises a processor and a memory, said memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of: receiving a voice instruction uploaded by a terminal, and converting the voice instruction into a text instruction; identifying key words in the character instruction; reading a configuration file, wherein the configuration file comprises a plurality of instruction parameters; traversing a plurality of instruction parameters, and matching the instruction parameters with the keywords; if the unmatched instruction parameters exist, generating corresponding prompt information according to the unmatched instruction parameters; receiving a voice instruction corresponding to the prompt message and uploaded by the terminal, and repeating the step of recognizing the keywords in the character instruction until all instruction parameters are matched with the corresponding keywords; and generating an operation instruction by using the plurality of instruction parameters matched with the keywords, and issuing the operation instruction to the intelligent home equipment so that the intelligent home equipment executes the operation instruction.
In one embodiment, before the step of receiving the voice instruction, the method further comprises: acquiring a data table corresponding to the configuration file; displaying a data table, wherein the data table comprises a plurality of instruction parameters and corresponding prompt information; receiving a modification instruction, and modifying the instruction parameter and the corresponding prompt information according to the modification instruction; and storing the modified instruction parameters and the corresponding prompt information into a configuration file.
In one embodiment, after the step of identifying the keyword in the text instruction, the method further includes: reading a semantic word set file, wherein the semantic word set file comprises a plurality of instruction semantic words; and performing semantic comparison on the keywords and the instruction related semantic words, and converting the keywords into the instruction semantic words if the semantics are the same or similar.
In one embodiment, the voice command carries a time stamp, and the method further comprises: acquiring current system time; calculating the difference value between the current system time and the time stamp of the voice instruction, and comparing the difference value with the preset overtime duration; and when the difference value is larger than the preset timeout duration, repeating the step of traversing the plurality of instruction parameters until the operation instruction is executed.
In one embodiment, a computer readable storage medium is provided, the computer readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps of: receiving a voice instruction uploaded by the intelligent home equipment, and converting the voice instruction into a character instruction; identifying key words in the character instruction; reading a configuration file, wherein the configuration file comprises a plurality of instruction parameters; traversing a plurality of instruction parameters, and matching the instruction parameters with the keywords; if the unmatched instruction parameters exist, generating corresponding prompt information according to the unmatched instruction parameters; receiving a voice instruction corresponding to the prompt message and uploaded by the intelligent home equipment, and repeating the step of recognizing the keywords in the character instruction until all instruction parameters are matched with the corresponding keywords; and generating an operation instruction by using the plurality of instruction parameters matched with the keywords, and issuing the operation instruction to the intelligent home equipment so that the intelligent home equipment executes the operation instruction.
In one embodiment, before the step of receiving the voice command uploaded by the smart home device, the method further includes: acquiring a data table corresponding to the configuration file; displaying a data table, wherein the data table comprises a plurality of instruction parameters and corresponding prompt information; receiving a modification instruction, and modifying the instruction parameter and the corresponding prompt information according to the modification instruction; and storing the modified instruction parameters and the corresponding prompt information into a configuration file.
In one embodiment, after the step of identifying the keyword in the text instruction, the method further includes: reading a semantic word set file, wherein the semantic word set file comprises a plurality of instruction semantic words; and performing semantic comparison on the keywords and the instruction related semantic words, and converting the keywords into the instruction semantic words if the semantics are the same or similar.
In one embodiment, the voice command carries a time stamp, and the method further comprises: acquiring current system time; calculating the difference value between the current system time and the time stamp of the voice instruction, and comparing the difference value with the preset overtime duration; and when the difference value is larger than the preset timeout duration, repeating the step of traversing the plurality of instruction parameters until the operation instruction is executed.
In one embodiment, a computer readable storage medium is provided, the computer readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps of: receiving a voice instruction uploaded by a terminal, and converting the voice instruction into a text instruction; identifying key words in the character instruction; reading a configuration file, wherein the configuration file comprises a plurality of instruction parameters; traversing a plurality of instruction parameters, and matching the instruction parameters with the keywords; if the unmatched instruction parameters exist, generating corresponding prompt information according to the unmatched instruction parameters; receiving a voice instruction corresponding to the prompt message and uploaded by the terminal, and repeating the step of recognizing the keywords in the character instruction until all instruction parameters are matched with the corresponding keywords; and generating an operation instruction by using the plurality of instruction parameters matched with the keywords, and issuing the operation instruction to the intelligent home equipment so that the intelligent home equipment executes the operation instruction.
In one embodiment, before the step of receiving the voice command uploaded by the terminal, the method further includes: acquiring a data table corresponding to the configuration file; displaying a data table, wherein the data table comprises a plurality of instruction parameters and corresponding prompt information; receiving a modification instruction, and modifying the instruction parameter and the corresponding prompt information according to the modification instruction; and storing the modified instruction parameters and the corresponding prompt information into a configuration file.
In one embodiment, after the step of identifying the keyword in the text instruction, the method further includes: reading a semantic word set file, wherein the semantic word set file comprises a plurality of instruction semantic words; and performing semantic comparison on the keywords and the instruction related semantic words, and converting the keywords into the instruction semantic words if the semantics are the same or similar.
In one embodiment, the voice command carries a time stamp, and the method further comprises: acquiring current system time; calculating the difference value between the current system time and the time stamp of the voice instruction, and comparing the difference value with the preset overtime duration; and when the difference value is larger than the preset timeout duration, repeating the step of traversing the plurality of instruction parameters until the operation instruction is executed.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the computer program is executed. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1. A method of voice instruction processing, the method comprising:
receiving a voice instruction uploaded by intelligent home equipment, and converting the voice instruction into a text instruction;
identifying key words in the character instruction, checking the legality and instruction integrity of the key words, and converting the key words into corresponding instruction semantic words; the converting the keywords into corresponding instruction semantic words comprises: reading a semantic word set file, wherein the semantic word set file comprises a plurality of instruction semantic words; performing semantic comparison on the keywords and the instruction semantic words, and if the keywords are the same as or similar to the semantics, converting the keywords into the instruction semantic words;
reading a configuration file; the configuration file is a file based on customizable configuration parameters in an extensible markup language form, and comprises a plurality of instruction parameters, wherein the instruction parameters comprise an instruction subject parameter, an instruction object parameter, an instruction behavior parameter and an instruction condition parameter; the instruction subject parameter corresponds to a subject of an execution instruction, the instruction object parameter corresponds to a project to be executed, the instruction behavior parameter corresponds to an operation to be executed, and the instruction condition parameter corresponds to a time range of the execution instruction;
traversing the instruction parameters, and matching the instruction semantic words with the instruction parameters;
if the unmatched instruction parameters exist, generating corresponding prompt information according to the unmatched instruction parameters and sending the prompt information to the intelligent home equipment;
receiving a voice instruction corresponding to the prompt information uploaded by the intelligent home equipment, and repeating the step of identifying the keywords in the character instruction until all instruction parameters are matched with the corresponding keywords;
generating an operation instruction by using a plurality of instruction parameters matched with the keywords, and issuing the operation instruction to the intelligent home equipment so that the intelligent home equipment executes the operation instruction.
2. The method according to claim 1, wherein before the step of receiving the voice command uploaded by the smart home device, the method further comprises:
acquiring a data table corresponding to the configuration file;
displaying the data table, wherein the data table comprises a plurality of instruction parameters and corresponding prompt information;
receiving a modification instruction, and modifying the instruction parameter and the corresponding prompt information according to the modification instruction;
and storing the modified instruction parameters and the corresponding prompt information into the configuration file.
3. The method of claim 1, wherein the voice instruction carries a timestamp, the method further comprising:
acquiring current system time;
calculating a difference value between the current system time and a timestamp of the voice instruction, and comparing the difference value with a preset timeout duration;
and when the difference is larger than the timeout duration, repeating the step of traversing the plurality of instruction parameters until the operation instruction is executed.
4. A method of voice instruction processing, the method comprising:
receiving a voice instruction uploaded by a terminal, and converting the voice instruction into a text instruction;
identifying key words in the character instruction, checking the legality and the instruction integrity of the key words, and converting the key words into corresponding instruction semantic words; the converting the keywords into corresponding instruction semantic words comprises: reading a semantic word set file, wherein the semantic word set file comprises a plurality of instruction semantic words; performing semantic comparison on the keywords and the instruction semantic words, and if the keywords are the same as or similar to the semantics, converting the keywords into the instruction semantic words;
reading a configuration file; the configuration file is a file based on customizable configuration parameters in an extensible markup language form, and comprises a plurality of instruction parameters, wherein the instruction parameters comprise an instruction subject parameter, an instruction object parameter, an instruction behavior parameter, an instruction condition parameter and a query statement parameter; the instruction subject parameter corresponds to a subject of an execution instruction, the instruction object parameter corresponds to a project to be executed, the instruction behavior parameter corresponds to an operation to be executed, and the instruction condition parameter corresponds to a time range of the execution instruction;
traversing the instruction parameters, and matching the instruction semantic words with the instruction parameters;
if the unmatched instruction parameters exist, generating corresponding prompt information according to the unmatched instruction parameters and sending the prompt information to the terminal;
receiving a voice instruction corresponding to the prompt message and uploaded by the terminal, and repeating the step of identifying the keywords in the character instruction until all instruction parameters are matched with the corresponding keywords;
generating an operation instruction by using a plurality of instruction parameters matched with the keywords, and issuing the operation instruction to the intelligent home equipment so that the intelligent home equipment executes the operation instruction.
5. The method of claim 4, wherein before the step of receiving the voice command uploaded by the terminal, further comprising:
acquiring a data table corresponding to the configuration file;
displaying the data table, wherein the data table comprises a plurality of instruction parameters and corresponding prompt information;
receiving a modification instruction, and modifying the instruction parameter and the corresponding prompt information according to the modification instruction;
and storing the modified instruction parameters and the corresponding prompt information into the configuration file.
6. A voice instruction processing apparatus, the apparatus comprising:
the command receiving module is used for receiving a voice command uploaded by the intelligent household equipment and converting the voice command into a character command;
the matching module is used for identifying key words in the character instruction, checking the legality and the instruction integrity of the key words and converting the key words into corresponding instruction semantic words; the converting the keywords into corresponding instruction semantic words comprises: reading a semantic word set file, wherein the semantic word set file comprises a plurality of instruction semantic words; performing semantic comparison on the keywords and the instruction semantic words, and if the keywords are the same as or similar to the semantics, converting the keywords into the instruction semantic words; reading a configuration file; the configuration file is a file based on customizable configuration parameters in an extensible markup language form, and comprises a plurality of instruction parameters, wherein the instruction parameters comprise an instruction subject parameter, an instruction object parameter, an instruction behavior parameter, an instruction condition parameter and a query statement parameter; the instruction subject parameter corresponds to a subject of an execution instruction, the instruction object parameter corresponds to a project to be executed, the instruction behavior parameter corresponds to an operation to be executed, and the instruction condition parameter corresponds to a time range of the execution instruction; traversing the instruction parameters, and matching the instruction semantic words with the instruction parameters;
the information prompt module is used for generating corresponding prompt information according to the unmatched instruction parameters and sending the prompt information to the intelligent household equipment if the unmatched instruction parameters exist;
the instruction receiving module is further used for receiving a voice instruction which is uploaded by the intelligent household equipment and corresponds to the prompt information;
the matching module is further used for repeating the step of identifying the keywords in the character instruction until all instruction parameters are matched with the corresponding keywords;
and the instruction issuing module is used for generating an operation instruction by using the plurality of instruction parameters matched with the keywords and issuing the operation instruction to the intelligent home equipment so that the intelligent home equipment executes the operation instruction.
7. The apparatus according to claim 6, wherein the voice command processing apparatus further comprises a modification module, configured to obtain a data table corresponding to the configuration file; displaying the data table, wherein the data table comprises a plurality of instruction parameters and corresponding prompt information; receiving a modification instruction, and modifying the instruction parameter and the corresponding prompt information according to the modification instruction; and storing the modified instruction parameters and the corresponding prompt information into the configuration file.
8. A voice instruction processing apparatus, the apparatus comprising:
the instruction receiving module is used for receiving a voice instruction uploaded by a terminal and converting the voice instruction into a character instruction;
the matching module is used for identifying key words in the character instruction, checking the legality and the instruction integrity of the key words and converting the key words into corresponding instruction semantic words; the converting the keywords into corresponding instruction semantic words comprises: reading a semantic word set file, wherein the semantic word set file comprises a plurality of instruction semantic words; performing semantic comparison on the keywords and the instruction semantic words, and if the keywords are the same as or similar to the semantics, converting the keywords into the instruction semantic words; reading a configuration file; the configuration file is a file based on customizable configuration parameters in an extensible markup language form, and comprises a plurality of instruction parameters, wherein the instruction parameters comprise an instruction subject parameter, an instruction object parameter, an instruction behavior parameter, an instruction condition parameter and a query statement parameter; the instruction subject parameter corresponds to a subject of an execution instruction, the instruction object parameter corresponds to a project to be executed, the instruction behavior parameter corresponds to an operation to be executed, and the instruction condition parameter corresponds to a time range of the execution instruction; traversing the instruction parameters, and matching the instruction semantic words with the instruction parameters;
the information prompt module is used for generating corresponding prompt information according to the unmatched instruction parameters and sending the prompt information to the terminal if the unmatched instruction parameters exist;
the instruction receiving module is further used for receiving a voice instruction which is uploaded by the terminal and corresponds to the prompt information;
the matching module is further used for repeating the step of identifying the keywords in the character instruction until all instruction parameters are matched with the corresponding keywords;
the instruction issuing module is used for generating an operation instruction by using the plurality of instruction parameters matched with the keywords and issuing the operation instruction to the intelligent home equipment so that the intelligent home equipment executes the operation instruction.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any one of claims 1 to 5 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 5.
CN201710969298.0A 2017-10-18 2017-10-18 Voice instruction processing method and device, computer equipment and storage medium Active CN107909998B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710969298.0A CN107909998B (en) 2017-10-18 2017-10-18 Voice instruction processing method and device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710969298.0A CN107909998B (en) 2017-10-18 2017-10-18 Voice instruction processing method and device, computer equipment and storage medium

Publications (2)

Publication Number Publication Date
CN107909998A CN107909998A (en) 2018-04-13
CN107909998B true CN107909998B (en) 2021-06-15

Family

ID=61840582

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710969298.0A Active CN107909998B (en) 2017-10-18 2017-10-18 Voice instruction processing method and device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN107909998B (en)

Families Citing this family (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110764422A (en) * 2018-07-27 2020-02-07 珠海格力电器股份有限公司 Control method and device of electric appliance
CN109637529A (en) * 2018-11-01 2019-04-16 平安科技（深圳）有限公司 Voice-based functional localization method, apparatus, computer equipment and storage medium
CN110058916A (en) * 2019-04-23 2019-07-26 深圳创维数字技术有限公司 A kind of phonetic function jump method, device, equipment and computer storage medium
CN112445450A (en) * 2019-08-30 2021-03-05 比亚迪股份有限公司 Method and device for controlling terminal based on voice, storage medium and electronic equipment
CN110597082A (en) * 2019-10-23 2019-12-20 北京声智科技有限公司 Intelligent household equipment control method and device, computer equipment and storage medium
CN110853638A (en) * 2019-10-23 2020-02-28 吴杰 Method and equipment for interrupting voice robot in real time in voice interaction process
CN110992960A (en) * 2019-12-18 2020-04-10 Oppo广东移动通信有限公司 Control method, control device, electronic equipment and storage medium
CN111145747A (en) * 2019-12-30 2020-05-12 智车优行科技（北京）有限公司 Voice control implementation method and device
US11663611B2 (en) * 2020-04-23 2023-05-30 Capital One Services, Llc Device requirement and configuration analysis
CN112581957B (en) * 2020-12-04 2023-04-11 浪潮电子信息产业股份有限公司 Computer voice control method, system and related device
CN114697717A (en) * 2020-12-28 2022-07-01 深圳Tcl新技术有限公司 Text input method and terminal equipment
CN112965603A (en) * 2021-03-26 2021-06-15 南京阿凡达机器人科技有限公司 Method and system for realizing man-machine interaction
CN115421396A (en) * 2022-09-29 2022-12-02 深圳康佳电子科技有限公司 Intelligent household equipment control method and device and electronic equipment

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102789176A (en) * 2012-07-04 2012-11-21 北京捷通华声语音技术有限公司 Control method and system for household appliance terminal
CN103093755A (en) * 2012-09-07 2013-05-08 深圳市信利康电子有限公司 Method and system of controlling network household appliance based on terminal and Internet voice interaction
US8914287B2 (en) * 2010-12-31 2014-12-16 Echostar Technologies L.L.C. Remote control audio link
CN106789170A (en) * 2016-11-28 2017-05-31 北京奇虎科技有限公司 A kind of task processing method and device
CN206516350U (en) * 2017-01-20 2017-09-22 浙江小尤鱼智能技术有限公司 A kind of intelligent domestic system controlled based on distributed sound

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103646646B (en) * 2013-11-27 2018-08-31 联想(北京)有限公司 A kind of sound control method and electronic equipment
CN104239043B (en) * 2014-09-04 2017-10-31 百度在线网络技术（北京）有限公司 The execution method and apparatus of instruction
CN106898349A (en) * 2017-01-11 2017-06-27 梅其珍 A kind of Voice command computer method and intelligent sound assistant system
CN107220292A (en) * 2017-04-25 2017-09-29 上海庆科信息技术有限公司 Intelligent dialogue device, reaction type intelligent sound control system and method
CN107170449A (en) * 2017-06-14 2017-09-15 上海雍敏信息科技有限公司 Intelligent domestic system and its control method
CN109063166A (en) * 2018-08-15 2018-12-21 中国联合网络通信集团有限公司 A kind of voice inquiry method and device, user equipment

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8914287B2 (en) * 2010-12-31 2014-12-16 Echostar Technologies L.L.C. Remote control audio link
CN102789176A (en) * 2012-07-04 2012-11-21 北京捷通华声语音技术有限公司 Control method and system for household appliance terminal
CN103093755A (en) * 2012-09-07 2013-05-08 深圳市信利康电子有限公司 Method and system of controlling network household appliance based on terminal and Internet voice interaction
CN106789170A (en) * 2016-11-28 2017-05-31 北京奇虎科技有限公司 A kind of task processing method and device
CN206516350U (en) * 2017-01-20 2017-09-22 浙江小尤鱼智能技术有限公司 A kind of intelligent domestic system controlled based on distributed sound

Also Published As

Publication number Publication date
CN107909998A (en) 2018-04-13

Similar Documents

Publication Publication Date Title
CN107909998B (en) Voice instruction processing method and device, computer equipment and storage medium
CN107146612B (en) Voice guidance method and device, intelligent equipment and server
KR102309540B1 (en) Server for seleting a target device according to a voice input, and controlling the selected target device, and method for operating the same
CN111880645B (en) Server for determining target device and controlling target device based on voice input of user and operation method thereof
KR102222317B1 (en) Speech recognition method, electronic device, and computer storage medium
CN108133707B (en) Content sharing method and system
CN109618202B (en) Method for controlling peripheral equipment, television and readable storage medium
KR100764174B1 (en) Apparatus for providing voice dialogue service and method for operating the apparatus
EP3779972A1 (en) Voice wake-up method and apparatus
US10504513B1 (en) Natural language understanding with affiliated devices
CN110164435A (en) Audio recognition method, device, equipment and computer readable storage medium
WO2018045646A1 (en) Artificial intelligence-based method and device for human-machine interaction
CN112799630B (en) Creating a cinematized storytelling experience using network addressable devices
WO2017084185A1 (en) Intelligent terminal control method and system based on semantic analysis, and intelligent terminal
US20200101383A1 (en) Method and apparatus for recognizing game command
CN111462741B (en) Voice data processing method, device and storage medium
CN111326154B (en) Voice interaction method and device, storage medium and electronic equipment
CN103744836A (en) Man-machine conversation method and device
KR20200084260A (en) Electronic apparatus and controlling method thereof
CN113516961B (en) Note generation method, related device, storage medium and program product
CN112163084A (en) Question feedback method, device, medium and electronic equipment
WO2019101067A1 (en) Information processing method and apparatus for data visualization
CN113205809A (en) Voice wake-up method and device
CN115148212A (en) Voice interaction method, intelligent device and system
CN111210824B (en) Voice information processing method and 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
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20231031

Address after: No.2, Danzi North Road, Kengzi street, Pingshan District, Shenzhen, Guangdong 518000

Patentee after: SHENZHEN GONGJIN ELECTRONICS Co.,Ltd.

Address before: 610000 area B, 10th floor, building 1, No.168, Tianfu 5th Street, high tech Zone, Chengdu, Sichuan Province

Patentee before: CHENGDU GONGWEI TECHNOLOGY CO.,LTD.