WO2019144543A1 - 语音控制方法及装置、电子设备和计算机可读存储介质 - Google Patents

语音控制方法及装置、电子设备和计算机可读存储介质 Download PDF

Info

Publication number
WO2019144543A1
WO2019144543A1 PCT/CN2018/088459 CN2018088459W WO2019144543A1 WO 2019144543 A1 WO2019144543 A1 WO 2019144543A1 CN 2018088459 W CN2018088459 W CN 2018088459W WO 2019144543 A1 WO2019144543 A1 WO 2019144543A1
Authority
WO
WIPO (PCT)
Prior art keywords
instruction
target
planting
voice
command
Prior art date
Application number
PCT/CN2018/088459
Other languages
English (en)
French (fr)
Inventor
卢吉
克纳普·爱德温·范德
黄元钧
Original Assignee
深圳春沐源控股有限公司
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 深圳春沐源控股有限公司 filed Critical 深圳春沐源控股有限公司
Publication of WO2019144543A1 publication Critical patent/WO2019144543A1/zh

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
    • 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
    • G10L15/10—Speech classification or search using distance or distortion measures between unknown speech and reference templates
    • 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
    • G10L15/14—Speech classification or search using statistical models, e.g. Hidden Markov Models [HMMs]
    • 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
    • G10L15/18—Speech classification or search using natural language modelling
    • G10L15/1822—Parsing for meaning understanding
    • 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
    • G10L17/00—Speaker identification or verification techniques
    • 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
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/02—Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
    • 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
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/04—Training, enrolment or model building
    • 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
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/06—Decision making techniques; Pattern matching strategies
    • G10L17/08—Use of distortion metrics or a particular distance between probe pattern and reference templates
    • 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
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/22—Interactive procedures; Man-machine interfaces
    • 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
    • G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
    • 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
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • 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

Definitions

  • the present invention relates to the field of intelligent voice technologies, and in particular, to a voice control method and apparatus, an electronic device, and a computer readable storage medium.
  • a voice control method comprising:
  • the determining a target planting task instruction that matches the target voice instruction to target the planting task instruction comprises:
  • the task instruction is planted as the target.
  • the determining a target planting task instruction that matches the target voice instruction to target the planting task instruction comprises:
  • the task instruction is planted as the target.
  • the determining a target planting task instruction that matches the target voice instruction to target the planting task instruction comprises:
  • the task instruction is planted as the target.
  • the method further includes:
  • An alert is issued when a planting task command that matches the target voice command cannot be determined to be a target planting task command.
  • the method further includes:
  • the method further includes:
  • a planting task instruction corresponding to the target crop is configured based on the matched voice instruction data.
  • a voice control device comprising:
  • a configuration unit configured to configure a correspondence between the voice instruction and the planting task instruction, and generate an instruction operation set
  • a receiving unit configured to receive a target voice
  • An identification unit configured to identify the target voice, to obtain a target voice instruction
  • a determining unit configured to determine a planting task instruction that matches the target voice instruction to plant a task instruction as a target
  • the control unit is configured to control the planting operation of the planting equipment according to the target planting task instruction.
  • the determining unit is specifically configured to:
  • the task instruction is planted as the target.
  • the determining unit is further configured to:
  • the task instruction is planted as the target.
  • the determining unit is further configured to:
  • the task instruction is planted as the target.
  • the apparatus further includes:
  • the alarm unit issues an alarm when the planting task command that matches the target voice command cannot be determined to be the target planting task command.
  • the apparatus further includes:
  • An obtaining unit configured to acquire a voice instruction of the updated voiceprint identity data when receiving a request to change the voiceprint identity data of the target voice command in the instruction operation set;
  • An update unit that updates the target voice command to a voice command of the updated voiceprint identity data.
  • the acquiring unit is further configured to: when the input instruction of the planting task instruction for the target crop is acquired, acquire the voice instruction data that matches the planting task instruction from the instruction operation set;
  • the configuration unit is further configured to configure a planting task instruction corresponding to the target crop based on the matched voice instruction data.
  • An electronic device comprising:
  • a memory instructions stored in the memory are executed by the processor to implement the voice control method.
  • a computer readable storage medium the instructions stored in the computer readable storage medium being executed by a processor in an electronic device to implement the voice control method.
  • the present invention generates an instruction operation set by configuring the correspondence between the voice instruction and the planting task instruction, and the instruction operation set integrates all the operation instructions that need to be used to facilitate storage and management, and the subsequent operation can be performed.
  • FIG. 1 is an application environment diagram of a preferred embodiment of a voice control method according to the present invention.
  • FIG. 2 is a flow chart of a preferred embodiment of the voice control method of the present invention.
  • Figure 3 is a functional block diagram of a preferred embodiment of the voice control device of the present invention.
  • FIG. 4 is a schematic structural diagram of an electronic device according to a preferred embodiment of the voice control method of the present invention.
  • FIG. 1 is an application environment diagram of a preferred embodiment of a voice control method according to the present invention.
  • the application environment diagram includes an electronic device 1 and a planting device 2, the electronic device 1 being in communication with the planting device 2.
  • the electronic device 1 is used to control a planting operation of the planting device 2;
  • the planting device 2 is used to perform a planting operation.
  • FIG. 2 is a flow chart of a preferred embodiment of the voice control method of the present invention.
  • the order of the steps in the flowchart may be changed according to different requirements, and some steps may be omitted.
  • the voice control method is applied to one or more electronic devices 1, and the electronic device 1 is a device capable of automatically performing numerical calculation and/or information processing according to an instruction set or stored in advance, the hardware of which includes It is not limited to a microprocessor, an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, or the like.
  • ASIC application specific integrated circuit
  • FPGA field-programmable gate array
  • DSP digital signal processor
  • embedded device or the like.
  • the electronic device 1 can be any electronic product that can interact with a user, such as a personal computer, a tablet, a smart phone, a personal digital assistant (PDA), a game machine, an interactive network television. (Internet Protocol Television, IPTV), smart wearable devices, etc.
  • a personal computer such as a personal computer, a tablet, a smart phone, a personal digital assistant (PDA), a game machine, an interactive network television. (Internet Protocol Television, IPTV), smart wearable devices, etc.
  • PDA personal digital assistant
  • IPTV Internet Protocol Television
  • smart wearable devices etc.
  • the electronic device 1 may also comprise a network device and/or a user device.
  • the network device includes, but is not limited to, a single network server, a server group composed of multiple network servers, or a cloud computing-based cloud composed of a large number of hosts or network servers.
  • the network in which the electronic device 1 is located includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), and the like.
  • the Internet includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), and the like.
  • VPN virtual private network
  • the electronic device 1 configures a correspondence between a voice command and a planting task command, and generates an instruction operation set.
  • the electronic device 1 in order to facilitate subsequent identification of the received speech using the set of command operations to control the planting operation of the planting device 2 in communication with the electronic device 1, the electronic device 1 Configure the correspondence between the voice command and the planting task command to generate an instruction operation set.
  • the voice command can be customized by the user.
  • the user may configure the voice instruction according to common technical terms in the technical field, so that the relevant operator can quickly grasp the voice instruction without having basic knowledge in the technical field, thereby avoiding The cumbersome setting of the voice command causes the related operator to cause a malfunction due to the input of the wrong voice command.
  • the voice command may also include other settings, which are not limited in the present invention.
  • the planting task instructions include, but are not limited to, sowing, fertilizing, spraying, watering, and the like.
  • the electronic device 1 configures a correspondence between a voice instruction and a planting task instruction, and the generating the instruction operation set includes:
  • the electronic device 1 acquires at least one planting task command, and respectively configures corresponding voice commands for the at least one planting task command, and the electronic device 1 configures the at least one planting task command and the Corresponding voice commands are combined into the set of instruction operations.
  • the electronic device 1 is configured with a planting task commanding tomato fertilization, corresponding to a voice commanding fertilization A, the electronic device 1 is configured to plant a task command cucumber to fight drugs, corresponding to a voice command to fight drugs B, and the electronic device 1 is configured to plant a task instruction lettuce. Seeding, corresponding to the voice instruction seeding C, etc., the electronic device 1 merges the above correspondence into the instruction operation set.
  • the electronic device 1 receives the target voice.
  • the electronic device 1 receives the target speech for subsequent recognition of the target speech command from the target speech.
  • the present invention does not limit the manner in which the electronic device 1 receives the target voice.
  • the electronic device 1 can receive the target voice or the like through a voice collecting device in communication with the electronic device 1.
  • the electronic device 1 identifies the target voice to obtain a target voice command.
  • the electronic device 1 identifies the target voice, and the obtained target voice command includes: a model training phase and a recognition phase.
  • the model training phase includes two parts: training of an acoustic model and training of a language model.
  • the acoustic model mainly uses the context triphone as the modeling unit, establishes the speech corpus by collecting a large number of speech samples, and uses the hidden Markov model Baum-Welch algorithm to train the model to obtain a stable acoustic model.
  • the electronic device 1 Before performing the training of the acoustic model, the electronic device 1 also needs to perform preprocessing of the sound signal, extracting stable acoustic features, and the like. Specifically, the electronic device 1 may adopt a characteristic of the Mel frequency cepstrum coefficient.
  • MFCC Mel Frequency Cepstrum Coefficient
  • PLP Perceptual Linear Prediction
  • the identification phase is a process of decoding a voice signal
  • the electronic device 1 may be based on a decoding process of a hidden Markov model and adopt a Viterbi algorithm.
  • the electronic device 1 performs feature extraction on the input speech signal at the front end, and the obtained feature vector is acoustically compared with the acoustic model.
  • the electronic device 1 selects candidate words whose probability distribution is closest from the sound dictionary, and further constrains the language model to obtain a final recognition result.
  • the electronic device 1 may identify the target voice in other manners, and the present invention is not limited herein.
  • the electronic device 1 determines a planting task instruction that matches the target voice instruction to be a target planting task instruction.
  • the electronic device 1 determines a target planting task instruction that matches the target voice command, and the target planting task instruction includes:
  • the electronic device 1 determines whether the voiceprint identity data of the target voice command is the same as the voiceprint identity data corresponding to the target voice command configured in the command operation, and if the same, the target task is planted as the target .
  • the electronic device 1 determines whether the voiceprint identity data of the target voice instruction is the same as the voiceprint identity data corresponding to the target voice command configured in the instruction operation, when the voice of the target voice command is When the pattern identity data is the same as the voiceprint identity data corresponding to the target voice instruction configured in the instruction operation, the electronic device 1 controls the planting operation of the planting device according to the target planting task instruction.
  • the electronic device 1 determines that the voiceprint identity data of the target voice instruction belongs to the user D, if the electronic device 1 simultaneously determines the voiceprint identity corresponding to the target voice command configured in the command operation set The data also belongs to the user D, and the electronic device 1 controls the planting operation of the planting device according to the target planting task instruction.
  • the electronic device 1 controls the planting operation of the planting device only when the designated person issues the target voice command, thereby ensuring the safety of the planting operation.
  • the electronic device 1 determines a target planting task instruction that matches the target voice command, and the target planting task instruction further includes:
  • the electronic device 1 determines whether the crop corresponding to the target voice command is the same as the crop corresponding to the target voice command configured in the command operation, and if the same, the plant task command is used as the target.
  • the electronic device 1 determines a crop corresponding to the target voice instruction by using a voice recognition technology, and determines whether a crop corresponding to the target voice instruction and a crop corresponding to the target voice instruction configured in the instruction operation are Similarly, when the crop corresponding to the target voice is the same as the crop corresponding to the target voice instruction configured in the command operation, the electronic device 1 controls the planting operation of the planting device according to the target planting task instruction.
  • the electronic device 1 may determine that the crop corresponding to the target voice command is a tomato, if the electronic device is 1 At the same time, it is determined that the crop corresponding to the target voice instruction configured in the instruction operation is also a tomato, and the electronic device 1 controls the planting operation of the planting device according to the target planting task instruction.
  • the electronic device 1 controls the planting operation of the planting equipment only when the crops are matched, thereby avoiding the occurrence of misoperation.
  • the electronic device 1 determines a target planting task instruction that matches the target voice command, and the target planting task instruction further includes:
  • the electronic device 1 determines whether the planting link corresponding to the target voice command is the same as the planting link corresponding to the target voice command disposed in the command operation, and if the same, the planting task command is used as the target.
  • the electronic device 1 determines a planting link corresponding to the target voice command by using a voice recognition technology, and determines that the planting link corresponding to the target voice command is corresponding to the target voice command configured in the command operation. Whether the planting link is the same, when the planting link corresponding to the target voice command is the same as the planting link corresponding to the target voice command configured in the command operation, the electronic device 1 controls according to the target planting task command Planting equipment planting operations.
  • the electronic device 1 determines that the planting link corresponding to the target voice command is seeding, if the electronic device 1 simultaneously determines that the planting link corresponding to the target voice command configured in the command operation is also seeded, Then, the electronic device 1 controls the planting operation of the planting equipment according to the target planting task instruction.
  • the electronic device 1 can control the planting operation of the planting equipment only when the planting links are matched, and the phenomenon of misoperation can also be avoided.
  • the electronic device 1 may further match the corresponding crops and/or corresponding planting links after matching the voiceprint identity data of the target voice command to ensure more Safely perform planting operations.
  • the foregoing three matching processes may be implemented in combination according to actual needs.
  • the present invention does not limit the order and combination manner of the foregoing three matching processes in the combined implementation manner.
  • the electronic device 1 may select all or part of the above three matching processes, and perform the sequence according to the configuration sequence, and the configuration sequence may be set by the relevant staff according to actual conditions.
  • the electronic device 1 can also issue an error alert, specifically:
  • the electronic device 1 issues an alarm when the electronic device 1 cannot determine a planting task instruction that matches the target voice command to be a target planting task command.
  • the electronic device 1 determines that the planting link corresponding to the target voice command is seeding, if the electronic device 1 simultaneously determines that the planting link corresponding to the target voice command configured in the command operation is fertilized, If the two do not match, the electronic device 1 issues an alarm.
  • the alarm may be in the form of a prompt tone, or a flashing of the light, etc., and the invention is not limited.
  • the electronic device 1 can also prompt the user to issue an alarm for the user to re-issue the correct voice command.
  • the electronic device 1 can promptly prompt the user that “the planting link does not match, please re-enter the command, thank you” and the like.
  • the electronic device 1 controls a planting operation of the planting device according to the target planting task instruction.
  • the method when the voiceprint identity data of the target voice command is changed in the instruction operation set, the method further includes:
  • the electronic device 1 When receiving a request to change the voiceprint identity data of the target voice command in the instruction operation set, the electronic device 1 acquires a voice instruction of the updated voiceprint identity data, and updates the target voice command to the updated Voice instructions for voiceprint identity data.
  • the electronic device 1 can acquire the voiceprint identity data of the new operator, and update the voiceprint identity data of the new operator to the
  • the voiceprint identity data of the target voice command simultaneously updates the command input by the target voice command to the new operator to avoid an unusable command due to personnel changes.
  • the method further includes:
  • the electronic device 1 When acquiring an input instruction to a planting task instruction for the target crop, the electronic device 1 acquires voice instruction data matching the planting task instruction from the instruction operation set, the electronic device 1 based on the matching The voice command data is configured to correspond to a planting task instruction of the target crop.
  • the electronic device 1 can directly obtain the voice command data matching the planting task command from the instruction operation set, thereby avoiding the related command operator. Repeated entry instructions result in redundant and repetitive workloads.
  • the present invention can configure a correspondence between a voice command and a planting task command, generate an instruction operation set, receive a target voice, identify the target voice, obtain a target voice command, and determine to match the target voice command.
  • the planting task instruction is used as a target planting task instruction; the planting operation of the planting equipment is controlled according to the target planting task instruction. Therefore, the present invention can perform voice operation on the planting task of the crop, which is convenient and fast, and brings a better operating experience to the user.
  • the voice control device 11 includes a configuration unit 110, a receiving unit 111, an identification unit 112, a determining unit 113, a control unit 114, an obtaining unit 115, an alarm unit 116, and an updating unit 117.
  • the module/unit referred to in the present invention refers to a series of computer program segments that can be executed by the processor 13 and that can perform fixed functions, which are stored in the memory 12. In this embodiment, the functions of the respective modules/units will be detailed in the subsequent embodiments.
  • the configuration unit 110 configures a correspondence between the voice command and the planting task command, and generates an instruction operation set.
  • the configuration unit 110 configures a correspondence between a voice command and a planting task command, and generates an instruction operation set.
  • the voice command can be customized by the user.
  • the user may configure the voice instruction according to common technical terms in the technical field, so that the relevant operator can quickly grasp the voice instruction without having basic knowledge in the technical field, thereby avoiding The cumbersome setting of the voice command causes the related operator to cause a malfunction due to the input of the wrong voice command.
  • the voice command may also include other settings, which are not limited in the present invention.
  • the planting task instructions include, but are not limited to, sowing, fertilizing, spraying, watering, and the like.
  • the configuration unit 110 configures a correspondence between a voice instruction and a planting task instruction, and the generating the instruction operation set includes:
  • the configuration unit 110 acquires at least one planting task instruction, and respectively configures corresponding voice commands for the at least one planting task instruction, and the configuration unit 110 configures the at least one planting task instruction and the Corresponding voice commands are combined into the set of instruction operations.
  • the configuration unit 110 configures a planting task to command tomato fertilization, corresponding to the voice command fertilization A, the configuration unit 110 configures the planting task to command the cucumber to fight the medicine, and corresponds to the voice command to fight the medicine B, and the configuration unit 110 configures the planting task instruction lettuce. Seeding, corresponding to the voice instruction seeding C, etc., the configuration unit 110 merges the above correspondence into the instruction operation set.
  • the receiving unit 111 receives the target voice.
  • the receiving unit 111 receives the target speech for subsequent recognition of the target speech command from the target speech.
  • the present invention does not limit the manner in which the receiving unit 111 receives the target voice.
  • the receiving unit 111 can receive the target voice or the like through a voice collecting device that communicates with the electronic device 1.
  • the identification unit 112 identifies the target speech to obtain a target voice instruction.
  • the identifying unit 112 identifies the target voice, and the obtained target voice command includes: a model training phase and a recognition phase.
  • the model training phase includes two parts: training of an acoustic model and training of a language model.
  • the acoustic model mainly uses the context triphone as the modeling unit, establishes the speech corpus by collecting a large number of speech samples, and uses the hidden Markov model Baum-Welch algorithm to train the model to obtain a stable acoustic model.
  • the identification unit 112 Before performing the training of the acoustic model, the identification unit 112 also needs to perform preprocessing on the sound signal, extract stable acoustic features, and the like. Specifically, the identification unit 112 may adopt a characteristic of the Mel frequency cepstrum coefficient.
  • MFCC Mel Frequency Cepstrum Coefficient
  • PLP Perceptual Linear Prediction
  • the identification phase is a process of decoding a speech signal
  • the identification unit 112 may be based on a decoding process of a hidden Markov model and adopt a Viterbi algorithm.
  • the identification unit 112 performs feature extraction on the input speech signal at the front end, and the obtained feature vector is acoustically compared with the acoustic model.
  • the identification unit 112 selects the candidate words whose probability distribution is closest from the pronunciation dictionary, and further uses the language model to further constrain the final recognition result.
  • the identification unit 112 may also identify the target voice in other manners, and the present invention is not limited herein.
  • the determining unit 113 determines a planting task instruction that matches the target voice command to be a target planting task instruction.
  • the determining unit 113 determines a target planting task instruction that matches the target voice instruction, and the target planting task instruction includes:
  • the determining unit 113 determines whether the voiceprint identity data of the target voice command is the same as the voiceprint identity data corresponding to the target voice command configured in the command operation, and if the same, the target task is planted as the target .
  • the determining unit 113 determines whether the voiceprint identity data of the target voice instruction is the same as the voiceprint identity data corresponding to the target voice instruction configured in the instruction operation, when the voice of the target voice instruction is When the pattern identity data is the same as the voiceprint identity data corresponding to the target voice command configured in the command operation, the control unit 114 controls the planting operation of the planting device according to the target planting task instruction.
  • the determining unit 113 determines that the voiceprint identity data of the target voice instruction belongs to the user D, if the determining unit 113 simultaneously determines the voiceprint identity corresponding to the target voice command configured in the command operation set.
  • the data also belongs to the user D, and the control unit 114 controls the planting operation of the planting equipment according to the target planting task instruction.
  • control unit 114 controls the planting operation of the planting equipment only when the designated person issues the target voice command, thereby ensuring the safety of the planting operation.
  • the determining unit 113 determines that the target planting task instruction that matches the target voice instruction to target the planting task instruction comprises:
  • the determining unit 113 determines whether the crop corresponding to the target voice command is the same as the crop corresponding to the target voice command configured in the command operation, and if the same, the planting task command is used as the target.
  • the determining unit 113 determines a crop corresponding to the target voice instruction by using a voice recognition technology, and the determining unit 113 determines a crop corresponding to the target voice instruction and the target voice and the target voice Whether the crop corresponding to the instruction is the same, and when the crop corresponding to the target voice is the same as the crop corresponding to the target voice instruction configured in the instruction operation, the control unit 114 controls the planting according to the target planting task instruction. Planting operations of the equipment.
  • the determining unit 113 may determine that the crop corresponding to the target voice instruction is a tomato, if the determining unit is 113. At the same time, it is determined that the crop corresponding to the target voice instruction configured in the instruction operation is also a tomato, and the control unit 114 controls the planting operation of the planting device according to the target planting task instruction.
  • control unit 114 controls the planting operation of the planting equipment only when the crops are matched, thereby avoiding the occurrence of misoperation.
  • the determining unit 113 determines that the target planting task instruction that matches the target voice instruction to target the planting task instruction comprises:
  • the determining unit 113 determines whether the planting link corresponding to the target voice command is the same as the planting link corresponding to the target voice command configured in the command operation, and if the same, the planting task command is used as the target.
  • the determining unit 113 determines a planting link corresponding to the target voice command by using a voice recognition technology, and the determining unit 113 determines that the planting link corresponding to the target voice command is centrally configured with the command operation and Whether the planting links corresponding to the target voice command are the same, and when the planting link corresponding to the target voice command is the same as the planting link corresponding to the target voice command configured in the command operation, the control unit 114 is configured according to the target Planting task instructions to control planting operations of planting equipment.
  • the determining unit 113 determines that the planting link corresponding to the target voice command is seeding, and if the determining unit 113 simultaneously determines that the planting link corresponding to the target voice command configured in the command operation is also seeded, Then, the control unit 114 controls the planting operation of the planting equipment according to the target planting task instruction.
  • control unit 114 controls the planting operation of the planting equipment only when the planting links are matched, and the phenomenon of misoperation can also be avoided.
  • the electronic device 1 may further match the corresponding crops and/or corresponding planting links after matching the voiceprint identity data of the target voice command to ensure more Safely perform planting operations.
  • the foregoing three matching processes may be implemented in combination according to actual needs.
  • the present invention does not limit the order and combination manner of the foregoing three matching processes in the combined implementation manner.
  • the electronic device 1 may select all or part of the above three matching processes, and perform the sequence according to the configuration sequence, and the configuration sequence may be set by the relevant staff according to actual conditions.
  • the alarm unit 116 can also issue an error alert, specifically:
  • the alarm unit 116 issues an alarm when the determination unit 113 cannot determine a planting task instruction that matches the target voice instruction to be a target planting task instruction.
  • the determining unit 113 determines that the planting link corresponding to the target voice command is seeding, if the determining unit 113 simultaneously determines that the planting link corresponding to the target voice command configured in the command operation is fertilized, If the two do not match, the alarm unit 116 issues an alarm.
  • the alarm may be in the form of a prompt tone, or a flashing of the light, etc., and the invention is not limited.
  • the alarm unit 116 may also prompt the user to issue an alarm for the user to re-issue the correct voice command.
  • the alarm unit 116 can promptly prompt the user that the planting link does not match, please re-enter the command, thank you, and the like.
  • the control unit 114 controls the planting operation of the planting equipment according to the target planting task instruction.
  • the method when the voiceprint identity data of the target voice command is changed in the instruction operation set, the method further includes:
  • the acquiring unit 115 acquires the voice command of the updated voiceprint identity data, and the updating unit 117 sets the target voice.
  • the instruction is updated to the voice command of the updated voiceprint identity data.
  • the obtaining unit 115 may acquire the voiceprint identity data of the new operator, and the update unit 117 sets the voiceprint identity data of the new operator. Updating to the voiceprint identity data of the target voice command, and updating the command input by the target voice command for the new operator to avoid a situation in which the command is unavailable due to personnel changes.
  • the method further includes:
  • the obtaining unit 115 acquires an input instruction of a planting task instruction for the target crop
  • the obtaining unit 115 acquires voice instruction data matching the planting task instruction from the instruction operation set, and the configuration unit 110 A planting task instruction corresponding to the target crop is configured based on the matched voice instruction data.
  • the obtaining unit 115 can directly obtain the voice command data matching the planting task command from the instruction operation set, thereby avoiding the related command operator. Repeated entry instructions result in redundant and repetitive workloads.
  • the present invention can configure a correspondence between a voice command and a planting task command, generate an instruction operation set, receive a target voice, identify the target voice, obtain a target voice command, and determine to match the target voice command.
  • the planting task instruction is used as a target planting task instruction; the planting operation of the planting equipment is controlled according to the target planting task instruction. Therefore, the invention can perform voice operation on the planting task of the crop, which is convenient and fast, and brings a better operating experience to the user.
  • FIG. 4 is a schematic structural diagram of an electronic device according to a preferred embodiment of the voice control method of the present invention.
  • the electronic device 1 is a device capable of automatically performing numerical calculation and/or information processing according to an instruction set or stored in advance, and the hardware includes, but not limited to, a microprocessor, an application specific integrated circuit (ASIC). ), a Field-Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.
  • ASIC application specific integrated circuit
  • FPGA Field-Programmable Gate Array
  • DSP Digital Signal Processor
  • embedded device and the like.
  • the electronic device 1 can also be, but is not limited to, any electronic product that can interact with a user through a keyboard, a mouse, a remote controller, a touch panel, or a voice control device, such as a personal computer, a tablet, or a smart phone. , Personal Digital Assistant (PDA), game consoles, Internet Protocol Television (IPTV), smart wearable devices, etc.
  • PDA Personal Digital Assistant
  • IPTV Internet Protocol Television
  • the electronic device 1 can also be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server.
  • the network in which the electronic device 1 is located includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), and the like.
  • the Internet includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), and the like.
  • VPN virtual private network
  • the electronic device 1 includes, but is not limited to, a memory 12, a processor 13, and a computer program stored in the memory 12 and operable on the processor 13, such as Voice control program.
  • the schematic diagram is merely an example of the electronic device 1, does not constitute a limitation on the electronic device 1, may include more or less components than those illustrated, or combine some components, or different. Components such as the electronic device 1 may also include input and output devices, network access devices, buses, and the like.
  • the processor 13 may be a central processing unit (CPU), or may be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc.
  • the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, and the processor 13 is an operation core and a control center of the electronic device 1, and connects the entire electronic device by using various interfaces and lines. Each part of 1 and an operating system of the electronic device 1 and various installed applications, program codes, and the like.
  • the processor 13 executes an operating system of the electronic device 1 and various types of installed applications.
  • the processor 13 executes the application to implement the steps in the foregoing various voice control method embodiments, such as steps S10, S11, S12, S13, and S14 shown in FIG.
  • the processor 13 implements the functions of each module/unit in each device embodiment when executing the computer program, for example, configuring a correspondence between a voice command and a planting task command, generating an instruction operation set, and receiving a target voice;
  • the target voice is identified to obtain a target voice instruction;
  • a planting task instruction matching the target voice command is determined to be a target planting task instruction; and the planting operation of the planting device is controlled according to the target planting task instruction.
  • the computer program can be partitioned into one or more modules/units, which are stored in the memory 12 and executed by the processor 13 to complete the present invention.
  • the one or more modules/units may be a series of computer program instruction segments capable of performing a particular function, the instruction segments being used to describe the execution of the computer program in the electronic device 1.
  • the computer program may be divided into a configuration unit 110, a receiving unit 111, an identification unit 112, a determination unit 113, a control unit 114, an acquisition unit 115, an alarm unit 116, and an update unit 117.
  • the memory 12 can be used to store the computer program and/or module by running or executing a computer program and/or module stored in the memory 12, and recalling data stored in the memory 12, Various functions of the electronic device 1 are implemented.
  • the memory 12 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function (such as a sound playing function, an image playing function, etc.), and the like; Stores data created based on the use of the phone (such as audio data, phone book, etc.).
  • the memory 12 may include a high-speed random access memory, and may also include a non-volatile memory such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SMC), and a secure digital (SD).
  • a non-volatile memory such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SMC), and a secure digital (SD).
  • SSD secure digital
  • flash card at least one disk storage device, flash device, or other volatile solid state storage device.
  • the memory 12 may be an external memory and/or an internal memory of the electronic device 1. Further, the memory 12 may be a circuit having a storage function in a physical form, such as a RAM (Random-Access Memory), a FIFO (First In First Out), or the like. Alternatively, the memory 12 may also be a memory having a physical form such as a memory stick, a TF card, or the like.
  • the modules/units integrated by the electronic device 1 can be stored in a computer readable storage medium if implemented in the form of a software functional unit and sold or used as a standalone product. Based on such understanding, the present invention implements all or part of the processes in the foregoing embodiments, and may also be completed by a computer program to instruct related hardware.
  • the computer program may be stored in a computer readable storage medium. The steps of the various method embodiments described above may be implemented when the program is executed by the processor.
  • the computer program comprises computer program code, which may be in the form of source code, object code form, executable file or some intermediate form.
  • the computer readable medium may include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM). , random access memory (RAM, Random Access Memory), electrical carrier signals, telecommunications signals, and software distribution media.
  • RAM random access memory
  • computer readable media Does not include electrical carrier signals and telecommunication signals.
  • the memory 12 in the electronic device 1 stores a plurality of instructions to implement a voice control method
  • the processor 13 can execute the plurality of instructions to implement: configuring voice commands and planting task instructions. Corresponding relationship, generating an instruction operation set; receiving a target speech; identifying the target speech to obtain a target voice instruction; determining a planting task instruction matching the target voice instruction, as a target planting task instruction; Planting task instructions to control planting operations of planting equipment.
  • the processor 13 further executes a plurality of instructions including:
  • the task instruction is planted as the target.
  • the processor 13 further executes a plurality of instructions including:
  • the task instruction is planted as the target.
  • the processor 13 further executes a plurality of instructions including:
  • the task instruction is planted as the target.
  • the processor 13 further executes a plurality of instructions including:
  • An alert is issued when a planting task command that matches the target voice command cannot be determined to be a target planting task command.
  • the processor 13 further executes a plurality of instructions including:
  • the processor 13 further executes a plurality of instructions including:
  • a planting task instruction corresponding to the target crop is configured based on the matched voice instruction data.
  • modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional module in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of hardware plus software function modules.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Telephonic Communication Services (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种语音控制方法及装置、电子设备和计算机可读存储介质。该方法包括：配置语音指令及种植任务指令的对应关系，生成指令操作集（S10）；接收目标语音（S11）；对该目标语音进行识别，得到目标语音指令（S12）；确定与该目标语音指令相匹配的种植任务指令，以作为目标种植任务指令（S13）；根据该目标种植任务指令，控制种植设备的种植操作（S14）。本方法能对作物的种植任务进行语音操作，方便、快捷，给用户带来更好的操作体验。

Description

语音控制方法及装置、电子设备和计算机可读存储介质
本申请要求于2018年01月29日提交中国专利局，申请号为201810085318.2、发明名称为“语音控制方法及装置、电子设备和计算机可读存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及智能语音技术领域，尤其涉及一种语音控制方法及装置、电子设备和计算机可读存储介质。
背景技术
目前，农业作业场景大多是在广阔的空间，具有多样性、多变性、分散性等特点，因此，由于农业采集现场较复杂，也给用户的操作带来诸多不便，例如：
(1)无论在室内或室外环境中，由于手持设备屏幕小，使用户带护具操作时不够顺畅。
(2)烈日、风沙、雨雪等恶劣天气环境下，用户在进行取防护措施的操作时不方便。
(3)由于用户在操作种植设备的同时也承担着农事作业，因此，影响人机交互的效率。
(4)用户携带手持设备移动作业不方便。
(5)种植设备的操作对用户的知识水平及操作水平有一定要求。
发明内容
鉴于以上内容，有必要提供一种语音控制方法及装置、电子设备和计算机可读存储介质，能对作物的种植任务进行语音操作，方便、快捷，给用户带来更好的操作体验。
一种语音控制方法，所述方法包括：
配置语音指令及种植任务指令的对应关系，生成指令操作集；
接收目标语音；
对所述目标语音进行识别，得到目标语音指令；
确定与所述目标语音指令相匹配的种植任务指令，以作为目标种植任务 指令；
根据所述目标种植任务指令，控制种植设备的种植操作。
根据本发明优选实施例，所述确定与所述目标语音指令匹配的目标种植任务指令，以作为目标种植任务指令包括：
判断所述目标语音指令的声纹身份数据与所述指令操作集中配置的与所述目标语音指令对应的声纹身份数据是否相同；
若相同，则作为所述目标种植任务指令。
根据本发明优选实施例，所述确定与所述目标语音指令匹配的目标种植任务指令，以作为目标种植任务指令包括：
判断所述目标语音指令对应的作物与所述指令操作集中配置的与所述目标语音指令对应的作物是否相同；
若相同，则作为所述目标种植任务指令。
根据本发明优选实施例，所述确定与所述目标语音指令匹配的目标种植任务指令，以作为目标种植任务指令包括：
判断所述目标语音指令对应的种植环节与所述指令操作集中配置的与所述目标语音指令对应的种植环节是否相同；
若相同，则作为所述目标种植任务指令。
根据本发明优选实施例，所述方法还包括：
当不能确定与所述目标语音指令相匹配的种植任务指令，以作为目标种植任务指令时，发出警报。
根据本发明优选实施例，所述方法还包括：
当接收到改变所述指令操作集中目标语音指令的声纹身份数据的请求时，获取更新的声纹身份数据的语音指令；
将所述目标语音指令更新为所述更新的声纹身份数据的语音指令。
根据本发明优选实施例，所述方法还包括：
当获取到对目标作物的种植任务指令的输入指令时，从所述指令操作集中获取与所述种植任务指令相匹配的语音指令数据；
基于所述匹配的语音指令数据，配置对应所述目标作物的种植任务指令。
一种语音控制装置，所述装置包括：
配置单元，用于配置语音指令及种植任务指令的对应关系，生成指令操作集；
接收单元，用于接收目标语音；
识别单元，用于对所述目标语音进行识别，得到目标语音指令；
确定单元，用于确定与所述目标语音指令相匹配的种植任务指令，以作 为目标种植任务指令；
控制单元，用于根据所述目标种植任务指令，控制种植设备的种植操作。
根据本发明优选实施例，所述确定单元具体用于：
判断所述目标语音指令对应的作物与所述指令操作集中配置的与所述目标语音指令对应的作物是否相同；
若相同，则作为所述目标种植任务指令。
根据本发明优选实施例，所述确定单元具体还用于：
判断所述目标语音指令对应的作物与所述指令操作集中配置的与所述目标语音指令对应的作物是否相同；
若相同，则作为所述目标种植任务指令。
根据本发明优选实施例，所述确定单元具体还用于：
判断所述目标语音指令对应的种植环节与所述指令操作集中配置的与所述目标语音指令对应的种植环节是否相同；
若相同，则作为所述目标种植任务指令。
根据本发明优选实施例，所述装置还包括：
警报单元，由于当不能确定与所述目标语音指令相匹配的种植任务指令，以作为目标种植任务指令时，发出警报。
根据本发明优选实施例，所述装置还包括：
获取单元，用于当接收到改变所述指令操作集中目标语音指令的声纹身份数据的请求时，获取更新的声纹身份数据的语音指令；
更新单元，由于将所述目标语音指令更新为所述更新的声纹身份数据的语音指令。
根据本发明优选实施例，所述获取单元，还用于当获取到对目标作物的种植任务指令的输入指令时，从所述指令操作集中获取与所述种植任务指令相匹配的语音指令数据；
所述配置单元，还用于基于所述匹配的语音指令数据，配置对应所述目标作物的种植任务指令。
一种电子设备，所述电子设备包括：
处理器；及
存储器，存储在所述存储器中的指令被所述处理器执行以实现所述语音控制方法。
一种计算机可读存储介质，所述计算机可读存储介质中存储的指令被电子设备中的处理器执行以实现所述语音控制方法。
由以上技术方案可以看出，本发明通过配置语音指令及种植任务指令的 对应关系，生成指令操作集，该指令操作集将所有需要使用的操作指令集成在一起，方便存储和管理，后续可以对接收的语音进行识别，触发相对应的与操作指令集中相匹配的指令，从而控制与所述电子设备相通信的所述种植设备执行相关种植操作，这样，通过语音操作实现对作物执行种植任务，不仅方便、快捷，同时给用户带来更好的操作体验。
附图说明
图1是本发明实现语音控制方法的较佳实施例的应用环境图。
图2是本发明语音控制方法的较佳实施例的流程图。
图3是本发明语音控制装置的较佳实施例的功能模块图。
图4是本发明实现语音控制方法的较佳实施例的电子设备的结构示意图。
主要元件符号说明
电子设备 1
存储器 12
处理器 13
语音控制装置 11
配置单元 110
接收单元 111
识别单元 112
确定单元 113
控制单元 114
获取单元 115
警报单元 116
更新单元 117
种植设备 2
具体实施方式
为了使本发明的目的、技术方案和优点更加清楚，下面结合附图和具体实施例对本发明进行详细描述。
如图1所示，图1是本发明实现语音控制方法的较佳实施例的应用环境图。所述应用环境图中包括电子设备1及种植设备2，所述电子设备1与所 述种植设备2相通信。
其中，所述电子设备1用于控制所述种植设备2的种植操作；
所述种植设备2用于执行种植操作。
如图2所示，是本发明语音控制方法的较佳实施例的流程图。根据不同的需求，该流程图中步骤的顺序可以改变，某些步骤可以省略。
所述语音控制方法应用于一个或者多个电子设备1中，所述电子设备1是一种能够按照事先设定或存储的指令，自动进行数值计算和/或信息处理的设备，其硬件包括但不限于微处理器、专用集成电路(Application Specific Integrated Circuit，ASIC)、可编程门阵列(Field－Programmable Gate Array，FPGA)、数字处理器(Digital Signal Processor，DSP)、嵌入式设备等。
所述电子设备1可以是任何一种可与用户进行人机交互的电子产品，例如，个人计算机、平板电脑、智能手机、个人数字助理(Personal Digital Assistant，PDA)、游戏机、交互式网络电视(Internet Protocol Television，IPTV)、智能式穿戴式设备等。
所述电子设备1还可以包括网络设备和/或用户设备。其中，所述网络设备包括，但不限于单个网络服务器、多个网络服务器组成的服务器组或基于云计算(Cloud Computing)的由大量主机或网络服务器构成的云。
所述电子设备1所处的网络包括但不限于互联网、广域网、城域网、局域网、虚拟专用网络(Virtual Private Network，VPN)等。
S10，所述电子设备1配置语音指令及种植任务指令的对应关系，生成指令操作集。
在本发明的至少一个实施例中，为了便于后续利用所述指令操作集对接收的语音进行识别，以控制与所述电子设备1相通信的所述种植设备2的种植操作，所述电子设备1配置语音指令及种植任务指令的对应关系，生成指令操作集。
优选地，所述语音指令可以由所述用户进行自定义设置。具体地，所述用户可以根据本技术领域中的常用技术用语配置所述语音指令，以使相关操作人员能够在具备本技术领域内的基本常识的情况下，快速掌握所述语音指令，避免由于繁琐的语音指令的设置，使所述相关操作人员由于输入错误的语音指令造成误操作。
当然，在其他实施例中，所述语音指令也可以包括其他设置方式，本发明不作限制。
优选地，所述种植任务指令包括，但不限于：播种、施肥、打药、浇水 等等。
在本发明的至少一个实施例中，所述电子设备1配置语音指令及种植任务指令的对应关系，生成指令操作集包括：
所述电子设备1获取至少一种种植任务指令，并为所述至少一种种植任务指令分别配置对应的语音指令，所述电子设备1将配置好的所述至少一种种植任务指令及所述对应的语音指令合并为所述指令操作集。
例如：所述电子设备1配置种植任务指令番茄施肥，对应于语音指令施肥A，所述电子设备1配置种植任务指令黄瓜打药，对应于语音指令打药B，所述电子设备1配置种植任务指令生菜播种，对应于语音指令播种C等等，所述电子设备1将上述对应关系合并为所述指令操作集。
S11，所述电子设备1接收目标语音。
在本发明的至少一个实施例中，所述电子设备1接收目标语音，以便后续从所述目标语音中识别出目标语音指令。
具体地，本发明对所述电子设备1接收所述目标语音的方式不作限制。例如：所述电子设备1可以通过与所述电子设备1相通信的语音采集设备接收所述目标语音等等。
S12，所述电子设备1对所述目标语音进行识别，得到目标语音指令。
在本发明的至少一个实施例中，所述电子设备1对所述目标语音进行识别，得到目标语音指令包括：模型训练阶段、识别阶段。
具体地，所述模型训练阶段包括声学模型的训练和语言模型的训练两部分。所述声学模型主要采用上下文三音子为建模单元，通过采集大量的语音样本建立语音语料库，采用隐马尔可夫模型Baum－Welch等算法进行模型的训练，得到稳定的声学模型。在进行所述声学模型的训练之前，所述电子设备1还需要对声音信号进行预处理、提取稳定的声学特征等处理，具体地，所述电子设备1可以采用特征为梅尔频率倒谱系数(Mel Frequency Cepstrum Coefficient，MFCC)或感知线性预测系数(Perceptual Linear Prediction，PLP)等解决特征提取问题。所述语言模型的训练主要是对文本信息的处理，所述电子设备1首先对特定的应用场景用文本提取工具提取大量的文本，再建立语料库，并对所述语料库进行语义分析，同时对所述语料库中的语法结构进行推断，进而形成一系列的语法规则，即训练得到所述语言模型。
进一步地，所述识别阶段是对语音信号进行解码的过程，所述电子设备1可以基于隐马尔科夫模型的解码过程，并采用Viterbi算法(Viterbi Algorithm)。首先，所述电子设备1在前端对输入语音信号进行特征提取，得到的特征向量与所述声学模型进行声学对比。然后，所述电子设备1从发 音词典中选出概率分布最为接近的候选词，再利用所述语言模型进一步进行约束，得到最终的识别结果。
需要说明的是，在其他实施例中，所述电子设备1也可以采用其他方式对所述目标语音进行识别，本发明在此不作限制。
S13，所述电子设备1确定与所述目标语音指令相匹配的种植任务指令，以作为目标种植任务指令。
在本发明的至少一个实施例中，所述电子设备1确定与所述目标语音指令匹配的目标种植任务指令，以作为目标种植任务指令包括：
所述电子设备1判断所述目标语音指令的声纹身份数据与所述指令操作集中配置的与所述目标语音指令对应的声纹身份数据是否相同，若相同，则作为所述目标种植任务指令。
具体地，所述电子设备1确定所述目标语音指令的声纹身份数据与所述指令操作集中配置的与所述目标语音指令对应的声纹身份数据是否相同，当所述目标语音指令的声纹身份数据与所述指令操作集中配置的与所述目标语音指令对应的声纹身份数据相同时，所述电子设备1根据所述目标种植任务指令，控制种植设备的种植操作。
例如：所述电子设备1在确定所述目标语音指令的声纹身份数据属于用户D时，如果所述电子设备1同时确定所述指令操作集中配置的与所述目标语音指令对应的声纹身份数据也属于所述用户D，则所述电子设备1根据所述目标种植任务指令，控制种植设备的种植操作。
这样，只有指定人员发出所述目标语音指令时，所述电子设备1才会控制种植设备的种植操作，保证了种植操作的安全性。
在本发明的至少一个实施例中，所述电子设备1确定与所述目标语音指令匹配的目标种植任务指令，以作为目标种植任务指令还包括：
所述电子设备1判断所述目标语音指令对应的作物与所述指令操作集中配置的与所述目标语音指令对应的作物是否相同，若相同，则作为所述目标种植任务指令。
具体地，所述电子设备1利用语音识别技术，确定所述目标语音指令对应的作物，确定所述目标语音指令对应的作物与所述指令操作集中配置的与所述目标语音指令对应的作物是否相同，当所述目标语音对应的作物与所述指令操作集中配置的与所述目标语音指令对应的作物相同时，所述电子设备1根据所述目标种植任务指令，控制种植设备的种植操作。
例如：当用户在所述电子设备1输入的目标语音指令为“施肥番茄”时，利用语音识别技术，所述电子设备1可确定所述目标语音指令对应的作物为 番茄，如果所述电子设备1同时确定所述指令操作集中配置的与所述目标语音指令对应的作物也是番茄，则所述电子设备1根据所述目标种植任务指令，控制种植设备的种植操作。
这样，只有作物匹配时，所述电子设备1才会控制种植设备的种植操作，避免误操作的现象发生。
在本发明的至少一个实施例中，所述电子设备1确定与所述目标语音指令匹配的目标种植任务指令，以作为目标种植任务指令还包括：
所述电子设备1判断所述目标语音指令对应的种植环节与所述指令操作集中配置的与所述目标语音指令对应的种植环节是否相同，若相同，则作为所述目标种植任务指令。
具体地，所述电子设备1利用语音识别技术，确定所述目标语音指令对应的种植环节，确定所述目标语音指令对应的种植环节与所述指令操作集中配置的与所述目标语音指令对应的种植环节是否相同，当所述目标语音指令对应的种植环节与所述指令操作集中配置的与所述目标语音指令对应的种植环节相同时，所述电子设备1根据所述目标种植任务指令，控制种植设备的种植操作。
例如：所述电子设备1在确定所述目标语音指令对应的种植环节为播种时，如果所述电子设备1同时确定所述指令操作集中配置的与所述目标语音指令对应的种植环节也是播种，则所述电子设备1根据所述目标种植任务指令，控制种植设备的种植操作。
这样，只有种植环节匹配时，所述电子设备1才会控制种植设备的种植操作，同样可以避免误操作的现象发生。
在本发明的至少一个实施例中，所述电子设备1还可以在匹配了所述目标语音指令的声纹身份数据后，再进行对应的作物及/或对应的种植环节的匹配，以保证更加安全的执行种植操作。需要说明的是，在其他实施例中，上述三种匹配过程可以根据实际需要组合实施，本发明对组合实施方式中上述三种匹配过程的顺序及组合方式等不做限制。例如：所述电子设备1可以从上述三种匹配过程中选择全部或者部分过程，按照配置顺序进行，所述配置顺序可以由相关工作人员根据实际情况设置。
在本发明的至少一个实施例中，所述电子设备1还可以发出错误警报，具体地：
当所述电子设备1不能确定与所述目标语音指令相匹配的种植任务指令，以作为目标种植任务指令时，所述电子设备1发出警报。
例如：所述电子设备1在确定所述目标语音指令对应的种植环节为播种 时，如果所述电子设备1同时确定所述指令操作集中配置的与所述目标语音指令对应的种植环节是施肥，二者不匹配，则所述电子设备1发出警报。
具体地，警报的形式可以是发出提示音，或者是灯光闪烁等等，本发明不作限制。
进一步地，所述电子设备1还可以提示所述用户发出警报的原因，以便所述用户重新发出正确的语音指令。
例如：所述电子设备1可以语音提示所述用户“种植环节不匹配，请重新输入指令，谢谢”等。
S14，所述电子设备1根据所述目标种植任务指令，控制种植设备的种植操作。
在本发明的至少一个实施例中，当所述指令操作集中目标语音指令的声纹身份数据改变时，所述方法还包括：
当接收到改变所述指令操作集中目标语音指令的声纹身份数据的请求时，所述电子设备1获取更新的声纹身份数据的语音指令，并将所述目标语音指令更新为所述更新的声纹身份数据的语音指令。
这样，当所述目标语音指令对应的指定操作人员改变时，所述电子设备1可以获取新的操作人员的声纹身份数据，并将所述新的操作人员的声纹身份数据更新为所述目标语音指令的声纹身份数据，同时更新所述目标语音指令为所述新的操作人员输入的指令，以避免由于人事变动造成指令不可用的情况。
在本发明的至少一个实施例中，为了给不同的作物配置相同的目标语音指令，所述方法还包括：
当获取到对目标作物的种植任务指令的输入指令时，所述电子设备1从所述指令操作集中获取与所述种植任务指令相匹配的语音指令数据，所述电子设备1基于所述匹配的语音指令数据，配置对应所述目标作物的种植任务指令。
这样，当同一个目标语音指令可以同时控制不同作物的种植任务时，所述电子设备1可以直接从所述指令操作集中获取与所述种植任务指令相匹配的语音指令数据，避免相关指令操作人员重复录入指令带来多余且重复的工作量。
综上所述，本发明能配置语音指令及种植任务指令的对应关系，生成指令操作集；接收目标语音；对所述目标语音进行识别，得到目标语音指令；确定与所述目标语音指令相匹配的种植任务指令，以作为目标种植任务指令；根据所述目标种植任务指令，控制种植设备的种植操作。因此，本发明能对 作物的种植任务进行语音操作，方便、快捷，给用户带来更好的操作体验。
如图3所示，是本发明语音控制装置的较佳实施例的功能模块图。所述语音控制装置11包括配置单元110、接收单元111、识别单元112、确定单元113、控制单元114、获取单元115、警报单元116及更新单元117。本发明所称的模块/单元是指一种能够被处理器13所执行，并且能够完成固定功能的一系列计算机程序段，其存储在存储器12中。在本实施例中，关于各模块/单元的功能将在后续的实施例中详述。
配置单元110配置语音指令及种植任务指令的对应关系，生成指令操作集。
在本发明的至少一个实施例中，为了便于后续利用所述指令操作集对接收的语音进行识别，以控制与所述电子设备1相通信的所述种植设备2的种植操作，所述配置单元110配置语音指令及种植任务指令的对应关系，生成指令操作集。
优选地，所述语音指令可以由所述用户进行自定义设置。具体地，所述用户可以根据本技术领域中的常用技术用语配置所述语音指令，以使相关操作人员能够在具备本技术领域内的基本常识的情况下，快速掌握所述语音指令，避免由于繁琐的语音指令的设置，使所述相关操作人员由于输入错误的语音指令造成误操作。
当然，在其他实施例中，所述语音指令也可以包括其他设置方式，本发明不作限制。
优选地，所述种植任务指令包括，但不限于：播种、施肥、打药、浇水等等。
在本发明的至少一个实施例中，所述配置单元110配置语音指令及种植任务指令的对应关系，生成指令操作集包括：
所述配置单元110获取至少一种种植任务指令，并为所述至少一种种植任务指令分别配置对应的语音指令，所述配置单元110将配置好的所述至少一种种植任务指令及所述对应的语音指令合并为所述指令操作集。
例如：所述配置单元110配置种植任务指令番茄施肥，对应于语音指令施肥A，所述配置单元110配置种植任务指令黄瓜打药，对应于语音指令打药B，所述配置单元110配置种植任务指令生菜播种，对应于语音指令播种C等等，所述配置单元110将上述对应关系合并为所述指令操作集。
接收单元111接收目标语音。
在本发明的至少一个实施例中，所述接收单元111接收目标语音，以便 后续从所述目标语音中识别出目标语音指令。
具体地，本发明对所述接收单元111接收所述目标语音的方式不作限制。例如：所述接收单元111可以通过与所述电子设备1相通信的语音采集设备接收所述目标语音等等。
识别单元112对所述目标语音进行识别，得到目标语音指令。
在本发明的至少一个实施例中，所述识别单元112对所述目标语音进行识别，得到目标语音指令包括：模型训练阶段、识别阶段。
具体地，所述模型训练阶段包括声学模型的训练和语言模型的训练两部分。所述声学模型主要采用上下文三音子为建模单元，通过采集大量的语音样本建立语音语料库，采用隐马尔可夫模型Baum－Welch等算法进行模型的训练，得到稳定的声学模型。在进行所述声学模型的训练之前，所述识别单元112还需要对声音信号进行预处理、提取稳定的声学特征等处理，具体地，所述识别单元112可以采用特征为梅尔频率倒谱系数(Mel Frequency Cepstrum Coefficient，MFCC)或感知线性预测系数(Perceptual Linear Prediction，PLP)等解决特征提取问题。所述语言模型的训练主要是对文本信息的处理，所述识别单元112首先对特定的应用场景用文本提取工具提取大量的文本，再建立语料库，并对所述语料库进行语义分析，同时对所述语料库中的语法结构进行推断，进而形成一系列的语法规则，即训练得到所述语言模型。
进一步地，所述识别阶段是对语音信号进行解码的过程，所述识别单元112可以基于隐马尔科夫模型的解码过程，并采用Viterbi算法(Viterbi Algorithm)。首先，所述识别单元112在前端对输入语音信号进行特征提取，得到的特征向量与所述声学模型进行声学对比。然后，所述识别单元112从发音词典中选出概率分布最为接近的候选词，再利用所述语言模型进一步进行约束，得到最终的识别结果。
需要说明的是，在其他实施例中，所述识别单元112也可以采用其他方式对所述目标语音进行识别，本发明在此不作限制。
确定单元113确定与所述目标语音指令相匹配的种植任务指令，以作为目标种植任务指令。
在本发明的至少一个实施例中，所述确定单元113确定与所述目标语音指令匹配的目标种植任务指令，以作为目标种植任务指令包括：
所述确定单元113判断所述目标语音指令的声纹身份数据与所述指令操作集中配置的与所述目标语音指令对应的声纹身份数据是否相同，若相同，则作为所述目标种植任务指令。
具体地，所述确定单元113确定所述目标语音指令的声纹身份数据与所述指令操作集中配置的与所述目标语音指令对应的声纹身份数据是否相同，当所述目标语音指令的声纹身份数据与所述指令操作集中配置的与所述目标语音指令对应的声纹身份数据相同时，控制单元114根据所述目标种植任务指令，控制种植设备的种植操作。
例如：所述确定单元113在确定所述目标语音指令的声纹身份数据属于用户D时，如果所述确定单元113同时确定所述指令操作集中配置的与所述目标语音指令对应的声纹身份数据也属于所述用户D，则所述控制单元114根据所述目标种植任务指令，控制种植设备的种植操作。
这样，只有指定人员发出所述目标语音指令时，所述控制单元114才会控制种植设备的种植操作，保证了种植操作的安全性。
在本发明的至少一个实施例中，所述确定单元113所述确定与所述目标语音指令匹配的目标种植任务指令，以作为目标种植任务指令包括：
所述确定单元113判断所述目标语音指令对应的作物与所述指令操作集中配置的与所述目标语音指令对应的作物是否相同，若相同，则作为所述目标种植任务指令。
具体地，所述确定单元113利用语音识别技术，确定所述目标语音指令对应的作物，所述确定单元113确定所述目标语音指令对应的作物与所述指令操作集中配置的与所述目标语音指令对应的作物是否相同，当所述目标语音对应的作物与所述指令操作集中配置的与所述目标语音指令对应的作物相同时，所述控制单元114根据所述目标种植任务指令，控制种植设备的种植操作。
例如：当用户在所述电子设备1输入的目标语音指令为“施肥番茄”时，利用语音识别技术，所述确定单元113可确定所述目标语音指令对应的作物为番茄，如果所述确定单元113同时确定所述指令操作集中配置的与所述目标语音指令对应的作物也是番茄，则所述控制单元114根据所述目标种植任务指令，控制种植设备的种植操作。
这样，只有作物匹配时，所述控制单元114才会控制种植设备的种植操作，避免误操作的现象发生。
在本发明的至少一个实施例中，所述确定单元113所述确定与所述目标语音指令匹配的目标种植任务指令，以作为目标种植任务指令包括：
所述确定单元113判断所述目标语音指令对应的种植环节与所述指令操作集中配置的与所述目标语音指令对应的种植环节是否相同，若相同，则作为所述目标种植任务指令。
具体地，所述确定单元113利用语音识别技术，确定所述目标语音指令对应的种植环节，所述确定单元113确定所述目标语音指令对应的种植环节与所述指令操作集中配置的与所述目标语音指令对应的种植环节是否相同，当所述目标语音指令对应的种植环节与所述指令操作集中配置的与所述目标语音指令对应的种植环节相同时，所述控制单元114根据所述目标种植任务指令，控制种植设备的种植操作。
例如：所述确定单元113在确定所述目标语音指令对应的种植环节为播种时，如果所述确定单元113同时确定所述指令操作集中配置的与所述目标语音指令对应的种植环节也是播种，则所述控制单元114根据所述目标种植任务指令，控制种植设备的种植操作。
这样，只有种植环节匹配时，所述控制单元114才会控制种植设备的种植操作，同样可以避免误操作的现象发生。
在本发明的至少一个实施例中，所述电子设备1还可以在匹配了所述目标语音指令的声纹身份数据后，再进行对应的作物及/或对应的种植环节的匹配，以保证更加安全的执行种植操作。需要说明的是，在其他实施例中，上述三种匹配过程可以根据实际需要组合实施，本发明对组合实施方式中上述三种匹配过程的顺序及组合方式等不做限制。例如：所述电子设备1可以从上述三种匹配过程中选择全部或者部分过程，按照配置顺序进行，所述配置顺序可以由相关工作人员根据实际情况设置。
在本发明的至少一个实施例中，警报单元116还可以发出错误警报，具体地：
当所述确定单元113不能确定与所述目标语音指令相匹配的种植任务指令，以作为目标种植任务指令时，所述警报单元116发出警报。
例如：所述确定单元113在确定所述目标语音指令对应的种植环节为播种时，如果所述确定单元113同时确定所述指令操作集中配置的与所述目标语音指令对应的种植环节是施肥，二者不匹配，则所述警报单元116发出警报。
具体地，警报的形式可以是发出提示音，或者是灯光闪烁等等，本发明不作限制。
进一步地，所述警报单元116还可以提示所述用户发出警报的原因，以便所述用户重新发出正确的语音指令。
例如：所述警报单元116可以语音提示所述用户“种植环节不匹配，请重新输入指令，谢谢”等。
所述控制单元114根据所述目标种植任务指令，控制种植设备的种植操 作。
在本发明的至少一个实施例中，当所述指令操作集中目标语音指令的声纹身份数据改变时，所述方法还包括：
当所述获取单元115接收到改变所述指令操作集中目标语音指令的声纹身份数据的请求时，所述获取单元115获取更新的声纹身份数据的语音指令，更新单元117将所述目标语音指令更新为所述更新的声纹身份数据的语音指令。
这样，当所述目标语音指令对应的指定操作人员改变时，所述获取单元115可以获取新的操作人员的声纹身份数据，所述更新单元117将所述新的操作人员的声纹身份数据更新为所述目标语音指令的声纹身份数据，同时更新所述目标语音指令为所述新的操作人员输入的指令，以避免由于人事变动造成指令不可用的情况。
在本发明的至少一个实施例中，为了给不同的作物配置相同的目标语音指令，所述方法还包括：
当所述获取单元115获取到对目标作物的种植任务指令的输入指令时，所述获取单元115从所述指令操作集中获取与所述种植任务指令相匹配的语音指令数据，所述配置单元110基于所述匹配的语音指令数据，配置对应所述目标作物的种植任务指令。
这样，当同一个目标语音指令可以同时控制不同作物的种植任务时，所述获取单元115可以直接从所述指令操作集中获取与所述种植任务指令相匹配的语音指令数据，避免相关指令操作人员重复录入指令带来多余且重复的工作量。
综上所述，本发明能配置语音指令及种植任务指令的对应关系，生成指令操作集；接收目标语音；对所述目标语音进行识别，得到目标语音指令；确定与所述目标语音指令相匹配的种植任务指令，以作为目标种植任务指令；根据所述目标种植任务指令，控制种植设备的种植操作。因此，本发明能对作物的种植任务进行语音操作，方便、快捷，给用户带来更好的操作体验。
如图4所示，是本发明实现语音控制方法的较佳实施例的电子设备的结构示意图。
所述电子设备1是一种能够按照事先设定或存储的指令，自动进行数值计算和/或信息处理的设备，其硬件包括但不限于微处理器、专用集成电路(Application Specific Integrated Circuit，ASIC)、可编程门阵列(Field－Programmable Gate Array，FPGA)、数字处理器(Digital Signal Processor，DSP)、 嵌入式设备等。
所述电子设备1还可以是但不限于任何一种可与用户通过键盘、鼠标、遥控器、触摸板或声控设备等方式进行人机交互的电子产品，例如，个人计算机、平板电脑、智能手机、个人数字助理(Personal Digital Assistant，PDA)、游戏机、交互式网络电视(Internet Protocol Television，IPTV)、智能式穿戴式设备等。
所述电子设备1还可以是桌上型计算机、笔记本、掌上电脑及云端服务器等计算设备。
所述电子设备1所处的网络包括但不限于互联网、广域网、城域网、局域网、虚拟专用网络(Virtual Private Network，VPN)等。
在本发明的一个实施例中，所述电子设备1包括，但不限于，存储器12、处理器13，以及存储在所述存储器12中并可在所述处理器13上运行的计算机程序，例如语音控制程序。
本领域技术人员可以理解，所述示意图仅仅是电子设备1的示例，并不构成对电子设备1的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件，例如所述电子设备1还可以包括输入输出设备、网络接入设备、总线等。
所称处理器13可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等，所述处理器13是所述电子设备1的运算核心和控制中心，利用各种接口和线路连接整个电子设备1的各个部分，及执行所述电子设备1的操作系统以及安装的各类应用程序、程序代码等。
所述处理器13执行所述电子设备1的操作系统以及安装的各类应用程序。所述处理器13执行所述应用程序以实现上述各个语音控制方法实施例中的步骤，例如图1所示的步骤S10、S11、S12、S13、S14。
或者，所述处理器13执行所述计算机程序时实现上述各装置实施例中各模块/单元的功能，例如：配置语音指令及种植任务指令的对应关系，生成指令操作集；接收目标语音；对所述目标语音进行识别，得到目标语音指令；确定与所述目标语音指令相匹配的种植任务指令，以作为目标种植任务指令；根据所述目标种植任务指令，控制种植设备的种植操作。
示例性的，所述计算机程序可以被分割成一个或多个模块/单元，所述一个或者多个模块/单元被存储在所述存储器12中，并由所述处理器13执行，以完成本发明。所述一个或多个模块/单元可以是能够完成特定功能的一系列计算机程序指令段，该指令段用于描述所述计算机程序在所述电子设备1中的执行过程。例如，所述计算机程序可以被分割成配置单元110、接收单元111、识别单元112、确定单元113、控制单元114、获取单元115、警报单元116及更新单元117。
所述存储器12可用于存储所述计算机程序和/或模块，所述处理器13通过运行或执行存储在所述存储器12内的计算机程序和/或模块，以及调用存储在存储器12内的数据，实现所述电子设备1的各种功能。所述存储器12可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能、图像播放功能等)等；存储数据区可存储根据手机的使用所创建的数据(比如音频数据、电话本等)等。此外，存储器12可以包括高速随机存取存储器，还可以包括非易失性存储器，例如硬盘、内存、插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)、至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。
所述存储器12可以是电子设备1的外部存储器和/或内部存储器。进一步地，所述存储器12可以是集成电路中没有实物形式的具有存储功能的电路，如RAM(Random-Access Memory，随机存取存储器)、FIFO(First In First Out，)等。或者，所述存储器12也可以是具有实物形式的存储器，如内存条、TF卡(Trans-flash Card)等等。
所述电子设备1集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明实现上述实施例方法中的全部或部分流程，也可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一计算机可读存储介质中，该计算机程序在被处理器执行时，可实现上述各个方法实施例的步骤。
其中，所述计算机程序包括计算机程序代码，所述计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。所述计算机可读介质可以包括：能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、电载波信号、电信信号以及软件分发介质等。需要说明的是，所述计算机可 读介质包含的内容可以根据司法管辖区内立法和专利实践的要求进行适当的增减，例如在某些司法管辖区，根据立法和专利实践，计算机可读介质不包括电载波信号和电信信号。
结合图2，所述电子设备1中的所述存储器12存储多个指令以实现一种语音控制方法，所述处理器13可执行所述多个指令从而实现：配置语音指令及种植任务指令的对应关系，生成指令操作集；接收目标语音；对所述目标语音进行识别，得到目标语音指令；确定与所述目标语音指令相匹配的种植任务指令，以作为目标种植任务指令；根据所述目标种植任务指令，控制种植设备的种植操作。
根据本发明优选实施例，所述处理器13还执行多个指令包括：
判断所述目标语音指令的声纹身份数据与所述指令操作集中配置的与所述目标语音指令对应的声纹身份数据是否相同；
若相同，则作为所述目标种植任务指令。
根据本发明优选实施例，所述处理器13还执行多个指令包括：
判断所述目标语音指令对应的作物与所述指令操作集中配置的与所述目标语音指令对应的作物是否相同；
若相同，则作为所述目标种植任务指令。
根据本发明优选实施例，所述处理器13还执行多个指令包括：
判断所述目标语音指令对应的种植环节与所述指令操作集中配置的与所述目标语音指令对应的种植环节是否相同；
若相同，则作为所述目标种植任务指令。
根据本发明优选实施例，所述处理器13还执行多个指令包括：
当不能确定与所述目标语音指令相匹配的种植任务指令，以作为目标种植任务指令时，发出警报。
根据本发明优选实施例，所述处理器13还执行多个指令包括：
当接收到改变所述指令操作集中目标语音指令的声纹身份数据的请求时，获取更新的声纹身份数据的语音指令；
将所述目标语音指令更新为所述更新的声纹身份数据的语音指令。
根据本发明优选实施例，所述处理器13还执行多个指令包括：
当获取到对目标作物的种植任务指令的输入指令时，从所述指令操作集中获取与所述种植任务指令相匹配的语音指令数据；
基于所述匹配的语音指令数据，配置对应所述目标作物的种植任务指令。
具体地，所述处理器13对上述指令的具体实现方法可参考图2对应实施 例中相关步骤的描述，在此不赘述。
在本发明所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述模块的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。
所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能模块可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能模块的形式实现。
对于本领域技术人员而言，显然本发明不限于上述示范性实施例的细节，而且在不背离本发明的精神或基本特征的情况下，能够以其他的具体形式实现本发明。
因此，无论从哪一点来看，均应将实施例看作是示范性的，而且是非限制性的，本发明的范围由所附权利要求而不是上述说明限定，因此旨在将落在权利要求的等同要件的含义和范围内的所有变化涵括在本发明内。不应将权利要求中的任何附关联图标记视为限制所涉及的权利要求。
此外，显然“包括”一词不排除其他单元或步骤，单数不排除复数。系统权利要求中陈述的多个单元或装置也可以由一个单元或装置通过软件或者硬件来实现。第二等词语用来表示名称，而并不表示任何特定的顺序。
最后应说明的是，以上实施例仅用以说明本发明的技术方案而非限制，尽管参照较佳实施例对本发明进行了详细说明，本领域的普通技术人员应当理解，可以对本发明的技术方案进行修改或等同替换，而不脱离本发明技术方案的精神和范围。

Claims (10)

  1. 一种语音控制方法，其特征在于，所述方法包括：
    配置语音指令及种植任务指令的对应关系，生成指令操作集；
    接收目标语音；
    对所述目标语音进行识别，得到目标语音指令；
    确定与所述目标语音指令相匹配的种植任务指令，以作为目标种植任务指令；
    根据所述目标种植任务指令，控制种植设备的种植操作。
  2. 如权利要求1所述的语音控制方法，其特征在于，所述确定与所述目标语音指令匹配的目标种植任务指令，以作为目标种植任务指令包括：
    判断所述目标语音指令的声纹身份数据与所述指令操作集中配置的与所述目标语音指令对应的声纹身份数据是否相同；
    若相同，则作为所述目标种植任务指令。
  3. 如权利要求1所述的语音控制方法，其特征在于，所述确定与所述目标语音指令匹配的目标种植任务指令，以作为目标种植任务指令还包括：
    判断所述目标语音指令对应的作物与所述指令操作集中配置的与所述目标语音指令对应的作物是否相同；
    若相同，则作为所述目标种植任务指令。
  4. 如权利要求1所述的语音控制方法，其特征在于，所述确定与所述目标语音指令匹配的目标种植任务指令，以作为目标种植任务指令还包括：
    判断所述目标语音指令对应的种植环节与所述指令操作集中配置的与所述目标语音指令对应的种植环节是否相同；
    若相同，则作为所述目标种植任务指令。
  5. 如权利要求1至4中任一项所述的语音控制方法，其特征在于，所述方法还包括：
    当不能确定与所述目标语音指令相匹配的种植任务指令，以作为目标种植任务指令时，发出警报。
  6. 如权利要求1所述的语音控制方法，其特征在于，所述方法还包括：
    当接收到改变所述指令操作集中目标语音指令的声纹身份数据的请求时，获取更新的声纹身份数据的语音指令；
    将更新的声纹身份数据的语音指令取代所述指令操作集中的所述目标语音。
  7. 如权利要求1所述的语音控制方法，其特征在于，所述方法还包括：
    当获取到对目标作物的种植任务指令的输入指令时，从所述指令操作集中获取与所述种植任务指令相匹配的语音指令数据；
    基于所述匹配的语音指令数据，配置对应所述目标作物的种植任务指令。
  8. 一种语音控制装置，其特征在于，所述装置包括：
    配置单元，用于配置语音指令及种植任务指令的对应关系，生成指令操作集；
    接收单元，用于接收目标语音；
    识别单元，用于对所述目标语音进行识别，得到目标语音指令；
    确定单元，用于确定与所述目标语音指令相匹配的种植任务指令，以作为目标种植任务指令；
    控制单元，用于根据所述目标种植任务指令，控制种植设备的种植操作。
  9. 一种电子设备，其特征在于，所述电子设备包括：
    处理器；及
    存储器，存储在所述存储器中的指令被所述处理器执行以实现如权利要求1至7中任意一项所述语音控制方法。
  10. 一种计算机可读存储介质，其特征在于：所述计算机可读存储介质中存储的指令被电子设备中的处理器执行以实现如权利要求1至7中任意一项所述语音控制方法。
PCT/CN2018/088459 2018-01-29 2018-05-25 语音控制方法及装置、电子设备和计算机可读存储介质 WO2019144543A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810085318.2 2018-01-29
CN201810085318.2A CN108305625B (zh) 2018-01-29 2018-01-29 语音控制方法及装置、电子设备和计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2019144543A1 true WO2019144543A1 (zh) 2019-08-01

Family

ID=62866995

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/088459 WO2019144543A1 (zh) 2018-01-29 2018-05-25 语音控制方法及装置、电子设备和计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN108305625B (zh)
WO (1) WO2019144543A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112309369A (zh) * 2020-09-29 2021-02-02 天津工程机械研究院有限公司 一种基于语音识别的插秧机无人驾驶系统及方法

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS6368438A (ja) * 1986-09-08 1988-03-28 Iseki & Co Ltd 農作業機等の音声一体形処理装置
JPH0895593A (ja) * 1995-09-25 1996-04-12 Iseki & Co Ltd 音声認識装置
DE102004032642A1 (de) * 2004-07-06 2006-02-16 Rabe Agrarsysteme Gmbh & Co. Kg Sprachsteuerung für eine Landmaschine, insbesondere für eine Verteilmaschine
CN101477799A (zh) * 2009-01-19 2009-07-08 北京农业信息技术研究中心 一种使用语音对农业设备进行控制的系统及控制方法
CN103345709A (zh) * 2013-07-01 2013-10-09 南通农业职业技术学院 农业信息化服务系统及其信息传送方法
US20170004830A1 (en) * 2015-07-01 2017-01-05 Kverneland Group Mechatronics B.V. Method for controlling operation of an agricultural machine and system thereof
CN106356054A (zh) * 2016-11-23 2017-01-25 广西大学 一种基于语音识别的农产品信息采集方法和系统

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2010018453A2 (en) * 2008-08-15 2010-02-18 University Of Cape Town System and method for processing electronically generated text
CN102332265B (zh) * 2011-06-20 2014-04-16 浙江吉利汽车研究院有限公司 一种提高汽车声控系统语音识别率的方法
DE102015102881A1 (de) * 2015-02-27 2016-09-01 Claas Saulgau Gmbh Steuerungssystem für ein landwirtschaftliches Arbeitsgerät
CN106601250A (zh) * 2015-11-10 2017-04-26 刘芨可 一种语音控制方法及装置、设备
JP6067157B2 (ja) * 2016-02-09 2017-01-25 小橋工業株式会社 リモコンホルダ
CN105702255A (zh) * 2016-03-28 2016-06-22 华智水稻生物技术有限公司 农业数据采集方法、装置及移动终端
EP3252769B8 (en) * 2016-06-03 2020-04-01 Sony Corporation Adding background sound to speech-containing audio data
CN106683673B (zh) * 2016-12-30 2020-11-13 智车优行科技（北京）有限公司 驾驶模式的调整方法、装置和系统、车辆
CN106857199A (zh) * 2017-03-01 2017-06-20 深圳春沐源农业科技有限公司 一种无线远程灌溉方法及系统
CN206620072U (zh) * 2017-04-24 2017-11-07 南京师范大学 一种播种控制系统
CN107193391A (zh) * 2017-04-25 2017-09-22 北京百度网讯科技有限公司 一种上屏显示文本信息的方法和装置
CN107145549B (zh) * 2017-04-27 2020-01-14 深圳智高点知识产权运营有限公司 一种数据库缓存控制方法以及系统

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS6368438A (ja) * 1986-09-08 1988-03-28 Iseki & Co Ltd 農作業機等の音声一体形処理装置
JPH0895593A (ja) * 1995-09-25 1996-04-12 Iseki & Co Ltd 音声認識装置
DE102004032642A1 (de) * 2004-07-06 2006-02-16 Rabe Agrarsysteme Gmbh & Co. Kg Sprachsteuerung für eine Landmaschine, insbesondere für eine Verteilmaschine
CN101477799A (zh) * 2009-01-19 2009-07-08 北京农业信息技术研究中心 一种使用语音对农业设备进行控制的系统及控制方法
CN103345709A (zh) * 2013-07-01 2013-10-09 南通农业职业技术学院 农业信息化服务系统及其信息传送方法
US20170004830A1 (en) * 2015-07-01 2017-01-05 Kverneland Group Mechatronics B.V. Method for controlling operation of an agricultural machine and system thereof
CN106356054A (zh) * 2016-11-23 2017-01-25 广西大学 一种基于语音识别的农产品信息采集方法和系统

Also Published As

Publication number Publication date
CN108305625A (zh) 2018-07-20
CN108305625B (zh) 2020-12-18

Similar Documents

Publication Publication Date Title
CN108735201B (zh) 连续语音识别方法、装置、设备和存储介质
CN111063341B (zh) 复杂环境中多人语音的分割聚类方法及系统
CN104969288B (zh) 基于话音记录日志提供话音识别系统的方法和系统
JP7130194B2 (ja) ユーザ意図認識方法、装置、電子機器、コンピュータ可読記憶媒体及びコンピュータプログラム
US20190156822A1 (en) Multiple turn conversational task assistance
US7539654B2 (en) User interaction management using an ongoing estimate of user interaction skills
CN107134279A (zh) 一种语音唤醒方法、装置、终端和存储介质
WO2019096056A1 (zh) 语音识别方法、装置及系统
WO2015171646A1 (en) Method and system for speech input
CN110188356B (zh) 信息处理方法及装置
CN107424614A (zh) 一种声纹模型更新方法
JP6585112B2 (ja) 音声キーワード検出装置および音声キーワード検出方法
EP3627498B1 (en) Method and system, for generating speech recognition training data
CN105551498A (zh) 一种语音识别的方法及装置
CN109036395A (zh) 个性化的音箱控制方法、系统、智能音箱及存储介质
Williams et al. Crowd-sourcing for difficult transcription of speech
WO2020233381A1 (zh) 基于语音识别的服务请求方法、装置及计算机设备
US8498859B2 (en) Voice processing system, method for allocating acoustic and/or written character strings to words or lexical entries
CN110674320A (zh) 一种检索方法、装置和电子设备
WO2019144543A1 (zh) 语音控制方法及装置、电子设备和计算机可读存储介质
CN109918619A (zh) 一种基于基础字典标注的发音标注方法和装置
CN109584881A (zh) 基于语音处理的号码识别方法、装置及终端设备
CN110491394B (zh) 唤醒语料的获取方法和装置
CN107894882A (zh) 一种移动终端的语音输入方法
CN109243549B (zh) 一种智能随访方法、装置及服务器

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18902132

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 27.11.2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18902132

Country of ref document: EP

Kind code of ref document: A1