CN109656952B - Query processing method and device and electronic equipment - Google Patents
Query processing method and device and electronic equipment Download PDFInfo
- Publication number
- CN109656952B CN109656952B CN201811287487.0A CN201811287487A CN109656952B CN 109656952 B CN109656952 B CN 109656952B CN 201811287487 A CN201811287487 A CN 201811287487A CN 109656952 B CN109656952 B CN 109656952B
- Authority
- CN
- China
- Prior art keywords
- query
- matrix
- knowledge
- implicit
- explicit
- 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
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a query processing method, a query processing device and electronic equipment, wherein the method comprises the following steps: generating an explicit query statement according to a query message input by a user; if the query result cannot be obtained in the knowledge graph according to the explicit query statement, generating an implicit query matrix according to the query message; matching a query result corresponding to the implicit query matrix in a knowledge set, wherein the knowledge set comprises the knowledge graph; and outputting the query result to the user. The method can greatly improve the accuracy and recall rate of the query, and can greatly reduce the cost of intelligent question answering.
Description
Technical Field
The embodiment of the invention relates to computer technologies, and in particular relates to a query processing method and device and electronic equipment.
Background
With the continuous development of science and technology, more and more industries hope to reduce the operation cost and improve the operation efficiency by means of intelligent question answering. For example, intelligent customer service, intelligent consultation, intelligent decision making and the like all rely on intelligent question and answer capability. Therefore, how to continuously improve the intelligent question answering capability is a hot point of research.
In the prior art, intelligent question answering is mainly realized through a matching method based on manual configuration template or natural language understanding. The method for manually configuring the template needs to manually configure answer results for questions in different expression forms. The matching method based on natural language understanding obtains an answer result by performing semantic analysis on the question and inquiring according to an analysis result.
However, none of the prior art methods can simultaneously satisfy the requirements of high accuracy, high recall rate and low cost of intelligent question answering.
Disclosure of Invention
The embodiment of the invention provides a query processing method, a query processing device and electronic equipment, which are used for solving the problem that the requirements of high accuracy, high recall rate and low cost of intelligent question answering cannot be met simultaneously in the prior art.
A first aspect of an embodiment of the present invention provides a query processing method, including:
generating an explicit query statement according to a query message input by a user;
if the query result cannot be obtained in the knowledge graph according to the explicit query statement, generating an implicit query matrix according to the query message;
matching a query result corresponding to the implicit query matrix in a knowledge set, wherein the knowledge set comprises the knowledge graph;
and outputting the query result to the user.
Further, the matching of the query result corresponding to the implicit query matrix in the knowledge set includes:
generating an implicit expression matrix corresponding to the knowledge set according to the knowledge graph included in the knowledge set and data except the knowledge graph included in the knowledge set, wherein the implicit expression matrix is used for representing the knowledge set;
and matching the implicit expression matrix and the implicit query matrix to obtain a query result corresponding to the implicit query matrix.
Further, the matching processing of the implicit expression matrix and the implicit query matrix includes:
inputting the implicit expression matrix and the implicit query matrix into a first model, and performing matching processing on the implicit expression matrix and the implicit query matrix by the first model, wherein the first model is a neural network model based on interaction or an attention mechanism.
Further, the generating an explicit query statement according to a query message input by a user includes:
analyzing the query message input by the user based on preset rule information to obtain the explicit query statement, wherein the rule information is used for representing a rule of mapping the natural query language to the knowledge graph.
Further, the generating an explicit query statement according to a query message input by a user includes:
and inputting the query message input by the user into a second model to obtain the explicit query statement output by the second model.
Further, after generating the explicit query statement according to the query message input by the user, the method further includes:
and querying a database corresponding to the knowledge graph by using the explicit query statement.
Further, before generating an implicit query matrix according to the query message if the query result cannot be obtained in the knowledge graph according to the explicit query statement, the method further includes:
and if the query result is queried in the knowledge graph according to the explicit query statement, taking the query result queried in the knowledge graph as a query result output to a user.
A second aspect of the embodiments of the present invention provides a query processing apparatus, including:
the first generation module is used for generating an explicit query statement according to a query message input by a user;
a second generation module, configured to generate an implicit query matrix according to the query message when a query result cannot be obtained in a knowledge graph according to the explicit query statement;
the matching module is used for matching the query result corresponding to the implicit query matrix in a knowledge set, wherein the knowledge set comprises the knowledge map;
and the output module is used for outputting the query result to the user.
Further, the matching module includes:
a generating unit, configured to generate an implicit expression matrix corresponding to the knowledge set according to the knowledge graph included in the knowledge set and data other than the knowledge graph included in the knowledge set, where the implicit expression matrix is used to characterize the knowledge set;
and the matching unit is used for matching the implicit expression matrix and the implicit query matrix to obtain a query result corresponding to the implicit query matrix.
Further, the matching unit is specifically configured to:
inputting the implicit expression matrix and the implicit query matrix into a first model, and performing matching processing on the implicit expression matrix and the implicit query matrix by the first model, wherein the first model is a neural network model based on interaction or an attention mechanism.
Further, the first generating module includes:
the first analysis unit is used for analyzing the query message input by the user based on preset rule information to obtain the explicit query statement, wherein the rule information is used for representing the rule of mapping the natural query language to the knowledge graph.
Further, the first generating module further includes:
and the second analysis unit is used for inputting the query message input by the user into a second model to obtain the explicit query statement output by the second model.
Further, the method also comprises the following steps:
and the query module is used for querying the database corresponding to the knowledge graph by using the explicit query statement.
Further, the method also comprises the following steps:
and the determining module is used for taking the query result queried in the knowledge graph as the query result output to the user when the query result is queried in the knowledge graph according to the explicit query statement.
A third aspect of embodiments of the present invention provides an electronic device, including:
a memory for storing program instructions;
a processor for calling and executing the program instructions in the memory to perform the method steps of the first aspect.
An implementation of the fourth aspect of the present invention provides a readable storage medium, wherein a computer program is stored in the readable storage medium, and the computer program is configured to execute the method according to the first aspect.
According to the query processing method, the query processing device and the electronic equipment provided by the embodiment of the invention, when the query result cannot be queried in the structured knowledge map, the implicit query matrix can be generated and the query result of the implicit query matrix is matched in the knowledge set. Therefore, the embodiment of the invention can simultaneously meet the requirements of high accuracy, high recall rate and low cost of intelligent question answering.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the following briefly introduces the drawings needed to be used in the description of the embodiments or the prior art, and obviously, the drawings in the following description are some embodiments of the present invention, and those skilled in the art can obtain other drawings according to the drawings without inventive labor.
Fig. 1 is a schematic flow chart of a query processing method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a query processing method according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a query processing method according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a query processing method according to an embodiment of the present invention;
fig. 5 is a block diagram of a first query processing apparatus according to a first embodiment of the present invention;
fig. 6 is a block diagram of a second query processing apparatus according to a second embodiment of the present invention;
fig. 7 is a block diagram of a third embodiment of a query processing apparatus according to the present invention;
fig. 8 is a block diagram of a fourth embodiment of a query processing apparatus according to the present invention;
fig. 9 is a block diagram of a fifth module of the query processing apparatus according to the embodiment of the present invention;
fig. 10 is a block diagram of a sixth embodiment of a query processing apparatus according to an embodiment of the present invention;
fig. 11 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the field of intelligent question answering, a method for manually configuring a template is used, so that the accuracy is high, and the cost is high. Although the matching method based on natural language understanding has the advantage of low cost, the method cannot achieve high accuracy rate when meeting the recall rate, and may not meet the recall rate when meeting the accuracy rate. The recall rate refers to the probability of being able to feed back the query result normally. Therefore, the existing methods cannot meet the requirements of high accuracy, high recall rate and low cost of intelligent question answering.
The scheme provided by the embodiment of the invention aims to solve the problems.
The method of the embodiment of the invention can be applied to intelligent question and answer scenes of various industries. For a particular industry, an industry knowledge set for that industry has been pre-established before intelligent question answering is implemented using the method of embodiments of the present invention. The knowledge set is established based on a preset industry knowledge set, and the structure of the established knowledge set is consistent with that of the knowledge set. Fig. 1 is a schematic structural diagram of an industry knowledge set according to an embodiment of the present invention, as shown in fig. 1, the industry knowledge set is a hierarchical knowledge set, and the industry knowledge set may include, from bottom to top, a knowledge graph layer, a graph epitaxial layer, a rule/decision/process layer, a Frequently Asked Questions (FAQ) layer, and a parameter (para) layer. The knowledge graph layer is a knowledge graph of the structured symbolic description, and all knowledge which can be described by using the structured symbolic description in the industry knowledge can be contained in the knowledge graph layer. Various kinds of knowledge-epitaxies can be built on top of the knowledge-graph, which can be represented by graph-epitaxies, rules/decisions/procedures, FAQ, and knowledge para layers. The map epitaxial layer may include an entity-associated picture, entity-associated comment information, entity-associated service information, and the like. And the rule/decision/process layer above the map epitaxial layer can complete the reasoning calculation of industry knowledge. The FAQ layer above the rule/decision/process layer may express industry knowledge in the form of Key-Value (KV for short). At the knowledge para layer above the FAQ layer, industry knowledge can be expressed through text passages.
The industry knowledge set related by the embodiment of the invention expresses industry knowledge by hierarchical knowledge and forms a knowledge set taking a knowledge map as a core. Namely, the expression modes of the knowledge graph are rich and the rules/decisions/processes are enhanced, and the expression capacities of FAQ and knowledge para are utilized to fuse the signed knowledge expression and the non-signed knowledge expression. Accordingly, the knowledge set on which embodiments of the present invention are based also has the above features.
Illustratively, for a conventional knowledge para paragraph, which is applied to intelligent applications, it represents a knowledge word embedding (word embedding) vector in the form of N (N is an integer greater than 0) dimension. The labeled form after the intellectual understanding of the knowledge-graph is combined is a knowledge vector of dimension N + M (M is an integer greater than 0). Wherein N is the original word embedding, and M is the knowledge embedding of the knowledge map. The N + M-dimensional vector can be learned by knowledge composed of a multilayer neural network in a specific application process to form an expression vector R fusing characters and knowledge.
The following aspects of embodiments of the invention are performed based on the aforementioned set of industry knowledge sets.
Fig. 2 is a schematic flowchart of a query processing method according to an embodiment of the present invention, where an execution subject of the method may be an electronic device with processing capability. As shown in fig. 2, the method includes:
s201, generating an explicit query statement according to a query message input by a user.
Optionally, in a specific industry, when a user needs to query industry knowledge, the user may first input a query message, where the query message may be a voice message or a text message, and this is not specifically limited in the embodiment of the present invention.
Further, after receiving a query message input by a user, an explicit query statement may be generated from the query message.
Optionally, the explicit query statement may be, for example, a Gremlin statement or a lambda expression.
The Gremlin is a graph traversal language, and is specifically a functional data stream source, so that a user can represent traversal or query of a complex attribute graph in a simple manner. Each Gremlin traversal consists of a series of steps, each of which performs an atomic operation on the data stream.
The lambda expression is an anonymous function, that is, a function without a function name, and may specifically include a statement lambda and an expression lambda.
And S202, if the query result cannot be obtained in the knowledge graph according to the explicit query statement, generating an implicit query matrix according to the query message.
As shown in FIG. 1 above, in the set of industry knowledge sets upon which embodiments of the invention are based, a knowledge graph is a low level of basis. After generating an explicit query statement from a user's query message, a knowledge graph is first queried using the explicit query statement. In the specific implementation process, the knowledge graph can be stored in a graph form of S-P-O triples, S-S association relations and S-S concept upper and lower relations. Accordingly, knowledge graphs may be queried using the explicit query statements described above, based on graph retrieval and/or computational inference engines, and the like.
In an alternative embodiment, the knowledge graph may be stored in a database, and then the explicit query statement may be used to query the database corresponding to the knowledge graph.
The industry knowledge represented by the knowledge graph belongs to an explicit expression mode, and if a query result can be queried based on the explicit expression mode, the accuracy of the query result is necessarily high. Therefore, as an alternative implementation, if the query result can be obtained in the knowledge graph, the query result queried in the knowledge graph can be directly used as the query result output to the user, and subsequent processing procedures are not performed any more.
In this step, if the query result cannot be obtained in the knowledge graph according to the explicit query statement, an implicit query matrix may be generated according to the query message.
The implicit query matrix is a matrix that expresses query statements, and since an explicit query statement can be regarded as an explicit query statement, the query statement expressed in the matrix can be regarded as an implicit expression form, that is, the implicit query matrix can be referred to as the implicit query matrix.
In an optional manner, the implicit query matrix may be obtained by performing query knowledge analysis on a query message input by a user.
In another alternative, the implicit query matrix may be obtained by performing query-embedding (query-embedding) on a query message input by a user.
And S203, matching the query result corresponding to the implicit query matrix in a knowledge set, wherein the knowledge set comprises the knowledge map.
The knowledge set is an industry knowledge set having the structure shown in fig. 1, and the knowledge set includes relatively complete knowledge of an industry, that is, the knowledge set includes, in addition to the structured knowledge represented by the knowledge graph, knowledge in other representation forms such as own text and picture, and the knowledge represented by these multiple representation forms jointly constitutes a knowledge set of an industry. Therefore, the query result corresponding to the implicit query matrix is matched in the knowledge set, and the query accuracy and recall rate can be greatly improved.
And S204, outputting the query result to the user.
Alternatively, the query results may be output to the user in a manner consistent with the manner in which the user entered. For example, if the user inputs a voice message, the query result may be played to the user by voice.
In the embodiment, when the query result cannot be queried in the structured knowledge map, the implicit query matrix can be generated and the query result of the implicit query matrix is matched in the knowledge set, and the knowledge set contains complete knowledge in the industry, so that the query is performed based on the knowledge set, the query accuracy and recall rate can be greatly improved, and meanwhile, the query can be automatically completed based on the pre-constructed knowledge set, so that the intelligent question and answer cost can be greatly reduced. Therefore, the embodiment of the invention can simultaneously meet the requirements of high accuracy, high recall rate and low cost of intelligent question answering.
On the basis of the above embodiment, the present embodiment relates to a process of matching the query result corresponding to the implicit query matrix in the knowledge set.
Fig. 3 is a schematic flowchart of a query processing method according to an embodiment of the present invention, and as shown in fig. 3, an optional implementation manner of the step S203 includes:
and S301, generating an implicit expression matrix corresponding to the knowledge set according to the knowledge map included in the knowledge set and data except the knowledge map included in the knowledge set, wherein the implicit expression matrix is used for representing the knowledge set.
The data other than the aforementioned intellectual graph means any one or more layers of intellectual representation other than the aforementioned intellectual graph in fig. 1. In a specific implementation process, for a specific industry, the industry knowledge set may be represented by using all layers shown in fig. 1, or may also be represented by selecting a part of layers in the knowledge graph and the rest of layers, which is not specifically limited in the embodiment of the present invention.
In an alternative embodiment, the knowledge graph and data outside the knowledge graph can be subjected to joint representation learning, so that an implicit expression matrix of the knowledge set is obtained. Through knowledge expressed by the implicit expression matrix, the semantic expression capability of data can be greatly optimized.
S302, matching the implicit expression matrix and the implicit query matrix to obtain a query result corresponding to the implicit query matrix.
In an alternative embodiment, the implicit expression matrix and the implicit query matrix may be input into a first model, and the first model performs matching processing on the implicit expression matrix and the implicit query matrix, where the first model is a neural network model based on interaction or a neural network model based on attention mechanism.
Optionally, the first model may be a neural network model.
Optionally, the first model may perform neural network level matching on an implicit expression matrix optimized through representation learning and an implicit query matrix. The first model may be an interaction-based neural network model (KB-aware interconnection net) or an Attention-based neural network model (KB-aware attachment net).
The neural network model based on the interaction uses a multi-stage matching method, in each stage, a part of each matrix to be matched is used for matching, and then the matching of the next stage is carried out based on the matching result of the stage.
When the attention mechanism-based neural network model is matched, different key segments in two matrixes to be matched are matched respectively, and the key segment can refer to one part of the matrixes.
On the basis of the above embodiments, the present embodiment relates to a process of generating an explicit query statement.
Fig. 4 is a schematic flowchart of a query processing method according to an embodiment of the present invention, and as shown in fig. 4, an optional implementation manner of the step S201 includes:
s401, analyzing the query message input by the user based on the preset rule information.
S402, obtaining the explicit query statement.
The rule information is used for representing rules of mapping the natural query language to the knowledge graph.
The natural query language may refer to query information expressed by a user using a natural language. Such as a question spoken or written by the user, etc.
Illustratively, the user speaks the statement "how big Zhang three this year," i.e., in a natural query language.
Alternatively, the rule information may be generated based on mining of large-scale user behavior or own user behavior data. Illustratively, for different expression forms used by massive user queries on the same problem, rule information corresponding to the problem is mined.
Furthermore, in this embodiment, based on the rule information, the query message input by the user can be directly parsed into a formalized query statement.
The rule information is obtained based on an automatic mining process, and any manual configuration action is not needed.
In another embodiment, another optional implementation manner of the step S201 includes:
and inputting the query message input by the user into a second model to obtain the explicit query statement output by the second model.
Optionally, the second model may be a neural network model.
Optionally, the second model may be trained in advance, so that the second model has the capability of parsing natural language into explicit query statements. Furthermore, in this embodiment, the explicit query statement corresponding to the query message can be directly obtained through the second model.
In the embodiment, the conversion from the natural language to the explicit query statement can be completed only through the second model without depending on any rule, so that the formalized analysis can be completed without being based on the rule.
Fig. 5 is a block diagram of a first embodiment of a query processing apparatus according to the present invention, and as shown in fig. 5, the apparatus includes:
a first generating module 501, configured to generate an explicit query statement according to a query message input by a user.
A second generating module 502, configured to generate an implicit query matrix according to the query message when a query result cannot be obtained in a knowledge graph according to the explicit query statement.
A matching module 503, configured to match a query result corresponding to the implicit query matrix in a knowledge set, where the knowledge set includes the knowledge graph.
An output module 504, configured to output the query result to a user.
Fig. 6 is a block diagram of a second embodiment of the query processing apparatus according to the present invention, and as shown in fig. 6, the matching module 503 includes:
a generating unit 5031, configured to generate an implicit expression matrix corresponding to the knowledge set according to the knowledge graph included in the knowledge set and data other than the knowledge graph included in the knowledge set, where the implicit expression matrix is used to characterize the knowledge set.
A matching unit 5032, configured to perform matching processing on the implicit expression matrix and the implicit query matrix to obtain a query result corresponding to the implicit query matrix.
In another embodiment, the matching unit 5032 is specifically configured to:
inputting the implicit expression matrix and the implicit query matrix into a first model, and performing matching processing on the implicit expression matrix and the implicit query matrix by the first model, wherein the first model is a neural network model based on interaction or an attention mechanism.
Fig. 7 is a block diagram of a third embodiment of a query processing apparatus according to the present invention, and as shown in fig. 7, a first generating module 501 includes:
the first parsing unit 5011 is configured to parse a query message input by a user based on preset rule information to obtain the explicit query statement, where the rule information is used to represent a rule that a natural query language is mapped to a knowledge graph.
Fig. 8 is a block diagram of a fourth embodiment of a query processing apparatus according to the present invention, and as shown in fig. 8, the first generating module 501 further includes:
the second parsing unit 5012 is configured to input the query message input by the user into a second model, so as to obtain the explicit query statement output by the second model.
Fig. 9 is a block diagram of a fifth embodiment of a query processing apparatus according to an embodiment of the present invention, and as shown in fig. 9, the apparatus further includes:
and the query module 505 is configured to query the database corresponding to the knowledge graph by using the explicit query statement.
Fig. 10 is a block diagram of a sixth embodiment of a query processing apparatus according to an embodiment of the present invention, and as shown in fig. 10, the apparatus further includes:
a determining module 506, configured to, when a query result is queried in the knowledge graph according to the explicit query statement, take the query result queried in the knowledge graph as a query result output to the user.
Fig. 11 is a block diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 11, the electronic device includes:
a memory 1101 for storing program instructions.
The processor 1102 is configured to call and execute the program instructions in the memory 1101 to perform the method steps described in the above method implementation.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A query processing method, comprising:
generating an explicit query statement according to a query message input by a user;
if the query result cannot be obtained in the knowledge graph according to the explicit query statement, generating an implicit query matrix according to the query message, wherein the implicit query matrix is a matrix expression form of the explicit query statement corresponding to the query message;
matching a query result corresponding to the implicit query matrix in a knowledge set, wherein the knowledge set comprises the knowledge map and is established based on a preset hierarchical industry knowledge set;
and outputting the query result to the user.
2. The method of claim 1, wherein matching the query result corresponding to the implicit query matrix in the knowledge set comprises:
generating an implicit expression matrix corresponding to the knowledge set according to the knowledge graph included in the knowledge set and data except the knowledge graph included in the knowledge set, wherein the implicit expression matrix is used for representing the knowledge set;
and matching the implicit expression matrix and the implicit query matrix to obtain a query result corresponding to the implicit query matrix.
3. The method of claim 2, wherein the matching the implicit expression matrix and the implicit query matrix comprises:
and inputting the implicit expression matrix and the implicit query matrix into a first neural network model, and performing matching processing on the implicit expression matrix and the implicit query matrix by the first neural network model, wherein the first neural network model is a neural network model based on interaction or an attention mechanism.
4. The method of any one of claims 1-3, wherein generating an explicit query statement from a user-entered query message comprises:
analyzing the query message input by the user based on preset rule information to obtain the explicit query statement, wherein the rule information is used for representing a rule of mapping the natural query language to the knowledge graph.
5. The method of any one of claims 1-3, wherein generating an explicit query statement from a user-entered query message comprises:
inputting the query message input by the user into a second neural network model to obtain the explicit query statement output by the second neural network model.
6. The method according to any one of claims 1-3, wherein after generating the explicit query statement according to the query message input by the user, the method further comprises:
and querying a database corresponding to the knowledge graph by using the explicit query statement.
7. The method according to any one of claims 1-3, wherein after generating the explicit query statement according to the query message input by the user, the method further comprises:
and if the query result is queried in the knowledge graph according to the explicit query statement, taking the query result queried in the knowledge graph as a query result output to a user.
8. A query processing apparatus, comprising:
the first generation module is used for generating an explicit query statement according to a query message input by a user;
a second generation module, configured to generate an implicit query matrix according to the query message when a query result cannot be obtained in a knowledge graph according to the explicit query statement, where the implicit query matrix is a matrix expression form of the explicit query statement corresponding to the query message;
the matching module is used for matching a query result corresponding to the implicit query matrix in a knowledge set, the knowledge set comprises the knowledge map, and the knowledge set is established based on a preset hierarchical industry knowledge set;
and the output module is used for outputting the query result to the user.
9. An electronic device, comprising:
a memory for storing program instructions;
a processor for invoking and executing program instructions in said memory for performing the method steps of any of claims 1-7.
10. A readable storage medium, characterized in that a computer program is stored in the readable storage medium for performing the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811287487.0A CN109656952B (en) | 2018-10-31 | 2018-10-31 | Query processing method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811287487.0A CN109656952B (en) | 2018-10-31 | 2018-10-31 | Query processing method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109656952A CN109656952A (en) | 2019-04-19 |
| CN109656952B true CN109656952B (en) | 2021-04-13 |
Family
ID=66110616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811287487.0A Active CN109656952B (en) | 2018-10-31 | 2018-10-31 | Query processing method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109656952B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110390005A (en) * | 2019-07-23 | 2019-10-29 | 北京香侬慧语科技有限责任公司 | A kind of data processing method and device |
| WO2021212683A1 (en) * | 2020-04-24 | 2021-10-28 | 平安国际智慧城市科技股份有限公司 | Law knowledge map-based query method and apparatus, and electronic device and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101093559A (en) * | 2007-06-12 | 2007-12-26 | 北京科技大学 | Method for constructing expert system based on knowledge discovery |
| US7587377B2 (en) * | 2005-11-07 | 2009-09-08 | Tom Yitao Ren | Method of scoring and automatically qualifying search results based on a pre-defined scoring matrix relating to a knowledge domain of third-parties invoking a rule construction tool to construct scoring rules to answers for questions within the knowledge domain |
| CN104820694A (en) * | 2015-04-28 | 2015-08-05 | 中国科学院自动化研究所 | Automatic Q&A method and system based on multi-knowledge base and integral linear programming ILP |
| CN107451276A (en) * | 2017-08-05 | 2017-12-08 | 龙飞 | A kind of intelligent self-service guide system and its method based on deep learning |
| CN107895037A (en) * | 2017-11-28 | 2018-04-10 | 北京百度网讯科技有限公司 | A kind of question and answer data processing method, device, equipment and computer-readable medium |
-
2018
- 2018-10-31 CN CN201811287487.0A patent/CN109656952B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7587377B2 (en) * | 2005-11-07 | 2009-09-08 | Tom Yitao Ren | Method of scoring and automatically qualifying search results based on a pre-defined scoring matrix relating to a knowledge domain of third-parties invoking a rule construction tool to construct scoring rules to answers for questions within the knowledge domain |
| CN101093559A (en) * | 2007-06-12 | 2007-12-26 | 北京科技大学 | Method for constructing expert system based on knowledge discovery |
| CN104820694A (en) * | 2015-04-28 | 2015-08-05 | 中国科学院自动化研究所 | Automatic Q&A method and system based on multi-knowledge base and integral linear programming ILP |
| CN107451276A (en) * | 2017-08-05 | 2017-12-08 | 龙飞 | A kind of intelligent self-service guide system and its method based on deep learning |
| CN107895037A (en) * | 2017-11-28 | 2018-04-10 | 北京百度网讯科技有限公司 | A kind of question and answer data processing method, device, equipment and computer-readable medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109656952A (en) | 2019-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109284363B (en) | Question answering method and device, electronic equipment and storage medium | |
| US11599714B2 (en) | Methods and systems for modeling complex taxonomies with natural language understanding | |
| US8078647B2 (en) | Ontology data import/export method and apparatus | |
| TW201935273A (en) | A statement user intention identification method and device | |
| CN109325040B (en) | FAQ question-answer library generalization method, device and equipment | |
| CN105706092B (en) | The method and system of four values simulation | |
| CN110597992A (en) | Semantic reasoning method and device based on knowledge graph and electronic equipment | |
| US20150066476A1 (en) | Methods and Systems of Four Valued Analogical Transformation Operators Used in Natural Language Processing and Other Applications | |
| US11461317B2 (en) | Method, apparatus, system, device, and storage medium for answering knowledge questions | |
| CN109656952B (en) | Query processing method and device and electronic equipment | |
| CN114564595A (en) | Knowledge graph updating method and device and electronic equipment | |
| CN111831624A (en) | Data table creating method and device, computer equipment and storage medium | |
| CN117972038A (en) | Intelligent question-answering method, device and computer readable medium | |
| CN117667973A (en) | Data query method, device, electronic equipment and storage medium | |
| CN117290478A (en) | Knowledge graph question-answering method, device, equipment and storage medium | |
| CN114579605B (en) | Table question-answer data processing method, electronic equipment and computer storage medium | |
| CN114756655A (en) | Data query method, device, equipment and storage medium | |
| CN110019709B (en) | Automatic question and answer method for robot and automatic question and answer system for robot | |
| CN111858881A (en) | Mass data question-answering system design method, system and electronic equipment | |
| CN116737964B (en) | Artificial intelligence brain system | |
| CN115455036B (en) | Processing method, device, equipment and medium of joint statement | |
| CN117235236B (en) | Dialogue method, dialogue device, computer equipment and storage medium | |
| CN117493372A (en) | SQL sentence generation method and device based on relational awareness | |
| CN116881398A (en) | Method and device for improving information quality generated by large model | |
| CN116069911A (en) | Intelligent question-answering method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |