CN116894078A - Information interaction method, device, electronic equipment and medium - Google Patents
Information interaction method, device, electronic equipment and medium Download PDFInfo
- Publication number
- CN116894078A CN116894078A CN202310944323.5A CN202310944323A CN116894078A CN 116894078 A CN116894078 A CN 116894078A CN 202310944323 A CN202310944323 A CN 202310944323A CN 116894078 A CN116894078 A CN 116894078A
- Authority
- CN
- China
- Prior art keywords
- instruction
- information
- target
- server
- target response
- 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
- 230000003993 interaction Effects 0.000 title claims abstract description 74
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000004044 response Effects 0.000 claims abstract description 153
- 238000004458 analytical method Methods 0.000 claims abstract description 39
- 230000006870 function Effects 0.000 claims description 39
- 238000004590 computer program Methods 0.000 claims description 16
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 230000002452 interceptive effect Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 3
- 241000196324 Embryophyta Species 0.000 description 2
- 241000220223 Fragaria Species 0.000 description 2
- 235000016623 Fragaria vesca Nutrition 0.000 description 2
- 235000011363 Fragaria x ananassa Nutrition 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- 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
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Mathematical Physics (AREA)
- Acoustics & Sound (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses an information interaction method, an information interaction device, electronic equipment and a medium. Wherein the method comprises the following steps: acquiring voice information to be queried received through a target input interface, and converting the voice information to be queried into text information to be queried; semantic analysis is carried out on the text information to be queried through a large language model pre-deployed by the server side to obtain target response information, so that the server side executes target operation according to the target response information; receiving identification information associated with a target response instruction sent by a server, and determining a target feedback instruction from a preset instruction library according to the identification information associated with the target response instruction; and executing the target feedback instruction, and returning an execution result of the target feedback instruction to the target input interface. According to the technical scheme, the voice input information can be subjected to semantic analysis based on the large language model, and accurate and effective response is performed according to the semantic analysis result, so that information interaction is more intelligent, and the information interaction requirement can be better met.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to an information interaction method, an information interaction device, an electronic device, and a medium.
Background
Along with the rapid development of intelligent integrated machines, the interactive integrated machines are more and more widely used. The interactive all-in-one machine is a high-tech product integrating the functions of equipment such as a high-definition television, a tablet personal computer, an interactive electronic whiteboard and the like, such as a conference all-in-one machine, a teaching all-in-one machine and the like.
In the prior art, when man-machine interaction is realized through the interaction integrated machine, related instructions are generally searched and matched according to the voice input by the client, if the instructions are successfully matched, the instructions are executed, if the instructions are failed to be matched, the instructions are not executed, and meanwhile, the voice input by the user cannot be recognized is prompted.
However, the existing interactive all-in-one machine can only recognize a fixed simple voice input, for example, can only recognize "open screen" but cannot recognize "i want screen", even if the meaning expressed by the two words is basically consistent, but cannot recognize the meaning expressed by the latter. Because the interactive all-in-one machine can only recognize the voice input with simple fixation, when the voice input exceeds the fixed recognition range, the interactive all-in-one machine cannot recognize the voice input, and therefore the corresponding instruction cannot be matched for accurate response.
Disclosure of Invention
The invention provides an information interaction method, an information interaction device, electronic equipment and a medium, which can carry out semantic analysis on voice input information based on a large language model, and can accurately and effectively respond according to a semantic analysis result, so that information interaction is more intelligent, and the information interaction requirement can be better met.
According to an aspect of the present invention, there is provided an information interaction method, the method including:
acquiring voice information to be queried received through a target input interface, and converting the voice information to be queried into text information to be queried;
semantic analysis is carried out on the text information to be queried through a large language model pre-deployed by a server side to obtain target response information, so that the server side executes target operation according to the target response information; the target operation is to determine a target response instruction corresponding to the target response information from an instruction database pre-deployed by the server, and determine identification information associated with the target response instruction;
receiving the identification information associated with the target response instruction sent by the server, and determining a target feedback instruction from a preset instruction library according to the identification information associated with the target response instruction; the target response instruction and the identification information associated with the target feedback instruction are the same;
and executing the target feedback instruction, and returning an execution result of the target feedback instruction to the target input interface.
According to another aspect of the present invention, there is provided an information interaction apparatus including:
the text information determining module is used for acquiring the voice information to be queried received through the target input interface and converting the voice information to be queried into text information to be queried;
the target operation execution module is used for carrying out semantic analysis on the text information to be queried through a large language model pre-deployed by a server to obtain target response information, so that the server executes target operation according to the target response information; the target operation is to determine a target response instruction corresponding to the target response information from an instruction database pre-deployed by the server, and determine identification information associated with the target response instruction;
the feedback instruction determining module is used for receiving the identification information associated with the target response instruction sent by the server and determining a target feedback instruction from a preset instruction library according to the identification information associated with the target response instruction; the target response instruction and the identification information associated with the target feedback instruction are the same;
and the feedback instruction execution module is used for executing the target feedback instruction and returning the execution result of the target feedback instruction to the target input interface.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the information interaction method according to any one of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to execute the information interaction method according to any embodiment of the present invention.
According to the technical scheme, the voice information to be queried received through the target input interface is obtained, and the voice information to be queried is converted into text information to be queried; semantic analysis is carried out on the text information to be queried through a large language model pre-deployed by the server side to obtain target response information, so that the server side executes target operation according to the target response information; the target operation comprises the steps of determining a target response instruction corresponding to target response information from an instruction database pre-deployed by a server side, and determining identification information associated with the target response instruction; receiving identification information associated with a target response instruction sent by a server, and determining a target feedback instruction from a preset instruction library according to the identification information associated with the target response instruction; the target response instruction and the target feedback instruction are associated with the same identification information; and executing the target feedback instruction, and returning an execution result of the target feedback instruction to the target input interface. According to the technical scheme, the voice input information can be subjected to semantic analysis based on the large language model, and accurate and effective response is performed according to the semantic analysis result, so that information interaction is more intelligent, and the information interaction requirement can be better met.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an information interaction method according to a first embodiment of the present invention;
fig. 2 is a flowchart of an information interaction method according to a second embodiment of the present invention;
FIG. 3 is a schematic diagram of an information interaction process provided according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an information interaction device according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device implementing an information interaction method according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," "target," and the like in the description and claims of the present invention and in the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise 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.
Example 1
Fig. 1 is a flowchart of an information interaction method according to an embodiment of the present invention, where the method may be applied to a case of intelligent information interaction based on a large language model, and the method may be performed by an information interaction device, where the information interaction device may be implemented in hardware and/or software, and the information interaction device may be configured in an electronic device with data processing capability. As shown in fig. 1, the method includes:
s110, acquiring voice information to be queried received through a target input interface, and converting the voice information to be queried into text information to be queried.
The technical scheme of the embodiment can be executed by an interaction all-in-one machine, such as a conference all-in-one machine. The conference integrated machine integrates multiple functions of a projector, an electronic whiteboard, a sound device, a television, a video conference terminal and the like, and is office equipment specially designed for meeting. According to the technical scheme, the input voice information can be subjected to semantic analysis based on the large language model, and accurate response is performed according to the analysis result, so that the method is applicable to response of simple voice input and complex voice input, and the problem that accurate response cannot be performed because the interaction integrated machine cannot accurately understand voice input can be effectively avoided. Among them, a large language model (such as GPT) is an artificial intelligence model, which aims at understanding and generating human language. They train on a large amount of text data and can perform a wide range of tasks including text summarization, translation, emotion analysis, and so forth.
Wherein the target input interface may be used to receive voice information input by a user. Specifically, the target input interface may be a voice input interface set on the interaction integrated machine, or may be a voice input interface set on other devices, so long as the interaction integrated machine is ensured to obtain voice input, and the target input interface may be specifically set according to actual requirements, which is not limited in this embodiment. The voice information to be queried may refer to voice information which is input by a user through a target input interface and is desired to be queried. The text information to be queried may refer to text information corresponding to the voice information to be queried.
In this embodiment, after the user inputs the voice information to be queried through the target input interface, the interaction integrated machine may acquire the voice information to be queried received through the target input interface, and convert the voice information to be queried into the text information to be queried by calling the third party service. Wherein, the third party service can be used for converting the voice information into corresponding text information.
S120, carrying out semantic analysis on the text information to be queried through a large language model pre-deployed by the server to obtain target response information, so that the server executes target operation according to the target response information.
The target response information may be information obtained by performing semantic analysis on the text information to be queried through a large language model. By way of example, assuming that the text information to be queried is "I want to record a screen", the target response information can be obtained as "open the screen" after semantic analysis is performed through a large language model. The target operation is to determine a target response instruction corresponding to the target response information from an instruction database pre-deployed by the server side, and determine identification information associated with the target response instruction. The instruction database is a database which is deployed in advance by a server side and can be used for storing different functional instructions. The target response instruction may refer to a functional instruction in the instruction database corresponding to the target response information. The identification information may be used to uniquely characterize the instruction, such as ID information.
In this embodiment, after obtaining the text information to be queried, a large language model pre-deployed by the server may be called by the interaction integrated machine, and the text information to be queried is subjected to semantic analysis through the large language model to obtain the target response information. After obtaining the target response information, the server can search a function instruction matched with the target response information from a pre-deployed instruction database according to the target response information to serve as a target response instruction, determine identification information associated with the target response instruction, and send the identification information associated with the target response instruction to the interaction all-in-one machine. In this embodiment, a corresponding identification information is preset for each instruction in the instruction database, which can be used to uniquely characterize the instruction.
It should be noted that, because the instruction in the instruction database is limited, that is, the instruction database may not include all the function instructions that the user wants to implement, there may be a case that the server cannot match the target response instruction corresponding to the target response information from the instruction database, so that the voice information to be queried input by the user cannot obtain correct response feedback. At this time, the text information to be queried corresponding to the voice information to be queried can be stored in the server, and the server analyzes the user requirement according to the text information to be queried so as to expand the instructions in the instruction database later. If the target response instruction corresponding to the target response information is not matched, the identification information associated with the target response instruction can be determined to be preset identification information, and the preset identification information can be used for representing the target response instruction which cannot be matched with the target response instruction corresponding to the target response information.
S130, receiving identification information associated with the target response instruction sent by the server, and determining a target feedback instruction from a preset instruction library according to the identification information associated with the target response instruction.
The preset instruction library may be an instruction library which is deployed in advance in the interaction integrated machine and may be used for storing function execution instructions. It should be noted that, the function execution instruction of the preset instruction library in the interaction integrated machine is matched with the function instruction of the instruction database in the server. The target feedback instruction may refer to a function execution instruction matched with the identification information row associated with the target response instruction in the preset instruction library. It should be noted in particular that the target response instruction is identical to the identification information associated with the target feedback instruction. The target response instruction and the target feedback instruction have adaptive functions, the target response instruction focuses on the function description, and the target feedback instruction focuses on the function implementation.
In this embodiment, when the interaction integrated machine receives the identification information associated with the target response instruction sent by the server, the interaction integrated machine may search from a preset instruction library according to the identification information associated with the target response instruction, and determine a function execution instruction having the same identification information as the target response instruction as a target feedback instruction. Further, if the identification information associated with the target response instruction is preset identification information, it indicates that the target response instruction corresponding to the target response information cannot be matched, at this time, the target feedback instruction may be determined as a preset feedback instruction, where the preset feedback instruction may be used to indicate that there is no feedback instruction matched with the voice information to be queried.
And S140, executing the target feedback instruction, and returning an execution result of the target feedback instruction to the target input interface.
In this embodiment, after the target feedback instruction is determined, the target feedback instruction may be executed by the interaction integrated machine, and an execution result of the target feedback instruction is returned to the target input interface, so that intelligent information interaction may be implemented. Wherein the execution result may be a voice or an action. Further, if the target feedback instruction is a preset feedback instruction, when the target feedback instruction is executed, a preset execution result can be obtained. The preset execution result can be used for representing that voice information to be queried cannot be identified.
According to the technical scheme, the voice information to be queried received through the target input interface is obtained, and the voice information to be queried is converted into text information to be queried; semantic analysis is carried out on the text information to be queried through a large language model pre-deployed by the server side to obtain target response information, so that the server side executes target operation according to the target response information; the target operation comprises the steps of determining a target response instruction corresponding to target response information from an instruction database pre-deployed by a server side, and determining identification information associated with the target response instruction; receiving identification information associated with a target response instruction sent by a server, and determining a target feedback instruction from a preset instruction library according to the identification information associated with the target response instruction; the target response instruction and the target feedback instruction are associated with the same identification information; and executing the target feedback instruction, and returning an execution result of the target feedback instruction to the target input interface. According to the technical scheme, the voice input information can be subjected to semantic analysis based on the large language model, and accurate and effective response is performed according to the semantic analysis result, so that information interaction is more intelligent, and the information interaction requirement can be better met.
In this embodiment, optionally, the instruction database includes a function name and a response instruction associated with the function name; correspondingly, determining the target response instruction corresponding to the target response information from the instruction database pre-deployed by the server side comprises the following steps: determining a target function name from an instruction database of the server according to the target response information; a response instruction associated with the target function name is determined from the instruction database as a target response instruction.
The target function name may refer to a function name in the instruction database that matches the target response information. In this embodiment, the instruction database may specifically include a function name and a response instruction associated with the function name. Therefore, when determining the target response instruction corresponding to the target response information, the target function name matched with the target response information can be determined from the instruction database of the server according to the target response information, and then the response instruction associated with the target function name can be determined as the target response instruction.
According to the scheme, through the function division of the instructions in the instruction database, when the target response instructions corresponding to the target response information are determined, the functional modules are determined first, then the specific instructions associated with the functional modules are determined, global searching of the instructions in the instruction database is avoided, the instruction searching time can be effectively shortened, and the determining efficiency of the target response instructions is improved.
In this embodiment, optionally, the method further includes: if the server detects an instruction adding event, acquiring newly added instruction information in the instruction adding event through the server; adding a new instruction into the instruction database according to the newly added instruction information, and generating identification information for the new instruction; and generating a new instruction list according to the new instruction and the identification information of the new instruction.
The instruction adding event may refer to an operation instruction requesting to add a new instruction. The newly added instruction information may be used to describe instruction related information to be added. For example, the newly added instruction information may include an instruction function name and an instruction content description. The new instruction list may be a list generated according to the new instruction and the identification information of the new instruction, and may include one or more groups of new instructions and corresponding identification information thereof.
In this embodiment, an instruction registry may be pre-deployed at the server, where the instruction registry may be used as a key module for instruction scalability to register new instructions and maintain old instructions. When a new instruction needs to be added, an instruction addition event can be generated through an external API interface provided by the instruction registry. When the instruction registration center of the server detects the instruction adding event, new instruction information (such as instruction function name and instruction content description) in the instruction adding event can be automatically acquired. And then the server can store the newly-added instruction information acquired by the instruction registration center in the instruction database, so that the addition of the new instruction is realized, corresponding identification information is generated for the new instruction, and a newly-added instruction list can be generated according to the new instruction and the identification information of the new instruction.
Through the arrangement, the new instruction registration center deployed in advance in the server side can register new instructions and maintain old instructions, and the instructions can be expanded according to requirements so as to better meet actual application requirements.
In this embodiment, optionally, the method further includes: periodically acquiring a new instruction list from a server; and updating the preset instruction library according to the newly-added instruction list.
In this embodiment, an instruction management center is correspondingly disposed in the interaction integrated machine, where the instruction management center may periodically obtain a new instruction list from the server, and then update the instructions in the preset instruction library according to the new instruction list, so that the instructions in the instruction database in the server are functionally matched with the instructions in the preset database in the interaction integrated machine.
According to the scheme, through the arrangement, the preset instruction library can be periodically updated according to the newly-added instruction list generated by the server, so that the instructions of the instruction database in the server are matched with the instructions of the preset database in the interaction integrated machine in function, and corresponding functions can be better realized.
Example two
Fig. 2 is a flowchart of an information interaction method according to a second embodiment of the present invention, where the optimization is performed based on the foregoing embodiment.
As shown in fig. 2, the method of this embodiment specifically includes the following steps:
s210, acquiring voice information to be queried received through a target input interface, and converting the voice information to be queried into text information to be queried.
S220, carrying out semantic analysis on the text information to be queried through a large language model pre-deployed by the server side within the functional range provided by the query prompt information to obtain target response information, so that the server side executes target operation according to the target response information.
The server side is pre-deployed with query prompt information, the query prompt information is used for representing a functional range allowing the large language model to perform semantic analysis, and the functional range can be determined according to the functional characteristics of the interaction integrated machine. For example, taking a conference integrated machine as an example, the inquiry prompt information may include opening a screen, pausing the screen, continuing the screen, closing the screen, opening a whiteboard, closing the whiteboard, opening notes, closing notes, and the like. The target operation is to determine a target response instruction corresponding to the target response information from an instruction database pre-deployed by the server side, and determine identification information associated with the target response instruction.
In this embodiment, query prompt information is deployed in advance in the server, and when semantic analysis is performed on text information to be queried through the large language model, the query prompt information needs to be analyzed within a functional range provided by the query prompt information, so that the large language model can be analyzed within the functional range provided by the interaction integrated machine, thereby realizing a specific function provided by the interaction integrated machine. It should be noted that, for the large language model, if the analysis content is limited without adding query prompt information, it only performs the analysis behavior similar to idiom according to the huge data set and parameter set of the large language model. Once the limit of the query prompt information is added, the large language model can analyze the text information to be queried according to the query prompt information, so that target response information conforming to the query prompt information is generated, and the problem that real intention of a user cannot be analyzed and target response information cannot be accurately analyzed due to semantic analysis of the world space of the text information to be queried by the large language model can be avoided.
For example, assume that the text message to be queried is "what is the strawberry to ask? If query hints are not added, the large language model may generate some interpretations and descriptions about the strawberry. However, if the inquiry prompt message "animal, plant" is added, the large language model can accurately answer "plant". Therefore, the large language model can be constrained and controlled to carry out semantic analysis on the text information to be queried according to the preset prompt through querying the prompt information, so that target response information which is more fit with the real intention of the user is generated.
S230, receiving identification information associated with the target response instruction sent by the server, and determining a target feedback instruction from a preset instruction library according to the identification information associated with the target response instruction.
The target response instruction and the target feedback instruction are associated with the same identification information.
S240, executing the target feedback instruction, and returning an execution result of the target feedback instruction to the target input interface.
The specific implementation of S230-S240 may be referred to in the detailed description of S130-S140, and will not be described herein.
According to the technical scheme, query prompt information is deployed in advance in the server side, the query prompt information is used for representing a functional range allowing the large language model to perform semantic analysis, and when the large language model pre-deployed by the server side performs semantic analysis on the text information to be queried, the query prompt information is required to perform semantic analysis within the functional range provided by the query prompt information to obtain target response information. According to the technical scheme, the voice input information can be accurately and semantically analyzed through the large language model under the constraint of the query prompt information, and the voice input information can be accurately and effectively answered according to the semantic analysis result, so that the problem that the real intention of a user cannot be analyzed due to the fact that the large language model performs semantic analysis on the word information to be queried in the world can be avoided, the specific function provided by the interaction integrated machine can be realized, the information interaction is more intelligent, and the information interaction requirement can be better met.
Fig. 3 is a schematic diagram of an information interaction process according to an embodiment of the present invention. As shown in fig. 3, the interaction integrated machine first obtains the voice information to be queried received through the target input interface, then converts the voice information to be queried into text information to be queried, and sends the text information to be queried to the instruction analyzer. After receiving the text information to be queried, the instruction analyzer calls an API to perform semantic analysis on the text information to be queried under the constraint of query prompt information through a large language model deployed by a server side to obtain target response information. And then the server determines a target response instruction corresponding to the target response information from a pre-deployed instruction database, determines identification information associated with the target response instruction, and returns the identification information associated with the target response instruction to an instruction parser of the interaction all-in-one machine. After receiving the identification information associated with the target response instruction, the instruction analyzer can determine a target feedback instruction from a preset instruction library according to the identification information associated with the target response instruction, and send the target feedback instruction to the instruction operator. And then the instruction operator executes the target feedback instruction to obtain a corresponding execution result, and returns the execution result to the target input interface, thereby realizing intelligent information interaction. In addition, the instruction registration center deployed by the server side can register new instructions, and the preset instruction library of the interaction integrated machine is updated periodically based on the newly-added instructions and the identification information thereof in the instruction database, so that the instructions in the instruction database and the preset instruction library are matched functionally.
Example III
Fig. 4 is a schematic structural diagram of an information interaction device according to a third embodiment of the present invention, where the device may execute the information interaction method according to any embodiment of the present invention, and the device has functional modules and beneficial effects corresponding to the execution method. As shown in fig. 4, the apparatus includes:
the text information determining module 310 is configured to obtain the to-be-queried voice information received through the target input interface, and convert the to-be-queried voice information into to-be-queried text information;
the target operation execution module 320 is configured to perform semantic analysis on the text information to be queried through a large language model pre-deployed by a server to obtain target response information, so that the server executes a target operation according to the target response information; the target operation is to determine a target response instruction corresponding to the target response information from an instruction database pre-deployed by the server, and determine identification information associated with the target response instruction;
the feedback instruction determining module 330 is configured to receive the identification information associated with the target response instruction sent by the server, and determine a target feedback instruction from a preset instruction library according to the identification information associated with the target response instruction; the target response instruction and the identification information associated with the target feedback instruction are the same;
and the feedback instruction execution module 340 is configured to execute the target feedback instruction, and return an execution result of the target feedback instruction to the target input interface.
Optionally, query prompt information is deployed in advance in the server, where the query prompt information is used to characterize a functional range that allows the large language model to perform semantic analysis.
Optionally, the target operation execution module 320 is configured to:
and in the functional range provided by the query prompt information, carrying out semantic analysis on the text information to be queried through a large language model pre-deployed by a server side to obtain target response information.
Optionally, the instruction database includes a function name and a response instruction associated with the function name;
accordingly, the target operation execution module 320 is further configured to:
determining a target function name from an instruction database of the server according to the target response information;
and determining a response instruction associated with the target function name from the instruction database as a target response instruction.
Optionally, the apparatus further includes:
the newly-added instruction information acquisition module is used for acquiring newly-added instruction information in the instruction adding event through the server if the server detects the instruction adding event;
the new instruction adding module is used for adding a new instruction into the instruction database according to the new instruction information and generating identification information for the new instruction;
and the new instruction list generation module is used for generating a new instruction list according to the new instruction and the identification information of the new instruction.
Optionally, the apparatus further includes:
the new instruction list acquisition module is used for periodically acquiring the new instruction list from the server;
and the preset instruction library updating module is used for updating the preset instruction library according to the new instruction list.
The information interaction device provided by the embodiment of the invention can execute the information interaction method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example IV
Fig. 5 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as information interaction methods.
In some embodiments, the information interaction method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the information interaction method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the information interaction method in any other suitable way (e.g. by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems-on-chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. An information interaction method, characterized in that the method comprises:
acquiring voice information to be queried received through a target input interface, and converting the voice information to be queried into text information to be queried;
semantic analysis is carried out on the text information to be queried through a large language model pre-deployed by a server side to obtain target response information, so that the server side executes target operation according to the target response information; the target operation is to determine a target response instruction corresponding to the target response information from an instruction database pre-deployed by the server, and determine identification information associated with the target response instruction;
receiving the identification information associated with the target response instruction sent by the server, and determining a target feedback instruction from a preset instruction library according to the identification information associated with the target response instruction; the target response instruction and the identification information associated with the target feedback instruction are the same;
and executing the target feedback instruction, and returning an execution result of the target feedback instruction to the target input interface.
2. The method of claim 1, wherein query hints are pre-deployed in the server, the query hints being used to characterize a functional scope that allows semantic parsing of the large language model.
3. The method of claim 2, wherein the semantic parsing of the text information to be queried to obtain target response information by a large language model pre-deployed by a server comprises:
and in the functional range provided by the query prompt information, carrying out semantic analysis on the text information to be queried through a large language model pre-deployed by a server side to obtain target response information.
4. The method of claim 1, wherein the instruction database includes a function name and a response instruction associated with the function name;
correspondingly, determining the target response instruction corresponding to the target response information from the instruction database pre-deployed by the server side comprises the following steps:
determining a target function name from an instruction database of the server according to the target response information;
and determining a response instruction associated with the target function name from the instruction database as a target response instruction.
5. The method according to claim 1, wherein the method further comprises:
if the server detects an instruction adding event, acquiring newly added instruction information in the instruction adding event through the server;
adding a new instruction into the instruction database according to the new instruction information, and generating identification information for the new instruction;
and generating a new instruction list according to the new instruction and the identification information of the new instruction.
6. The method of claim 5, wherein the method further comprises:
periodically acquiring the newly-added instruction list from the server;
and updating the preset instruction library according to the newly added instruction list.
7. An information interaction device, the device comprising:
the text information determining module is used for acquiring the voice information to be queried received through the target input interface and converting the voice information to be queried into text information to be queried;
the target operation execution module is used for carrying out semantic analysis on the text information to be queried through a large language model pre-deployed by a server to obtain target response information, so that the server executes target operation according to the target response information; the target operation is to determine a target response instruction corresponding to the target response information from an instruction database pre-deployed by the server, and determine identification information associated with the target response instruction;
the feedback instruction determining module is used for receiving the identification information associated with the target response instruction sent by the server and determining a target feedback instruction from a preset instruction library according to the identification information associated with the target response instruction; the target response instruction and the identification information associated with the target feedback instruction are the same;
and the feedback instruction execution module is used for executing the target feedback instruction and returning the execution result of the target feedback instruction to the target input interface.
8. The apparatus of claim 7, wherein query hints information is pre-deployed in the server, the query hints information being used to characterize a range of functionality that allows semantic parsing of the large language model.
9. An electronic device, the device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the information interaction method of any of claims 1-6.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores computer instructions for causing a processor to implement the information interaction method of any of claims 1-6 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310944323.5A CN116894078A (en) | 2023-07-28 | 2023-07-28 | Information interaction method, device, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310944323.5A CN116894078A (en) | 2023-07-28 | 2023-07-28 | Information interaction method, device, electronic equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116894078A true CN116894078A (en) | 2023-10-17 |
Family
ID=88314854
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310944323.5A Pending CN116894078A (en) | 2023-07-28 | 2023-07-28 | Information interaction method, device, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116894078A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117251473A (en) * | 2023-11-20 | 2023-12-19 | 摩斯智联科技有限公司 | Vehicle data query analysis method, system, device and storage medium |
| CN118070811A (en) * | 2024-04-16 | 2024-05-24 | 江苏微皓智能科技有限公司 | Information interaction method, device, equipment and medium based on natural language understanding |
-
2023
- 2023-07-28 CN CN202310944323.5A patent/CN116894078A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117251473A (en) * | 2023-11-20 | 2023-12-19 | 摩斯智联科技有限公司 | Vehicle data query analysis method, system, device and storage medium |
| CN117251473B (en) * | 2023-11-20 | 2024-03-15 | 摩斯智联科技有限公司 | Vehicle data query analysis method, system, device and storage medium |
| CN118070811A (en) * | 2024-04-16 | 2024-05-24 | 江苏微皓智能科技有限公司 | Information interaction method, device, equipment and medium based on natural language understanding |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102677454B1 (en) | Event argument extraction method, event argument extraction apparatus and electronic device | |
| CN116894078A (en) | Information interaction method, device, electronic equipment and medium | |
| CN117076719B (en) | Database joint query method, device and equipment based on large language model | |
| US20160335267A1 (en) | Method and apparatus for natural language search for variables | |
| CN111368145A (en) | Knowledge graph creating method and system and terminal equipment | |
| CN115481227A (en) | Man-machine interaction dialogue method, device and equipment | |
| CN116611411A (en) | Business system report generation method, device, equipment and storage medium | |
| EP3961433A2 (en) | Data annotation method and apparatus, electronic device and storage medium | |
| CN115098729A (en) | Video processing method, sample generation method, model training method and device | |
| CN105335466A (en) | Audio data retrieval method and apparatus | |
| CN113111658B (en) | Method, device, equipment and storage medium for checking information | |
| CN113220710B (en) | Data query method, device, electronic equipment and storage medium | |
| CN117112065A (en) | Large model plug-in calling method, device, equipment and medium | |
| CN113239054B (en) | Information generation method and related device | |
| US11941414B2 (en) | Unstructured extensions to rpa | |
| CN112632241A (en) | Method, device, equipment and computer readable medium for intelligent conversation | |
| CN114501112B (en) | Method, apparatus, device, medium, and article for generating video notes | |
| CN115529271B (en) | Service request distribution method, device, equipment and medium | |
| US20230117749A1 (en) | Method and apparatus for processing audio data, and electronic device | |
| CN113835893B (en) | Data processing method, device, equipment, storage medium and program product | |
| US20220021636A1 (en) | System and Method for Alerts for Missing Coverage of Chatbot Conversation Messages | |
| CN117093274A (en) | Application running stack analysis method, device, equipment and storage medium | |
| CN116467339A (en) | Homepage display method, device, equipment and medium of log management platform | |
| CN116567145A (en) | Customer service call operation quality inspection method and device, electronic equipment and storage medium | |
| CN118012936A (en) | Data extraction method, device, 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 |