CN113836944A - Control method and system for intelligent equipment, device thereof and electronic equipment - Google Patents
Control method and system for intelligent equipment, device thereof and electronic equipment Download PDFInfo
- Publication number
- CN113836944A CN113836944A CN202111017354.3A CN202111017354A CN113836944A CN 113836944 A CN113836944 A CN 113836944A CN 202111017354 A CN202111017354 A CN 202111017354A CN 113836944 A CN113836944 A CN 113836944A
- Authority
- CN
- China
- Prior art keywords
- data
- tag data
- model
- instruction
- reply
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000004458 analytical method Methods 0.000 claims abstract description 61
- 238000012545 processing Methods 0.000 claims abstract description 29
- 230000003993 interaction Effects 0.000 claims abstract description 22
- 230000008569 process Effects 0.000 claims description 11
- 230000002452 interceptive effect Effects 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000013136 deep learning model Methods 0.000 claims description 5
- 230000000717 retained effect Effects 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004378 air conditioning Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Human Computer Interaction (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a control method, a control system and a control device for intelligent equipment and electronic equipment. The control method comprises the following steps: receiving information data of a target user, respectively analyzing the information data through a first type model in a model set to obtain tag data, wherein the number N of the first type models is larger than 1, the first type models have no incidence relation, and processing the tag data through a second type model in the model set to generate reply tag data and/or instruction tag data. The method and the device solve the technical problems that in the related technology, the serial semantic analysis model is easy to cause the analysis error of other associated models due to the analysis error of one model, so that the interaction is failed and the user experience is reduced.
Description
Technical Field
The invention relates to the technical field of intelligent equipment, in particular to a control method, a control system and a control device for the intelligent equipment and electronic equipment.
Background
With the rapid development of intelligent equipment technology, more and more users begin to use intelligent equipment more conveniently and efficiently for life and work. How to improve the intelligence of a dialog system for controlling a smart device becomes an important issue for increasing the user experience. In the related art, an existing dialogue system generally comprises a semantic analysis model, a dialogue management model and a natural language generation model, wherein the dialogue management model generates a corresponding reply word based on the current operation data of the intelligent device according to an analysis result of the semantic analysis model and issues a device control instruction.
As shown in fig. 1, a conventional analysis model is generally composed of a plurality of semantic analysis models (i.e., semantic analysis models 1 and 2 … … N) in series, and the plurality of semantic analysis models have a serial correlation in the vertical direction, and in a dialogue system, a dialogue is performed with a user and an instruction is issued to an intelligent device by an analysis result of the serial semantic analysis model. However, in the existing cascaded serial semantic parsing model architecture, an inevitable cascading error occurs, that is, when a certain parsing model predicts an error, the next-level model associated with the certain parsing model performs parsing of the current model on the basis of the above erroneous parsing result, which is prone to cause errors in the parsing result, and finally causes failure in device control and language interaction, thereby reducing user experience.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a control method, a control system, a control device and an electronic device for intelligent equipment, and aims to at least solve the technical problems that in the related technology, a serial semantic parsing model is easy to have parsing errors of other associated models due to parsing errors of one model, so that interaction failure is caused, and user experience is reduced.
According to an aspect of an embodiment of the present invention, there is provided a control method for an intelligent device, including: receiving information data of a target user, wherein the information data comprises voice information data and/or text information data; respectively analyzing the information data through first models in a model set to obtain tag data, wherein the number N of the first models is greater than 1, and the first models have no association relation; and processing the tag data through a second type model in the model set to generate reply tag data and/or instruction tag data, wherein the reply tag data is used for replying interaction information to the target user, the instruction tag data is used for issuing an operation instruction to the intelligent equipment, and the instruction tag data carries equipment control parameters.
Optionally, before receiving the information data of the target user, the control method further includes: inputting historical information data and original label data, wherein the historical information data comprises historical voice information data and/or historical text information data, and the original label data is data obtained by performing data analysis on the historical information data in a historical process and processing the analyzed information data; and training the original label data based on a third type model in the model set to obtain the trained label data.
Optionally, after the information data is respectively analyzed through the first type model in the model set to obtain the tag data, the control method further includes: acquiring historical operating data of the intelligent equipment; and updating the analyzed label data through a third type model in the model set based on the historical operating data to obtain updated label data.
Optionally, after the information data is respectively analyzed through the first type model in the model set to obtain the tag data, the control method further includes: if the updated tag data has tag data with the repetition rate larger than the preset threshold, the tag data is retained, and the tag data with the repetition rate smaller than or equal to the preset threshold is deleted.
Optionally, the step of processing the tag data through a second type model in the model set to generate reply tag data and/or instruction tag data includes: acquiring operation parameters of each intelligent device in the current set range; and after the tag data are processed through a second type model in the model set, generating reply tag data and/or instruction tag data based on the operating parameters of the intelligent equipment.
Optionally, the step of generating reply tag data and/or instruction tag data based on the operating parameter of the smart device includes: judging the operating state of the intelligent equipment indicated in the tag data based on the operating parameters of the intelligent equipment; generating instruction tag data based on the operating state; the instruction tag data includes at least one of: starting equipment control parameters, closing equipment control parameters and adjusting equipment control parameters.
Optionally, after generating instruction tag data based on the operating state, the control method further includes: if the instruction tag data includes the startup device control parameter, generating reply startup tag data, or if the instruction tag data includes the shutdown device control parameter, generating reply shutdown tag data, or if the instruction tag data includes the regulation device control parameter, generating reply regulation tag data.
Optionally, the type of the first type model includes at least one of: deep learning model, probability model, supervised learning model and unsupervised learning model.
According to another aspect of the embodiments of the present invention, there is also provided a control system for an intelligent device, including: the semantic analysis system is used for analyzing information data of a target user and outputting label data, wherein the semantic analysis system comprises first models without incidence relation, and the number N of the first models is more than 1; the dialogue management system is used for processing the tag data and generating reply tag data and/or instruction tag data, wherein the reply tag data is used for replying interactive information to the target user, the instruction tag data is used for issuing an operation instruction to the intelligent equipment, and the instruction tag data carries equipment control parameters; and the natural language generation system is used for converting the reply tag data into a reply language interacted with the target user and converting the instruction tag data into instruction data which can be recognized by the intelligent equipment, wherein the instruction data is used for controlling the intelligent equipment to execute corresponding instructions.
According to another aspect of the embodiments of the present invention, there is also provided a control apparatus for an intelligent device, including: the receiving unit is used for receiving information data of a target user, wherein the information data comprises voice information data and/or text information data; the analysis unit is used for respectively analyzing the information data through first-class models in a model set to obtain label data, wherein the number N of the first-class models is larger than 1, and the first-class models are not related; and the processing unit is used for processing the tag data through a second type model in the model set to generate reply tag data and/or instruction tag data, wherein the reply tag data is used for replying interaction information to the target user, the instruction tag data is used for issuing an operation instruction to the intelligent equipment, and the instruction tag data carries equipment control parameters.
Optionally, the control device further comprises: the system comprises a first input module, a second input module and a third input module, wherein the first input module is used for inputting historical information data and original label data before receiving information data of a target user, the historical information data comprises historical voice information data and/or historical text information data, and the original label data is data obtained by analyzing the historical information data in a historical process and processing the analyzed information data; and the first training module is used for training the original label data based on a third type model in the model set to obtain the trained label data.
Optionally, the control device further comprises: the first acquisition module is used for acquiring historical operating data of the intelligent equipment after the information data are respectively analyzed through the first type of model in the model set to obtain tag data; and the first updating module is used for updating the analyzed tag data through a third type model in the model set based on the historical operating data to obtain updated tag data.
Optionally, the control device further comprises: and the first deleting module is used for respectively analyzing the information data through the first type of model in the model set to obtain the tag data, if the updated tag data has tag data with the repetition rate larger than a preset threshold value, retaining the tag data, and deleting the tag data with the repetition rate smaller than or equal to the preset threshold value.
Optionally, the processing unit comprises: the second acquisition module is used for acquiring the operating parameters of each intelligent device in the current set range; and the first generation module is used for generating reply tag data and/or instruction tag data based on the operating parameters of the intelligent equipment after the tag data is processed through the second type of model in the model set.
Optionally, the first generating module comprises: the first judgment submodule is used for judging the operation state of the intelligent equipment indicated in the tag data based on the operation parameters of the intelligent equipment; the first generation submodule is used for generating instruction tag data based on the running state; the instruction tag data includes at least one of: starting equipment control parameters, closing equipment control parameters and adjusting equipment control parameters.
Optionally, the control device further comprises: after generating instruction tag data based on the operating state, a second generation module is configured to generate reply opening tag data if the instruction tag data includes the opening device control parameter, or a third generation module is configured to generate reply closing tag data if the instruction tag data includes the closing device control parameter, or a fourth generation module is configured to generate reply adjustment tag data if the instruction tag data includes the adjustment device control parameter.
Optionally, the type of the first type model includes at least one of: deep learning model, probability model, supervised learning model and unsupervised learning model.
According to another aspect of the embodiments of the present invention, there is also provided a control system for an intelligent device, including: the semantic analysis system is used for analyzing information data of a target user and outputting label data, wherein the semantic analysis system comprises first models without incidence relation, and the number N of the first models is more than 1; the dialogue management system is used for processing the tag data and generating reply tag data and/or instruction tag data, wherein the reply tag data is used for replying interactive information to the target user, the instruction tag data is used for issuing an operation instruction to the intelligent equipment, and the instruction tag data carries equipment control parameters; and the natural language generation system is used for converting the reply tag data into a reply language interacted with the target user and converting the instruction tag data into instruction data which can be recognized by the intelligent equipment, wherein the instruction data is used for controlling the intelligent equipment to execute corresponding instructions.
According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the above control methods for a smart device via execution of the executable instructions.
According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, and when the computer program runs, the apparatus where the computer-readable storage medium is located is controlled to execute any one of the above control methods for an intelligent device.
In the application, information data of a target user are received, wherein the information data comprise voice information data and/or text information data, the information data are respectively analyzed through a first type of model in a model set to obtain tag data, the number N of the first type of model is larger than 1, no incidence relation exists among the first type of model, the tag data are processed through a second type of model in the model set to generate reply tag data and/or instruction tag data, the reply tag data are used for replying interaction information to the target user, the instruction tag data are used for issuing an operation instruction to intelligent equipment, and equipment control parameters are carried in the instruction tag data. According to the method, an original serial semantic analysis model is optimized into a parallel multi-candidate dynamic analysis model through a parallel dialogue system of a first type model (capable of indicating the semantic analysis model), corresponding reply words interacting with a user are generated by combining the current running state of the intelligent equipment, and corresponding equipment instructions are issued to control the intelligent equipment to run, so that the risk of interaction failure caused by cascade errors of the serial semantic analysis model can be reduced, the user experience is improved, and the problem that other associated model analysis errors are caused due to one model analysis error easily occurring in the serial semantic analysis model in the related technology, interaction failure is caused, and the user experience is reduced is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a schematic diagram of a serial semantic parsing model according to the prior art;
FIG. 2 is a flow chart of an alternative control method for a smart device according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an alternative dialog system for controlling a smart device in accordance with an embodiment of the present invention;
FIG. 4 is a schematic diagram of an alternative control system for a smart device in accordance with embodiments of the present invention;
fig. 5 is a schematic diagram of a control apparatus for a smart device according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
To facilitate understanding of the invention by those skilled in the art, some terms or nouns referred to in the embodiments of the invention are explained below:
natural Language Processing (NLP) is a technology for performing interactive communication with a machine using a Natural Language used for human communication.
A slot refers to an attribute that an entity has been clearly defined, and is composed of a slot position.
IOT: the Internet of things means that the ubiquitous connection of objects and people is realized through various possible network connections, and the intelligent perception, identification and management of the objects and the processes are realized.
The following embodiments of the present invention may be applied to an intelligent device control dialogue system, where the intelligent device includes but is not limited to: the intelligent equipment control dialogue system receives information data (such as voice data, text input data and the like) of a user, analyzes the information data to identify the intention of the user, controls the intelligent equipment to work according to the intention of the user, and finally interacts with the user to control the result.
Example one
In accordance with an embodiment of the present invention, there is provided an embodiment of a control method for an intelligent device, it is noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.
Fig. 2 is a flowchart of an alternative control method for an intelligent device according to an embodiment of the present invention, as shown in fig. 2, the method includes the following steps:
step S202, receiving information data of a target user, wherein the information data comprises voice information data and/or text information data.
And S204, respectively analyzing the information data through first models in the model set to obtain label data, wherein the number N of the first models is greater than 1, and the first models have no association relation.
Step S206, processing the tag data through the second type model in the model set, and generating reply tag data and/or instruction tag data, wherein the reply tag data is used for replying interactive information to a target user, the instruction tag data is used for issuing an operation instruction to the intelligent equipment, and the instruction tag data carries equipment control parameters.
Through the steps, information data of a target user can be received, wherein the information data comprise voice information data and/or text information data, the information data are respectively analyzed through first models in a model set to obtain tag data, the number N of the first models is larger than 1, no incidence relation exists among the first models, the tag data are processed through second models in the model set to generate reply tag data and/or instruction tag data, the reply tag data are used for replying interaction information to the target user, the instruction tag data are used for issuing an operation instruction to intelligent equipment, and the instruction tag data carry equipment control parameters. According to the embodiment of the invention, through a parallel dialogue system of a first type of model (which can indicate a semantic analysis model), an original serial semantic analysis model is optimized into a parallel multi-candidate dynamic analysis model, a corresponding reply language interacting with a user is generated by combining the current operation state of the intelligent equipment, and a corresponding equipment instruction is issued to control the operation of the intelligent equipment, so that the risk of interaction failure caused by cascade errors of the serial semantic analysis model can be reduced, the user experience is increased, and the technical problems that the interaction failure is caused by other associated model analysis errors due to one model analysis error and the user experience is reduced in the serial semantic analysis model in the related technology are solved.
The following will explain the embodiments of the present invention in detail with reference to the above steps.
The execution subject of the following steps may be an intelligent device control dialog system.
Step S202, receiving information data of a target user, wherein the information data comprises voice information data and/or text information data.
In the embodiment of the present invention, the information data may be a voice of a user interacting directly with the dialog system (for example, the user may directly say "turn up the air conditioning temperature" to the dialog system (which may be run on a home control terminal or a cloud platform)), or may be a text information manually input by the user through the terminal (for example, an input box of the dialog system is opened in the terminal, and "turn up the air conditioning temperature") where the terminal includes, but is not limited to: cell phone, IPAD, PC, tablet, etc.
Optionally, before receiving the information data of the target user, the control method further includes: inputting historical information data and original label data, wherein the historical information data comprises historical voice information data and/or historical text information data, and the original label data is data obtained by analyzing the historical information data in the historical process and processing the analyzed information data; and training the original label data based on a third type model in the model set to obtain the trained label data.
In the embodiment of the present invention, the historical information data refers to information data (e.g., voice data of a user, text data input by the user, etc.) of a user interacting with a dialog system in a historical time period, and the original tag data refers to data labeling the historical information data of the user, and the trained tag data can be obtained by training a decision model (i.e., a third type model in a model set).
And S204, respectively analyzing the information data through first models in the model set to obtain label data, wherein the number N of the first models is greater than 1, and the first models have no association relation.
In the embodiment of the invention, the first type of model in the model set refers to a semantic analysis model in a dialog system, the number of the semantic analysis models can be multiple, the multiple semantic analysis models are mutually independent and mutually candidate parallel relations, and a group of label data can be obtained by analyzing the information data of the user through the first type of model.
Optionally, after the information data is respectively analyzed through the first type model in the model set to obtain the tag data, the control method further includes: acquiring historical operating data of the intelligent equipment; and updating the analyzed label data through a third type model in the model set based on the historical operating data to obtain updated label data.
In the embodiment of the present invention, the operating state of the smart device is dynamically changed, for example, the temperature of the air conditioner is adjusted from 16 degrees to 26 degrees by a user, the first type model may analyze the information data of the user in real time according to the operating state data of the smart device to obtain the tag data, and then update the tag data through a trained decision model (i.e., a third type model in the model set) to obtain updated tag data.
Optionally, after the information data is respectively analyzed through the first type model in the model set to obtain the tag data, the control method further includes: if the updated tag data has tag data with the repetition rate larger than the preset threshold, the tag data is retained, and the tag data with the repetition rate smaller than or equal to the preset threshold is deleted.
In the embodiment of the present invention, the results obtained by analyzing the information data of the user by the multiple semantic analysis models may overlap, and if the overlap rate is greater than a preset overlap rate (for example, there are 3 data overlaps), the tag data is retained, and the tag data that is not overlapped is discarded.
Alternatively, the label data obtained by analyzing the plurality of semantic analysis models may be sorted according to the overlapping rate, corresponding weights are set for the label data according to the sorting result, and the label data is further screened according to the corresponding weights.
Step S206, processing the tag data through the second type model in the model set, and generating reply tag data and/or instruction tag data, wherein the reply tag data is used for replying interactive information to a target user, the instruction tag data is used for issuing an operation instruction to the intelligent equipment, and the instruction tag data carries equipment control parameters.
In the embodiment of the present invention, the tag data is processed through a dialog management model (i.e. a second type model in the model set), so as to generate an operation instruction that can reply the interaction information data to the target user and control the operation of the intelligent device, where the operation instruction includes, but is not limited to: starting equipment control parameters, closing equipment control parameters, adjusting equipment control parameters, and the like.
Optionally, the step of processing the tag data through a second type model in the model set to generate reply tag data and/or instruction tag data includes: acquiring operation parameters of each intelligent device in the current set range; after the tag data is processed through the second type model in the model set, reply tag data and/or instruction tag data are generated based on the operating parameters of the intelligent device.
In the embodiment of the present invention, the operation parameters (e.g., the current operation temperature, whether the device is in a power-off state, etc.) of the smart device in the space where the user is located (i.e., the current aggregation range, e.g., the home, the company, etc. where the user is located) are obtained, information interacting with the user is generated based on the operation parameters, and the smart device is controlled to change the operation state.
Optionally, the step of generating reply tag data and/or instruction tag data based on the operating parameter of the smart device includes: judging the operating state of the intelligent equipment indicated in the label data based on the operating parameters of the intelligent equipment; generating instruction tag data based on the operating state; the instruction tag data includes at least one of: starting equipment control parameters, closing equipment control parameters and adjusting equipment control parameters.
In the embodiment of the invention, the operating state of the intelligent device which the user wants to control (for example, the user wants to increase the temperature of the air conditioner, and the air conditioner is in the off state at present) can be judged through the operating parameters of the intelligent device stored in the IOT cloud, and based on the current operating state of the intelligent device, corresponding instruction tag data is generated to control the intelligent device to work, for example, a starting instruction needs to be generated and the temperature instruction of the air conditioner needs to be increased according to the current off state of the air conditioner.
Optionally, after generating the instruction tag data based on the operating state, the control method further includes: if the instruction tag data includes the startup device control parameter, generating reply startup tag data, or if the instruction tag data includes the shutdown device control parameter, generating reply shutdown tag data, or if the instruction tag data includes the regulation device control parameter, generating reply regulation tag data.
In the embodiment of the present invention, if the issued instruction is an open instruction, a message that the intelligent device corresponding to the user is already powered on needs to be replied, if the issued instruction is a close instruction, a message that the intelligent device corresponding to the user is already powered off needs to be replied, if the issued instruction is an adjustment instruction, a message that the intelligent device corresponding to the user is adjusted to a corresponding state needs to be replied, a reply manner and a reply content format of the message are not limited herein, for example, a user "owner" can be replied by voice, and the air conditioner is already turned on and adjusted to 26 degrees according to your instruction.
Optionally, the type of the first type model includes at least one of: deep learning model, probability model, supervised learning model and unsupervised learning model.
In the embodiment of the present invention, the type of the first type model (i.e., the type of the multiple semantic analysis models that are parallel to each other) may be a model that selects a deep learning algorithm, a model that selects a probabilistic algorithm, or a model that selects a supervised learning algorithm or an unsupervised learning algorithm.
According to the embodiment of the invention, the intelligent equipment control dialogue system architecture of the parallel semantic analysis model is constructed, the submodel which is originally cascaded in series in the semantic analysis model is optimized into the parallel multi-candidate dynamic optimization path selection, the optimal judgment is carried out in dialogue management by combining the current running state of the intelligent equipment, the problem of cascade error of semantic analysis in the interactive system in the field of the traditional intelligent equipment can be solved, and the user experience is improved.
Example two
Fig. 3 is a schematic diagram of an alternative dialog system for controlling a smart device according to an embodiment of the present invention, as shown in fig. 3, including: semantic parsing modules 1 and 2 … … N, a dialogue management decision module and a natural language generation module.
The dialogue system in the embodiment of the invention comprises semantic parsing modules 1 and 2 … … N which are parallel to each other, wherein the information data of a user are parsed through a plurality of parallel parsing modules, then the information data of the user are combined with internet-of-things data, optimal judgment is carried out through a dialogue management decision module, information used for interactive reply with the user and an instruction used for controlling intelligent equipment are obtained, a reply language which can be understood by the user is finally obtained through a natural language generation module and is used for interacting with the user, the instruction is issued to the intelligent equipment indicated by the information data of the user, and the intelligent equipment is controlled to work according to the intention of the user.
According to the embodiment of the invention, by constructing the intelligent equipment control dialogue system architecture of the parallel semantic analysis model, the problem of cascade errors of semantic analysis in the interactive system in the field of traditional intelligent equipment can be avoided, and the user experience is improved.
EXAMPLE III
Fig. 4 is a schematic diagram of an alternative control system for a smart device according to an embodiment of the present invention, as shown in fig. 4, including: a semantic parsing system 40, a dialog management system 42, a natural language generation system 44, wherein,
the semantic analysis system 40 is used for analyzing the information data of the target user and outputting the label data, wherein the semantic analysis system comprises first models without incidence relation, and the number N of the first models is more than 1;
the dialogue management system 42 is configured to process the tag data and generate reply tag data and/or instruction tag data, where the reply tag data is used to reply the interaction information to the target user, the instruction tag data is used to issue an operation instruction to the intelligent device, and the instruction tag data carries the device control parameter;
and the natural language generation system 44 is used for converting the reply tag data into a reply language for interacting with the target user and converting the instruction tag data into instruction data which can be recognized by the intelligent device, wherein the instruction data is used for controlling the intelligent device to execute corresponding instructions.
In an embodiment of the present invention, information data of a target user may be received, wherein the information data includes voice information data and/or text information data, the information data are respectively analyzed through a parallel semantic analysis model in the semantic analysis system 40 to obtain label data, the tag data is processed by dialog management system 42, reply tag data and/or instruction tag data is generated, wherein, the reply label data is used for replying the interactive information to the target user, the instruction label data is used for issuing an operation instruction to the intelligent device, the instruction label data carries the device control parameter, and then, the reply tag data is converted by natural language generation system 44 into a reply language for interaction with the target user, and converting the instruction tag data into instruction data which can be recognized by the intelligent equipment, wherein the instruction data is used for controlling the intelligent equipment to execute corresponding instructions. According to the embodiment of the invention, through a parallel dialogue system of a first type of model (indication semantic analysis model), namely, an original serial semantic analysis model is optimized into a parallel multi-candidate dynamic analysis model, a corresponding reply language interacting with a user is generated by combining the current operation state of the intelligent equipment, and a corresponding equipment instruction is issued to control the operation of the intelligent equipment, so that the risk of interaction failure caused by cascade errors of the serial semantic analysis model can be reduced, the user experience is increased, and the technical problems that the interaction failure is caused by other associated model analysis errors due to one model analysis error and the user experience is reduced in the serial semantic analysis model in the related technology are solved.
Example four
The control device for the intelligent device provided in this embodiment includes a plurality of implementation units, and each implementation unit corresponds to each implementation step in the first embodiment.
Fig. 5 is a schematic diagram of a control apparatus for a smart device according to an embodiment of the present invention, and as shown in fig. 5, the authentication apparatus may include: a receiving unit 50, a parsing unit 52, a processing unit 54, wherein,
a receiving unit 50 for receiving information data of a target user, wherein the information data includes voice information data and/or text information data;
the analyzing unit 52 is configured to analyze the information data respectively through first-class models in the model set to obtain tag data, where the number N of the first-class models is greater than 1, and there is no association between the first-class models;
and the processing unit 54 is configured to process the tag data through the second type model in the model set, and generate reply tag data and/or instruction tag data, where the reply tag data is used to reply the interaction information to the target user, the instruction tag data is used to issue an operation instruction to the smart device, and the instruction tag data carries the device control parameter.
The control device may receive information data of a target user through the receiving unit 50, where the information data includes voice information data and/or text information data, and the parsing unit 52 may parse the information data in first-class models in a model set respectively to obtain tag data, where N is greater than 1, and there is no correlation between the first-class models, and the processing unit 54 may process the tag data in second-class models in the model set to generate reply tag data and/or instruction tag data, where the reply tag data is used to reply interaction information to the target user, the instruction tag data is used to issue an operation instruction to an intelligent device, and the instruction tag data carries device control parameters, the method is characterized in that an original serial semantic analysis model is optimized into a parallel multi-candidate dynamic analysis model, corresponding reply words interacting with a user are generated by combining the current operation state of the intelligent equipment, and corresponding equipment instructions are issued to control the intelligent equipment to operate, so that the risk of interaction failure caused by cascade errors of the serial semantic analysis model can be reduced, the user experience is increased, and the technical problems that interaction failure and user experience are reduced due to the fact that analysis errors of other associated models are caused by the fact that one model is analyzed incorrectly in the serial semantic analysis model in the related technology are solved.
Optionally, the control device further includes: the system comprises a first input module, a second input module and a third input module, wherein the first input module is used for inputting historical information data and original label data before receiving information data of a target user, the historical information data comprises historical voice information data and/or historical text information data, and the original label data is data obtained by analyzing the historical information data in a historical process and processing the analyzed information data; and the first training module is used for training the original label data based on a third type model in the model set to obtain the trained label data.
Optionally, the control device further includes: the first acquisition module is used for acquiring historical operating data of the intelligent equipment after the information data are respectively analyzed through the first type of model in the model set to obtain tag data; and the first updating module is used for updating the analyzed tag data through a third type model in the model set based on the historical operating data to obtain the updated tag data.
Optionally, the control device further includes: and the first deleting module is used for respectively analyzing the information data through the first type of model in the model set to obtain the tag data, if the updated tag data has tag data with the repetition rate larger than the preset threshold value, retaining the tag data, and deleting the tag data with the repetition rate smaller than or equal to the preset threshold value.
Optionally, the processing unit includes: the second acquisition module is used for acquiring the operating parameters of each intelligent device in the current set range; and the first generation module is used for generating reply tag data and/or instruction tag data based on the operating parameters of the intelligent equipment after the tag data is processed through the second type of model in the model set.
Optionally, the first generating module includes: the first judgment submodule is used for judging the operation state of the intelligent equipment indicated in the tag data based on the operation parameters of the intelligent equipment; the first generation submodule is used for generating instruction tag data based on the running state; the instruction tag data includes at least one of: starting equipment control parameters, closing equipment control parameters and adjusting equipment control parameters.
Optionally, the control device further includes: after generating the instruction tag data based on the operating state, a second generation module is configured to generate reply opening tag data if the instruction tag data includes an opening device control parameter, or a third generation module is configured to generate reply closing tag data if the instruction tag data includes a closing device control parameter, or a fourth generation module is configured to generate reply adjustment tag data if the instruction tag data includes an adjustment device control parameter.
Optionally, the type of the first type model includes at least one of: deep learning model, probability model, supervised learning model and unsupervised learning model.
The authentication device may further include a processor and a memory, and the receiving unit 50, the analyzing unit 52, the processing unit 54, and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions.
The processor comprises a kernel, and the kernel calls a corresponding program unit from the memory. The kernel may set one or more of the reply tag data and/or the instruction tag data by adjusting kernel parameters.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device: receiving information data of a target user, respectively analyzing the information data through a first type model in a model set to obtain tag data, wherein the number N of the first type models is larger than 1, the first type models have no incidence relation, and processing the tag data through a second type model in the model set to generate reply tag data and/or instruction tag data.
According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including: a processor; and a memory for storing executable instructions for the processor; wherein the processor is configured to perform the control method for the smart device of any one of the above via execution of the executable instructions.
According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, and when the computer program runs, the apparatus where the computer-readable storage medium is located is controlled to execute any one of the above control methods for an intelligent device.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (12)
1. A control method for a smart device, comprising:
receiving information data of a target user, wherein the information data comprises voice information data and/or text information data;
respectively analyzing the information data through first models in a model set to obtain tag data, wherein the number N of the first models is greater than 1, and the first models have no association relation;
and processing the tag data through a second type model in the model set to generate reply tag data and/or instruction tag data, wherein the reply tag data is used for replying interaction information to the target user, the instruction tag data is used for issuing an operation instruction to the intelligent equipment, and the instruction tag data carries equipment control parameters.
2. The control method according to claim 1, wherein before receiving the information data of the target user, the control method further comprises:
inputting historical information data and original label data, wherein the historical information data comprises historical voice information data and/or historical text information data, and the original label data is data obtained by performing data analysis on the historical information data in a historical process and processing the analyzed information data;
and training the original label data based on a third type model in the model set to obtain the trained label data.
3. The control method according to claim 2, wherein after the information data is respectively analyzed by the first type models in the model set to obtain the tag data, the control method further comprises:
acquiring historical operating data of the intelligent equipment;
and updating the analyzed label data through a third type model in the model set based on the historical operating data to obtain updated label data.
4. The control method according to claim 3, wherein after the information data is respectively analyzed by the first type models in the model set to obtain the tag data, the control method further comprises:
if the updated tag data has tag data with the repetition rate larger than the preset threshold, the tag data is retained, and the tag data with the repetition rate smaller than or equal to the preset threshold is deleted.
5. The control method according to claim 1, wherein the step of processing the tag data through a second type model in the model set to generate reply tag data and/or instruction tag data comprises:
acquiring operation parameters of each intelligent device in the current set range;
and after the tag data are processed through a second type model in the model set, generating reply tag data and/or instruction tag data based on the operating parameters of the intelligent equipment.
6. The control method according to claim 5, wherein the step of generating reply tag data and/or instruction tag data based on the operating parameters of the smart device comprises:
judging the operating state of the intelligent equipment indicated in the tag data based on the operating parameters of the intelligent equipment;
generating instruction tag data based on the operating state;
the instruction tag data includes at least one of: starting equipment control parameters, closing equipment control parameters and adjusting equipment control parameters.
7. The control method according to claim 6, wherein after generating instruction tag data based on the operating state, the control method further comprises:
if the instruction tag data includes the opener control parameter, generating reply opener tag data, or,
if the instruction tag data includes the shutdown device control parameter, generating reply shutdown tag data, or,
and if the instruction tag data comprise the adjusting equipment control parameters, generating reply adjusting tag data.
8. The control method of claim 1, wherein the type of the first type of model comprises at least one of: deep learning model, probability model, supervised learning model and unsupervised learning model.
9. A control system for a smart device, comprising:
the semantic analysis system is used for analyzing information data of a target user and outputting label data, wherein the semantic analysis system comprises first models without incidence relation, and the number N of the first models is more than 1;
the dialogue management system is used for processing the tag data and generating reply tag data and/or instruction tag data, wherein the reply tag data is used for replying interactive information to the target user, the instruction tag data is used for issuing an operation instruction to the intelligent equipment, and the instruction tag data carries equipment control parameters;
and the natural language generation system is used for converting the reply tag data into a reply language interacted with the target user and converting the instruction tag data into instruction data which can be recognized by the intelligent equipment, wherein the instruction data is used for controlling the intelligent equipment to execute corresponding instructions.
10. A control apparatus for a smart device, comprising:
the receiving unit is used for receiving information data of a target user, wherein the information data comprises voice information data and/or text information data;
the analysis unit is used for respectively analyzing the information data through first-class models in a model set to obtain label data, wherein the number N of the first-class models is larger than 1, and the first-class models are not related;
and the processing unit is used for processing the tag data through a second type model in the model set to generate reply tag data and/or instruction tag data, wherein the reply tag data is used for replying interaction information to the target user, the instruction tag data is used for issuing an operation instruction to the intelligent equipment, and the instruction tag data carries equipment control parameters.
11. An electronic device, comprising:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform the control method for a smart device of any one of claims 1 to 8 via execution of the executable instructions.
12. A computer-readable storage medium, comprising a stored computer program, wherein when the computer program runs, the computer-readable storage medium controls a device to execute the control method for the smart device according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111017354.3A CN113836944A (en) | 2021-08-31 | 2021-08-31 | Control method and system for intelligent equipment, device thereof and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111017354.3A CN113836944A (en) | 2021-08-31 | 2021-08-31 | Control method and system for intelligent equipment, device thereof and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113836944A true CN113836944A (en) | 2021-12-24 |
Family
ID=78961716
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111017354.3A Pending CN113836944A (en) | 2021-08-31 | 2021-08-31 | Control method and system for intelligent equipment, device thereof and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113836944A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114661010A (en) * | 2022-03-17 | 2022-06-24 | 北京金波融安科技有限公司 | Drive detection processing method based on artificial intelligence and cloud platform |
| CN116756277A (en) * | 2023-04-20 | 2023-09-15 | 海尔优家智能科技（北京）有限公司 | Processing method of interactive statement based on target generation type pre-training GPT model |
-
2021
- 2021-08-31 CN CN202111017354.3A patent/CN113836944A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114661010A (en) * | 2022-03-17 | 2022-06-24 | 北京金波融安科技有限公司 | Drive detection processing method based on artificial intelligence and cloud platform |
| CN116756277A (en) * | 2023-04-20 | 2023-09-15 | 海尔优家智能科技（北京）有限公司 | Processing method of interactive statement based on target generation type pre-training GPT model |
| CN116756277B (en) * | 2023-04-20 | 2023-11-24 | 海尔优家智能科技（北京）有限公司 | Processing method of interactive statement based on target generation type pre-training GPT model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111859960B (en) | Semantic matching method, device, computer equipment and medium based on knowledge distillation | |
| CN108733722B (en) | Automatic generation method and device for conversation robot | |
| CN106571140B (en) | Intelligent electric appliance control method and system based on voice semantics | |
| CN109760041B (en) | Chat robot-based cloud management system and operation method thereof | |
| CN109885810A (en) | Nan-machine interrogation's method, apparatus, equipment and storage medium based on semanteme parsing | |
| US11455148B2 (en) | Software programming assistant | |
| CN115328756A (en) | Test case generation method, device and equipment | |
| CN113836944A (en) | Control method and system for intelligent equipment, device thereof and electronic equipment | |
| CN112989035A (en) | Method, device and storage medium for recognizing user intention based on text classification | |
| US20200202068A1 (en) | Computing apparatus and information input method of the computing apparatus | |
| CN107239447B (en) | Junk information identification method, device and system | |
| CN111753090A (en) | Document auditing method, device, equipment and medium based on RPA and AI | |
| CN113516340A (en) | Intelligent work order pushing method and device | |
| CN112765981A (en) | Text information generation method and device | |
| CN113312924A (en) | Risk rule classification method and device based on NLP high-precision analysis label | |
| CN114913590A (en) | Data emotion recognition method, device and equipment and readable storage medium | |
| CN114694644A (en) | Voice intention recognition method and device and electronic equipment | |
| CN110458383B (en) | Method and device for realizing demand processing servitization, computer equipment and storage medium | |
| CN115858776B (en) | Variant text classification recognition method, system, storage medium and electronic equipment | |
| CN109145124B (en) | Information storage method and device, storage medium and electronic device | |
| CN111460811A (en) | Crowdsourcing task answer verification method and device, computer equipment and storage medium | |
| KR20210033837A (en) | Electronic device and method for controlling the electronic device thereof | |
| KR102363958B1 (en) | Method, apparatus and program for analyzing customer perception based on double clustering | |
| US20210350088A1 (en) | Systems and methods for digital document generation using natural language interaction | |
| CN111538810A (en) | Data generation 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 |