CN111090739A - Information processing method, information processing device, electronic device, and storage medium - Google Patents
Information processing method, information processing device, electronic device, and storage medium Download PDFInfo
- Publication number
- CN111090739A CN111090739A CN201911044333.3A CN201911044333A CN111090739A CN 111090739 A CN111090739 A CN 111090739A CN 201911044333 A CN201911044333 A CN 201911044333A CN 111090739 A CN111090739 A CN 111090739A
- Authority
- CN
- China
- Prior art keywords
- information
- query
- knowledge
- response
- entity
- 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
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
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present disclosure provides an information processing method, an information processing apparatus, an electronic device, and a storage medium, and relates to the technical field of computers, wherein the method includes: extracting query information from the consultation information, acquiring first response information in a preset knowledge graph according to the query information, acquiring supplementary query information based on the query information and/or the first response information, acquiring second response information in the knowledge graph according to the supplementary query information, and generating and outputting a consultation result by using the first response information and the second response information; the method, the device, the electronic equipment and the storage medium disclosed by the invention are used for establishing the knowledge map to provide the consultation response information, obtaining the supplementary response information with higher correlation degree with the user consultation information according to the supplementary query information and through the knowledge map, and generating the consultation result by using the consultation response information and the supplementary response information, so that the response accuracy is high, the correlation information can be actively provided for the user, and the use experience of the user is improved.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to an information processing method and apparatus, an electronic device, and a storage medium.
Background
In some service areas, customers can ask questions and obtain answers through customer service systems, such as a house property customer service system. The existing customer service system generally relies on a general search technology, all possible questions of a customer on service contents are used as article titles, standard answers aiming at the questions are used as article contents, and a knowledge base is formed. When the customer service system receives the questions of the customer, the questions of the customer are used as search titles to search, and the obtained article contents are used as answers to be provided for the customer. Customer service systems using search technology and knowledge bases rely heavily on the scale, accuracy of the knowledge base (question-answer pairs) and the ranking strategy of text retrieval. Due to the long construction period and high cost of the knowledge base, the current customer service system has poor question answering effect and low accuracy for the customer with weak correlation or long fuzzy subject of the knowledge base.
Disclosure of Invention
The present disclosure is proposed to solve the above technical problems. The embodiment of the disclosure provides an information processing method and device, an electronic device and a storage medium.
According to an aspect of an embodiment of the present disclosure, there is provided an information processing method including: receiving consultation information input by a user, and extracting query information from the consultation information; acquiring first response information in a preset knowledge graph according to the query information; acquiring supplementary query information based on the query information and/or the first response information; acquiring second response information in the knowledge graph according to the supplementary query information; and generating a consultation result according to the first response information and the second response information and outputting the consultation result.
Optionally, before the step of receiving the consulting information input by the user and extracting query information from the consulting information, the method further includes a step of constructing the knowledge graph, and the step includes: extracting knowledge graph triples from a knowledge base; wherein the knowledge-graph triplets include: two first entities, first relationship information between the two first entities; and constructing the knowledge graph based on the knowledge graph triples.
Optionally, the extracting of the knowledge-graph triples from the knowledge base includes: processing the consulting knowledge content in the knowledge base based on a preset information extraction method, and extracting the first entity and the first relation information; normalizing the first entity and the first relation information; and generating the knowledge graph triple according to the first entity subjected to the normalization processing and the first relation information.
Optionally, the information extraction method includes: the method comprises an information extraction method based on semantic analysis and an information extraction method based on machine learning.
Optionally, the extracting query information from the consulting information in the knowledge base includes: processing the consultation information based on the information extraction method to obtain the query information; wherein the query information comprises: a second entity, second relationship information.
Optionally, the obtaining first response information in a preset knowledge graph according to the query information includes: normalizing the query information; generating a first query statement with a triple structure according to the query information subjected to the normalization processing; and inputting the first query statement into the knowledge graph for querying to obtain the first response information.
Optionally, the obtaining of the supplemental query information based on the query information and/or the first response information includes: obtaining at least one first entity having an association relation with the second entity, and using the at least one first entity as the supplementary query information; and/or extracting a third entity from the first response information based on the information extraction method, and using the third entity as the supplementary query information.
Optionally, the obtaining second response information in the knowledge-graph according to the supplementary query information includes: generating a second query statement of a triple structure according to the supplementary query information; and inputting the second query statement into the knowledge graph for querying to obtain the second response information.
Optionally, data information related to the house property knowledge is collected in a web crawler mode and/or a dialogue text corresponding to user consultation is collected to obtain the consultation knowledge content, and the consultation knowledge content is added into the knowledge base.
According to another aspect of the embodiments of the present disclosure, there is provided a consultation information processing apparatus including: the query information acquisition module is used for receiving the consultation information input by the user and extracting the query information from the consultation information; the first response processing module is used for acquiring first response information in a preset knowledge graph according to the query information; a supplementary information obtaining module for obtaining supplementary query information based on the query information and/or the first response information; the second response processing module is used for acquiring second response information in the knowledge graph according to the supplementary query information; and the answer output module is used for generating and outputting a consultation result by using the first response information and the second response information.
Optionally, the knowledge graph processing module is configured to extract a knowledge graph triple from the knowledge base; wherein the knowledge-graph triplets include: two first entities, first relationship information between the two first entities; and constructing the knowledge graph based on the knowledge graph triples.
Optionally, the knowledge graph processing module is further configured to process the consulting knowledge content in the knowledge base based on a preset information extraction method, and extract the first entity and the first relationship information; normalizing the first entity and the first relation information; and generating the knowledge graph triple according to the first entity subjected to the normalization processing and the first relation information.
Optionally, the information extraction method includes: the method comprises an information extraction method based on semantic analysis and an information extraction method based on machine learning.
Optionally, the first response processing module is configured to process the consultation information based on the preset information extraction method to obtain the query information; wherein the query information comprises: a second entity, second relationship information.
Optionally, the first response processing module is further configured to perform normalization processing on the query information; generating a first query statement with a triple structure according to the query information subjected to the normalization processing; and inputting the first query statement into the knowledge graph for querying to obtain the first response information.
Optionally, the supplementary information obtaining module is configured to obtain at least one first entity having an association relationship with the second entity, and use the at least one first entity as the supplementary query information; and/or extracting a third entity from the first response information based on the preset information extraction method, and taking the third entity as the supplementary query information.
Optionally, the second response processing module is configured to generate a second query statement of a triple structure according to the supplemental query information; and the knowledge graph processing module is used for inputting the second query statement into the knowledge graph for query to obtain the second response information.
Optionally, the knowledge graph processing module is configured to collect data information related to the property knowledge in a web crawler manner and/or collect a dialog text corresponding to a user consultation, obtain the consultation knowledge content, and add the consultation knowledge content to the knowledge base.
According to yet another aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium storing a computer program for executing the above-mentioned method.
According to still another aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including: a processor; a memory for storing the processor-executable instructions; the processor is used for executing the method.
Based on the information processing method and device, the electronic equipment and the storage medium provided by the embodiment of the disclosure, the knowledge map is established to provide the consultation response information, the user consultation information and the consultation response information are subjected to knowledge reasoning to obtain the supplementary inquiry information, the supplementary response information with high correlation degree with the user consultation information is obtained according to the supplementary inquiry information and the knowledge map, and the consultation result is generated by using the consultation response information and the supplementary response information.
The technical solution of the present disclosure is further described in detail by the accompanying drawings and examples.
Drawings
The above and other objects, features and advantages of the present disclosure will become more apparent by describing in more detail embodiments of the present disclosure with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the disclosure, and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the principles of the disclosure and not to limit the disclosure. In the drawings, like reference numbers generally represent like parts or steps.
FIG. 1 is a flow chart of one embodiment of an information processing method of the present disclosure;
FIG. 2 is a flow diagram of construction of a knowledge graph in one embodiment of an information processing method of the present disclosure;
FIG. 3 is a flow diagram of extracting knowledge-graph triples in one embodiment of an information processing method of the present disclosure;
fig. 4 is a flowchart of acquiring first response information in an embodiment of an information processing method of the present disclosure;
fig. 5 is a flowchart of acquiring second response information in an embodiment of the information processing method of the present disclosure;
FIG. 6 is a diagram of a dialog text between a client and a customer service system;
FIG. 7 is a schematic block diagram of one embodiment of an information processing apparatus of the present disclosure;
fig. 8 is a schematic configuration diagram of another embodiment of an information processing apparatus of the present disclosure;
FIG. 9 is a block diagram of one embodiment of an electronic device of the present disclosure.
Detailed Description
Example embodiments according to the present disclosure will be described in detail below with reference to the accompanying drawings. It is to be understood that the described embodiments are merely a subset of the embodiments of the present disclosure and not all embodiments of the present disclosure, with the understanding that the present disclosure is not limited to the example embodiments described herein.
It should be noted that: the relative arrangement of the components and steps, the numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.
It will be understood by those of skill in the art that the terms "first," "second," and the like in the embodiments of the present disclosure are used merely to distinguish one element from another, and are not intended to imply any particular technical meaning, nor is the necessary logical order between them.
It is also understood that in embodiments of the present disclosure, "a plurality" may refer to two or more than two and "at least one" may refer to one, two or more than two.
It is also to be understood that any reference to any component, data, or structure in the embodiments of the disclosure, may be generally understood as one or more, unless explicitly defined otherwise or stated otherwise.
In addition, the term "and/or" in the present disclosure is only one kind of association relationship describing the associated object, and means that there may be three kinds of relationships, such as a and/or B, and may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" in the present disclosure generally indicates that the former and latter associated objects are in an "or" relationship.
It should also be understood that the description of the various embodiments of the present disclosure emphasizes the differences between the various embodiments, and the same or similar parts may be referred to each other, so that the descriptions thereof are omitted for brevity.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
Embodiments of the present disclosure may be implemented in electronic devices such as terminal devices, computer systems, servers, etc., which are operational with numerous other general purpose or special purpose computing system environments or configurations. Examples of well known terminal devices, computing systems, environments, and/or configurations that may be suitable for use with an electronic device, such as a terminal device, computer system, or server, include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, microprocessor-based systems, set top boxes, programmable consumer electronics, network pcs, minicomputer systems, mainframe computer systems, distributed cloud computing environments that include any of the above, and the like.
Electronic devices such as terminal devices, computer systems, servers, etc. may be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc. that perform particular tasks or implement particular abstract data types. The computer system/server may be implemented in a distributed cloud computing environment. In a distributed cloud computing environment, tasks may be performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computer system storage media including memory storage devices.
Summary of the application
In the process of implementing the present disclosure, the inventors found that a question of a client is searched as a search title, and the obtained article content is provided to the client as an answer. The customer service system using the existing search technology and knowledge base has great dependence on the scale and accuracy of the knowledge base (question-answer pair) and the ordering strategy of text retrieval, and has poor effect and accuracy on the question response of customers.
The information processing method comprises the steps of extracting query information from consultation information, obtaining first response information in a preset knowledge graph according to the query information, obtaining supplementary query information based on the query information and/or the first response information, obtaining second response information in the knowledge graph according to the supplementary query information, and generating and outputting a consultation result by using the first response information and the second response information; the method comprises the steps of establishing a knowledge graph to provide consultation response information, carrying out knowledge reasoning on user consultation information and the consultation response information to obtain supplementary inquiry information, obtaining supplementary response information with high correlation degree with the user consultation information according to the supplementary inquiry information and the knowledge graph, and generating a consultation result by using the consultation response information and the supplementary response information.
Exemplary method
Fig. 1 is a flowchart of an embodiment of an information processing method of the present disclosure, and the method shown in fig. 1 includes the steps of: S101-S105. The following describes each step.
S101, receiving the consultation information input by the user, and extracting the inquiry information from the consultation information. The counseling information can be various, such as customer service counseling information.
S102, acquiring first response information in a preset knowledge graph according to the query information. The knowledge map is a semantic network formed by connecting knowledge points and is used for knowledge reasoning and automatic question answering.
S103, acquiring the supplementary query information based on the query information and/or the first response information.
In an embodiment, the supplementary query information may be obtained based on the query information or the first response information, or the supplementary query information may be obtained based on the query information and the first response information together.
And S104, acquiring second response information in the knowledge graph according to the supplementary query information.
And S105, generating and outputting a consultation result by using the first response information and the second response information.
Fig. 2 is a flowchart of constructing a knowledge graph in an embodiment of the information processing method of the present disclosure, and the method shown in fig. 2 includes the steps of: S201-S202. The following describes each step.
S201, extracting a knowledge graph triple from a knowledge base, wherein the knowledge graph triple comprises: two first entities, first relationship information between the two first entities.
S202, constructing a customer service knowledge graph based on the knowledge graph triples.
The minimum composition unit for constructing the knowledge graph is a knowledge graph triple, the knowledge graph triple comprises two knowledge graph entities and an attribute relation between the two knowledge graph entities, and the basic form of the knowledge graph triple is as follows: entity-relationship-entity.
For example, the knowledge base is a house property customer service knowledge base, and the consulting knowledge content in the house property customer service knowledge base is knowledge information such as "extracting preparation materials of the accumulation fund including house purchase contracts". Extracting knowledge graph triples from ' extracting the quasi-materials of the public accumulation fund ' including the house-buying contract ', wherein ' extracting the public accumulation fund ' and ' the house-buying contract ' are two first entities, and ' extracting the public accumulation fund ' and ' the house-buying contract ' have first relation information of ' preparation materials '. In a knowledge graph, most of the first-degree information (direct relationships between entities) is added during the graph construction process. And mining the semantic relation of the text through relation extraction to obtain first-degree information during construction of the map entity relation.
The first entities can be subjected to cluster analysis, the first entities with different description information in the same cluster are combined according to the result of the cluster analysis, the knowledge graph triples are adjusted through the combined first entities, and the knowledge graph is constructed by the adjusted knowledge graph triples. The knowledge graph constructed by the triple data has the logical structure capability of knowledge reasoning, and the knowledge graph constructed by the data triple is used for searching the user consultation problem, so that the semantic range domain can be better understood, and the searching accuracy is improved.
Fig. 3 is a flowchart of extracting knowledge-graph triples in an embodiment of the information processing method of the present disclosure, where the method shown in fig. 3 includes the steps of: S301-S303. The following describes each step.
S301, consulting knowledge content in the knowledge base is processed based on a preset information extraction method, and a first entity and first relation information are extracted. The information extraction method comprises the following steps: semantic analysis-based information extraction methods, machine learning-based information extraction methods, and the like.
In one embodiment, there may be multiple information extraction methods based on semantic analysis. For example, a grammar template is generated according to a plurality of set grammar rules, information matched with the grammar template is searched in the consulting knowledge content, and the first entity and the first relation information are extracted from the consulting knowledge content according to the triple extraction rule corresponding to the grammar template. Or setting a syntactic analysis tool, carrying out text structure analysis on the consulting knowledge content by using the syntactic analysis tool, and acquiring the first entity and the first relation information according to the analysis result.
There may be various information extraction methods based on machine learning. For example, a training sample set is generated according to the consulting knowledge content and the first entity and the first relation information extracted from the consulting knowledge content, and the neural network is trained according to the training sample set to obtain the neural network model. The Neural network model can be established by adopting various algorithm models, such as a residual error network (ResNet), and the like.
The neural network model includes an input layer neuron model, a middle layer neuron model and an output layer neuron model, an output of each layer of neuron model is used as an input of the next layer of neuron model, the neural network model may be a sub-network structure of a plurality of neural network layers having a full connection structure, and the middle layer neuron model is a full connection layer. And inputting the consultation knowledge content into the trained neural network model, and outputting the first entity and the first relation information through the neural network model.
S302, normalization processing is carried out on the first entity and the first relation information.
By normalizing the first entity and the first relation information, different descriptions with the same meaning in the first entity and the first relation information can be integrated, so that redundant descriptions with the same meaning can be eliminated, and the first entity and the first relation information become normalized standard entities and standard relation texts.
The first entity and the first relationship information can be conceptually aligned, in the process of mining the first entity and the first relationship information, the same entity words and relationship words need to be classified into synonyms in a specific scene, and different expressions can refer to the same meaning. For example, entity words ("earmark", "earmark extraction") and the like need to be classified as synonyms in different scenes, different expressions are guaranteed to refer to the same concept, and synonyms or near synonyms can be obtained through house domain word vectors and syntactic structure analysis.
And S303, generating a knowledge graph triple according to the first entity subjected to normalization processing and the first relation information.
Fig. 4 is a flowchart of acquiring first response information in an embodiment of the information processing method of the present disclosure, where the method shown in fig. 4 includes the steps of: S401-S403. The following describes each step.
S401, normalization processing is carried out on the query information.
In one embodiment, the query information is obtained by processing the query information through a semantic analysis-based information extraction method, a machine learning-based information extraction method, or the like, and the query information includes: a second entity, second relationship information. And normalizing the second entity and the second relation information to make the second entity and the second relation information become a normalized standard entity and a normalized standard relation text.
S402, generating a first query statement with a triple structure according to the query information after normalization processing.
S403, inputting the first query sentence into the knowledge graph for query, and obtaining first response information.
In one embodiment, filtering processing is carried out according to the entity words and the relation words in a knowledge base of the defined scene, the user questions are matched accurately in the knowledge base, and the matched answers are given. And (4) extracting answers from the knowledge graph, and using a corresponding query statement SPARQL, wherein the form of the SPARQL is close to that of SQL.
The consultation information input by the user is 'which preparation materials for extracting the accumulation fund are', and the 'which preparation materials for extracting the accumulation fund are' is processed on the basis of a machine learning algorithm, and the obtained inquiry information comprises: the second entity extracts the accumulation fund and the second relation information prepares materials.
The method comprises the steps of normalizing the second entity 'extraction public accumulation fund' and the second relation information 'preparation material', generating a first query statement 'SELECT X WHERE' (extraction public accumulation fund, preparation material, X) 'based on a triple structure (' extraction public accumulation fund ',' preparation material ',' is), inputting the first query statement into a knowledge graph for query, finding a first entity at the other end having a relation with the entity 'extraction public accumulation fund', and obtaining first response information, wherein the first response information is equal to a house purchase portfolio, for example.
Fig. 5 is a flowchart of acquiring second response information in an embodiment of the information processing method of the present disclosure, and the method shown in fig. 5 includes the steps of: S501-S504. The following describes each step.
S501, at least one first entity having an association relation with a second entity is obtained, and the at least one first entity is used as supplementary query information.
In an embodiment, the association relationship between the first entities may be preset. Real-world entities may be represented by corresponding nodes in the knowledge-graph network, and connecting edges in the knowledge-graph describe various connections between entities. For example, "house wall", "wall color", and the like have an association in reality, and an association relationship between the first entity "house wall", "wall color", and the like may be established in advance. When the second entity is the 'house wall', obtaining the first entity 'wall color' and the like which have an association relation with the second entity 'house wall', and taking the first entity 'wall color' and the like as the supplementary query information.
S502, extracting a third entity from the first response information based on an information extraction method, and taking the third entity as supplementary query information.
In an embodiment, a first query statement with a triple structure is generated according to a second entity "house wall" and a second relation information "composition feature", and the first query statement is input into a knowledge graph for query, so as to obtain first response information "orientation, height, material, and the like". The third entity "wall orientation", "wall height", etc. is extracted from the first answer information "wall orientation, wall color, wall height, etc" based on the information extraction method, and the third entity "wall orientation", "wall height", etc. is used as the supplementary query information.
S503, generating a second query statement with a triple structure according to the supplementary query information.
S504, inputting the second query sentence into the knowledge graph for query, and obtaining second response information.
In an embodiment, a second query statement of a triple structure is generated according to a third entity, namely "wall color", "wall orientation", "wall height", and the like, the second query statement is input into a knowledge graph for query, so as to obtain second response information, and the wall height and orientation information of a house, color decoration information of different walls, and the like are obtained through the second response information. Through reasoning, the information such as the decoration style and the decoration theme of the house can be obtained.
In one embodiment, the consultation information "which the preparation material for extracting the accumulation fund is included" input by the user is received, the second entity "the extraction accumulation fund" and the second relation information "preparation material" are extracted from the consultation information "which the material for extracting the accumulation fund is included", and the second entity "the extraction accumulation fund" and the second relation information "preparation material" are normalized.
And generating a first query statement with a triple structure according to the normalized second entity 'extraction public accumulation fund' and the second relation information 'preparation material', inputting the first query statement into a knowledge graph for query, and obtaining first response information 'house purchasing contract, identity information and the like'. And extracting a third entity 'house purchase contract' and the like from the first response information based on an information extraction method, generating a second query sentence with a triple structure according to the third entity 'house purchase contract' by using the third entity 'house purchase contract' and the like as supplementary query information, inputting the second query sentence into a knowledge graph for querying, and obtaining second response information. And generating and outputting a consultation result by using the first response information and the second response information.
In one embodiment, the offline real-time writing function of consultation uses a text trigrouging method to process all knowledge base contents and extract the entity and attribute relationship of the knowledge base text as the feature point of the knowledge text. The consulting online service function processes the text input by the user by using the same text three-component method, extracts entity and attribute relations from the online user questions, and searches in a knowledge base by using a three-component-based recall strategy.
Data information related to the house property knowledge can be collected in a web crawler mode, and conversation texts corresponding to user consultation can also be collected to obtain consultation knowledge contents. And cleaning the crawled data information to avoid information redundancy. As shown in fig. 6, in the online service, a large number of dialog texts of users and customer services are accumulated, and online relationship extraction and entity alignment are performed on the texts to supplement the knowledge content that has not been accumulated in the knowledge base.
The information processing method in the embodiment includes the steps of establishing a knowledge graph to provide consultation response information, carrying out knowledge reasoning on user consultation information and the consultation response information to obtain supplementary inquiry information, obtaining supplementary response information with high correlation degree with the user consultation information according to the supplementary inquiry information and through the knowledge graph, and generating a consultation result by using the consultation response information and the supplementary response information, so that the problems that a current customer service system is poor in questioning response effect and low in accuracy for a client with weak correlation or long fuzzy theme in a knowledge base are solved, correlation information can be provided for the user actively, and use experience of the user is improved.
Exemplary devices
In one embodiment, as shown in fig. 7, the present disclosure provides an information processing apparatus including: a query information obtaining module 701, a first response processing module 702, a supplementary information obtaining module 703, a second response processing module 704 and an answer output module 705. The query information obtaining module 701 receives the consultation information input by the user, and extracts the query information from the consultation information. The first response processing module 702 obtains the first response information in the preset knowledge graph according to the query information. The supplementary information obtaining module 703 obtains supplementary query information based on the query information and/or the first response information. The second response processing module 704 obtains the second response information in the knowledge-graph according to the supplementary query information. The answer output module 705 generates a consultation result using the first response information and the second response information and outputs the consultation result.
In one embodiment, as shown in FIG. 8, the information processing apparatus includes a knowledge-graph processing module 706. The knowledge-graph processing module 706 extracts knowledge-graph triples from the knowledge base, the knowledge-graph triples including: two first entities, first relationship information between the two first entities. The knowledge-graph processing module 706 constructs a knowledge-graph based on the knowledge-graph triples. The knowledge graph processing module 706 processes the consulting knowledge content based on a preset information extraction method, and extracts the first entity and the first relationship information, wherein the information extraction method comprises the following steps: semantic analysis-based information extraction methods, machine learning-based information extraction methods, and the like.
The knowledge-graph processing module 706 normalizes the first entity and the first relationship information. The knowledge-graph processing module 706 generates a knowledge-graph triple according to the normalized first entity and the first relationship information. The first response processing module 702 processes the consultation information based on the information extraction method to obtain query information, which includes: a second entity, second relationship information. The first response processing module 702 performs normalization processing on the query information, and generates a first query statement having a triple structure according to the query information after the normalization processing. The knowledge graph processing module 706 inputs the first query statement into the knowledge graph for query, so as to obtain the first response information.
In one embodiment, the supplemental information obtaining module 703 obtains at least one first entity having an association relationship with a second entity, and uses the at least one first entity as the supplemental query information; and/or, the supplementary information obtaining module 703 extracts the third entity from the first response information based on the information extraction method, and uses the third entity as supplementary query information. The second response processing module 704 generates a second query statement of the triple structure according to the supplementary query information; the knowledge graph processing module 706 inputs the second query statement into the knowledge graph for query, and obtains second response information. The knowledge graph processing module 706 collects data information related to the property knowledge and/or collects dialogue texts corresponding to the user consultation in a web crawler manner, so as to obtain consultation knowledge content.
Fig. 9 is a block diagram of one embodiment of an electronic device of the present disclosure, as shown in fig. 9, the electronic device 91 includes one or more processors 911 and memory 912.
The processor 911 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 91 to perform desired functions.
Memory 912 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. Volatile memory, for example, may include: random Access Memory (RAM) and/or cache memory (cache), etc. The nonvolatile memory, for example, may include: read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on a computer-readable storage medium and executed by the processor 911 to implement the information processing methods of the various embodiments of the present disclosure above and/or other desired functions. Various contents such as an input signal, a signal component, a noise component, etc. may also be stored in the computer-readable storage medium.
In one example, the electronic device 91 may further include: an input device 913, and an output device 914, among others, which are interconnected by a bus system and/or other form of connection mechanism (not shown). The input device 913 may include, for example, a keyboard, a mouse, or the like. The output device 914 may output various information to the outside. The output devices 914 can include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, among others.
Of course, for simplicity, only some of the components of the electronic device 91 relevant to the present disclosure are shown in fig. 9, omitting components such as buses, input/output interfaces, and the like. In addition, the electronic device 91 may include any other suitable components depending on the particular application.
In addition to the above-described methods and apparatus, embodiments of the present disclosure may also be a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the information processing method according to various embodiments of the present disclosure described in the above-mentioned "exemplary methods" section of this specification.
The computer program product may write program code for performing the operations of embodiments of the present disclosure in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present disclosure may also be a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform steps in an information processing method according to various embodiments of the present disclosure described in the "exemplary methods" section above of this specification.
The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium may include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The foregoing describes the general principles of the present disclosure in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present disclosure are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present disclosure. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the disclosure is not intended to be limited to the specific details so described.
The information processing method and device, the electronic device and the storage medium in the embodiments set up the knowledge map to provide the consultation response information, perform knowledge reasoning on the user consultation information and the consultation response information to obtain the supplementary inquiry information, obtain the supplementary response information with higher correlation with the user consultation information according to the supplementary inquiry information and through the knowledge map, and generate a consultation result by using the consultation response information and the supplementary response information, so that the problems that the current customer service system has poor question-asking response effect and low accuracy on the client with weak correlation in the knowledge base or longer subject fuzzy are solved, the correlation information can be actively provided for the user, and the use experience of the user is improved.
In the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts in the embodiments are referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The block diagrams of devices, apparatuses, systems referred to in this disclosure are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, and systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," comprising, "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
The methods and apparatus of the present disclosure may be implemented in a number of ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.
It is also noted that in the devices, apparatuses, and methods of the present disclosure, each component or step can be decomposed and/or recombined. These decompositions and/or recombinations are to be considered equivalents of the present disclosure.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects, and the like, will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, the description is not intended to limit embodiments of the disclosure to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.
Claims (10)
1. An information processing method comprising:
receiving consultation information input by a user, and extracting query information from the consultation information;
acquiring first response information in a preset knowledge graph according to the query information;
acquiring supplementary query information based on the query information and/or the first response information;
acquiring second response information in the knowledge graph according to the supplementary query information;
and generating a consultation result according to the first response information and the second response information and outputting the consultation result.
2. The method of claim 1, further comprising the step of constructing the knowledge-graph before the step of receiving the counseling information input by the user and extracting query information from the counseling information, the step comprising:
extracting knowledge graph triples from a knowledge base; wherein the knowledge-graph triplets include: two first entities, first relationship information between the two first entities;
and constructing the knowledge graph based on the knowledge graph triples.
3. The method of claim 2, the extracting knowledge-graph triples from a knowledge base comprising:
processing the consulting knowledge content in the knowledge base based on a preset information extraction method, and extracting the first entity and the first relation information;
normalizing the first entity and the first relation information;
and generating the knowledge graph triple according to the first entity subjected to the normalization processing and the first relation information.
4. The method of claim 3, wherein,
the information extraction method comprises the following steps: the method comprises an information extraction method based on semantic analysis and an information extraction method based on machine learning.
5. The method of claim 3, wherein said extracting query information from advisory information in said knowledge base comprises:
processing the consultation information based on the information extraction method to obtain the query information;
wherein the query information comprises: a second entity, second relationship information.
6. The method of claim 5, wherein the obtaining the first response information in the preset knowledge-graph according to the query information comprises:
normalizing the query information;
generating a first query statement with a triple structure according to the query information subjected to the normalization processing;
and inputting the first query statement into the knowledge graph for querying to obtain the first response information.
7. The method of claim 5, the obtaining supplemental query information based on the query information and/or the first response information comprising:
obtaining at least one first entity having an association relation with the second entity, and using the at least one first entity as the supplementary query information; and/or the presence of a gas in the gas,
and extracting a third entity from the first response information based on the information extraction method, and taking the third entity as the supplementary query information.
8. An information processing apparatus comprising:
the query information acquisition module is used for receiving the consultation information input by the user and extracting the query information from the consultation information;
the first response processing module is used for acquiring first response information in a preset knowledge graph according to the query information;
a supplementary information obtaining module for obtaining supplementary query information based on the query information and/or the first response information;
the second response processing module is used for acquiring second response information in the knowledge graph according to the supplementary query information;
and the answer output module is used for generating and outputting a consultation result by using the first response information and the second response information.
9. A computer-readable storage medium, the storage medium storing a computer program for performing the method of any of the preceding claims 1-7.
10. An electronic device, the electronic device comprising:
a processor; a memory for storing the processor-executable instructions;
the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911044333.3A CN111090739A (en) | 2019-10-30 | 2019-10-30 | Information processing method, information processing device, electronic device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911044333.3A CN111090739A (en) | 2019-10-30 | 2019-10-30 | Information processing method, information processing device, electronic device, and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111090739A true CN111090739A (en) | 2020-05-01 |
Family
ID=70393082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911044333.3A Pending CN111090739A (en) | 2019-10-30 | 2019-10-30 | Information processing method, information processing device, electronic device, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111090739A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111597205A (en) * | 2020-05-26 | 2020-08-28 | 北京金堤科技有限公司 | Template configuration method, information extraction method, device, electronic equipment and medium |
| CN111858890A (en) * | 2020-07-23 | 2020-10-30 | 平安证券股份有限公司 | Robot-based consultation method, consultation robot, computer equipment and medium |
| CN112182174A (en) * | 2020-09-24 | 2021-01-05 | 南方电网数字电网研究院有限公司 | Business question-answer knowledge query method and device, computer equipment and storage medium |
| CN112579600A (en) * | 2020-12-21 | 2021-03-30 | 广州橙行智动汽车科技有限公司 | Data processing method and device based on vehicle-mounted question answering |
| CN112650856A (en) * | 2020-12-28 | 2021-04-13 | 上海卓繁信息技术股份有限公司 | Consultation method and device for providing study direction in academic field and electronic equipment |
| CN112948547A (en) * | 2021-01-26 | 2021-06-11 | 中国石油大学(北京) | Logging knowledge graph construction query method, device, equipment and storage medium |
| CN116881398A (en) * | 2023-07-04 | 2023-10-13 | 华院计算技术(上海)股份有限公司 | Method and device for improving information quality generated by large model |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105893391A (en) * | 2015-01-26 | 2016-08-24 | 阿里巴巴集团控股有限公司 | Intelligent answering method, apparatus and system, and electronic device |
| CN108959627A (en) * | 2018-07-23 | 2018-12-07 | 北京光年无限科技有限公司 | Question and answer exchange method and system based on intelligent robot |
| CN109347798A (en) * | 2018-09-12 | 2019-02-15 | 东软集团股份有限公司 | Generation method, device, equipment and the storage medium of network security knowledge map |
| CN109739964A (en) * | 2018-12-27 | 2019-05-10 | 北京拓尔思信息技术股份有限公司 | Knowledge data providing method, device, electronic equipment and storage medium |
| CN110019836A (en) * | 2017-08-23 | 2019-07-16 | 中兴通讯股份有限公司 | A kind of intelligent answer method and device |
| CN110321408A (en) * | 2019-05-30 | 2019-10-11 | 重庆金融资产交易所有限责任公司 | Searching method, device, computer equipment and the storage medium of knowledge based map |
-
2019
- 2019-10-30 CN CN201911044333.3A patent/CN111090739A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105893391A (en) * | 2015-01-26 | 2016-08-24 | 阿里巴巴集团控股有限公司 | Intelligent answering method, apparatus and system, and electronic device |
| CN110019836A (en) * | 2017-08-23 | 2019-07-16 | 中兴通讯股份有限公司 | A kind of intelligent answer method and device |
| CN108959627A (en) * | 2018-07-23 | 2018-12-07 | 北京光年无限科技有限公司 | Question and answer exchange method and system based on intelligent robot |
| CN109347798A (en) * | 2018-09-12 | 2019-02-15 | 东软集团股份有限公司 | Generation method, device, equipment and the storage medium of network security knowledge map |
| CN109739964A (en) * | 2018-12-27 | 2019-05-10 | 北京拓尔思信息技术股份有限公司 | Knowledge data providing method, device, electronic equipment and storage medium |
| CN110321408A (en) * | 2019-05-30 | 2019-10-11 | 重庆金融资产交易所有限责任公司 | Searching method, device, computer equipment and the storage medium of knowledge based map |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111597205A (en) * | 2020-05-26 | 2020-08-28 | 北京金堤科技有限公司 | Template configuration method, information extraction method, device, electronic equipment and medium |
| CN111597205B (en) * | 2020-05-26 | 2024-02-13 | 北京金堤科技有限公司 | Template configuration method, information extraction device, electronic equipment and medium |
| CN111858890A (en) * | 2020-07-23 | 2020-10-30 | 平安证券股份有限公司 | Robot-based consultation method, consultation robot, computer equipment and medium |
| CN111858890B (en) * | 2020-07-23 | 2023-07-21 | 平安证券股份有限公司 | Consultation method based on robot, consultation robot, computer equipment and medium |
| CN112182174A (en) * | 2020-09-24 | 2021-01-05 | 南方电网数字电网研究院有限公司 | Business question-answer knowledge query method and device, computer equipment and storage medium |
| CN112579600A (en) * | 2020-12-21 | 2021-03-30 | 广州橙行智动汽车科技有限公司 | Data processing method and device based on vehicle-mounted question answering |
| CN112650856A (en) * | 2020-12-28 | 2021-04-13 | 上海卓繁信息技术股份有限公司 | Consultation method and device for providing study direction in academic field and electronic equipment |
| CN112948547A (en) * | 2021-01-26 | 2021-06-11 | 中国石油大学(北京) | Logging knowledge graph construction query method, device, equipment and storage medium |
| CN112948547B (en) * | 2021-01-26 | 2024-04-09 | 中国石油大学(北京) | Logging knowledge graph construction query method, device, equipment and storage medium |
| CN116881398A (en) * | 2023-07-04 | 2023-10-13 | 华院计算技术(上海)股份有限公司 | Method and device for improving information quality generated by large model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111090739A (en) | Information processing method, information processing device, electronic device, and storage medium | |
| US10922367B2 (en) | Method and system for providing real time search preview personalization in data management systems | |
| US9501503B2 (en) | Inferring entity attribute values | |
| CN105247507B (en) | Method, system and storage medium for the influence power score for determining brand | |
| US11004123B2 (en) | Method for trading goods on a computer network based on image processing for interest, emotion and affinity detection | |
| KR20160144384A (en) | Context-sensitive search using a deep learning model | |
| US20160299891A1 (en) | Matching of an input document to documents in a document collection | |
| KR20150086441A (en) | Connecting people based on content and relational distance | |
| Heck et al. | Horizontal traceability for just‐in‐time requirements: the case for open source feature requests | |
| CN111125566A (en) | Information acquisition method and device, electronic equipment and storage medium | |
| CN111754278A (en) | Article recommendation method and device, computer storage medium and electronic equipment | |
| CN110110053A (en) | Logical connection is established between indirect language and affairs | |
| CN111949785A (en) | Query statement management method and device, readable storage medium and electronic device | |
| KR101712291B1 (en) | System for recommending a user-customized famous place based on opinion mining and Method of the Same | |
| Kang et al. | Whose opinion matters? analyzing relationships between bitcoin prices and user groups in online community | |
| KR20180049277A (en) | Method and apparatus for recommendation of financial instruments using chatting user platform | |
| Mirtalaie et al. | Sentiment analysis of specific product’s features using product tree for application in new product development | |
| CN109684444A (en) | A kind of intelligent customer service method and system | |
| KR102119083B1 (en) | User review based rating re-calculation apparatus and method, storage media storing the same | |
| CN111723189B (en) | Interactive question and answer prompting method and device, storage medium and electronic equipment | |
| Soliman et al. | Utilizing support vector machines in mining online customer reviews | |
| US10296913B1 (en) | Integration of heterogenous data using omni-channel ontologies | |
| CN113821588A (en) | Text processing method and device, electronic equipment and storage medium | |
| CN110633410A (en) | Information processing method and device, storage medium, and electronic device | |
| Anwar et al. | Social relationship analysis using state-of-the-art embeddings |
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 |