CN112115245B - Query statement processing method, device, terminal and storage medium - Google Patents
Query statement processing method, device, terminal and storage medium Download PDFInfo
- Publication number
- CN112115245B CN112115245B CN202010892529.4A CN202010892529A CN112115245B CN 112115245 B CN112115245 B CN 112115245B CN 202010892529 A CN202010892529 A CN 202010892529A CN 112115245 B CN112115245 B CN 112115245B
- Authority
- CN
- China
- Prior art keywords
- slot
- information
- slot information
- position information
- query statement
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003672 processing method Methods 0.000 title abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 43
- 238000000034 method Methods 0.000 claims description 30
- 238000004590 computer program Methods 0.000 claims description 13
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 238000000605 extraction Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 239000000284 extract Substances 0.000 description 6
- 238000010413 gardening Methods 0.000 description 6
- 238000002372 labelling Methods 0.000 description 6
- 208000027418 Wounds and injury Diseases 0.000 description 5
- 230000006378 damage Effects 0.000 description 5
- 208000014674 injury Diseases 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000002618 waking 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
- G06F16/332—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
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Machine Translation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application belongs to the technical field of terminals, and particularly relates to a query statement processing method, a device, a terminal and a storage medium. The query statement processing method comprises the following steps: acquiring at least one first slot information and at least one second slot information corresponding to a query statement, wherein the at least one first slot information comprises at least one open domain slot information and at least one closed domain slot information, and the second slot information is statement information corresponding to the query statement; and acquiring target slot position information corresponding to the query statement based on the at least one first slot position information and the second slot position information. According to the embodiment of the application, the open domain slot information which is not included in the dictionary slot lifting model can be obtained, and the number of labels required when the target slot information is directly obtained based on the second slot information can be reduced, so that the accuracy of obtaining the target slot can be improved, the label cost can be reduced, and the accuracy of processing query sentences can be improved.
Description
Technical Field
The application belongs to the technical field of terminals, and particularly relates to a query statement processing method, a device, a terminal and a storage medium.
Background
With the development of science and technology, the advent of voice assistants enriches the functionality of terminals. The voice assistant aims to help the user to solve the problem through intelligent interaction of the intelligent dialogue with the instant question and answer. The user may use the voice assistant of the terminal to complete the operation on the terminal. For example, when a user queries for today's weather conditions, a query statement "how weather today is". When the voice assistant of the terminal receives the query statement, the terminal can obtain weather conditions of the current position of the terminal from a server, for example, and display the weather conditions on a display screen.
Disclosure of Invention
The embodiment of the application provides a query statement processing method, a device, a terminal and a storage medium, which can improve the accuracy of query statement processing. The technical scheme comprises the following steps:
In a first aspect, an embodiment of the present application provides a query statement processing method, where the method includes:
Acquiring at least one first slot information and at least one second slot information corresponding to a query statement, wherein the at least one first slot information comprises at least one open domain slot information and at least one closed domain slot information, and the second slot information is statement information corresponding to the query statement;
And acquiring target slot position information corresponding to the query statement based on the at least one first slot position information and the second slot position information.
In a second aspect, an embodiment of the present application provides a query statement processing apparatus, including:
The first acquisition unit is used for acquiring at least one first slot information and at least one second slot information corresponding to the query statement, wherein the at least one first slot information comprises at least one open domain slot information and at least one closed domain slot information, and the second slot information is statement information corresponding to the query statement;
The second acquisition unit is used for acquiring target slot position information corresponding to the query statement based on the at least one first slot position information and the second slot position information.
In a third aspect, an embodiment of the present application provides a terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the method according to any one of the first aspects when the processor executes the computer program.
In a fourth aspect, embodiments of the present application provide a computer readable storage medium having stored thereon a computer program which when executed by a processor performs a method according to any of the preceding claims.
In a fifth aspect, embodiments of the present application provide a computer program product, wherein the computer program product comprises a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package.
The embodiment of the application provides a query statement processing method, which is characterized in that at least one first slot information and at least one second slot information corresponding to a query statement are acquired, and the second slot information is statement information corresponding to the query statement, so that target slot information corresponding to the query statement can be acquired based on at least one open domain slot information, at least one closed domain slot information and the second slot information in the at least one first slot information, open domain slot information which is not included in a dictionary lifting slot model can be acquired, the number of labels required when the target slot information is acquired directly based on the second slot information is reduced, the accuracy of acquiring the target slot can be improved, the labeling cost can be reduced, and the accuracy of query statement processing can be improved.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 shows an application scenario diagram of a query term processing method or a query term processing apparatus applied to an embodiment of the present application;
FIG. 2 shows an exemplary schematic of a terminal interface according to an embodiment of the application;
FIG. 3 is a flow chart of a query statement processing method according to an embodiment of the present application;
FIG. 4 is a flow chart of a query statement processing method according to an embodiment of the present application;
FIG. 5 is a flow chart of a query statement processing method according to an embodiment of the present application;
FIG. 6 is a schematic diagram of a target slot information acquisition process according to an embodiment of the present application;
FIG. 7 is a flowchart of a query statement processing method according to an embodiment of the present application;
FIG. 8 is a flow chart of a query statement processing method according to an embodiment of the present application;
FIG. 9 is a flowchart of a query statement processing method according to an embodiment of the present application;
FIG. 10 shows an exemplary schematic of a terminal interface according to an embodiment of the present application;
FIG. 11 is a schematic diagram of a query term processing device according to an embodiment of the present application;
fig. 12 shows a schematic structural diagram of a terminal according to an embodiment of the present application.
Detailed Description
In order to make the present application better understood by those skilled in the art, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
With the development of the artificial intelligence industry, voice assistants have been rapidly developed. The voice assistant is typically applied in the terminal. The terminal of the embodiment of the application supports a voice assistant, and comprises, but is not limited to: personal computers, tablet computers, handheld devices, vehicle mounted devices, wearable devices, computing devices, or other processing devices connected to a wireless modem, and the like. Terminals may be called different names in different networks, for example: user equipment, access terminals, subscriber units, subscriber stations, mobile stations, remote terminals, mobile devices, user terminals, wireless communication devices, user agents or user equipment, cellular telephones, cordless telephones, personal Digital Assistants (PDAs), and the like.
According to some embodiments, fig. 1 shows a schematic diagram of an application scenario of a query term processing method or a query term processing apparatus applied to an embodiment of the present application. As shown in fig. 1, when a user uses a voice assistant of a terminal, the user may press a voice input control on a display screen of the terminal. When the terminal detects that the user presses the voice input control, the terminal starts to acquire voice information input by the user. When the terminal detects that the user stops pressing the voice input control, the terminal acquires the voice information, namely the terminal can acquire the query statement input by the user. As shown in fig. 2, when the user wakes up the voice assistant of the terminal, the user can directly input voice information without pressing the voice input control. At this time, the terminal may display the query sentence input by the user on the display screen.
It is easy to understand that when the terminal obtains the query sentence input by the user through the voice assistant of the terminal, the terminal can obtain the slot information corresponding to the query sentence by adopting the slot recognition algorithm, and determine the intention of the user based on the slot information. However, when the terminal acquires the slot information by adopting a dictionary slot extraction algorithm or a regular slot extraction algorithm, the slot information which is not contained in the dictionary cannot be extracted by the dictionary slot extraction algorithm, so that the slot information acquisition is inaccurate, namely the terminal has lower accuracy in processing the query statement. Secondly, sentence patterns of the regular groove extraction algorithm are complex, and conflicts exist among the sentence patterns, so that the method cannot be used for extracting the open domain groove position information, the groove position information is obtained inaccurately, and the accuracy of the terminal on query sentence processing is low. When the model slot extraction algorithm obtains slot information corresponding to the query statement, the quality of any slot extraction is difficult to adjust and optimize, and the extracted labeling cost is high, so that the slot information is obtained inaccurately, and the problem of lower accuracy of a terminal in processing the query statement occurs. The embodiment of the application provides a query statement processing method which can improve the accuracy of query statement processing.
The following describes in detail the query sentence processing method provided in the embodiment of the present application with reference to fig. 3 to fig. 10. The execution body of the embodiment shown in fig. 3-10 may be, for example, a terminal.
Referring to fig. 3, a flowchart of a query sentence processing method is provided in an embodiment of the present application. As shown in fig. 3, the method according to the embodiment of the present application may include the following steps S101 to S102.
S101, acquiring at least one first slot information and at least one second slot information corresponding to a query statement, wherein the at least one first slot information comprises at least one open domain slot information and at least one closed domain slot information, and the second slot information is statement information corresponding to the query statement.
According to some embodiments, the query term refers to a query term input by a user, where the query term may be a query term input by the user by pressing a voice input control, a query term input by the user by waking up a voice assistant of the terminal, or a query term directly input by the user.
It is easy to understand that the first slot information refers to slot information obtained by adopting a dictionary slot lifting model after the terminal obtains the query statement. The dictionary slot extraction model may be used to extract open domain slot information and closed domain slot information, but for open domain slot information, the dictionary slot extraction model may only extract slot information that is included in the dictionary, but may not extract slot information that is not included in the dictionary.
Alternatively, the closed domain slot information is slot information indicating that there are N possible lists of O skills of the voice assistant in the terminal. The closure domain slot information may be, for example, slot information about animal grade. The closed domain slot information may also be slot information about chinese provinces, for example. The open domain slot information indicates that there are no N pieces of slot information that can be enumerated for the O skill of the voice assistant in the terminal, that is, the slot information corresponding to the O skill cannot be fully enumerated. The open domain slot information may be, for example, slot information about real-time news. The open domain slot information may also be slot information about a flat pattern, for example. The slot information about the planar pattern includes, but is not limited to, triangles, quadrilaterals, pentagons, and the like. The at least one first slot information Ω in the embodiment of the present application may be, for example, N, Ω= { slot 1,slot2,…,slotN }, where the open domain slot information may be, for example, 1, and the closed domain slot information may be, for example, (N-1), where the 1 open domain slot information may be, for example, slot open, i.e., Ω open＝{slotopen }. In addition, (N-1) closed domain slot information can be represented as a setWherein i is more than or equal to1 and less than or equal to N-1; the relation between the 1 open domain slot information and the (N-1) closed domain slot information is: Ω=Ω close∪Ωopen,/>
According to some embodiments, the query statement obtained by the terminal may be, for example, "news looking at injuries of university C athletes of the province B today". The terminal obtains at least one first slot information corresponding to the query statement, which may be, for example, "province a", "university B", and "today". Wherein the at least one open domain slot information is "university B" and the at least one closed domain slot information is "province a" and "today".
It is easy to understand that the second slot information refers to statement information corresponding to the query statement. The term information may be term information corresponding to a query term acquired by a terminal using a speech recognition model, for example, when the terminal acquires the query term. The statement information may refer to a statement corresponding to the query statement. For example, the query sentence acquired by the terminal may be "watch news about injury of the player C at university B of a province today". The second slot information acquired by the terminal may be, for example, "news of injury to the player C at university B, a province today".
S102, acquiring target slot information corresponding to the query statement based on at least one piece of first slot information and second slot information.
According to some embodiments, the target slot information refers to slot information corresponding to a query statement determined by the terminal, and the terminal may obtain a user intention corresponding to the query statement based on the slot information.
It is easy to understand that, when the terminal obtains at least one first slot information and at least one second slot information corresponding to the query sentence, the terminal may obtain the target slot information corresponding to the query sentence based on at least one open domain slot information, at least one closed domain slot information, and at least one second slot information in the at least one first slot information. At this time, the terminal may split the second slot information using at least one open domain slot information and at least one closed domain slot information, and generate target slot information corresponding to the query statement based on the split second slot information, at least one open domain slot information and at least one closed domain slot information.
Alternatively, the query sentence acquired by the terminal may be, for example, "news about injury of C athlete at university a, B, today. The terminal obtains at least one first slot information corresponding to the query statement, which may be, for example, "province a", "university B", and "today". Wherein the at least one open domain slot information is "university B" and the at least one closed domain slot information is "province a" and "today". The second slot information acquired by the terminal may be, for example, "news of injury to the player C at university B, a province today". The terminal splits the second slot information by using at least one open domain slot information and at least one closed domain slot information, and the second split slot information can be, for example, "a C athlete" and "an injured". The target slot information obtained by the terminal may thus be "province a", "university B", "today", "athlete C" and "injured". The terminal may obtain the user intent corresponding to the query statement from a memory or a server of the terminal based on the target slot information.
The embodiment of the application provides a query statement processing method, which is characterized in that at least one first slot information and at least one second slot information corresponding to a query statement are acquired, and the second slot information is statement information corresponding to the query statement, so that target slot information corresponding to the query statement can be acquired based on at least one open domain slot information, at least one closed domain slot information and the second slot information in the at least one first slot information, the open domain slot information not included in a dictionary lifting slot model can be acquired, the accuracy of acquiring the target slot can be improved, and the accuracy of query statement processing can be improved. In addition, when the terminal acquires the target slot information corresponding to the query statement based on at least one first slot information and at least one second slot information, the number of labels required when the target slot information is acquired directly based on the second slot information can be reduced, the labeling cost can be reduced, the cost of processing the query statement can be reduced, and the application range of processing the query statement can be enlarged.
Referring to fig. 4, a flowchart of a query sentence processing method is provided in an embodiment of the present application. As shown in fig. 4, the method according to the embodiment of the present application may include the following steps S201 to S205.
S201, at least one first slot information and at least one second slot information corresponding to the query statement are obtained, wherein the at least one first slot information comprises at least one open domain slot information and at least one closed domain slot information, and the second slot information is statement information corresponding to the query statement.
The specific process is as described above, and will not be described here again.
According to some embodiments, when the terminal obtains at least one first slot information corresponding to the query statement, the terminal may extract the at least one first slot information using a dictionary slot model. The dictionary slot model is generated by the terminal based on dictionary information input by the user or dictionary information downloaded from the server before acquiring the query sentence. By adopting the dictionary slot model, the terminal can acquire accurate at least one closed domain slot information. However, for the open domain slot information, the terminal can only acquire the open domain slot information included in the dictionary information.
It is easy to understand that when the terminal obtains the second slot information corresponding to the query statement, the terminal may extract the second slot information by using a single slot model. When the terminal adopts the single slot model to extract the second slot information, the terminal can acquire statement information corresponding to the query statement. The terminal of the embodiment of the application can change or expand dictionary information of the dictionary slot position model, a preset sentence pattern and a preset dictionary of the single slot position model, and can use the processing method of the query sentence in various scenes.
Referring to fig. 5, a flowchart of a query sentence processing method is provided according to an embodiment of the present application. As shown in fig. 5, the method for extracting the second slot information by using the single slot model according to the embodiment of the present application may include the following steps S301 to S302. S301, extracting at least one slot information of a query sentence by adopting a preset dictionary in a single slot model; s302, merging at least one slot information based on a preset sentence pattern in the single slot model to generate second slot information.
According to some embodiments, when the terminal uses the single-slot model to extract the second slot information, the terminal may use a preset dictionary in the single-slot model to extract at least one slot information of the query statement. When the terminal obtains the at least one slot information, the terminal can combine the at least one slot information based on a preset sentence pattern in the single slot model to generate second slot information.
It is easy to understand that the query sentence acquired by the terminal may be, for example, "troublesome to open a video of G star singing the third song on gardening section of F university in D city today". The terminal extracts at least one slot information of the query sentence by adopting a preset dictionary in the single slot model, for example, the information can be "today", "D city", "F university", "campus art festival", "G star" and "third song". The terminal merges at least one slot information based on a preset sentence pattern in the single slot model, and the generated second slot information may be, for example, "third song of the campus art festival G star of university F in D city today".
S202, splitting the second slot information based on at least one piece of first slot information to obtain third slot information except for the at least one piece of first slot information in the second slot information.
Fig. 6 illustrates a flowchart of obtaining target slot information according to an embodiment of the present application, according to some embodiments. When the terminal obtains at least one first slot information and second slot information corresponding to the query statement, the terminal can split the second slot information based on the at least one first slot information, extract the at least one first slot information included in the second slot information, and obtain third slot information except the at least one first slot information in the second slot information.
It is easy to understand that, for example, the query sentence acquired by the terminal may be, for example, "troublesome to open a video of G star singing the third song on gardening section of F university in D city today". The second slot information acquired by the terminal may be, for example' third song of university F campus art festival G star, D city today). The at least one first slot information acquired by the terminal may be, for example, "today," "D city," "concert," "third song," where "today," "D city," "F university" are closed domain slot information, "concert," and "third song" are open domain slot information. The third slot information obtained by the terminal can be, for example, "campus art festival" and "G star".
Referring to fig. 7, a flowchart of a query sentence processing method is provided according to an embodiment of the present application. As shown in fig. 7, the method according to the embodiment of the present application splits the second slot information based on at least one first slot information, and obtaining third slot information except for the at least one first slot information in the second slot information may include the following steps S401 to S402. S401, splitting the second slot position information by sequentially adopting the open domain slot position information to obtain fifth slot position information; s402, splitting the fifth slot information by sequentially adopting the slot information of each closed domain to obtain the third slot information.
According to some embodiments, when the terminal splits the second slot information based on the at least one first slot information to obtain third slot information except for the at least one first slot information in the second slot information, the terminal may split the second slot information by sequentially adopting each open domain slot information to obtain fifth slot information. After the terminal obtains the fifth slot information, the terminal can split the fifth slot information by sequentially adopting the slot information of each closed domain to obtain the third slot information, so that the condition that the third slot information obtained by splitting the second information by adopting the slot information of the closed domain is inaccurate is reduced, and the accuracy of obtaining the target slot information can be improved. For example, the query sentence acquired by the terminal is "third song of the campus art festival G star of today T university", where T is the province. The at least one first slot information acquired by the terminal may be, for example, "T", "today", "T university", where "today", "T" is closed domain slot information and "T university" is open domain slot information. When the terminal splits the second slot information by using the closed domain slot information, the area limitation of the university is lost, so that the third slot information is obtained inaccurately, and the target slot information is obtained inaccurately.
And S203, combining the at least one open domain slot position information and the third slot position information to obtain fourth slot position information.
According to some embodiments, after splitting the second slot information based on the at least one first slot information to obtain third slot information except the at least one first slot information in the second slot information, the terminal may combine the at least one open domain slot information and the third slot information to obtain fourth slot information.
It is easy to understand that, for example, the query sentence acquired by the terminal may be, for example, "troublesome to open a video of G star singing the third song on gardening section of F university in D city today". The second slot information acquired by the terminal may be, for example' third song of university F campus art festival G star, D city today). The at least one first slot information acquired by the terminal may be, for example, "today," "D city," "concert," "third song," where "today," "D city," "F university" are closed domain slot information, "concert," and "third song" are open domain slot information. The third slot information obtained by the terminal can be, for example, "campus art festival" and "G star". And the terminal combines the at least one open domain slot information with the third slot information, and the obtained fourth slot information can be, for example, "concert", "third song", "campus art festival" and "G star".
S204, taking the fourth slot information and at least one closed domain slot information as target slot information corresponding to the query statement.
According to some embodiments, when the terminal merges the at least one open domain slot information and the third slot information to obtain fourth slot information, the terminal may use the fourth slot information and the at least one closed domain slot information as target slot information corresponding to the query statement. For example, the query sentence acquired by the terminal may be "troublesome to open a video of G star singing a third song on gardening section of F university in D city today". The third slot information obtained by the terminal can be, for example, "campus art festival" and "G star". And the terminal combines the at least one open domain slot information with the third slot information, and the obtained fourth slot information can be, for example, "concert", "third song", "campus art festival" and "G star". The target slot information corresponding to the query statement determined by the terminal may be, for example, "today," "D city," "F university," "concert," "third song," "campus art festival," and "G star.
S205, adjusting the dictionary slot model based on the fourth slot information.
According to some embodiments, when the terminal obtains the fourth slot information, the terminal may adjust the dictionary slot model based on the fourth slot information. The dictionary information in the dictionary slot model can be enriched by adjusting the dictionary slot model by the terminal, and the accuracy of next query statement processing can be improved. The terminal may adjust the dictionary slot model by, for example, adding slot information that is not included in the dictionary slot model in the fourth slot information to the dictionary slot model.
Referring to fig. 8, a flowchart of a query sentence processing method is provided according to an embodiment of the present application. As shown in fig. 8, the method according to the embodiment of the present application may further include the following steps S501 to S503. S501, confirming the intention corresponding to the query statement based on the target slot position information; s502, displaying the intention corresponding to the query statement on a display screen; s503, receiving an operation instruction aiming at the intention, and executing an operation corresponding to the intention.
It is easy to understand that when the terminal obtains the target slot information corresponding to the query sentence, the terminal can confirm the intention corresponding to the query sentence based on the target slot information. When the terminal determines the intention corresponding to the query sentence, the terminal can display the intention corresponding to the query sentence on the display screen. The terminal can also output the intention corresponding to the query statement through voice of the voice assistant. After the terminal displays the intention corresponding to the query statement, the terminal may also receive an operation instruction for the intention corresponding to the query statement, and execute an operation corresponding to the intention corresponding to the query statement. The terminal determines the user intention based on the target slot position information, so that the accuracy of acquiring the user intention can be improved, and the use experience of the user can be improved.
Alternatively, for example, the query sentence acquired by the terminal is "i want to see the video of the third song by G stars on the gardening section of the university F in D today", and the terminal may display the video of the third song by G stars on the gardening section of the university F in D today on the display screen. When the terminal receives a play instruction for the video, the terminal can play the video. When the terminal receives a pause play instruction for the video, the terminal can pause playing the video.
Referring to fig. 9, a flowchart of a query sentence processing method is provided in an embodiment of the present application. As shown in fig. 9, the method of the embodiment of the present application for displaying the intent corresponding to the query sentence on the display screen may include the following steps S601 to S602. S601, when the number of intentions corresponding to the query statement is multiple, acquiring the matching degree of each intention and the target slot position information; s602, displaying a plurality of intents on a display screen according to the order of the matching degree.
It is easy to understand that when the number of intentions corresponding to the query statement is plural, the terminal may acquire the matching degree of each intention and the target slot information. The terminal may display a plurality of intents on the display screen in order of the degree of matching. At this time, an exemplary schematic diagram of the terminal interface may be shown in fig. 10. The matching degree may be determined based on titles in which the target slot information corresponds to a plurality of intents, or may be determined based on play amounts of a plurality of intents.
The embodiment of the application provides a query statement processing method, which is characterized in that at least one first slot information and at least one second slot information corresponding to a query statement are acquired, the second slot information is split based on the at least one first slot information, third slot information except the at least one first slot information in the second slot information can be obtained, at least one open domain slot information and the third slot information can be combined to obtain fourth slot information, and the acquisition accuracy of the open domain slot information can be improved. And secondly, the fourth slot position information and at least one closed domain slot position information are used as target slot position information corresponding to the query statement, so that the accuracy of target slot position acquisition can be improved, and the accuracy of query statement processing can be improved. In addition, the terminal can adjust the dictionary slot position model based on the fourth slot position information, so that the accuracy of the dictionary slot position model in acquiring at least one first slot position information can be improved, and the accuracy of query statement processing can be further improved. Finally, when the terminal obtains the target slot position information based on the first slot position information and the second slot position information, the number of labels required when the terminal directly obtains the target slot position information based on the second slot position information is reduced, and the labeling cost can be reduced.
The following describes in detail the query sentence processing device according to the embodiment of the present application with reference to fig. 11. It should be noted that, the query sentence processing device shown in fig. 11 is used to execute the method of the embodiment shown in fig. 3 to 10 of the present application, and for convenience of explanation, only the portion relevant to the embodiment of the present application is shown, and specific technical details are not disclosed, please refer to the embodiment shown in fig. 3 to 10 of the present application.
Fig. 11 is a schematic diagram of a query term processing apparatus according to an embodiment of the application. The query term processing means 1100 may be implemented as all or part of the user terminal by software, hardware or a combination of both. According to some embodiments, the query sentence processing apparatus 1100 includes a first obtaining unit 1101 and a second obtaining unit 1102, specifically configured to:
A first obtaining unit 1101, configured to obtain at least one first slot information and second slot information corresponding to a query statement, where the at least one first slot information includes at least one open domain slot information and at least one closed domain slot information, and the second slot information is statement information corresponding to the query statement;
the second obtaining unit 1102 is configured to obtain target slot information corresponding to the query statement based on at least one of the first slot information and the second slot information.
According to some embodiments, when the first obtaining unit 1101 is configured to obtain at least one of the first slot information and the second slot information corresponding to the query statement, the first obtaining unit is specifically configured to:
at least one first slot information is extracted using a dictionary slot model, and a second slot information is extracted using a single slot model.
According to some embodiments, the first obtaining unit 1101 is configured to, when extracting the second slot information by using the single slot model, specifically:
Extracting at least one slot information of the query sentence by adopting a preset dictionary in the single slot model;
and merging at least one piece of slot information based on a preset sentence pattern in the single slot model to generate second slot information.
According to some embodiments, the second obtaining unit 1102 is configured to, when obtaining target slot information corresponding to the query statement based on at least one of the first slot information and the second slot information, specifically:
Splitting the second slot information based on the at least one first slot information to obtain third slot information except the at least one first slot information in the second slot information;
combining at least one open domain slot position information with the third slot position information to obtain fourth slot position information;
And taking the fourth slot position information and at least one closed domain slot position information as target slot position information corresponding to the query statement.
According to some embodiments, the second obtaining unit 1102 is configured to split the second slot information based on the at least one first slot information, and when obtaining third slot information except for the at least one first slot information in the second slot information, the second obtaining unit is specifically configured to:
Splitting the second slot position information by adopting the open domain slot position information in sequence to obtain fifth slot position information;
And splitting the fifth slot position information by sequentially adopting the slot position information of each closed domain to obtain the third slot position information.
According to some embodiments, the query sentence processing apparatus 1100 includes a model adjustment unit 1103, configured to, after taking the fourth slot information and the at least one closed domain slot information as target slot information corresponding to the query sentence, further specifically:
based on the fourth slot information, the dictionary slot model is adjusted.
According to some embodiments, the query sentence processing apparatus 1100 includes an intention display unit 1104 for confirming an intention corresponding to a query sentence based on target slot information;
displaying the intention corresponding to the query statement on a display screen;
And receiving an operation instruction aiming at the intention, and executing an operation corresponding to the intention.
According to some embodiments, the intent display unit 1104 is configured to, when displaying an intent corresponding to a query statement on a display screen, specifically:
When the number of intentions corresponding to the query statement is multiple, acquiring the matching degree of each intention and the target slot position information;
and displaying a plurality of intents on the display screen according to the order of the matching degree.
The embodiment of the application provides a query sentence processing device, a first acquisition unit acquires at least one first slot information and at least one second slot information corresponding to a query sentence, wherein the at least one first slot information comprises at least one open domain slot information and at least one closed domain slot information, the second slot information is sentence information corresponding to the query sentence, and a second acquisition unit acquires target slot information corresponding to the query sentence based on the at least one first slot information and the second slot information, so that open domain slot information which is not included in a dictionary lifting slot model can be acquired, the accuracy of acquiring the target slot can be improved, and the accuracy of processing the query sentence can be improved. In addition, when the terminal acquires the target slot information corresponding to the query statement based on at least one first slot information and at least one second slot information, the number of labels required when the target slot information is acquired directly based on the second slot information can be reduced, the labeling cost can be reduced, the cost of processing the query statement can be reduced, and the application range of processing the query statement can be enlarged.
Fig. 12 is a schematic structural diagram of a terminal according to an embodiment of the present application. As shown in fig. 12, the terminal 1200 may include: at least one processor 1201, at least one network interface 1204, a user interface 1203, a memory 1205, at least one communication bus 1202.
Wherein a communication bus 1202 is used to enable connected communications between these components.
The user interface 1203 may include a Display screen (Display) and a GPS, and the optional user interface 1203 may further include a standard wired interface, a wireless interface, among others.
The network interface 1204 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.
Wherein the processor 1201 may include one or more processing cores. The processor 1201 performs various functions of the terminal 1200 and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 1205, and invoking data stored in the memory 1205, using various interfaces and lines connecting the various parts throughout the terminal 1200. Alternatively, the processor 1201 may be implemented in at least one hardware form of digital signal Processing (DIGITAL SIGNAL Processing, DSP), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 1201 may integrate one or a combination of several of a central processing unit (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 1201 and may be implemented by a single chip.
The Memory 1205 may include a random access Memory (Random Access Memory, RAM) or a Read-Only Memory (Read-Only Memory). Optionally, the memory 1205 includes a non-transitory computer readable medium (non-transitory computer-readable storage medium). The memory 1205 may be used to store instructions, programs, code sets, or instruction sets. The memory 1205 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-described various method embodiments, etc.; the storage data area may store data or the like referred to in the above respective method embodiments. The memory 1205 may also optionally be at least one storage device located remotely from the processor 1201. As shown in fig. 12, an operating system, a network communication module, a user interface module, and an application program for query statement processing may be included in the memory 1205 as one type of computer storage medium.
In the terminal 1200 shown in fig. 12, the user interface 1203 is mainly used for providing an input interface for a user, and acquiring data input by the user; and the processor 1201 may be used to invoke an application program for query statement processing stored in the memory 1205, and specifically perform the following operations:
Acquiring at least one first slot information and second slot information corresponding to a query statement, wherein the at least one first slot information comprises at least one open domain slot information and at least one closed domain slot information, and the second slot information is statement information corresponding to the query statement;
And acquiring target slot information corresponding to the query statement based on the at least one first slot information and the second slot information.
According to some embodiments, the processor 1201 is configured to obtain at least one of the first slot information and the second slot information corresponding to the query statement, and specifically configured to perform the following steps:
at least one first slot information is extracted using a dictionary slot model, and a second slot information is extracted using a single slot model.
According to some embodiments, the processor 1201 is configured to extract the second slot information using a single slot model, and in particular is configured to perform the following steps:
Extracting at least one slot information of the query sentence by adopting a preset dictionary in the single slot model;
and merging at least one piece of slot information based on a preset sentence pattern in the single slot model to generate second slot information.
According to some embodiments, the processor 1201 is configured to obtain target slot information corresponding to the query statement based on at least one of the first slot information and the second slot information, and specifically configured to perform the following steps:
Splitting the second slot information based on the at least one first slot information to obtain third slot information except the at least one first slot information in the second slot information;
combining at least one open domain slot position information with the third slot position information to obtain fourth slot position information;
And taking the fourth slot position information and at least one closed domain slot position information as target slot position information corresponding to the query statement.
According to some embodiments, the processor 1201 is configured to split the second slot information based on the at least one first slot information, to obtain third slot information except for the at least one first slot information in the second slot information, and specifically configured to perform the following steps:
Splitting the second slot position information by adopting the open domain slot position information in sequence to obtain fifth slot position information;
And splitting the fifth slot position information by sequentially adopting the slot position information of each closed domain to obtain the third slot position information.
According to some embodiments, after the processor 1201 is configured to use the fourth slot information and the at least one closed domain slot information as the target slot information corresponding to the query statement, the following steps are further specifically performed:
based on the fourth slot information, the dictionary slot model is adjusted.
According to some embodiments, the processor 1201 is configured to further specifically perform the steps of:
confirming the intention corresponding to the query statement based on the target slot position information;
displaying the intention corresponding to the query statement on a display screen;
And receiving an operation instruction aiming at the intention, and executing an operation corresponding to the intention.
According to some embodiments, the processor 1201 is configured to display the intent corresponding to the query statement on the display screen, specifically configured to perform the following steps:
When the number of intentions corresponding to the query statement is multiple, acquiring the matching degree of each intention and the target slot position information;
and displaying a plurality of intents on the display screen according to the order of the matching degree.
The embodiment of the application provides a terminal, which is used for acquiring at least one first slot information and at least one second slot information corresponding to a query statement, wherein the second slot information is statement information corresponding to the query statement, so that the target slot information corresponding to the query statement can be acquired based on at least one open domain slot information, at least one closed domain slot information and the second slot information in the at least one first slot information, the open domain slot information not included in a dictionary lifting slot model can be acquired, the accuracy of acquiring the target slot can be improved, and the accuracy of processing the query statement can be improved. In addition, when the terminal acquires the target slot information corresponding to the query statement based on at least one first slot information and at least one second slot information, the number of labels required when the target slot information is acquired directly based on the second slot information can be reduced, the labeling cost can be reduced, the cost of processing the query statement can be reduced, and the application range of processing the query statement can be enlarged.
The present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above method. The computer-readable storage medium may include, among other things, any type of disk including floppy disks, optical disks, DVDs, CD-ROMs, micro-drives, and magneto-optical disks, ROM, RAM, EPROM, EEPROM, DRAM, VRAM, flash memory devices, magnetic or optical cards, nanosystems (including molecular memory ICs), or any type of media or device suitable for storing instructions and/or data.
Embodiments of the present application also provide a computer program product comprising a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any one of the query statement processing methods described in the method embodiments above.
It will be clear to a person skilled in the art that the solution according to the application can be implemented by means of software and/or hardware. "Unit" and "module" in this specification refer to software and/or hardware capable of performing a particular function, either alone or in combination with other components, such as Field programmable gate arrays (Field-ProgrammaBLE GATE ARRAY, FPGA), integrated circuits (INTEGRATED CIRCUIT, ICs), etc.
It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required for the present application.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, such as the division of the units, merely a logical function division, and there may be additional manners of dividing the actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some service interface, device or unit indirect coupling or communication connection, electrical or otherwise.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory. Based on this understanding, the technical solution of the present application may be embodied essentially or partly in the form of a software product, or all or part of the technical solution, which is stored in a memory, and includes several instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned memory includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Those of ordinary skill in the art will appreciate that all or a portion of the steps in the various methods of the above embodiments may be performed by hardware associated with a program that is stored in a computer readable memory, which may include: flash disk, read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), magnetic disk or optical disk, etc.
The foregoing is merely exemplary embodiments of the present disclosure and is not intended to limit the scope of the present disclosure. That is, equivalent changes and modifications are contemplated by the teachings of this disclosure, which fall within the scope of the present disclosure. Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a scope and spirit of the disclosure being indicated by the claims.
Claims (7)
1. A method for processing a query statement, the method comprising:
Extracting at least one first slot information of a query sentence by adopting a dictionary slot model, and extracting at least one slot information of the query sentence by adopting a preset dictionary in a single slot model;
Combining the at least one slot information based on a preset sentence pattern in the single slot model to generate second slot information, wherein the at least one first slot information comprises at least one open domain slot information and at least one closed domain slot information, and the second slot information is sentence information corresponding to the query sentence;
splitting the second slot position information by adopting each open domain slot position information in sequence to obtain fifth slot position information;
splitting the fifth slot position information by adopting the slot position information of each closed domain in sequence to obtain third slot position information;
Combining the at least one open domain slot position information and the third slot position information to obtain fourth slot position information;
And taking the fourth slot position information and the at least one closed domain slot position information as target slot position information corresponding to the query statement.
2. The method of claim 1, wherein after using the fourth slot information and the at least one closed domain slot information as the target slot information corresponding to the query statement, further comprises:
and adjusting the dictionary slot model based on the fourth slot information.
3. The method according to claim 1 or 2, characterized in that the method further comprises:
confirming the intention corresponding to the query statement based on the target slot position information;
displaying the intention corresponding to the query statement on a display screen;
and receiving an operation instruction aiming at the intention, and executing an operation corresponding to the intention.
4. A method according to claim 3, wherein displaying the intent corresponding to the query statement on a display screen comprises:
When the number of the intentions corresponding to the query statement is multiple, acquiring the matching degree of each intention and the target slot position information;
and displaying the plurality of intents on the display screen according to the order of the matching degree.
5. A query statement processing apparatus, the apparatus comprising:
The first acquisition unit is used for extracting at least one first slot information of the query statement by adopting a dictionary slot model, and extracting at least one slot information of the query statement by adopting a preset dictionary in a single slot model; combining the at least one slot information based on a preset sentence pattern in the single slot model to generate second slot information, wherein the at least one first slot information comprises at least one open domain slot information and at least one closed domain slot information, and the second slot information is sentence information corresponding to the query sentence;
The second acquisition unit is used for splitting the second slot position information by adopting the open domain slot position information in sequence to obtain fifth slot position information; splitting the fifth slot position information by adopting the slot position information of each closed domain in sequence to obtain third slot position information; combining the at least one open domain slot position information and the third slot position information to obtain fourth slot position information; and taking the fourth slot position information and the at least one closed domain slot position information as target slot position information corresponding to the query statement.
6. A terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the method of any of the preceding claims 1-4 when executing the computer program.
7. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method of any of the preceding claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010892529.4A CN112115245B (en) | 2020-08-31 | 2020-08-31 | Query statement processing method, device, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010892529.4A CN112115245B (en) | 2020-08-31 | 2020-08-31 | Query statement processing method, device, terminal and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112115245A CN112115245A (en) | 2020-12-22 |
| CN112115245B true CN112115245B (en) | 2024-06-04 |
Family
ID=73805092
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010892529.4A Active CN112115245B (en) | 2020-08-31 | 2020-08-31 | Query statement processing method, device, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112115245B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114266258B (en) * | 2021-12-30 | 2023-06-23 | 北京百度网讯科技有限公司 | Semantic relation extraction method and device, electronic equipment and storage medium |
| CN118093638A (en) * | 2024-04-28 | 2024-05-28 | 青岛国创智能家电研究院有限公司 | Knowledge graph-based diet question-answering system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1512395A (en) * | 2002-12-27 | 2004-07-14 | 联想(北京)有限公司 | Establishing method for open type natural language |
| CN107450725A (en) * | 2017-07-31 | 2017-12-08 | 科大讯飞股份有限公司 | Man-machine interaction application platform, method and storage medium |
| CN109918682A (en) * | 2019-03-29 | 2019-06-21 | 科大讯飞股份有限公司 | A kind of text marking method and device |
| CN111209396A (en) * | 2019-12-27 | 2020-05-29 | 深圳市优必选科技股份有限公司 | Entity recognition model training method, entity recognition method and related device |
| CN111291157A (en) * | 2020-01-21 | 2020-06-16 | 招商银行股份有限公司 | Response method, response device, terminal and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107291828B (en) * | 2017-05-27 | 2021-06-11 | 北京百度网讯科技有限公司 | Spoken language query analysis method and device based on artificial intelligence and storage medium |
| US10394955B2 (en) * | 2017-12-21 | 2019-08-27 | International Business Machines Corporation | Relation extraction from a corpus using an information retrieval based procedure |
-
2020
- 2020-08-31 CN CN202010892529.4A patent/CN112115245B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1512395A (en) * | 2002-12-27 | 2004-07-14 | 联想(北京)有限公司 | Establishing method for open type natural language |
| CN107450725A (en) * | 2017-07-31 | 2017-12-08 | 科大讯飞股份有限公司 | Man-machine interaction application platform, method and storage medium |
| CN109918682A (en) * | 2019-03-29 | 2019-06-21 | 科大讯飞股份有限公司 | A kind of text marking method and device |
| CN111209396A (en) * | 2019-12-27 | 2020-05-29 | 深圳市优必选科技股份有限公司 | Entity recognition model training method, entity recognition method and related device |
| CN111291157A (en) * | 2020-01-21 | 2020-06-16 | 招商银行股份有限公司 | Response method, response device, terminal and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112115245A (en) | 2020-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11217236B2 (en) | Method and apparatus for extracting information | |
| EP2959476B1 (en) | Recognizing accented speech | |
| US20230308730A1 (en) | Subtitle editing method and apparatus, and electronic device | |
| CN112115245B (en) | Query statement processing method, device, terminal and storage medium | |
| CN107657973B (en) | Text and audio mixed display method and device, terminal equipment and storage medium | |
| US11157959B2 (en) | Multimedia information processing method, apparatus and system, and computer storage medium | |
| CN109979430B (en) | Robot story telling method and device, robot and storage medium | |
| CN109256125B (en) | Off-line voice recognition method and device and storage medium | |
| CN108304154B (en) | Information processing method, device, server and storage medium | |
| CN107766891B (en) | User gender identification method and device, storage medium and electronic equipment | |
| US20170168705A1 (en) | Method and electronic device for adjusting video progress | |
| CN110808065A (en) | Method and device for detecting refrain, electronic equipment and storage medium | |
| CN111107442A (en) | Method and device for acquiring audio and video files, server and storage medium | |
| WO2021179703A1 (en) | Sign language interpretation method and apparatus, computer device, and storage medium | |
| CN112686051A (en) | Semantic recognition model training method, recognition method, electronic device, and storage medium | |
| CN112528266A (en) | Visiting registration method and related device | |
| CN108933968A (en) | A kind of conversion method of message format, device, storage medium and android terminal | |
| CN112259078A (en) | Method and device for training audio recognition model and recognizing abnormal audio | |
| CN117319699A (en) | Live video generation method and device based on intelligent digital human model | |
| US11854422B2 (en) | Method and device for information interaction | |
| CN109948155B (en) | Multi-intention selection method and device and terminal equipment | |
| CN109725798B (en) | Intelligent role switching method and related device | |
| CN110781329A (en) | Image searching method and device, terminal equipment and storage medium | |
| CN116189663A (en) | Training method and device of prosody prediction model, and man-machine interaction method and device | |
| CN112990173B (en) | Reading processing method, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |