CN112231445A - Searching method, device, equipment and storage medium combining RPA and AI - Google Patents
Searching method, device, equipment and storage medium combining RPA and AI Download PDFInfo
- Publication number
- CN112231445A CN112231445A CN202011126674.8A CN202011126674A CN112231445A CN 112231445 A CN112231445 A CN 112231445A CN 202011126674 A CN202011126674 A CN 202011126674A CN 112231445 A CN112231445 A CN 112231445A
- Authority
- CN
- China
- Prior art keywords
- entity
- condition
- entities
- search
- searching
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000005516 engineering process Methods 0.000 claims abstract description 19
- 238000003058 natural language processing Methods 0.000 claims description 18
- 230000011218 segmentation Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 7
- 208000032839 leukemia Diseases 0.000 description 26
- 238000013473 artificial intelligence Methods 0.000 description 24
- 238000013461 design Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 11
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000012217 deletion Methods 0.000 description 4
- 230000037430 deletion Effects 0.000 description 4
- 239000003607 modifier Substances 0.000 description 4
- 239000000470 constituent Substances 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000004801 process automation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Artificial Intelligence (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure provides a searching method, a device, equipment and a storage medium combining RPA and AI, relating to the field of intelligent searching in RPA and AI. The searching method combining the RPA and the AI provided by the embodiment of the disclosure comprises the steps of performing semantic analysis on received problem information by adopting an NLP technology to obtain a first entity and a condition; according to the first entity and the condition, searching a second entity meeting the condition from the knowledge graph; wherein, the knowledge map comprises: the system comprises a first entity and a second entity, wherein the first entity points to at least one second entity, and the second entities are linked through a conditional link; and feeding back the second entity as an answer to the user side. Therefore, a plurality of second entities in the knowledge graph can be filtered according to conditions set in the questions, answers matched with the questions are obtained, and accuracy of search results is improved.
Description
Technical Field
The present disclosure relates to the field of intelligent search technologies, and in particular, to a method, an apparatus, a device, and a storage medium for searching in combination with RPA and AI.
Background
Robot Process Automation (RPA) is a Process task automatically executed according to rules by simulating human operations on a computer through specific robot software.
Artificial Intelligence (AI) is a new technology science for researching and developing theories, methods, techniques and application systems for simulating, extending and expanding human Intelligence. Research in the field of artificial intelligence includes robotics, language recognition, image recognition, natural language processing, and expert systems, among others.
The knowledge graph is a tool for semantic search proposed by google in 2012, can express an objective world by using a mesh structure, and the basic constituent units of the knowledge graph are entities, relations and attributes.
Knowledge maps in the prior art generally describe the relationship between entities through simple relationship features, and then find answer entities corresponding to problem entities based on the relationship features during searching.
However, the search results obtained by the search in this way are wide, the positioning accuracy of the answers is not sufficient, the answers cannot be applied in a scene with multi-condition search, and the matching degree of the search results is poor.
Disclosure of Invention
The disclosure provides a searching method, a searching device and a searching storage medium which combine RPA and AI, and can filter a plurality of second entities in a knowledge graph according to conditions set in a question to obtain answers which are more matched with the question, so that the accuracy of a searching result is improved.
In a first aspect, the present disclosure provides a search method combining RPA and AI, including:
performing semantic analysis on the received problem information by adopting an NLP technology to obtain a first entity and a condition;
according to the first entity and the condition, searching a second entity meeting the condition from a knowledge graph; wherein, the knowledge-graph comprises: a first entity and a second entity, wherein the first entity points to at least one of the second entities, and the second entities are linked through a conditional link;
and feeding back the second entity as an answer to the user side.
In one possible design, the performing semantic analysis on the received problem information by using NLP technology to obtain a first entity and a condition includes:
decomposing the question information to obtain a word segmentation sequence;
extracting a first entity and at least one condition according to the part of speech and the semantics of each participle in the participle sequence; wherein the conditions are used to modify the first entity.
In one possible design, the condition is set to be unlimited when a participle for modifying the first entity is not extracted according to the part of speech and the semantics of each participle in the participle sequence.
In one possible design, the searching a second entity meeting the condition from a knowledge-graph according to the first entity and the condition includes:
locating a location of the first entity from the knowledge-graph;
traversing all connected search paths by taking the first entity as an initial node according to the condition; wherein the search path is formed by linking the first entity, the second entity and a conditional link;
and searching the second entity at the end position of the search path.
In one possible design, the feeding back the second entity as an answer to the user side includes:
and feeding back all the second entities positioned at the end positions of the search paths as answers to the user side.
In one possible design, before the searching for the second entity meeting the condition from the knowledge-graph according to the first entity and the condition, the method further includes:
determining the first entity and the second entity according to business and/or field requirements;
constructing a knowledge graph according to the orientation relation between the first entity and the second entity and the conditional link between the second entities; wherein each link between the second entities corresponds to a condition.
In a second aspect, the present disclosure also provides a search apparatus combining RPA and AI, including:
the analysis module is used for performing semantic analysis on the received problem information by adopting an NLP technology to obtain a first entity and a condition;
the searching module is used for searching a second entity meeting the condition from the knowledge graph according to the first entity and the condition; wherein, the knowledge-graph comprises: a first entity and a second entity, wherein the first entity points to at least one of the second entities, and the second entities are linked through a conditional link;
and the feedback module is used for feeding back the second entity serving as an answer to the user side.
In one possible design, the analysis module is specifically configured to:
decomposing the question information to obtain a word segmentation sequence;
extracting a first entity and at least one condition according to the part of speech and the semantics of each participle in the participle sequence; wherein the conditions are used to modify the first entity.
In one possible design, the analysis module is specifically configured to:
and when the participles used for modifying the first entity are not extracted according to the part of speech and the semantics of each participle in the participle sequence, setting the condition as unlimited.
In one possible design, the search module is specifically configured to:
locating a location of the first entity from the knowledge-graph;
traversing all connected search paths by taking the first entity as an initial node according to the condition; wherein the search path is formed by linking the first entity, the second entity and a conditional link;
and searching the second entity at the end position of the search path.
In one possible design, the feedback module is specifically configured to:
and feeding back all the second entities positioned at the end positions of the search paths as answers to the user side.
In one possible design, further comprising: a map building module to:
determining the first entity and the second entity according to business and/or field requirements;
constructing a knowledge graph according to the orientation relation between the first entity and the second entity and the conditional link between the second entities; wherein each link between the second entities corresponds to a condition.
In a third aspect, the present disclosure also provides an electronic device, including:
a processor; and the number of the first and second groups,
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform any one of the first aspect search methods in conjunction with RPA and AI via execution of the executable instructions.
In a fourth aspect, the disclosed embodiments also provide a storage medium, on which a computer program is stored, where the program, when executed by a processor, implements any one of the search methods in the first aspect, which combines RPA and AI.
The disclosure provides a searching method, a device, equipment and a storage medium combining RPA and AI, which are used for performing semantic analysis on received problem information by adopting an NLP technology to obtain a first entity and a condition; according to the first entity and the condition, searching a second entity meeting the condition from a knowledge graph; wherein, the knowledge-graph comprises: a first entity and a second entity, wherein the first entity points to at least one of the second entities, and the second entities are linked through a conditional link; and feeding back the second entity as an answer to the user side. Therefore, a plurality of second entities in the knowledge graph can be filtered according to conditions set in the questions, answers matched with the questions are obtained, and accuracy of search results is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present disclosure, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
Fig. 1 is a diagram illustrating an application scenario of a search method combining RPA and AI according to an example embodiment of the present disclosure;
FIG. 2 is a flow diagram illustrating a search method combining RPA and AI according to an example embodiment of the present disclosure;
FIG. 3 is a flow diagram illustrating a search method combining RPA and AI according to another example embodiment of the present disclosure;
FIG. 4 is a schematic structural diagram of a search apparatus combining an RPA and an AI according to an example embodiment of the present disclosure;
FIG. 5 is a schematic structural diagram of a search apparatus combining an RPA and an AI according to another example embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of an electronic device shown in the present disclosure according to an example embodiment.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are some, but not all embodiments of the present disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present disclosure and in the drawings described above, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The knowledge graph is a tool for semantic search proposed by google in 2012, can express an objective world by using a mesh structure, and the basic constituent units of the knowledge graph are entities, relations and attributes. Knowledge maps in the prior art generally describe the relationship between entities through simple relationship features, and then find answer entities corresponding to problem entities based on the relationship features during searching. However, the search results obtained by the search in this way are wide, the positioning accuracy of the answers is not sufficient, the answers cannot be applied in a scene with multi-condition search, and the matching degree of the search results is poor.
In view of the above technical problems, the present disclosure provides a search method, apparatus, device and storage medium that combine RPA and AI, which can filter a plurality of second entities in a knowledge graph according to conditions set in a question, obtain answers that are more matched with the question, and improve accuracy of a search result.
Fig. 1 is a diagram of an application scenario of a search method combining RPA and AI according to an example embodiment of the present disclosure, as shown in fig. 1, taking an insurance claim settlement service scenario as an example, the first entity (represented by a square) may be "wealth insurance win" or "leukemia" in the diagram according to an insurance category and a disease category. In the field of insurance claim settlement, claims are different for users of different ages and different sexes. Therefore, second entities (represented by circles) such as claim a, claim B, claim C, and the like can be constructed according to the gender condition, the age condition. Meanwhile, a conditional link between a first entity (a second entity) and the second entity can be constructed, so that a directional relationship is formed between the first entity and the second entity and between the second entity and the second entity. Meanwhile, the second entity can be continuously split according to the fine-grained requirement, and a plurality of second entities are split. The method can also be conveniently applied to service expansion, and the second entity is split according to the fine granularity without adjusting an application layer. Meanwhile, the method can also be conveniently applied to entity deletion or modification, and the second entity at the upper layer becomes the second entity of the search chain terminal after deletion.
In the searching process, the problem information can be decomposed to obtain a word segmentation sequence. Then, according to the part of speech and the semantics of each participle in the participle sequence, a first entity and at least one condition are extracted. For example, the question information of "about how leukemia is settled in 60 years old for women who have won wealth won" is first decomposed to obtain the respective phrases "about wealth won", "women", "60 years old", "leukemia", "settlement", and the like. From the parts of speech and semantic analysis, it can be known that "women", "60 years", "claims" and the like are conditions for modifying the first entity "wealth win", "leukemia". When the participles for modifying the first entity are not extracted according to the part of speech and the semantics of each participle in the participle sequence, the condition is set to be unlimited. For example, when the question information is "how to settle the leukemia of wealth winning", a segmentation sequence is obtained by decomposing the question information into individual segments such as "wealth winning", "leukemia", and "settling". Among them, there is no mention of the word segmentation for modification in terms of sex, age, and the like. Therefore, the gender condition may be set to be unlimited, and the age condition may be set to be unlimited. Similarly, when the question information is "how to pay for leukemia of women who win wealth", the age condition may be set without limitation because no modifier in terms of age is extracted. Similarly, when the question information is "how to pay for leukemia in the age of 60, wealth and safety", since the modifier in terms of gender is not extracted, the gender condition may be set without limitation. It can be seen that the embodiments of the present disclosure do not limit the conditions, the first entity may be limited by one or more conditions, and one or more conditions may be freely combined.
The position of a first entity can be positioned from the knowledge graph, and then the first entity is used as an initial node to traverse all connected search paths according to conditions; the search path is formed by linking a first entity, a second entity and a conditional link. And finally, searching a second entity located at the end position of the search path. For example, when the question information is "how to settle the leukemia due to wealth and win", the gender and age conditions are not limited, and are not limited. The second entity "claim D", "claim E", "claim F", "claim G" located at the end of the search route can be found by using the links "claim a" - "claim B" - "claim D", "claim a" - "claim B" - "claim E", "claim a" - "claim C" - "claim F", "claim a" - "claim C" - "claim G" as the starting point. Similarly, when the question information is "how to pay for leukemia of women who is cai and rich in nature", the second entity "claim F", "claim G" located at the end position of the search route may be found by using the links "claim a" - "claim C" - "claim F" - "claim C" - "claim G" as the starting point. When the question information is that the woman 60 years old who won the leukemia won who won the treasure won, the second entity "claim G" located at the end of the search route can be found by using the "treasure won" and "leukemia" as the starting point and through the only one of the links "claim A" - "claim C" - "claim G". And finally, feeding back the second entity as an answer to the user side.
By the method, the second entities in the knowledge graph can be filtered according to conditions set in the problem, answers matched with the problem are obtained, and accuracy of the search result is improved.
Fig. 2 is a flowchart illustrating a searching method combining an RPA and an AI according to an example embodiment of the present disclosure, and as shown in fig. 2, the method provided by the embodiment of the present disclosure may include:
In the embodiment of the present disclosure, a semantic analysis technique in the NLP technique may be adopted to perform semantic analysis on the received problem information, so as to obtain the first entity and the condition. The semantic analysis technology is mainly used for understanding semantic information such as meanings, themes and categories of words, sentences and chapters, and belongs to one of natural language processing technologies.
In a possible implementation manner of the embodiment of the present disclosure, the semantic analysis technology may be adopted to decompose the problem information to obtain a word segmentation sequence. Then, extracting a first entity and at least one condition according to the part of speech and the semantics of each participle in the participle sequence; wherein the conditions are used to modify the first entity.
As an example, the question information may be subjected to semantic analysis and syntactic analysis, the question information may be decomposed using the syntactic information and the semantic information to obtain a word segmentation sequence, and then, each word segmentation in the word segmentation sequence may be subjected to part-of-speech and semantic analysis to determine the first entity and the at least one condition.
For example, in a specific processing procedure of semantic analysis, the question information may be decomposed to obtain a word segmentation sequence. Then, the part of speech and the semantics of each participle in the participle sequence are analyzed. For example, the question information of "about how leukemia is settled in 60 years old for women who have won wealth won" is first decomposed to obtain the respective phrases "about wealth won", "women", "60 years old", "leukemia", "settlement", and the like. From the parts of speech and semantic analysis, it can be known that "women", "60 years", "claims" and the like are conditions for modifying the first entity "wealth win", "leukemia".
Alternatively, when a participle for modifying the first entity is not extracted according to the part-of-speech and the semantics of each participle in the participle sequence, the condition is set to be unlimited.
Specifically, when the question information is "how to settle the leukemia of wealth winning", a word segmentation sequence composed of words such as "wealth winning", "leukemia", and "settle the claims" is obtained according to the decomposition. Among them, there is no mention of the word segmentation for modification in terms of sex, age, and the like. Therefore, the gender condition may be set to be unlimited, and the age condition may be set to be unlimited. Similarly, when the question information is "how to pay for leukemia of women who win wealth", the age condition may be set without limitation because no modifier in terms of age is extracted. Similarly, when the question information is "how to pay for leukemia in the age of 60, wealth and safety", since the modifier in terms of gender is not extracted, the gender condition may be set without limitation. It can be seen that the embodiments of the present disclosure do not limit the conditions, the first entity may be limited by one or more conditions, and one or more conditions may be freely combined.
And 102, searching a second entity meeting the condition from the knowledge graph according to the first entity and the condition.
In the embodiment of the present disclosure, the knowledge graph may include: the system comprises a first entity and a second entity, wherein the first entity points to at least one second entity, and the second entities are linked through a conditional link. The position of a first entity can be firstly positioned from a knowledge graph, and then the first entity is used as an initial node to traverse all connected search paths according to conditions; the search path is formed by linking a first entity, a second entity and a conditional link. And finally, searching a second entity located at the end position of the search path.
Specifically, taking the knowledge graph shown in fig. 1 as an example, the first entity includes "wealth win", "leukemia", and the second entity includes claim a, claim B, claim C, and the like. The first entity and the second entity are linked through a conditional link of gender, age and the like. Therefore, when searching for a second entity meeting the condition from the knowledge-graph, all connected search paths can be traversed from the first entity, and finally, the second entity located at the end position of the search path is obtained. For example, when the question information is "how to settle the leukemia due to wealth and win", the gender and age conditions are not limited, and are not limited. The second entity "claim D", "claim E", "claim F", "claim G" located at the end of the search route can be found by using the links "claim a" - "claim B" - "claim D", "claim a" - "claim B" - "claim E", "claim a" - "claim C" - "claim F", "claim a" - "claim C" - "claim G" as the starting point. Similarly, when the question information is "how to pay for leukemia of women who is cai and rich in nature", the second entity "claim F", "claim G" located at the end position of the search route may be found by using the links "claim a" - "claim C" - "claim F" - "claim C" - "claim G" as the starting point. When the question information is that the woman 60 years old who won the leukemia won who won the treasure won, the second entity "claim G" located at the end of the search route can be found by using the "treasure won" and "leukemia" as the starting point and through the only one of the links "claim A" - "claim C" - "claim G".
And step 103, feeding back the second entity as an answer to the user side.
In the embodiment of the present disclosure, all the second entities located at the end position of the search path may be fed back to the user side as answers.
In particular, the second entity includes an answer to a particular question. And finding the second entity at the end point position of the search path through the conditional link, namely completing the positioning and searching of the problem. Therefore, the second entity found in step 102 can be fed back to the user end as an answer.
According to the embodiment of the disclosure, the received problem information is subjected to semantic analysis by adopting an NLP technology to obtain a first entity and a condition; according to the first entity and the condition, searching a second entity meeting the condition from the knowledge graph; wherein, the knowledge map comprises: the system comprises a first entity and a second entity, wherein the first entity points to at least one second entity, and the second entities are linked through a conditional link; and feeding back the second entity as an answer to the user side. Therefore, a plurality of second entities in the knowledge graph can be filtered according to conditions set in the questions, answers matched with the questions are obtained, and accuracy of search results is improved.
Fig. 3 is a flowchart illustrating a searching method combining an RPA and an AI according to another exemplary embodiment of the present disclosure, and as shown in fig. 3, the method provided by the embodiment of the present disclosure may include:
In the embodiment of the disclosure, a first entity and a second entity can be determined according to business and/or field requirements; constructing a knowledge graph according to the directional relation between the first entity and the second entity and the conditional link between the second entities; wherein each link between the second entities corresponds to a condition.
Specifically, taking an insurance claim settlement service scenario as an example, the first entity may be an insurance category or a disease category. In the field of insurance claim settlement, claims are different for users of different ages and different sexes. Therefore, second entities such as claim a, claim B, claim C, and the like can be constructed according to the gender condition, the age condition. Meanwhile, a conditional link between a first entity (a second entity) and the second entity can be constructed, so that a directional relationship is formed between the first entity and the second entity and between the second entity and the second entity. Meanwhile, the second entity can be continuously split according to the fine-grained requirement, and a plurality of second entities are split. The method can also be conveniently applied to service expansion, and the second entity is split according to the fine granularity without adjusting an application layer. Meanwhile, the method can also be conveniently applied to entity deletion or modification, and the second entity at the upper layer becomes the second entity of the search chain terminal after deletion. For example, when the "claim F" and "claim G" nodes are deleted, the application layer is not modified, and the answers to the questions "leukemia how claim for women who win wealth" and "leukemia how claim for women who win wealth 60 years are both" claim C ", because the" claim C "is already at the end position of the search route at this time. The method provided by the embodiment of the disclosure can also be applied to more complex actual application scenes, more conditions can be brought in the actual application scenes, and the finally formed knowledge graph is more complex.
It should be noted that, in the present disclosure, only step 201 is exemplified before step 202, and in practical applications, step 201 may also be executed before step 203, which is not limited by the present disclosure.
And step 204, feeding back the second entity as an answer to the user side.
In the embodiment of the present disclosure, please refer to the related description in step 101 to step 103 in the method shown in fig. 2 for the specific implementation process and technical principle of step 202 to step 204, which is not described herein again.
According to the embodiment of the disclosure, the received problem information is subjected to semantic analysis by adopting an NLP technology to obtain a first entity and a condition; according to the first entity and the condition, searching a second entity meeting the condition from the knowledge graph; wherein, the knowledge map comprises: the system comprises a first entity and a second entity, wherein the first entity points to at least one second entity, and the second entities are linked through a conditional link; and feeding back the second entity as an answer to the user side. Therefore, a plurality of second entities in the knowledge graph can be filtered according to conditions set in the questions, answers matched with the questions are obtained, and accuracy of search results is improved.
In addition, the embodiment of the disclosure can also determine a first entity and a second entity according to business and/or field requirements; constructing a knowledge graph according to the directional relation between the first entity and the second entity and the conditional link between the second entities; wherein each link between the second entities corresponds to a condition. Therefore, a plurality of second entities in the knowledge graph can be filtered according to conditions set in the questions, answers matched with the questions are obtained, and accuracy of search results is improved.
Fig. 4 is a schematic structural diagram of a search apparatus combining RPA and AI according to an example embodiment of the present disclosure. As shown in fig. 4, the search apparatus combining RPA and AI according to the embodiment of the present disclosure may include:
the analysis module 31 is configured to perform semantic analysis on the received problem information by using an NLP technique to obtain a first entity and a condition;
a searching module 32, configured to search, according to the first entity and the condition, a second entity that meets the condition from the knowledge graph; wherein, the knowledge map comprises: the system comprises a first entity and a second entity, wherein the first entity points to at least one second entity, and the second entities are linked through a conditional link;
and a feedback module 33, configured to feed back the second entity as an answer to the user side.
In one possible design, the analysis module 31 is specifically configured to:
decomposing the problem information to obtain a word segmentation sequence;
extracting a first entity and at least one condition according to the part of speech and the semantics of each participle in the participle sequence; wherein the conditions are used to modify the first entity.
In one possible design, the analysis module 31 is specifically configured to:
when the participles for modifying the first entity are not extracted according to the part of speech and the semantics of each participle in the participle sequence, the condition is set to be unlimited.
In one possible design, the search module 32 is specifically configured to:
locating a location of a first entity from a knowledge-graph;
traversing all connected search paths by taking the first entity as an initial node according to conditions; the search path is formed by linking a first entity, a second entity and a conditional link;
and searching for a second entity located at the end position of the search path.
In one possible design, the feedback module 33 is specifically configured to:
and feeding back all the second entities positioned at the end positions of the search paths as answers to the user side.
The apparatus provided in the embodiment of the present disclosure may be used to implement the technical solution of the method embodiment shown in fig. 2, and the implementation principle and the technical effect are similar, which are not described herein again.
According to the embodiment of the disclosure, the received problem information is subjected to semantic analysis by adopting an NLP technology to obtain a first entity and a condition; according to the first entity and the condition, searching a second entity meeting the condition from the knowledge graph; wherein, the knowledge map comprises: the system comprises a first entity and a second entity, wherein the first entity points to at least one second entity, and the second entities are linked through a conditional link; and feeding back the second entity as an answer to the user side. Therefore, a plurality of second entities in the knowledge graph can be filtered according to conditions set in the questions, answers matched with the questions are obtained, and accuracy of search results is improved.
Based on the embodiment shown in fig. 4, fig. 5 is a schematic structural diagram of a search apparatus shown in the present disclosure according to another exemplary embodiment, and as shown in fig. 5, the search apparatus combining an RPA and an AI provided in the embodiment of the present disclosure further includes:
a map building module 34 for:
determining a first entity and a second entity according to business and/or field requirements;
constructing a knowledge graph according to the directional relation between the first entity and the second entity and the conditional link between the second entities; wherein each link between the second entities corresponds to a condition.
The apparatus provided in the embodiment of the present disclosure may be used to implement the technical solutions of the method embodiments shown in fig. 2 and fig. 3, and the implementation principles and technical effects are similar, which are not described herein again.
According to the embodiment of the disclosure, the received problem information is subjected to semantic analysis by adopting an NLP technology to obtain a first entity and a condition; according to the first entity and the condition, searching a second entity meeting the condition from the knowledge graph; wherein, the knowledge map comprises: the system comprises a first entity and a second entity, wherein the first entity points to at least one second entity, and the second entities are linked through a conditional link; and feeding back the second entity as an answer to the user side. Therefore, a plurality of second entities in the knowledge graph can be filtered according to conditions set in the questions, answers matched with the questions are obtained, and accuracy of search results is improved.
In addition, the embodiment of the disclosure can also determine a first entity and a second entity according to business and/or field requirements; constructing a knowledge graph according to the directional relation between the first entity and the second entity and the conditional link between the second entities; wherein each link between the second entities corresponds to a condition. Therefore, a plurality of second entities in the knowledge graph can be filtered according to conditions set in the questions, answers matched with the questions are obtained, and accuracy of search results is improved.
Fig. 6 is a schematic structural diagram of an electronic device shown in the present disclosure according to an example embodiment. As shown in fig. 6, an electronic device 40 provided in an embodiment of the present disclosure includes:
a processor 401; and the number of the first and second groups,
a memory 402 for storing executable instructions of the processor, which may also be a flash (flash memory);
wherein the processor 401 is configured to perform the respective steps of the above-described method via execution of executable instructions. Reference may be made in particular to the description relating to the preceding method embodiment.
Alternatively, the memory 402 may be separate or integrated with the processor 401.
When the memory 402 is a device independent of the processor 401, the electronic device 40 may further include:
a bus 403 for connecting the processor 401 and the memory 402.
The disclosed embodiments also provide a readable storage medium, in which a computer program is stored, and when at least one processor of the electronic device executes the computer program, the electronic device executes the search method combining the RPA and the AI provided by the above-mentioned various embodiments.
The disclosed embodiments also provide a program product comprising a computer program stored in a readable storage medium. The computer program can be read from a readable storage medium by at least one processor of the electronic device, and the execution of the computer program by the at least one processor causes the electronic device to implement the search method combining RPA and AI provided by the various embodiments described above.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present disclosure, and not for limiting the same; while the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand 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 such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present disclosure.
Claims (14)
1. A searching method combining RPA and AI, characterized in that it comprises:
performing semantic analysis on the received problem information by adopting a Natural Language Processing (NLP) technology to obtain a first entity and a condition;
according to the first entity and the condition, searching a second entity meeting the condition from a knowledge graph; wherein, the knowledge-graph comprises: a first entity and a second entity, wherein the first entity points to at least one of the second entities, and the second entities are linked through a conditional link;
and feeding back the second entity as an answer to the user side.
2. The method of claim 1, wherein performing semantic analysis on the received problem information using NLP technology to obtain a first entity and a condition comprises:
decomposing the question information to obtain a word segmentation sequence;
extracting a first entity and at least one condition according to the part of speech and the semantics of each participle in the participle sequence; wherein the conditions are used to modify the first entity.
3. The method according to claim 2, wherein the condition is set to be unlimited when no participle for modifying the first entity is extracted according to the part of speech and the semantics of each participle in the participle sequence.
4. The method of claim 1, wherein searching for a second entity from a knowledge-graph that satisfies the condition based on the first entity and the condition comprises:
locating a location of the first entity from the knowledge-graph;
traversing all connected search paths by taking the first entity as an initial node according to the condition; wherein the search path is formed by linking the first entity, the second entity and a conditional link;
and searching the second entity at the end position of the search path.
5. The method of claim 4, wherein the feeding back the second entity as an answer to the user side comprises:
and feeding back all the second entities positioned at the end positions of the search paths as answers to the user side.
6. The method according to any of claims 1-5, further comprising, prior to said finding a second entity from a knowledge-graph that satisfies said condition based on said first entity and said condition:
determining the first entity and the second entity according to business and/or field requirements;
constructing a knowledge graph according to the orientation relation between the first entity and the second entity and the conditional link between the second entities; wherein each link between the second entities corresponds to a condition.
7. A search apparatus that combines RPA and AI, comprising:
the analysis module is used for performing semantic analysis on the received problem information by adopting an NLP technology to obtain a first entity and a condition;
the searching module is used for searching a second entity meeting the condition from the knowledge graph according to the first entity and the condition; wherein, the knowledge-graph comprises: a first entity and a second entity, wherein the first entity points to at least one of the second entities, and the second entities are linked through a conditional link;
and the feedback module is used for feeding back the second entity serving as an answer to the user side.
8. The apparatus of claim 7, wherein the analysis module is specifically configured to:
decomposing the question information to obtain a word segmentation sequence;
extracting a first entity and at least one condition according to the part of speech and the semantics of each participle in the participle sequence; wherein the conditions are used to modify the first entity.
9. The apparatus of claim 8, wherein the analysis module is specifically configured to:
and when the participles used for modifying the first entity are not extracted according to the part of speech and the semantics of each participle in the participle sequence, setting the condition as unlimited.
10. The apparatus of claim 7, wherein the search module is specifically configured to:
locating a location of the first entity from the knowledge-graph;
traversing all connected search paths by taking the first entity as an initial node according to the condition; wherein the search path is formed by linking the first entity, the second entity and a conditional link;
and searching the second entity at the end position of the search path.
11. The apparatus of claim 10, wherein the feedback module is specifically configured to:
and feeding back all the second entities positioned at the end positions of the search paths as answers to the user side.
12. The apparatus of any one of claims 7-11, further comprising: a map building module to:
determining the first entity and the second entity according to business and/or field requirements;
constructing a knowledge graph according to the orientation relation between the first entity and the second entity and the conditional link between the second entities; wherein each link between the second entities corresponds to a condition.
13. An electronic device, comprising:
a processor; and the number of the first and second groups,
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform the combined RPA and AI search method of any of claims 1-6 via execution of the executable instructions.
14. A storage medium on which a computer program is stored, the program, when executed by a processor, implementing the combined RPA and AI search method of any one of claims 1 to 6.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2020102279109 | 2020-03-27 | ||
| CN202010227910 | 2020-03-27 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112231445A true CN112231445A (en) | 2021-01-15 |
Family
ID=74118418
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011126674.8A Pending CN112231445A (en) | 2020-03-27 | 2020-10-20 | Searching method, device, equipment and storage medium combining RPA and AI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112231445A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095195A (en) * | 2015-07-03 | 2015-11-25 | 北京京东尚科信息技术有限公司 | Method and system for human-machine questioning and answering based on knowledge graph |
| CN109522465A (en) * | 2018-10-22 | 2019-03-26 | 国家电网公司 | The semantic searching method and device of knowledge based map |
| CN109885660A (en) * | 2019-02-22 | 2019-06-14 | 上海乐言信息科技有限公司 | A kind of question answering system and method based on information retrieval that knowledge mapping is energized |
| KR20200014047A (en) * | 2018-07-31 | 2020-02-10 | 주식회사 포티투마루 | Method, system and computer program for knowledge extension based on triple-semantic |
| CN110837550A (en) * | 2019-11-11 | 2020-02-25 | 中山大学 | Knowledge graph-based question and answer method and device, electronic equipment and storage medium |
-
2020
- 2020-10-20 CN CN202011126674.8A patent/CN112231445A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095195A (en) * | 2015-07-03 | 2015-11-25 | 北京京东尚科信息技术有限公司 | Method and system for human-machine questioning and answering based on knowledge graph |
| KR20200014047A (en) * | 2018-07-31 | 2020-02-10 | 주식회사 포티투마루 | Method, system and computer program for knowledge extension based on triple-semantic |
| CN109522465A (en) * | 2018-10-22 | 2019-03-26 | 国家电网公司 | The semantic searching method and device of knowledge based map |
| CN109885660A (en) * | 2019-02-22 | 2019-06-14 | 上海乐言信息科技有限公司 | A kind of question answering system and method based on information retrieval that knowledge mapping is energized |
| CN110837550A (en) * | 2019-11-11 | 2020-02-25 | 中山大学 | Knowledge graph-based question and answer method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111401066B (en) | Artificial intelligence-based word classification model training method, word processing method and device | |
| CN109325040B (en) | FAQ question-answer library generalization method, device and equipment | |
| CN111222305A (en) | Information structuring method and device | |
| CN110968684A (en) | Information processing method, device, equipment and storage medium | |
| CN108846138A (en) | A kind of the problem of fusion answer information disaggregated model construction method, device and medium | |
| CN111767394A (en) | Abstract extraction method and device based on artificial intelligence expert system | |
| CN112101042A (en) | Text emotion recognition method and device, terminal device and storage medium | |
| CN114091466A (en) | Multi-modal emotion analysis method and system based on Transformer and multi-task learning | |
| CN110795544B (en) | Content searching method, device, equipment and storage medium | |
| CN112287085A (en) | Semantic matching method, system, device and storage medium | |
| CN106202038A (en) | Synonym method for digging based on iteration and device | |
| CN110807323A (en) | Emotion vector generation method and device | |
| CN114528391A (en) | Method, device and equipment for training question-answer pair scoring model and storage medium | |
| CN114490926A (en) | Method and device for determining similar problems, storage medium and terminal | |
| CN117112754A (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| CN112231445A (en) | Searching method, device, equipment and storage medium combining RPA and AI | |
| CN114090778A (en) | Retrieval method and device based on knowledge anchor point, electronic equipment and storage medium | |
| CN114611529A (en) | Intention recognition method and device, electronic equipment and storage medium | |
| CN114065769A (en) | Method, device, equipment and medium for training emotion reason pair extraction model | |
| CN113870998A (en) | Interrogation method, device, electronic equipment and storage medium | |
| CN117743315B (en) | Method for providing high-quality data for multi-mode large model system | |
| Naykhanova et al. | Recognition of situations described in the text of legal documents | |
| CN116127050B (en) | Opinion mining method, electronic device, and computer-readable storage medium | |
| CN116453702B (en) | Data processing method, device, system and medium for autism behavior feature set | |
| CN117493588B (en) | Search result determining method and device, storage medium and electronic device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |