CN115455191A - Query instruction response method and device, storage medium and electronic device - Google Patents
Query instruction response method and device, storage medium and electronic device Download PDFInfo
- Publication number
- CN115455191A CN115455191A CN202210911118.4A CN202210911118A CN115455191A CN 115455191 A CN115455191 A CN 115455191A CN 202210911118 A CN202210911118 A CN 202210911118A CN 115455191 A CN115455191 A CN 115455191A
- Authority
- CN
- China
- Prior art keywords
- question
- query
- answer
- knowledge graph
- answer pair
- 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 56
- 230000004044 response Effects 0.000 title claims abstract description 24
- 238000004590 computer program Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 description 17
- 238000005406 washing Methods 0.000 description 15
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 10
- 238000012163 sequencing technique Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 239000003507 refrigerant Substances 0.000 description 4
- 239000007788 liquid Substances 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009191 jumping Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004321 preservation Methods 0.000 description 2
- 238000005057 refrigeration Methods 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 238000004887 air purification Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 235000019504 cigarettes Nutrition 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
Images
Classifications
-
- 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a response method, a device, a storage medium and an electronic device of a query instruction, which relate to the technical field of smart families, and the response method of the query instruction comprises the following steps: identifying equipment information and query intention from the obtained query instruction; determining a question-answer pair knowledge graph of target equipment corresponding to the equipment information, wherein the question-answer pair knowledge graph comprises a plurality of question-answer pairs related to the target equipment, and the question-answer pairs are used for representing the corresponding relation between questions and answers; and responding the query instruction to the knowledge graph by using the question and answer to obtain a query result corresponding to the query intention.
Description
Technical Field
The present application relates to the field of computers, and in particular, to a method and an apparatus for responding to a query, a storage medium, and an electronic apparatus.
Background
With the continuous development of artificial intelligence and interconnection technology, intelligent applications increasingly sink to various scenes and devices, such as intelligent automobiles capable of driving automatically and intelligent homes capable of being served intelligently. And among them, speech is an important interactive mode in various scenes. The knowledge graph is an important ring in intelligent interaction and provides services such as knowledge, disambiguation, quick retrieval and the like in conversation.
The existing knowledge graph is formed by connecting entities through relations. However, in real-world applications, for example, some problems about entities, there is no way to exist in the form of triples, and extra storage is required, and at this time, the relationship between the entities and the related problems cannot be presented. In comparison, the architecture with the separate storage brings a certain delay in query speed and association analysis, which puts higher requirements on query service, increases delay on the service experience side, and also improves the difficulty of data management and data service provision.
Disclosure of Invention
The embodiment of the invention provides a response method and device of a query instruction, a storage medium and an electronic device, which are used for at least solving the problem of low query efficiency of question answering in the related technology.
According to an embodiment of the present invention, there is provided a response method of a query instruction, including: identifying equipment information and query intention from the obtained query instruction; determining a question-answer pair knowledge graph of the target equipment corresponding to the equipment information, wherein the question-answer pair knowledge graph comprises a plurality of question-answer pairs related to the target equipment, and the question-answer pairs are used for representing the corresponding relation between questions and answers; and responding the query instruction to the knowledge graph by using the question and answer pair to obtain a query result corresponding to the query intention.
According to an embodiment of the present invention, there is provided a response device for a query instruction, including: the first identification module is used for identifying the equipment information and the query intention from the obtained query instruction; a first determining module, configured to determine a question-answer pair knowledge graph of a target device corresponding to the device information, where the question-answer pair knowledge graph includes multiple question-answer pairs related to the target device, and the question-answer pairs are used to indicate a correspondence between a question and an answer; and the first response module is used for responding the query instruction to the knowledge graph by using the question and answer to obtain a query result corresponding to the query intention.
In an exemplary embodiment, the first identification module includes: a first identification unit, configured to identify a keyword in the query instruction; and a second identification unit for identifying the device information and the query intention from the keyword.
In an exemplary embodiment, the apparatus further includes: a first obtaining module, configured to obtain a plurality of example samples related to a target device before determining a question-answer pair knowledge graph of the target device corresponding to the device information, where each example sample includes a question sample of a same type and one or more answer samples corresponding to the question sample; and the first construction module is used for constructing the question-answer pair knowledge graph by utilizing a plurality of example samples.
In an exemplary embodiment, the first determining module includes: a first determination unit configured to determine whether the query intention matches attribute information of the target device; a first querying unit, configured to query a question-answer pair knowledge graph of a target device corresponding to the device information if the query intention does not match the attribute information.
In an exemplary embodiment, the apparatus further comprises: and a second response module, configured to respond to the query instruction by using an attribute knowledge graph of the target device when the query intention matches the attribute information, where the attribute knowledge graph includes a plurality of pieces of attribute information related to the target device.
In an exemplary embodiment, the apparatus further comprises: and the first association module is used for associating the attribute knowledge graph with the question-answer pair knowledge graph so as to determine the question-answer pair knowledge graph as a sub-graph of the attribute knowledge graph.
In an exemplary embodiment, the apparatus further includes: and the first sequencing module is used for utilizing the question and answer pairs to respond the query instruction to the knowledge graph, obtaining a query result corresponding to the query intention, and sequencing a plurality of answers under the condition that the query result comprises a plurality of answers.
According to a further embodiment of the present invention, there is also provided a computer-readable storage medium having a computer program stored thereon, wherein the computer program is arranged to, when executed, perform the steps of any of the method embodiments described above.
According to yet another embodiment of the present invention, there is also provided an electronic device, including a memory in which a computer program is stored and a processor configured to execute the computer program to perform the steps in any of the above method embodiments.
According to the invention, the device information and the query intention are identified from the obtained query instruction; determining a question-answer pair knowledge graph of target equipment corresponding to the equipment information, wherein the question-answer pair knowledge graph comprises a plurality of question-answer pairs related to the target equipment, and the question-answer pairs are used for representing the corresponding relation between questions and answers; and responding the query instruction to the knowledge graph by using the question and answer to obtain a query result corresponding to the query intention. In the method, processes such as entity identification, entity linking, judgment according to the relationship, answer query and the like are not needed. But the inquiry process of the question-answer pairs related to the entity is inquired in the knowledge graph of the question-answer pairs, so that the inquiry process is simplified, and the inquiry efficiency is improved. Therefore, the problem of low query efficiency on question answering in the related art can be solved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a diagram illustrating a hardware environment for a method for responding to a query according to an embodiment of the present application;
FIG. 2 is a flow chart of a response method of a query instruction according to an embodiment of the present invention
FIG. 3 is an overall architecture diagram according to an embodiment of the invention;
FIG. 4 is a flow diagram of sub-graph query and quick recall according to an embodiment of the invention;
fig. 5 is a block diagram of a response apparatus of a query instruction according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all 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 application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the accompanying drawings 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 application described herein are capable of operation in sequences other than those illustrated or described herein. Moreover, 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.
According to an aspect of an embodiment of the present application, a method for responding to a query instruction is provided. The response method of the query instruction is widely applied to full-house intelligent digital control application scenes such as Smart Home (Smart Home), smart Home equipment ecology, smart Home (Intelligent House) ecology and the like. Alternatively, in this embodiment, the response method of the query instruction may be applied to a hardware environment formed by the terminal device 102 and the server 104 as shown in fig. 1. As shown in fig. 1, the server 104 is connected to the terminal device 102 through a network, and may be configured to provide a service (e.g., an application service) for the terminal or a client installed on the terminal, provide a database on or independent of the server for providing a data storage service for the server 104, and configure a cloud computing and/or edge computing service on or independent of the server for providing a data operation service for the server 104.
The network may include, but is not limited to, at least one of: wired networks, wireless networks. The wired network may include, but is not limited to, at least one of: wide area networks, metropolitan area networks, local area networks, which may include, but are not limited to, at least one of the following: WIFI (Wireless Fidelity), bluetooth. Terminal equipment 102 can be but not limited to be PC, the cell-phone, the panel computer, intelligent air conditioner, intelligent cigarette machine, intelligent refrigerator, intelligent oven, intelligent kitchen range, intelligent washing machine, intelligent water heater, intelligent washing equipment, intelligent dish washer, intelligent projection equipment, intelligent TV, intelligent clothes hanger, intelligent (window) curtain, intelligence audio-visual, smart jack, intelligent stereo set, intelligent audio amplifier, intelligent new trend equipment, intelligent kitchen guarding equipment, intelligent bathroom equipment, intelligence robot of sweeping the floor, intelligence robot of wiping the window, intelligence robot of mopping the ground, intelligent air purification equipment, intelligent steam ager, intelligent microwave oven, intelligent kitchen is precious, intelligent clarifier, intelligent water dispenser, intelligent lock etc..
The present embodiment provides a response method for a query instruction, fig. 2 is a flowchart of a response method for a query instruction according to an embodiment of the present invention, and as shown in fig. 2, the flowchart includes the following steps:
step S202, identifying equipment information and query intention from the obtained query instruction;
step S204, determining a question-answer pair knowledge graph of the target equipment corresponding to the equipment information, wherein the question-answer pair knowledge graph comprises a plurality of question-answer pairs related to the target equipment, and the question-answer pairs are used for representing the corresponding relation between questions and answers;
and step S206, responding the query instruction to the knowledge graph by using the question and answer to obtain a query result corresponding to the query intention.
Optionally, the method for responding to the query instruction may be, but is not limited to, applied to a query process of a question-answer pair. And the user sends a query instruction, identifies query intention and equipment information from the query instruction, and queries answers in the question-answer pair knowledge map.
Optionally, the device in this embodiment may be, but is not limited to, various home appliances, such as a refrigerator, a washing machine, an air conditioner, and the like.
Optionally, the query instruction may be a voice instruction, a text instruction, or the like sent by the user through the client (for example, sending a voice through an application in the mobile phone), or may be a voice instruction obtained through a voice acquisition device provided in the device (for example, a voice acquisition module provided in the air conditioner). The query instructions include a query for device attributes (e.g., name, model, function, etc. of the device) and a query for device failure issues (e.g., refrigerator is not cooling, why the washing machine leaks water, etc.). The question-answer pair knowledge graph in the embodiment is mainly used for responding to the query of the fault problem, namely, does not respond to the attribute. For example, the user utters "why the refrigerator uttered", what the query is required to be made is a question about the refrigerator, and the query intention is "why the refrigerator uttered" can be acquired from the voice instruction.
Optionally, question-answer pairs related to multiple devices may be included in the question-answer pair knowledge graph. Each device corresponds to one question-answer pair branch, wherein the question-answer pair branch comprises the incidence relation between each question and each answer.
The main body of the above steps may be a terminal, a server, a specific processor provided in the terminal or the server, or a processor or a processing device provided independently from the terminal or the server, but is not limited thereto.
Through the steps, the device information and the query intention are identified from the obtained query instruction; determining a question-answer pair knowledge graph of target equipment corresponding to the equipment information, wherein the question-answer pair knowledge graph comprises a plurality of question-answer pairs related to the target equipment, and the question-answer pairs are used for representing the corresponding relation between questions and answers; and responding the query instruction to the knowledge graph by using the question and answer to obtain a query result corresponding to the query intention. In the method, processes such as entity identification, entity linking, judgment according to the relationship, answer query and the like are not needed. But the inquiry process of the question-answer pairs related to the entity is inquired in the knowledge graph of the question-answer pairs, so that the inquiry process is simplified, and the inquiry efficiency is improved. Therefore, the problem of low query efficiency on question answering in the related art can be solved.
In one exemplary embodiment, identifying device information and query intent from the retrieved query instructions comprises:
s1, identifying key words in a query instruction;
and S2, identifying the equipment information and the query intention from the keywords.
Optionally, the keywords in the query execution include related information of the device and the intention of the query. For example, the user issues a query command of "why the washing machine shakes", from which the keyword of the included device is recognized as "washing machine", and the keyword of the query intention is "shake".
Alternatively, the device information and the query intention may be queried by identifying keywords. For example, if the user issues an inquiry command of "how to switch the rice cooker to the heat preservation state" and recognizes that the included keywords are "pot", "heat preservation", the intention may be recognized based on the keywords alone or by combining the keywords.
The embodiment can accurately determine the equipment information and the query intention by identifying the keywords.
In one exemplary embodiment, before determining the question-answer pair knowledge-graph of the target device corresponding to the device information, the method further comprises:
the method comprises the following steps of S1, obtaining a plurality of example samples related to target equipment, wherein each example sample comprises a question sample with the same type and one or more answer samples corresponding to the question sample;
and S2, constructing a question-answer pair knowledge graph by using the multiple example samples.
Alternatively, the example sample may include a voice command issued by the user when the home appliance is actually used, and an answer in response to the voice command. Questions and answers preset by the professional may also be included. Questions and answers associated with the device are built into the quiz-to-answer knowledge graph as much as possible. The purpose of accurately inquiring the answer can be achieved.
In one exemplary embodiment, determining a question-answer pair knowledge graph of a target device corresponding to device information includes:
s1, determining whether the query intention is matched with attribute information of target equipment;
and S2, under the condition that the query intention is not matched with the attribute information, querying a question-answer pair knowledge graph of the target equipment corresponding to the equipment information.
Optionally, in order to reduce the search range to the maximum, the attribute questions and answers of the device are separated, and answers related to the query instruction can be queried quickly. For example, the user issues "what model is a washing machine", recognizes that "washing machine" and "model" are included in the keywords, and determines that the inquiry is about the attribute of the device. And jumping to the attribute knowledge graph for inquiry instead of the question and answer.
For another example, if the user issues "how to take water from the washing machine", and recognizes that the keywords include "washing machine" and "water take pipe", it is determined that the keywords are not the attributes of the devices that are queried with each other. And jumping to a question-answer to inquire the knowledge graph. The steps of accessing other knowledge bases are reduced, so that the time is saved, and the query efficiency is improved.
In an exemplary embodiment, the method further includes:
s1, under the condition that the query intention is matched with the attribute information, responding to a query instruction by using an attribute knowledge graph of the target equipment, wherein the attribute knowledge graph comprises a plurality of attribute information related to the target equipment.
Optionally, the query process of the attribute knowledge graph is generally a query process about an entity question, and includes processes of entity identification, entity linking, judgment according to a relationship, answer query and the like. The knowledge graph is separated from the knowledge graph of the question-answer pair, the query generalization capability is improved, the relevant question-answer pair can be recalled more efficiently, the service layer is placed outside the database for accurate sequencing processing, and the query answer is finally obtained.
In an exemplary embodiment, the method further includes:
s1, associating the attribute knowledge graph with a question-answer pair knowledge graph to determine the question-answer pair knowledge graph as a subgraph of the attribute knowledge graph.
Alternatively, the attribute knowledge graph and the question-answer pair knowledge graph may be associated, but in the process of querying, different knowledge graphs are jumped to for different query instructions. The two do not have a superior-inferior relation, namely the attribute knowledge graph can be directly skipped to inquire the knowledge graph in question and answer, so that the inquiring efficiency is improved. For example, when the instruction of "how to receive water from the washing machine" is queried, the color, model and function of the washing machine do not need to be queried first, that is, the washing machine is not distinguished, but the answer of "how to receive water from the washing machine" is queried in the knowledge map directly by asking and answering of the washing machine.
In an exemplary embodiment, after the query instruction is responded to the knowledge graph by using the question and answer, and the query result corresponding to the query intention is obtained, the method further includes:
s1, under the condition that the query result comprises a plurality of answers, sequencing the answers.
Alternatively, a question may correspond to a plurality of answers, for example, "why a refrigerator has running water noise", and the corresponding answer includes "sound of refrigerant flowing in a refrigeration system of the refrigerator", "refrigeration principle of the refrigerator, when the refrigerant is compressed by a compressor into liquid, releases heat through a condenser, and then evaporates into gas through a capillary tube evaporator, this process needs to absorb a large amount of heat", "running water noise is echo generated when the refrigerant runs in a pipeline, the refrigerant changes between liquid state and gas state, the liquid state gradually absorbs heat and refrigerates when flowing in the evaporator, and then the gradual change to the gas state generates sound like water flow", and the above answers may be ranked, and the ranking rule may be ranking based on importance or based on how many letters of the answer are ranked.
The invention is illustrated below with reference to specific examples:
the embodiment is explained based on application of entity special question and answer sub-graph query and quick recall in a graph system. In the embodiment, the sub-graph query refers to querying sub-graphs in a graph database, so that the search space is reduced, the query processing speed is accelerated, and the generalization capability is improved by quick recall; and the results of the sub-graph query recall are further sorted in a fine ranking manner, the processing of the database on the service is further released, a faster network service response is generated, and the basic requirements of the industry on real-time service, application intelligence and the like are met.
Fig. 3 is an overall architecture diagram in the present embodiment, and fig. 3 includes knowledge maps of a device a, a device B, and a device C. Each device may include an attribute knowledge-graph and a question-and-answer pair knowledge-graph. For example, device a includes both a knowledge graph of device attributes (device name, device function, device color) and a question-and-answer pair knowledge graph (sub-graph one) (QA 1, QA2, QA 3). Device B includes a question-answer pair knowledge graph (sub-graph two) (QA 1, QA2, QA 3).
Fig. 4 is a flowchart of sub-map query and quick recall in this embodiment, and example 1 is a question query process of an entity, including processes of entity identification, entity linking, judgment according to relationship, answer query, and the like. Example 2 is a query process of question-answer pairs related to an entity, in which a keyword label is used as a query basis, so that query generalization capability is improved, the related question-answer pairs are recalled more highly, a service layer is placed outside a database for precise sequencing processing, and finally, a query answer is obtained.
The embodiment describes sub-graph query about entity question-answer pairs, which reduces the search range to the maximum extent, and takes the generalization capability, i.e. the service, out of the database as much as possible, and uses the keyword or the keyword to perform quick recall, and the recalled result is subjected to further logic processing, so as to obtain the final answer. For example, in a home scene, there are various home devices with their own questions, which cannot be directly answered by entities and relations, and if common questions are answered by the above method, the questions can be associated to specific examples, and needed answers can be obtained quickly, so that the steps of accessing other knowledge bases, which are needed in the past, are reduced, thereby saving time and increasing the Query Per Second (QPS).
In summary, according to the present embodiment, the sub-graph query is used to quickly recall the answer according to the device information, and the answer is processed through the code layer, so that on one hand, the time for processing the service of the database is released, and on the other hand, the phenomenon that the question-answer pair is separated from the entity is solved. The method realizes the integrated storage of the relation map and the question-answer pairs, and makes the related inquiry about the existing entity more rapid.
In this embodiment, a response device for a query instruction is further provided, where the device is used to implement the foregoing embodiments and preferred embodiments, and details of the description already given are not repeated. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware or a combination of software and hardware is also possible and contemplated.
Fig. 5 is a block diagram showing a structure of a response apparatus for a query instruction according to an embodiment of the present invention, and as shown in fig. 5, the apparatus includes:
a first identification module 52, configured to identify device information and query intent from the obtained query instruction;
a first determining module 54, configured to determine a knowledge graph of question and answer pairs of a target device corresponding to the device information, where the knowledge graph of question and answer pairs includes a plurality of question and answer pairs related to the target device, and the question and answer pairs are used to indicate a correspondence between a question and an answer;
the first response module 56 is configured to respond to the query instruction to the knowledge graph by using the question and answer, and obtain a query result corresponding to the query intention.
In an exemplary embodiment, the first identifying module includes:
the first identification unit is used for identifying the key words in the query instruction;
and a second identification unit for identifying the device information and the query intention from the keyword.
In an exemplary embodiment, the apparatus further comprises:
a first obtaining module, configured to obtain a plurality of example samples related to a target device before determining a question-answer pair knowledge graph of the target device corresponding to the device information, where each example sample includes a question sample of a same type and one or more answer samples corresponding to the question sample;
and the first construction module is used for constructing the question-answer pair knowledge graph by utilizing a plurality of the example samples.
In an exemplary embodiment, the first determining module includes:
a first determination unit configured to determine whether the query intention matches attribute information of the target device;
a first querying unit, configured to query a question-answer pair knowledge graph of a target device corresponding to the device information if the query intention does not match the attribute information.
In an exemplary embodiment, the apparatus further includes:
and a second response module, configured to respond to the query instruction by using an attribute knowledge graph of the target device when the query intention matches the attribute information, where the attribute knowledge graph includes a plurality of pieces of attribute information related to the target device.
In an exemplary embodiment, the apparatus further includes:
and the first association module is used for associating the attribute knowledge graph with the question-answer pair knowledge graph so as to determine the question-answer pair knowledge graph as a sub-graph of the attribute knowledge graph.
In an exemplary embodiment, the apparatus further comprises:
and the first sequencing module is used for utilizing the question and answer pairs to respond the query instruction to the knowledge graph, obtaining a query result corresponding to the query intention, and sequencing a plurality of answers under the condition that the query result comprises a plurality of answers.
The foregoing is only a preferred embodiment of the present application and it should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.
Claims (10)
1. A method for responding to a query, comprising:
identifying equipment information and query intention from the obtained query instruction;
determining a question-answer pair knowledge graph of target equipment corresponding to the equipment information, wherein the question-answer pair knowledge graph comprises a plurality of question-answer pairs related to the target equipment, and the question-answer pairs are used for representing the corresponding relation between questions and answers;
and responding the query instruction by using the question-answer pair knowledge graph to obtain a query result corresponding to the query intention.
2. The method of claim 1, wherein identifying device information and query intent from the obtained query instruction comprises:
identifying a keyword in the query instruction;
identifying the device information and the query intent from the keyword.
3. The method of claim 1, wherein prior to determining the question-answer pair knowledge-graph for the target device corresponding to the device information, the method further comprises:
obtaining a plurality of example samples related to the target device, wherein each example sample comprises a question sample with the same type and one or more answer samples corresponding to the question sample;
and constructing the question-answer pair knowledge graph by using a plurality of the example samples.
4. The method of claim 1, wherein determining a question-answer pair knowledge graph of a target device corresponding to the device information comprises:
determining whether the query intent matches attribute information of the target device;
and querying a question-answer pair knowledge graph of the target device corresponding to the device information under the condition that the query intention does not match with the attribute information.
5. The method of claim 4, further comprising:
and responding to the query instruction by utilizing an attribute knowledge graph of the target device under the condition that the query intention is matched with the attribute information, wherein the attribute knowledge graph comprises a plurality of attribute information related to the target device.
6. The method of claim 5, further comprising:
and associating the attribute knowledge graph with the question-answer pair knowledge graph to determine the question-answer pair knowledge graph as a sub-graph of the attribute knowledge graph.
7. The method of claim 1, wherein after responding to the query instruction with the challenge-response pair knowledge-graph to obtain a query result corresponding to the query intent, the method further comprises:
in the case that a plurality of answers are included in the query result, the plurality of answers are ranked.
8. A response device for a query instruction, comprising:
the first identification module is used for identifying the equipment information and the query intention from the obtained query instruction;
a first determining module, configured to determine a question-answer pair knowledge graph of a target device corresponding to the device information, where the question-answer pair knowledge graph includes multiple question-answer pairs related to the target device, and the question-answer pairs are used to represent a correspondence between a question and an answer;
and the first response module is used for responding the query instruction to the knowledge graph by using the question and answer to obtain a query result corresponding to the query intention.
9. A computer-readable storage medium, comprising a stored program, wherein the program when executed performs the method of any of claims 1 to 7.
10. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to execute the method of any of claims 1 to 7 by means of the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210911118.4A CN115455191A (en) | 2022-07-29 | 2022-07-29 | Query instruction response method and device, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210911118.4A CN115455191A (en) | 2022-07-29 | 2022-07-29 | Query instruction response method and device, storage medium and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115455191A true CN115455191A (en) | 2022-12-09 |
Family
ID=84296447
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210911118.4A Pending CN115455191A (en) | 2022-07-29 | 2022-07-29 | Query instruction response method and device, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115455191A (en) |
-
2022
- 2022-07-29 CN CN202210911118.4A patent/CN115455191A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111542810B (en) | Signal processing coordination among digital voice assistant computing devices | |
| CN110824953A (en) | Control method and device of intelligent household equipment and storage medium | |
| US10895863B2 (en) | Electronic device and method for controlling the same | |
| CN110618614A (en) | Control method and device for smart home, storage medium and robot | |
| EP3387821B1 (en) | Electronic device and method for controlling the same | |
| CN106338922B (en) | The generation method and device of intelligent scene mode | |
| CN106547870B (en) | Method and device for dividing tables of database | |
| WO2021027437A1 (en) | Resource scheduling method and system, and computer-readable storage medium | |
| CN104866650B (en) | Method and device for creating abstract device | |
| CN114755931A (en) | Control instruction prediction method and device, storage medium and electronic device | |
| WO2024001189A1 (en) | Food storage information determination method and apparatus, storage medium, and electronic apparatus | |
| CN114855416A (en) | Recommendation method and device of washing program, storage medium and electronic device | |
| CN110754948B (en) | Intention identification method in cooking process and intelligent cooking equipment | |
| CN110555981A (en) | Response method and device, search method and device, remote controller, terminal and medium | |
| CN115455191A (en) | Query instruction response method and device, storage medium and electronic device | |
| CN114915514B (en) | Method and device for processing intention, storage medium and electronic device | |
| CN110866122B (en) | Method and device for mapping entity words based on knowledge graph | |
| CN114911556B (en) | Interface display method, device, equipment and storage medium | |
| CN114691752A (en) | Usage intention prediction method and apparatus, storage medium, and electronic apparatus | |
| CN115168605A (en) | Map determination method and apparatus, storage medium, and electronic apparatus | |
| CN109284444A (en) | A kind of recommended method of good friend, device, server and storage medium | |
| CN115345225A (en) | Method and device for determining recommended scene, storage medium and electronic device | |
| CN113961804A (en) | Equipment recommendation method, device, equipment and storage medium | |
| CN112015090A (en) | Electronic equipment control method and device | |
| CN115484350A (en) | Method and device for processing consultation voice, storage medium and electronic device |
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 |