CN112417140B - Grammar configuration method, grammar matching method, grammar configuration device and computer equipment - Google Patents
Grammar configuration method, grammar matching method, grammar configuration device and computer equipment Download PDFInfo
- Publication number
- CN112417140B CN112417140B CN202011303704.8A CN202011303704A CN112417140B CN 112417140 B CN112417140 B CN 112417140B CN 202011303704 A CN202011303704 A CN 202011303704A CN 112417140 B CN112417140 B CN 112417140B
- Authority
- CN
- China
- Prior art keywords
- grammar
- list
- target
- candidate
- determining
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/34—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/0485—Scrolling or panning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Machine Translation (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The application provides a grammar configuration method, a grammar matching device and computer equipment, wherein the grammar configuration method comprises the following steps: and responding to the dragging operation by displaying the grammar configuration interface, determining a plurality of target nodes from a plurality of candidate grammar nodes, determining the node sequence among the plurality of target nodes, and generating the grammar in the grammar list based on the plurality of target nodes arranged in the node sequence. Therefore, the grammar nodes can be configured on the grammar configuration interface according to the requirements of the user to generate the grammar meeting the requirements of the user, and the grammar configuration mode is convenient and fast, and meets the personalized configuration requirements of the user.
Description
Technical Field
The present application relates to the field of natural language processing technology in the field of artificial intelligence, and in particular, to a grammar configuration method and apparatus, a grammar matching method and apparatus, a computer device, and a non-transitory computer readable storage medium.
Background
With the rapid development of artificial intelligence, intelligent robots in various application scenes gradually enter people's life. For example, children entertainment robots, educational robots, and the like. In the process of performing voice interaction with the intelligent robot, the intelligent robot needs to perform semantic analysis on the acquired voice.
The intelligent robot performs semantic analysis on the acquired voice, and comprises a plurality of elements, fields, intentions, grammar, word slots and the like. The field contains a plurality of intents, and the intents contain a plurality of grammatical and word slot information. In order for the robot to answer to the expected effect, the background needs to configure the corresponding domain intention and grammar for the desired effect, but the existing grammar configuration is complex and inflexible.
Disclosure of Invention
The present application aims to solve at least one of the technical problems in the related art to some extent.
The application provides a grammar configuration method and a grammar matching method, which are used for configuring grammar nodes in a grammar configuration interface according to the requirements of a user to generate a grammar meeting the requirements of the user.
An embodiment of a first aspect of the present application provides a grammar configuration method, including:
displaying a grammar configuration interface, wherein the grammar configuration interface comprises a plurality of candidate grammar nodes which are preconfigured;
Determining a plurality of target nodes from the plurality of candidate grammar nodes in response to a drag operation, and determining a node order between the plurality of target nodes;
and generating grammars in a grammar list based on the plurality of target nodes arranged in the node order.
According to the grammar configuration method, a grammar configuration interface is displayed, a plurality of target nodes are determined from a plurality of candidate grammar nodes in response to a dragging operation, the node sequence among the plurality of target nodes is determined, and the grammars in a grammar list are generated based on the plurality of target nodes arranged in the node sequence. Therefore, the grammar nodes can be configured on the grammar configuration interface according to the requirements of the user to generate the grammar meeting the requirements of the user, and the grammar configuration mode is convenient to operate and meets the personalized configuration requirements of the user.
An embodiment of a second aspect of the present application provides a grammar matching method, including:
Acquiring grammar in a grammar list; the grammar in the grammar list is configured according to the grammar configuration method;
After the target corpus is obtained, matching the target corpus with each grammar in the grammar list to obtain the semantics of the target corpus.
According to the grammar matching method, the grammar in the grammar list is obtained, and after the target corpus is obtained, the target corpus is matched with each grammar in the grammar list, so that the semantics of the target corpus are obtained. Therefore, when grammar matching is performed in semantic analysis, the grammar matching with the target corpus is determined according to the preconfigured grammar list, and the accuracy of grammar matching is improved.
An embodiment of a third aspect of the present application provides a grammar configuration apparatus, including:
The display module is used for displaying a grammar configuration interface, wherein the grammar configuration interface comprises a plurality of candidate grammar nodes which are configured in advance;
A response module for determining a plurality of target nodes from the plurality of candidate grammar nodes in response to a drag operation, and determining a node order between the plurality of target nodes;
And the generation module is used for generating the grammar in the grammar list based on the plurality of target nodes arranged in the node sequence.
An embodiment of a fourth aspect of the present application provides a grammar matching apparatus, including:
The acquisition module is used for acquiring the grammar in the grammar list; wherein, the grammar in the grammar list is configured by the grammar configuration method as the embodiment of the first aspect;
and the matching module is used for matching the target corpus with each grammar in the grammar list after the target corpus is acquired so as to obtain the semantics of the target corpus.
An embodiment of a fifth aspect of the present application proposes a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, said processor implementing the method of grammar configuration as in the embodiment of the first aspect or implementing the method of grammar matching as in the embodiment of the second aspect when said program is executed.
An embodiment of a sixth aspect of the present application proposes a non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor implements the grammar configuration method of the embodiment of the first aspect described above, or implements the grammar matching method of the embodiment of the second aspect described above.
Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a schematic flow chart of a grammar configuration method according to an embodiment of the present application;
FIG. 2 is an exemplary diagram of a grammar list provided by an embodiment of the present application;
FIG. 3 is a flowchart illustrating another method for grammar configuration according to an embodiment of the present application;
FIG. 4 is a flowchart illustrating another method for grammar configuration according to an embodiment of the present application;
FIG. 5 is an exemplary diagram of a configuration resource package according to an embodiment of the present application;
FIG. 6 is a schematic flow chart of a grammar matching method according to an embodiment of the present application;
FIG. 7 is a schematic diagram of a grammar configuration device according to an embodiment of the present application; and
Fig. 8 is a schematic structural diagram of a grammar matching apparatus according to an embodiment of the present application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present application and should not be construed as limiting the application.
The method and apparatus for grammar configuration, the method and apparatus for grammar matching, the computer device, and the non-transitory computer-readable storage medium of the embodiments of the present application are described below with reference to the accompanying drawings.
Fig. 1 is a flow chart of a grammar configuration method according to an embodiment of the present application.
As shown in fig. 1, the grammar configuration method includes the following steps:
Step 101, displaying a grammar configuration interface, wherein the grammar configuration interface comprises a plurality of candidate grammar nodes which are preconfigured.
According to the method and the device, a plurality of candidate grammar nodes can be preconfigured in the grammar configuration interface according to the service scene requirements.
In one possible scenario, each candidate grammar node is configured with a feature word, wherein the feature word may include at least one of: any character used for occupying space; characterizing characters that match within a specified range; wherein the specified range is determined according to word category and/or semantics; characters to be matched accurately; default characters may be used.
Any character used for the space may be any character located at the position, and the character is not limited to the type of character. The characters matched in the specified range refer to characters in the specified range determined according to word types and/or semantics, the characters contained in the specified range can be preconfigured, and when matching, only any character in the specified range is contained in the target corpus. For example, assuming that the specified range is a pronoun, the characters that match within the specified range may include "you", "me", "he", "your", "we", "they", and so on. As another example, assuming that the specified range is a praying verb, the characters that match within the specified range may include "please", "let", "certain", "don't want", "must", and so on. The character to be matched accurately means that the character at the position is required to be matched with the target corpus accurately. Default character means that the character at that location may be null.
It should be noted that, the feature word of each candidate grammar node may be further configured with an upper limit of the number of repetitions, where the upper limit of the number of repetitions is used to characterize the maximum number of repetitions of the feature word in the grammar.
For example, assuming that the upper limit of the number of repetitions of the feature word a is 3, the maximum number of repetitions of the feature word a in the grammar is 3. That is, the feature word a can appear at most 3 times in grammar.
In the application, each candidate grammar node can be further configured with a word slot for semantic analysis, so as to carry out slot completion during semantic analysis.
For example, assuming that a grammar configuration method is used for a dance robot, a plurality of candidate grammar nodes configured with word slots for semantic parsing may be exemplified as follows:
[ Arbitrary word ] [ pray verb ] [ dance ].
Wherein, the [ arbitrary character ] can be any character for occupying space, the [ pray verb ] can be a matched character in the pray verb, wherein, the pray verb can be a word representing command tone, such as must, not be, must, and the like. For example, a candidate grammar may be "you must dance".
In the embodiment of the application, when the grammar is configured, the grammar configuration interface can be displayed in response to the operation of the operator so as to perform grammar configuration according to the selection of the operator on a plurality of candidate grammar nodes.
As one possible implementation, multiple intents contained in the selected domain may be presented in response to a domain selection operation. Further, in response to the intent selection operation, a grammar configuration interface corresponding to the selected intent is presented.
Step 102, determining a plurality of target nodes from the plurality of candidate grammar nodes in response to the drag operation, and determining a node order between the plurality of target nodes.
In the application, operators can drag a plurality of pre-configured candidate grammar nodes on a grammar configuration interface according to service requirements, and further, in response to the drag operation of the operators, the operators can determine a plurality of target nodes from the plurality of candidate grammar nodes and determine the node sequence among the plurality of target nodes.
As an example, as shown in fig. 2, an operator may perform a drag operation on a plurality of candidate grammar nodes included in the grammar configuration interface, for example, assuming that the candidate grammar nodes are nodes in each rectangular box in fig. 2, in response to the drag operation, a target node determined from the plurality of candidate grammar nodes is shown in rectangular box 1 in fig. 2.
Also for example, a drag operation may be performed on the plurality of target grammar nodes of FIG. 2 to determine a node order between the plurality of target nodes.
Furthermore, in the grammar configuration process, the candidate grammar nodes can be dragged at will so as to adjust the position relation among the candidate grammar nodes in the grammar.
Further, after the grammar is generated, the grammar can be edited again according to the service requirement. For example, the candidate grammar nodes in the grammar are dragged to adjust the position relation among the candidate grammar nodes in the grammar. As another example, new candidate grammar nodes are added at any position of the grammar. For another example, deleting the existing candidate grammar node at any position from the grammar; etc.
Compared with the technical problem that the generalization effect is poor when grammar configuration is caused by the fact that the position of each grammar node in the grammar cannot be adjusted after the position of each grammar node in the grammar is determined in the prior art, the method and the device can also respond to the dragging operation of operators to adjust the positions of the target nodes after determining the target nodes from the candidate grammar nodes so as to meet different business requirements.
Step 103, generating grammar in the grammar list based on the plurality of target nodes arranged in the node order.
The grammar list refers to a list containing a plurality of configured grammars.
In the embodiment of the application, after determining a plurality of target nodes and node sequences among the plurality of target nodes from a plurality of candidate grammar nodes, grammar in a grammar list is generated based on the plurality of target nodes arranged in the node sequences.
As a possible implementation manner, after determining the node sequence between the plurality of target nodes and the plurality of target nodes from the plurality of candidate grammar nodes, the feature words associated with the plurality of target nodes may be arranged in the node sequence to obtain a feature word sequence, and then, the feature word sequence is determined as a grammar in the grammar list.
Continuing with the example in FIG. 2, after determining the target nodes and the node order between the target nodes in rectangular box 1 in FIG. 2, the grammar in the grammar list may be generated based on the plurality of target nodes arranged in the node order as follows:
[ words called photo_prefix ] [ dancing_short verb ] [ stop words_o ] [ photo_mix ]
According to the grammar configuration method, a grammar configuration interface is displayed, a plurality of target nodes are determined from a plurality of candidate grammar nodes in response to a dragging operation, the node sequence among the plurality of target nodes is determined, and the grammars in a grammar list are generated based on the plurality of target nodes arranged in the node sequence. Therefore, the grammar nodes can be configured on the grammar configuration interface according to the requirements of the user to generate the grammar meeting the requirements of the user, and the grammar configuration mode is convenient to operate and meets the personalized configuration requirements of the user.
On the basis of the above embodiment, after the grammar in the grammar list is generated in the above step 103, the grammars in the grammar list may be ordered to configure priorities of the grammars. Fig. 3 is a schematic flow chart of another grammar configuration method according to an embodiment of the present application.
As shown in fig. 3, the grammar configuration method may further include the following steps:
Step 201, a grammar configuration interface is displayed, wherein the grammar configuration interface comprises a plurality of candidate grammar nodes which are preconfigured.
Step 202, in response to the drag operation, determining a plurality of target nodes from the plurality of candidate grammar nodes, and determining a node order between the plurality of target nodes.
Step 203, generating a grammar in the grammar list based on a plurality of target nodes arranged in node order.
In the embodiment of the present application, the implementation process of step 201 to step 203 may refer to the implementation process of step 101 to step 103 in the embodiment, and will not be described herein.
In step 204, the ordering of the grammars in the grammar list is determined in response to a drag operation performed on the grammars in the grammar list.
As one possible implementation, an operator may adjust the ordering of the grammars in the grammar list via a drag operation to determine the ordering of the grammars in the grammar list in response to the operator performing a drag operation on the grammars in the grammar list.
Continuing with the example in fig. 2, the operator may perform a drag operation on the grammar in the grammar list, and, assuming that the drag operation is performed on the grammar with the number 4 in the grammar list in fig. 2, drag the grammar with the number 4 over the grammar with the number 1, and in response to the drag operation on the grammar with the number 4, obtain the ranking of the grammars in the dragged grammar list.
As another possible implementation manner, the operator may perform a deletion operation on each grammar in the grammar list, and after the operator deletes the grammar in the grammar list, in response to the deletion operation performed on the grammar in the grammar list, the order of each grammar in the deleted grammar list may be obtained.
Continuing with the example of fig. 2, the operator may perform a deletion operation on the grammar with the number 4 in the grammar list of fig. 2, and further, obtain the ranking of each grammar in the deleted grammar list.
Step 205, configuring a first priority of each grammar in the grammar list according to the ranking; the first priority is used for determining grammar matched with the target corpus from the grammar list.
The target corpus refers to text information for semantic analysis.
It should be noted that, the priority of each grammar in the grammar list is named as the first priority, so as to distinguish the priority from the subsequent intention and/or the field, and other naming manners may be adopted, which is not limited herein.
In the embodiment of the application, after the ordering of each grammar in the grammar list is determined, the first priority of each grammar in the grammar list can be configured according to the ordering of each grammar in the grammar list.
Alternatively, the first priority of each grammar in the grammar list may be configured according to the order of ordering of each grammar in the grammar list. For example, the top-ranked grammar in the grammar list may be configured with a high priority and the bottom-ranked grammar in the grammar list may be configured with a low priority.
Continuing with the example of fig. 2, assuming that the obtained grammars in the grammar list have a ranking of 1,4, and 3, the grammar with 1 may be configured to have a high priority, the grammar with 4 may be configured to have a medium priority, and the grammar with 3 may be configured to have a low priority according to the ranking of the grammars in the grammar list.
In the embodiment of the application, after the first priority of each grammar in the grammar list is configured, the candidate grammar matched with the target corpus can be determined from the grammar list according to the first priority of each grammar in the grammar list.
For example, after determining a plurality of candidate grammars matching the target corpus from the grammar list according to the first priority of each grammar in the grammar list, further, according to the first priority of the plurality of candidate grammars, the candidate grammar with the highest first priority is used as the grammar matching the target corpus.
In the application, after the first priority of each grammar in the grammar list is configured, the configuration result can be tested to determine whether to adjust the configuration result according to the test result.
In one possible case, the semantics of the target corpus obtained by matching the target corpus with each grammar in the grammar list may be a case of mismatch with the semantics expected by the user, in which case the ordering of the target grammar in the grammar list may be adjusted to update the first priority of the target grammar, or the target grammar may be edited to modify the information of the target grammar. Therefore, the priority and/or information of the target grammar are adjusted in a personalized manner, so that the accuracy of grammar matching is improved.
According to the method and the device, after the target grammar matched with the target corpus is determined from the grammar list according to the first priority of each grammar in the grammar list, the situation that the target grammar obtained by matching is inconsistent with the expected grammar possibly exists, and in this case, the grammar identifier corresponding to the target grammar can be displayed. Where the grammar identification may be used to uniquely represent the target grammar, for example, the grammar identification may be letters, numbers, a combination of letters and numbers, and so forth.
In one possible implementation manner of the embodiment of the present application, after displaying the grammar identifier corresponding to the target grammar, an operator may query the grammar list for the target grammar according to the grammar identifier, and further drag the target grammar corresponding to the grammar identifier in the grammar list, so as to adjust the order of the target grammar in the grammar list in response to the drag operation performed on the target grammar corresponding to the grammar identifier, and reconfigure the first priority of each grammar in the grammar list according to the adjusted order, so as to update the first priority of the target grammar.
Taking the example in fig. 2 as an example, assume that, according to the first priority, the target grammar that matches the target corpus determined from the grammar list is the grammar with the sequence number of 1, however, the grammar with the sequence number of 1 is not expected, and the grammar with the sequence number of 4 is the expected target grammar. In this case, the grammar with the sequence number 1 may be dragged to the position behind the grammar with the sequence number 4 by performing a drag operation on the grammar with the sequence number 1, and then the first priority of each grammar in the grammar list may be updated according to the adjusted sequence. After updating the first priority of each grammar, the priority of the grammar with the sequence number of 4 is higher than the priority of the grammar with the sequence number of 1.
In another possible implementation manner of the embodiment of the present application, after displaying the grammar identifier corresponding to the target grammar, the operator may further query the grammar list for the target grammar according to the grammar identifier, and further, perform a drag operation on each grammar node in the target grammar, so as to adjust the position of each node in the target grammar in response to the drag operation performed on each grammar node in the target grammar, so that the adjusted target grammar conforms to the expected target grammar.
As an example, the target grammar that matches the target corpus determined from the grammar list is the grammar with the sequence number of 1, however, the grammar with the sequence number of 1 is not expected, and a drag operation may be performed on the grammar node with the sequence number of 1 to edit the target grammar in response to the drag operation performed on each grammar node in the grammar with the sequence number of 1, so that the edited target grammar matches the expected target grammar.
In yet another possible implementation manner of the embodiment of the present application, after displaying the grammar identifier corresponding to the target grammar, the operator may query the grammar list for the target grammar according to the grammar identifier, further, may perform a drag operation on the target grammar corresponding to the grammar identifier in the grammar list, update the first priority of the target grammar by adjusting the ordering of the target grammar, and perform the drag operation on each grammar node in the target grammar to edit the target grammar. Therefore, through sequencing the target grammar and executing the dragging operation on each grammar node in the target grammar, the target grammar is edited while the first priority of the target grammar is updated, so that the adjusted target grammar is more in line with the expected result.
In the related art, at least two grammars may be matched in the same document at the same time during grammar configuration, so that grammar competition or conflict exists during grammar matching, and the situation is called grammar competition or grammar conflict. In order to solve the problem of grammar bidding or grammar conflict, the existing grammar configuration method determines a target grammar from a plurality of grammars matched simultaneously by presetting a certain rule. However, the existing grammar configuration method is complex and inflexible.
According to the grammar configuration method, the ordering of the grammars in the grammar list is determined by responding to the dragging operation executed on the grammars in the grammar list; and configuring the first priority of each grammar in the grammar list according to the ranking, so as to determine the grammar matched with the target corpus from the grammar list according to the first priority of each grammar. Therefore, when configuring the grammar, after determining the candidate grammar matched with the target corpus according to the priority of each grammar in the grammar list, only determining the candidate grammar with the highest priority as the grammar matched with the target corpus, thereby avoiding the condition that the grammar is in competition or conflict caused by the simultaneous matching to at least two grammars.
In one possible scenario of the present application, the number of grammar lists may be multiple, each grammar list may be attributed to a different intent, e.g., the intent to which grammar list a is attributed may be shopping, each text list may also be attributed to a different domain, e.g., the domain to which grammar list B is attributed may be education, each text may also be attributed to a different intent and domain simultaneously, e.g., the intent to which text list C is attributed may be ticket purchase, and the domain to which it is attributed may be travel. In this case, the second priority of the intention and/or the field may be configured for the grammar in the grammar list through an editing operation of the intention and/or the field. The above process is described in detail below with reference to fig. 4, and fig. 4 is a schematic flow chart of another grammar configuration method according to an embodiment of the present application.
As shown in fig. 4, the grammar configuration method may further include the following steps:
Step 301, configuring a second priority of the intent and/or domain in response to the editing operation of the intent and/or domain.
The second priority is used for determining grammar matched with the target corpus from candidate grammars of each grammar list.
In one possible scenario, when the number of grammar lists is plural, each grammar list is assigned to a corresponding intent, the second priority of the intent may be configured in response to an operator editing operation of the corresponding intent of the grammar list.
In another possible scenario, when the number of grammar lists is plural, and each grammar list belongs to a corresponding domain, the second priority of the domain may be configured in response to an editing operation of the domain corresponding to the grammar list by the operator.
In yet another possible scenario, when the number of grammar lists is plural, each grammar list is attributed to a corresponding intention and field, the respective second priorities of the intention and field may be configured in response to an editing operation of the operator on the intention and field corresponding to the grammar list.
It should be explained that intelligent robots adapted for different scenarios need to be configured with different intentions and/or fields, e.g. learning type intelligent robots, entertainment type intelligent robots, etc. Therefore, a second priority is required to configure the intention and/or the field according to the use scenario of the robot.
In the method, an operator can edit the intention and/or the domain, and further can configure the second priority of the intention and/or the domain in response to the editing operation of the intention and/or the domain, so that when grammar matching is performed, the grammar which has the highest second priority and matches with the target corpus is determined from candidate grammars of each grammar list according to the second priority of the intention and/or the domain. It can be appreciated that, when the grammars of the semantic parsing are matched, after determining a plurality of candidate grammars matched with the target corpus from the grammar list according to the first priority of each grammar in the grammar list, further, determining the grammar with the highest second priority as the target grammar matched with the target corpus from the candidate grammars of each grammar list according to the second priority of the configured intention and/or field.
Step 302, in response to a first configuration operation, configuring an applicable device range of a resource package; the resource package associates a specified intention and/or a grammar list corresponding to a specified field.
For ease of partitioning, the operation of configuring the applicable device scope of the resource package is named a first configuration operation, and the configuration operation of specifying the intent and/or domain for the resource package is named a second configuration operation. Of course, other naming schemes are possible and are not limited in this disclosure.
In the embodiment of the application, before the applicable device range of the resource package is configured, the intention and/or the field can be designated for the resource package in advance. Specifically, in response to the second configuration operation, an intention and/or a domain is specified for the resource package, so that a grammar list corresponding to the specified intention and/or domain is determined as a grammar list associated with the resource package.
In the embodiment of the application, after determining the grammar list associated with the resource package, the first configuration operation can be responded, and the applicable equipment range of the resource package can be configured according to the appointed intention associated with the resource package and/or the grammar list corresponding to the appointed field.
Step 303, configuring the resource package for each device in the applicable device range.
In the embodiment of the application, after the applicable equipment range of the resource package is determined, the resource package is further configured for each equipment in the range of the using equipment.
As an example, as shown in fig. 5, a grammar list specified by the intention and/or the domain associated with the resource package 1 and the resource package 2 may be acquired, and as shown in fig. 5, the number "+8" corresponding to the resource package 2 indicates that the number of the grammar list specified by the intention and/or the domain associated with the resource package 2 is 8. In fig. 5, a grammar list corresponding to the specified intention and/or the domain can be added to the newly added resource package through the newly added resource. In response to a first configuration operation of an operator, configuring an applicable device scope of the resource package 1 and the resource package 2, as in fig. 5, configuring a grammar list corresponding to an intention and/or a domain associated with the resource package 2 for each device in the applicable device scope.
According to the grammar configuration method, the second priority of the intention and/or the field is configured by responding to the editing operation of the intention and/or the field, and the applicable equipment range of the resource package is configured by responding to the first configuration operation; the resource package is associated with a designated intention and/or a grammar list corresponding to a designated field, and the resource package is configured for each device in the range of the applicable device. Therefore, the resource package is configured based on the actual scene demand, and the resource package is associated with the appointed intention and/or the grammar list corresponding to the appointed field, so that the personalized configuration of each device is realized, the same resource package can be suitable for different devices, and the resource utilization rate is improved.
In practical application, the grammar in the grammar list generated based on the grammar configuration method can be matched with the target corpus to obtain the semantics of the target corpus. The following describes the above process in detail with reference to fig. 6, and fig. 6 is a schematic flow chart of a grammar matching method according to an embodiment of the present application.
As shown in fig. 6, the grammar matching method may include the steps of:
Step 401, acquiring grammar in a grammar list.
In the embodiment of the present application, the grammar in the grammar list is configured according to the grammar configuration method in the above embodiment, and the specific configuration process is not described herein.
As one possible implementation manner, a resource package corresponding to the device may be acquired, and the grammar list may be acquired from the resource package due to the association of the resource package with the specified intent and/or the grammar list corresponding to the specified domain. The device may be a device for acquiring a target corpus, for example, a robot or the like.
Step 402, after obtaining the target corpus, matching the target corpus with each grammar in the grammar list to obtain the semantics of the target corpus.
The target corpus may be text information directly input by the user, or text information obtained after performing speech recognition processing on speech information input by the user in a speech manner.
In the embodiment of the application, after the target corpus is acquired, the target corpus can be matched with each grammar in the acquired grammar list, so that the grammar with the highest matching degree in the grammar list is determined as the target grammar of the target corpus, and the semantics of the target corpus is determined based on the target grammar.
As a possible scenario, the grammars in the grammar list are configured with a first priority, wherein the first priority is used to determine candidate grammars from the grammar list that match the target corpus. And according to the first priority, determining candidate grammars matched with the target corpus from the grammar list. The candidate grammar is the grammar with the highest first priority among the grammars matched with the target corpus in the corresponding grammar list. Further, a target grammar matching the target corpus is determined based on the candidate grammar. Therefore, the grammar matched with the target corpus is determined according to the priority of each grammar in the grammar list, and the problem of grammar bidding or grammar conflict during grammar matching is avoided.
As a possible scenario of an embodiment of the present application, the obtained grammar list may be plural, and each grammar list has a corresponding intention and/or domain, which is configured with a second priority. In this case, when matching the target corpus with each grammar in the plurality of grammar lists, the grammar in each grammar list may be first matched with the target corpus to obtain a plurality of candidate grammars with the highest first priority among the grammars matched with the target corpus in each grammar list, and further, from the candidate grammars in each grammar list, the candidate grammar in the grammar list corresponding to the intention and/or the field with the highest second priority is determined as the grammar matched with the target corpus.
For example, when matching the target corpus with each grammar in the plurality of grammar lists, a parallel matching mode is adopted, that is, the target corpus is matched with each grammar list at the same time.
According to the grammar matching method, the grammar in the grammar list is obtained, and after the target corpus is obtained, the target corpus is matched with each grammar in the grammar list, so that the semantics of the target corpus are obtained. Therefore, when grammar matching is performed in semantic analysis, the grammar matching with the target corpus is determined according to the preconfigured grammar list, and the accuracy of grammar matching is improved.
In order to implement the above embodiment, the present application proposes a grammar configuration apparatus.
Fig. 7 is a schematic structural diagram of a grammar configuration device according to an embodiment of the present application.
As shown in fig. 7, the grammar configuration apparatus 700 may include: presentation module 710, response module 720, and generation module 730.
The display module 710 is configured to display a grammar configuration interface, where the grammar configuration interface includes a plurality of candidate grammar nodes that are preconfigured.
A response module 720 for determining a plurality of target nodes from the plurality of candidate grammar nodes and determining a node order between the plurality of target nodes in response to the drag operation.
A generating module 730, configured to generate a grammar in the grammar list based on the plurality of target nodes arranged in the node order.
As a possible case, the grammar configuring apparatus 700 may further include:
the first determining module is used for responding to the dragging operation executed on the grammar in the grammar list and determining the sequence of each grammar in the grammar list;
the first configuration module is used for configuring the first priority of each grammar in the grammar list according to the sorting; the first priority is used for determining candidate grammars matched with the target corpus from a grammar list.
As another possibility, the number of grammar lists is plural, each grammar list being attributed to a corresponding intention and/or field; the grammar configuration apparatus 700 may further include:
a second configuration module for configuring a second priority of the intention and/or the domain in response to an editing operation of the intention and/or the domain; wherein the second priority is used to determine a target grammar having a highest second priority from among the candidate grammars of the respective grammar lists.
As another possible case, the grammar configuring apparatus 700 may further include:
the third configuration module is used for responding to the first configuration operation and configuring the applicable equipment range of the resource package; the resource package associates a designated intention and/or a grammar list corresponding to a designated field;
and the fourth configuration module is used for configuring resource packages for all devices in the range of the applicable devices.
As another possible case, the grammar configuring apparatus 700 may further include:
a designation module for designating an intention and/or a domain for the resource package in response to the second configuration operation;
And the second determining module is used for determining the grammar list corresponding to the appointed intention and/or the appointed field as the grammar list associated with the resource package.
As another possible case, each of the candidate grammar nodes is configured with a feature word;
wherein the feature words include at least one of the following:
any character used for occupying space;
characterizing characters that match within a specified range; wherein the specified range is determined according to word category and/or semantics;
Characters to be matched accurately;
default characters may be used.
As another possible scenario, the generating module is further configured to:
Arranging the feature words associated with the target nodes in a node sequence to obtain a feature word sequence; and determining the characteristic word sequence as grammar in the grammar list.
As another possible scenario, each candidate grammar node is also configured with word slots for semantic parsing.
As another possible case, the feature word is configured with an upper limit of the number of repetitions;
the upper limit of the repetition number is used for representing the maximum repetition number of the feature word in the grammar.
As another possible scenario, the display module 710 is further configured to:
responsive to a domain selection operation, presenting a plurality of intents contained in the selected domain; and responding to the intention selecting operation, and displaying a grammar configuration interface corresponding to the selected intention.
It should be noted that the foregoing explanation of the embodiment of the grammar configuration method for semantic parsing is also applicable to the grammar configuration device for semantic parsing of this embodiment, and will not be repeated here.
According to the grammar configuration device, a grammar configuration interface is displayed, a plurality of target nodes are determined from a plurality of candidate grammar nodes in response to a dragging operation, the node sequence among the plurality of target nodes is determined, and the grammars in a grammar list are generated based on the plurality of target nodes arranged in the node sequence. Therefore, the grammar nodes can be configured on the grammar configuration interface according to the requirements of the user to generate the grammar meeting the requirements of the user, and the grammar configuration mode is convenient and fast, and meets the personalized configuration requirements of the user.
In order to realize the embodiment, the application provides a grammar matching device.
Fig. 8 is a schematic structural diagram of a grammar matching device for semantic analysis according to an embodiment of the present application.
As shown in fig. 8, the grammar matching apparatus 800 may include: the acquisition module 810 and the matching module 820.
The obtaining module 810 is configured to obtain a grammar in the grammar list; the grammar in the grammar list is configured by the grammar configuration method for semantic analysis.
And the matching module 820 is used for matching the target corpus with each grammar in the grammar list after the target corpus is acquired so as to obtain the semantics of the target corpus.
As a possible scenario, the acquisition module 810 may also be configured to:
Acquiring a resource package corresponding to equipment; the resource package associates a designated intention and/or a grammar list corresponding to a designated field; and acquiring a grammar list from the resource package.
As another possible scenario, the grammar in the grammar list is configured with a first priority, and the matching module 820 may further include:
the first determining unit is used for determining candidate grammars matched with the target corpus from the grammar list according to the first priority; the candidate grammar is the grammar with the highest first priority among the grammars matched with the target corpus in the corresponding grammar list;
And the second determining unit is used for determining a target grammar matched with the target corpus according to the candidate grammar.
As another possibility, the grammar list is a plurality, each grammar list has a corresponding intention and/or field, and the intention and/or field is configured with a second priority; the second determining unit may be further configured to:
And determining the candidate grammar in the grammar list corresponding to the intention and/or the field with the highest second priority from the candidate grammars in each grammar list as a target grammar.
It should be noted that the foregoing explanation of the embodiment of the grammar matching method is also applicable to the grammar matching apparatus of this embodiment, and will not be repeated herein.
According to the grammar matching device, the grammar in the grammar list is obtained, and after the target corpus is obtained, the target corpus is matched with each grammar in the grammar list, so that the semantics of the target corpus are obtained. Therefore, when grammar matching is performed in semantic analysis, the grammar matching with the target corpus is determined according to the preconfigured grammar list, and the accuracy of grammar matching is improved.
In order to implement the above embodiment, the present application further provides a computer device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the grammar configuration method described in the above embodiment or implements the grammar matching method described in the above embodiment when executing the program.
In order to achieve the above embodiments, the present application also proposes a non-transitory computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the grammar configuration method as described in the above embodiments, or implements the grammar matching method as described in the above embodiments.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.
Claims (26)
1. A grammar configuration method, comprising the steps of:
displaying a grammar configuration interface, wherein the grammar configuration interface comprises a plurality of candidate grammar nodes which are preconfigured;
Determining a plurality of target nodes from the plurality of candidate grammar nodes in response to a drag operation, and determining a node order between the plurality of target nodes;
generating a grammar in a grammar list based on the plurality of target nodes arranged in the node order;
after generating the grammar in the grammar list based on the plurality of target nodes arranged in the node sequence, the method further comprises:
Determining the ranking of the grammars in the grammar list in response to drag operations performed on the grammars in the grammar list;
configuring a first priority of each grammar in the grammar list according to the ranking; the first priority is used for determining candidate grammars matched with the target corpus from the grammar list;
The number of the grammar lists is multiple, and each grammar list belongs to the corresponding intention and/or field; the method further comprises the steps of:
Configuring a second priority of the intent and/or domain in response to an editing operation on the intent and/or domain; the second priority is used for determining a target grammar matched with a target corpus from the candidate grammars of each grammar list.
2. The grammar configuration method of claim 1, wherein, after the configuring of the second priority of the intent and/or domain in response to the editing operation on the intent and/or domain, the method further comprises:
Responding to a first configuration operation, and configuring an applicable device range of a resource package; wherein, the resource package associates a designated intention and/or a grammar list corresponding to a designated field;
and configuring the resource package for each device in the range of the applicable device.
3. The grammar configuration method of claim 2, wherein prior to configuring the applicable device scope of the resource package in response to the first configuration operation, further comprising:
designating an intent and/or domain for the resource package in response to a second configuration operation;
and determining the grammar list corresponding to the appointed intention and/or the appointed field as the grammar list associated with the resource package.
4. The grammar allocation method according to any one of claims 1-2, wherein each of the candidate grammar nodes is configured with a feature word;
wherein the feature words include at least one of the following:
any character used for occupying space;
characterizing characters that match within a specified range; wherein the specified range is determined according to word category and/or semantics;
Characters to be matched accurately;
default characters may be used.
5. The grammar configuration method of claim 4, wherein the generating the grammars in the grammar list based on the plurality of target nodes arranged in the node order includes:
arranging the feature words associated with the target nodes in the node sequence to obtain a feature word sequence;
And determining the characteristic word sequence as the grammar in the grammar list.
6. The grammar allocation method of claim 4 wherein each of the candidate grammar nodes is further configured with word slots for semantic parsing.
7. The grammar configuration method of claim 4 wherein the feature word is configured with an upper limit on the number of repetitions;
the upper limit of the repetition number is used for representing the maximum repetition number of the feature word in the grammar.
8. The grammar configuration method of any one of claims 1-2, wherein the presentation grammar configuration interface includes:
Responsive to a domain selection operation, presenting a plurality of intents contained in the selected domain;
And responding to the intention selection operation, and displaying the grammar configuration interface corresponding to the selected intention.
9. The grammar matching method is characterized by comprising the following steps of:
Acquiring grammar in a grammar list; wherein the grammars in the grammar list are configured by the method of any one of claims 1-8;
After the target corpus is obtained, matching the target corpus with each grammar in the grammar list to obtain the semantics of the target corpus.
10. The grammar matching method of claim 9, wherein the obtaining the grammars in the grammar list comprises:
Acquiring a resource package corresponding to equipment; wherein, the resource package associates a designated intention and/or a grammar list corresponding to a designated field;
And acquiring the grammar list from the resource package.
11. The grammar matching method of claim 9, wherein the grammars in the grammar list are configured with a first priority, the matching the target corpus with the grammars in the grammar list comprising:
According to the first priority, determining candidate grammars matched with the target corpus from the grammar list; the candidate grammar is the grammar with the highest first priority among the grammars matched with the target corpus in the corresponding grammar list;
And determining a target grammar matched with the target corpus according to the candidate grammar.
12. The grammar matching method of claim 11, wherein the grammar list is a plurality of, each of the grammar lists having a corresponding intent and/or field configured with a second priority; the determining the target grammar according to the candidate grammar comprises the following steps:
And determining the candidate grammar in the grammar list corresponding to the intention and/or the field with the highest second priority from the candidate grammars in each grammar list as the target grammar.
13. A grammar configuring apparatus, comprising:
The display module is used for displaying a grammar configuration interface, wherein the grammar configuration interface comprises a plurality of candidate grammar nodes which are configured in advance;
A response module for determining a plurality of target nodes from the plurality of candidate grammar nodes in response to a drag operation, and determining a node order between the plurality of target nodes;
The generation module is used for generating grammars in grammar lists based on the target nodes arranged in the node sequence, the number of the grammar lists is multiple, and each grammar list belongs to corresponding intention and/or field;
a first determining module, configured to determine a ranking of the grammars in the grammar list in response to a drag operation performed on the grammars in the grammar list;
The first configuration module is used for configuring the first priority of each grammar in the grammar list according to the sorting; the first priority is used for determining candidate grammars matched with the target corpus from the grammar list;
A second configuration module for configuring a second priority of the intention and/or the domain in response to an editing operation of the intention and/or the domain; the second priority is used for determining a target grammar matched with the target corpus from the candidate grammars of each grammar list.
14. The apparatus of claim 13, wherein the apparatus further comprises:
The third configuration module is used for responding to the first configuration operation and configuring the applicable equipment range of the resource package; wherein, the resource package associates a designated intention and/or a grammar list corresponding to a designated field;
And a fourth configuration module, configured to configure the resource package for each device in the applicable device range.
15. The apparatus of claim 14, wherein the apparatus further comprises:
A designation module for designating an intention and/or a domain for the resource package in response to a second configuration operation;
And the second determining module is used for determining the grammar list corresponding to the appointed intention and/or the appointed field as the grammar list associated with the resource package.
16. The apparatus of any one of claims 13-14, wherein each of the candidate grammar nodes is configured with a feature word;
wherein the feature words include at least one of the following:
any character used for occupying space;
characterizing characters that match within a specified range; wherein the specified range is determined according to word category and/or semantics;
Characters to be matched accurately;
default characters may be used.
17. The apparatus of claim 16, wherein the generating module is further configured to:
Arranging the feature words associated with the target nodes in the node sequence to obtain a feature word sequence; and determining the feature word sequence as the grammar in the grammar list.
18. The apparatus of claim 16, wherein each candidate grammar node is further configured with a word slot for semantic parsing.
19. The grammar configuring apparatus of claim 16, wherein the feature word is configured with an upper limit of repetition times;
the upper limit of the repetition number is used for representing the maximum repetition number of the feature word in the grammar.
20. The apparatus of any one of claims 13-14, wherein the display module is further configured to:
Responsive to a domain selection operation, presenting a plurality of intents contained in the selected domain;
And responding to the intention selection operation, and displaying the grammar configuration interface corresponding to the selected intention.
21. A grammar matching apparatus, comprising:
The acquisition module is used for acquiring the grammar in the grammar list; wherein the grammars in the grammar list are configured by the method of any one of claims 1-8;
and the matching module is used for matching the target corpus with each grammar in the grammar list after the target corpus is acquired so as to obtain the semantics of the target corpus.
22. The apparatus of claim 21, wherein the acquisition module is further configured to:
acquiring a resource package corresponding to equipment, wherein the resource package is associated with a grammar list corresponding to a specified intention and/or a specified field; and acquiring the grammar list from the resource package.
23. The apparatus of claim 21, wherein the grammars in the grammar list are configured with a first priority, the matching module further comprising:
The first determining unit is used for determining candidate grammars matched with the target corpus from the grammar list according to the first priority; the candidate grammar is the grammar with the highest first priority among the grammars matched with the target corpus in the corresponding grammar list;
And the second determining unit is used for determining a target grammar matched with the target corpus according to the candidate grammar.
24. The apparatus of claim 23, wherein the grammar list is a plurality, each of the grammar lists having a corresponding intent and/or scope configured with a second priority; the second determining unit is further configured to:
And determining the candidate grammar in the grammar list corresponding to the intention and/or the field with the highest second priority from the candidate grammars in each grammar list as the target grammar.
25. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the grammar configuration method of any one of claims 1-8 or the grammar matching method of claims 9-12 when the program is executed.
26. A non-transitory computer readable storage medium having stored thereon a computer program, characterized in that the program, when executed by a processor, implements the grammar configuration method according to any one of claims 1-8 or the grammar matching method according to claims 9-12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011303704.8A CN112417140B (en) | 2020-11-19 | 2020-11-19 | Grammar configuration method, grammar matching method, grammar configuration device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011303704.8A CN112417140B (en) | 2020-11-19 | 2020-11-19 | Grammar configuration method, grammar matching method, grammar configuration device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112417140A CN112417140A (en) | 2021-02-26 |
| CN112417140B true CN112417140B (en) | 2024-07-16 |
Family
ID=74773175
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011303704.8A Active CN112417140B (en) | 2020-11-19 | 2020-11-19 | Grammar configuration method, grammar matching method, grammar configuration device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112417140B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114609932B (en) * | 2022-05-10 | 2022-07-29 | 北京橡鹭科技有限公司 | Material putting control method and device and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109271459A (en) * | 2018-09-18 | 2019-01-25 | 四川长虹电器股份有限公司 | Chat robots and its implementation based on Lucene and grammer networks |
| CN109345279A (en) * | 2012-10-12 | 2019-02-15 | 谷歌有限责任公司 | Dynamic content establishment of item |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1306775A1 (en) * | 2001-10-29 | 2003-05-02 | BRITISH TELECOMMUNICATIONS public limited company | Machine translation |
| US10210452B2 (en) * | 2011-09-21 | 2019-02-19 | Qualcomm Incorporated | High level neuromorphic network description apparatus and methods |
| US9070090B2 (en) * | 2012-08-28 | 2015-06-30 | Oracle International Corporation | Scalable string matching as a component for unsupervised learning in semantic meta-model development |
| CN107301129A (en) * | 2017-06-28 | 2017-10-27 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating test case |
| CN109828753A (en) * | 2018-03-26 | 2019-05-31 | 上海聆播信息科技有限公司 | A kind of behavior drives the visualizing editing method and its device of drama document in exploitation |
| CN110543595B (en) * | 2019-08-12 | 2023-07-04 | 南京莱斯信息技术股份有限公司 | In-station searching system and method |
| CN110674259A (en) * | 2019-09-27 | 2020-01-10 | 北京百度网讯科技有限公司 | Intent understanding method and apparatus |
-
2020
- 2020-11-19 CN CN202011303704.8A patent/CN112417140B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109345279A (en) * | 2012-10-12 | 2019-02-15 | 谷歌有限责任公司 | Dynamic content establishment of item |
| CN109271459A (en) * | 2018-09-18 | 2019-01-25 | 四川长虹电器股份有限公司 | Chat robots and its implementation based on Lucene and grammer networks |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112417140A (en) | 2021-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108090177B (en) | Multi-round question-answering system generation method, equipment, medium and multi-round question-answering system | |
| CN111291024B (en) | Data processing method, device, electronic equipment and storage medium | |
| CN105719649B (en) | Audio recognition method and device | |
| CN106548773B (en) | Child user searching method and device based on artificial intelligence | |
| US11036727B2 (en) | Natural language-aided conversational exploration of self-documenting application programming interfaces | |
| CN111145745B (en) | Dialogue flow customization method and device | |
| CN107590216A (en) | Answer preparation method, device and computer equipment | |
| CN109213486A (en) | Method and apparatus for generating customized visualization component | |
| EP1958106A2 (en) | Virtual designer | |
| CN107958059B (en) | Smart question answering method, device, terminal and computer readable storage medium | |
| CN111210816A (en) | Intelligent voice configuration management method and device and electronic equipment | |
| CN108958731A (en) | Application program interface generation method, device, equipment and storage medium | |
| CN112417140B (en) | Grammar configuration method, grammar matching method, grammar configuration device and computer equipment | |
| CN115440223A (en) | Intelligent interaction method, device, robot and computer readable storage medium | |
| CN119537576A (en) | A data analysis method and related system | |
| CN112634407A (en) | Method and device for drawing image | |
| CN112148844B (en) | Robot information reply method and device | |
| CN109753557B (en) | Answer output method, device, equipment and storage medium of question-answering system | |
| CN115129878A (en) | Conversation service execution method, device, storage medium and electronic equipment | |
| CN114416049A (en) | Configuration method and device of service interface combining RPA and AI | |
| CN110286893B (en) | Service generation method, device, equipment, system and storage medium | |
| KR102832319B1 (en) | Apparatus and method for supporting a learning using personalized knowledge concept tree | |
| US20190163810A1 (en) | Search User Interface | |
| CN115544041A (en) | Processing method and device for merging conflict, electronic equipment and storage medium | |
| CN111651560B (en) | Method and apparatus for configuring problems, electronic device, computer readable 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |