Multi-domain knowledge fusion method for intelligent customer service

Abstract

The invention provides a multi-domain knowledge fusion method for intelligent customer service, and relates to the technical field of data processing, and the method comprises the steps: determining a multi-domain data source based on big data, carrying out the knowledge extraction, carrying out the multi-domain knowledge connection according to an association mapping rule, calling a user target demand, formulating a fusion strategy, and carrying out the screening according to the target demand, knowledge fusion is carried out according to the fusion strategy, knowledge completion is carried out on fused data according to knowledge association, then knowledge field adaptation is carried out, and optimization is carried out according to feedback information. According to the method and the device, the problems that limitation still exists in the aspect of semantic comprehension in the prior art, the intention of the user cannot be accurately understood for the complex or unclear problem can be solved, the user problem can be more comprehensively understood, the answer accuracy and comprehensiveness are improved, and the answer is closer to the level of human customer service.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a multi-domain knowledge fusion method for intelligent customer service. Background Art

[0002] With the popularization of the Internet and the increasing attention paid by enterprises to customer service, customers' requirements for service quality are constantly increasing. Traditional manual customer service has been unable to meet these demands due to high labor costs, low efficiency and unstable service quality. Early intelligent customer service systems were mainly based on rules and templates, and had limited ability to handle complex problems. Subsequently, intelligent customer service systems based on machine learning began to emerge. These systems can understand user intent and provide more accurate answers, but there are still problems with insufficient understanding of context and incomplete answers.

[0003] In summary, existing technologies still have limitations in semantic understanding and cannot accurately understand user intentions for complex or ambiguous questions. Summary of the invention

[0004] The purpose of this application is to provide a multi-domain knowledge fusion method for intelligent customer service, in order to solve the limitations of existing technologies in semantic understanding and the inability to accurately understand the user's intentions for complex or ambiguous questions.

[0005] In view of the above problems, this application provides a multi-domain knowledge fusion method for intelligent customer service.

[0006] The present application provides a multi-domain knowledge fusion method for intelligent customer service, wherein the method includes: determining a multi-domain data source based on big data, extracting knowledge based on the multi-domain data source, and establishing an association mapping rule for the multi-domain knowledge based on the extracted information; connecting the multi-domain knowledge based on the association mapping rule to construct a first multi-domain knowledge information database; retrieving the conversation data of the intelligent customer service to determine the user target demand, and formulating a target knowledge fusion strategy based on the user target demand information; screening the multi-domain knowledge according to the user target demand to obtain a multi-target domain knowledge set, executing the target knowledge fusion strategy to perform knowledge fusion on the multi-target domain knowledge set, and obtaining a target fusion knowledge data set; completing the knowledge of the target fusion knowledge data set based on knowledge association, updating the first multi-domain knowledge information database according to the knowledge completion result, and obtaining a second multi-domain knowledge information database; traversing the second multi-domain knowledge information database to adapt the knowledge domain with the intelligent customer service, generating adaptation feedback information, and optimizing the intelligent customer service according to the adaptation feedback information.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The method determines a multi-domain data source based on big data, extracts knowledge based on the multi-domain data source, establishes an association mapping rule for multi-domain knowledge based on the extracted information; connects the multi-domain knowledge based on the association mapping rule to construct a first multi-domain knowledge information base; retrieves the conversation data of the intelligent customer service to determine the user's target demand, and formulates a target knowledge fusion strategy based on the user's target demand information; screens the multi-domain knowledge according to the user's target demand to obtain a multi-target domain knowledge set, executes the target knowledge fusion strategy to perform knowledge fusion on the multi-target domain knowledge set, and obtains a target fusion knowledge data set; completes the target fusion knowledge data set based on knowledge association, updates the first multi-domain knowledge information base according to the knowledge completion result, and obtains a second multi-domain knowledge information base; traverses the second multi-domain knowledge information base to adapt the knowledge domain with the intelligent customer service, generates adaptation feedback information, and optimizes the intelligent customer service based on the adaptation feedback information, which effectively solves the limitations of the existing technology in semantic understanding. For complex or ambiguous questions, the user's intention cannot be accurately understood, and the user's questions can be understood more comprehensively, the accuracy and comprehensiveness of the answers can be improved, and the answers can be closer to the level of human customer service.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0010] Figure 1 This is a flowchart of the multi-domain knowledge integration method used in intelligent customer service in this application; Figure 2 A flowchart of formulating a target knowledge fusion strategy for the multi-domain knowledge fusion method used in intelligent customer service in this application. DETAILED DESCRIPTION

[0011] This application solves the limitations of the existing technology in semantic understanding by providing a multi-domain knowledge fusion method for intelligent customer service. For complex or ambiguous questions, it is impossible to accurately understand the user's intention. It can understand user questions more comprehensively, improve the accuracy and comprehensiveness of answers, and make them closer to the level of human customer service.

[0012] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0013] Embodiment 1 Please refer to the attached Figure 1 The present application provides a multi-domain knowledge fusion method for intelligent customer service, wherein the method specifically includes the following steps: S1: Determine a multi-domain data source based on big data, extract knowledge based on the multi-domain data source, and establish an association mapping rule for multi-domain knowledge based on the extracted information; Specifically, big data technology is used to collect data sources from different fields. These data sources include public databases, research reports, academic papers, social media, internal corporate data, etc. The collected raw data is cleaned to remove duplicate, erroneous or irrelevant information. The cleaned data is integrated in a certain format to form a unified data set. Natural language processing technology is used to identify entities from text data, such as names of people, places, and organizations. Through semantic analysis and pattern matching and other technologies, the relationship between entities is extracted from the text, such as someone is a member of the management of a company. Identify and extract event information described in the text, such as mergers, acquisitions, and new product launches. Extract attribute information related to the entity, such as the price, color, and size of the product. Match and link the extracted entities with the entities in the existing knowledge base to ensure that the same entity in different data sources can be correctly identified and associated. Based on the extracted relationship information, establish relationship mapping rules between entities in different fields.

[0014] S2: Connecting the multi-domain knowledge based on the association mapping rule to construct a first multi-domain knowledge information base; Specifically, use association mapping rules to connect knowledge entities in different fields. For example, if the rule defines the association between authors and works, connect the corresponding author entity with its work entity. For knowledge entities with multiple associations, ensure that all necessary connections are correctly established according to the rules. Represent the connected multi-domain knowledge in the form of a graph, where nodes represent knowledge entities, such as people, places, concepts, etc., and edges represent the relationship between entities. Use a graph database or a specialized knowledge graph management tool to store and query this graph. Verify the constructed first multi-domain knowledge information base to check whether there are incorrect connections or missing information.

[0015] S3: Retrieve the conversation data of the intelligent customer service to determine the user's target demand, and formulate a target knowledge fusion strategy based on the user's target demand information; Specifically, retrieve the historical conversation data between the user and the customer service from the database of the intelligent customer service system. The conversation data may include text chat records, text converted from speech, user feedback ratings, etc. Use natural language processing technology to perform text analysis on the conversation data to identify the subject, intention, and sentiment of the user's inquiry. Through methods such as keyword extraction and semantic role labeling, deeply understand the user's query content and needs. Analyze the user's feedback ratings and comments to understand the user's satisfaction and dissatisfaction with the current service. Determine the focus of knowledge fusion based on the analysis results of user target needs. For example, if it is found that users often ask questions about product features, then the integration and update of product information should be the focus. Develop a flexible knowledge fusion strategy based on the diversity and complexity of user needs. For common problems, you can strengthen the integration and presentation of relevant knowledge; for professional or complex problems, introduce more professional knowledge resources or expert systems. Optimize the way and timing of knowledge fusion. For example, you can preload the knowledge that may be needed before the user asks a question to reduce the user's waiting time.

[0016] S4: screening the multi-domain knowledge according to the user's target requirements to obtain a multi-target domain knowledge set, executing the target knowledge fusion strategy to fuse the multi-target domain knowledge set to obtain a target fusion knowledge data set; Specifically, use keyword matching, semantic similarity calculation and other methods to select knowledge items that are closely related to user needs. Integrate the selected relevant knowledge into a multi-target domain knowledge set. This knowledge set will contain relevant knowledge points in multiple fields that meet user needs. According to the formulated target knowledge fusion strategy, the multi-target domain knowledge set is fused. Fusion may include merging repeated or similar knowledge items, supplementing missing information, correcting inaccurate data, etc. After fusion processing, a more refined, accurate and user-satisfied target fusion knowledge data set is obtained.

[0017] S5: performing knowledge completion on the target fusion knowledge data set based on knowledge association, updating the first multi-domain knowledge information base according to the knowledge completion result, and obtaining a second multi-domain knowledge information base; Specifically, the knowledge items in the target fusion knowledge dataset are analyzed to identify potential associations between them. These associations may include relationships between entities, hierarchical structures between concepts, temporal relationships between events, etc. By comparing and analyzing the associations between knowledge items, possible missing knowledge links or information are discovered. For example, if there is a clear association between two entities, but there is no direct description of this association in the knowledge dataset, then this is a missing knowledge point. Formulate a knowledge completion strategy, which may include using external data sources, reasoning mechanisms, or machine learning algorithms to predict and fill in missing knowledge. External data sources can be public databases, professional websites, or relevant literature. Reasoning mechanisms can perform logical inferences based on existing knowledge associations to discover new associations or attribute values. According to the formulated strategy, missing knowledge is obtained from external data sources, or new knowledge points are inferred through reasoning mechanisms. The completed knowledge is verified to ensure its authenticity and accuracy. The verified knowledge is integrated with the original target fusion knowledge dataset. Update the first multi-domain knowledge information base: The integrated knowledge dataset is used to update the first multi-domain knowledge information base, replacing or adding corresponding knowledge items.

[0018] S6: traverse the second multi-domain knowledge information base to adapt the knowledge domain with the intelligent customer service, generate adaptation feedback information, and optimize the intelligent customer service according to the adaptation feedback information.

[0019] Specifically, systematically access each knowledge entry in the second multi-domain knowledge information base. Ensure that various types of knowledge, such as entities, relationships, events, etc., can be identified and processed during the traversal process. For each knowledge entry, check whether the intelligent customer service system can understand and process the relevant knowledge. Test the responsiveness and accuracy of the intelligent customer service system to knowledge in different fields. Record the success and failure cases in the adaptation process, as well as the performance of the intelligent customer service system in processing knowledge. According to the problems pointed out in the adaptation feedback, make corresponding adjustments and optimizations to the intelligent customer service system. Including improving the natural language processing model, adding knowledge bases in specific fields, optimizing dialogue strategies, etc. If the knowledge in certain fields is too complex or difficult to understand for intelligent customer service, consider introducing human assistants to assist in processing. After each optimization, re-perform the adaptation test. Continuously adjust and optimize the system according to the test results until a satisfactory performance level is achieved.

[0020] Furthermore, step S1 of the present application also includes: Use big data technology to screen and identify data sets in multiple fields, and determine multi-field data sources based on the identification results; Integrate the multi-domain data sources to build a multi-domain data lake; Perform entity recognition based on the multi-domain data lake to generate multiple entities, use relationship extraction technology to identify the association relationship between the multiple entities for formal construction, and obtain knowledge triples; Acquire association rules between multi-domain knowledge in the multi-domain knowledge lake by using an association rule mining algorithm according to the knowledge triples; By calculating the similarity of the multi-domain knowledge, a mapping rule between the multi-domain knowledge is formulated according to the association rule.

[0021] Specifically, through big data processing frameworks such as Hadoop and Spark, data sets from different fields are screened and identified. Data sources are determined based on factors such as data quality, relevance, and reliability. Data cleaning, conversion, and integration are performed on the screened multi-domain data sources to ensure the uniformity of data formats and standards. All integrated data are stored in a centralized data lake, which will serve as the basis for subsequent knowledge extraction and association analysis. Natural language processing techniques, such as named entity recognition, are used to identify entities such as names of people, places, and companies from the multi-domain data lake. Relationship extraction techniques are used to identify the associations between multiple entities and represent these relationships in a formalized manner, such as triples of entity 1, relationship, and entity 2. Based on knowledge triples, association rule mining algorithms such as Apriori and FP-Growth are used to find association rules between multi-domain knowledge. The mined association rules are analyzed and verified to determine which rules are meaningful. Cross-domain knowledge associations are identified by calculating the similarity between knowledge in different fields, such as cosine similarity based on text vectors. Mapping rules between multi-domain knowledge are formulated based on association rules and similarity calculation results. These rules can be used to associate and integrate knowledge from different fields.

[0022] Further, if Figure 2 , step S3 of this application also includes: Analyze the conversation data to identify multiple user demand information, perform cluster analysis on the multiple user demand information according to the multi-domain knowledge, and extract the largest cluster according to the cluster analysis result; Determine the user target requirement based on the largest cluster, determine multiple knowledge domain fusion levels according to the user target requirement, and define the knowledge domain fusion scope; The knowledge domain fusion range is used as a fusion boundary value, and the target knowledge fusion strategy is formulated according to the multiple knowledge domain fusion levels.

[0023] Specifically, collect the conversation data between users and intelligent customer service or related systems. Use natural language processing technology to analyze the conversation data, identify and extract the topics, intentions, keywords, etc. of the user's inquiries as user demand information. Cluster the identified multiple user demand information according to multi-domain knowledge. Here, you can use algorithms such as K-means and hierarchical clustering to cluster similar user demand information into one category. Analyze the clustering results and find the cluster containing the most user demand information. This cluster represents the most concentrated and common needs of users. Based on the user demand information in the largest cluster, summarize the main target needs of users. According to the user's target needs, analyze which knowledge fields need to be integrated and the correlation level between these fields. According to the user's target needs and the knowledge field integration level, clarify the specific knowledge field range that needs to be integrated, which will serve as the boundary value of knowledge integration. Based on the defined knowledge field integration range and combined with the integration level of multiple knowledge fields, formulate a specific integration strategy. This includes determining which knowledge needs to be integrated first and how to integrate knowledge from different fields.

[0024] Furthermore, the present application also includes: Establishing knowledge credibility based on the fusion boundary value, traversing the multiple knowledge domain fusion levels according to the knowledge credibility, and determining in turn whether each knowledge domain fusion level meets a preset credibility threshold; If satisfied, the priority of the target knowledge domain fusion level is assigned; if not satisfied, the priority of the target knowledge domain fusion level is reset, and the process is repeated until each knowledge domain fusion level has a priority; The plurality of knowledge domain fusion levels are arranged in descending order according to the priority, and the target knowledge fusion strategy is formulated according to the priority sequence.

[0025] Specifically, based on the fusion boundary value, an initial credibility value is assigned to each knowledge domain or knowledge point. This credibility value can be set according to factors such as the reliability of the data source, the frequency of knowledge update, and historical usage feedback. For example, a credibility range from 0 to 1 can be set, where 1 indicates complete credibility and 0 indicates complete untrustworthiness. Traverse according to the determined multiple knowledge domain fusion levels. For each fusion level, evaluate the credibility of the knowledge points contained therein. Set a preset credibility threshold to determine whether the credibility of the knowledge point or knowledge domain meets the requirements. If the credibility of a knowledge domain fusion level meets, that is, is greater than or equal to, the preset credibility threshold, the level is considered to be credible. If the credibility of the knowledge domain fusion level meets the preset threshold, the priority of the level is assigned, for example, a relatively high priority value can be assigned. If not, the priority of the level is reset, for example, a lower priority value can be assigned, or it can be directly set to the default priority. Repeat the above steps until each knowledge domain fusion level is assigned a priority. According to the priority value of each knowledge domain fusion level, all levels are sorted in descending order. The fusion level with high priority will be ranked first, indicating that it should be processed first in the knowledge fusion process. Based on the arranged priority sequence, a specific knowledge fusion strategy is formulated. The knowledge domain or level with high priority will receive more fusion resources and attention to ensure the accuracy and effectiveness of the fusion results.

[0026] Furthermore, step S4 of the present application also includes: Analyze the user's target requirements to set an expected threshold, perform knowledge retrieval according to the expected threshold, and obtain a retrieved knowledge set; Performing knowledge screening on the retrieval knowledge set based on knowledge timeliness to obtain the multi-target domain knowledge set; Specifically, based on user needs, set appropriate expected thresholds for knowledge retrieval, such as requirements for relevance, timeliness, and authority. Use the set expected thresholds to retrieve relevant information in the knowledge base and obtain a preliminary retrieval knowledge set. Filter the retrieved knowledge to remove outdated or no longer relevant information to ensure the timeliness and accuracy of the knowledge, thereby forming a multi-target domain knowledge set. The filtered domain knowledge that is closely related to user needs is combined into a multi-target domain knowledge set, and each target domain knowledge set corresponds to a specific user need.

[0027] Furthermore, step S4 of the present application also includes: Based on the knowledge fusion channel, each target domain knowledge set in the multi-target domain knowledge set is fused through the target knowledge fusion strategy to determine whether there is a fusion conflict in the knowledge fusion; When there is a fusion conflict, the conflict type is identified, a conflict resolution strategy is formulated according to the conflict type, and the conflict resolution strategy is executed to complete the knowledge fusion of the multi-target domain knowledge sets and obtain the target fusion knowledge data set.

[0028] Specifically, each target domain knowledge in the multi-target domain knowledge set is fused through the formulated target knowledge fusion strategy. During the fusion process, detect whether there is a fusion conflict, such as inconsistent, repeated or contradictory information. Once a fusion conflict is found, first identify the specific type of conflict, such as data inconsistency, information redundancy, etc. According to the identified conflict type, formulate corresponding resolution strategies, such as conflict resolution, conflict avoidance, conflict ignoring, etc. Implement the formulated conflict resolution strategy to ensure the accuracy and completeness of knowledge fusion. After the above steps, a conflict-free, high-quality target fusion knowledge dataset is finally obtained.

[0029] Furthermore, the present application also includes: If there is a fusion conflict in the knowledge fusion, the fusion conflict data is recorded and the source of the conflict is analyzed; Perform knowledge tracing based on the conflict source, and generate fusion conflict constraints according to the tracing result; The fusion conflict constraints are integrated and synchronized to the knowledge fusion channel.

[0030] Specifically, when conflicts are detected during the knowledge fusion process, these conflict data are automatically recorded. The recorded content includes the conflicting knowledge points, the type of conflict, the data sources involved, etc. The recorded conflict data is deeply analyzed to determine the source of the conflict. Possible sources of conflict include inconsistency of data sources, differences in knowledge representation, outdated information, etc. Based on the analyzed sources of conflict, knowledge tracing is performed. This includes tracing the source of knowledge points and understanding how they are collected, processed, and fused. The results of tracing reveal problems with data sources, errors in processing, or inconsistencies in knowledge representation. Based on the tracing results, specific fusion conflict constraints are generated. These constraints are rules, conditions, or policies designed to prevent similar conflicts from happening again in the future. The generated fusion conflict constraints are integrated into the knowledge fusion system. This may include updates to the system rule base, policy base, or algorithm logic. Ensure that these new constraints are synchronized to the knowledge fusion channel so that they can be applied and executed in subsequent knowledge fusion processes.

[0031] Furthermore, step S5 of the present application also includes: Performing knowledge association analysis on the target fusion knowledge data set to obtain knowledge association factors; Constructing a knowledge association network based on the knowledge association factors; Traversing the target fusion knowledge data set through the knowledge association network to identify missing information and determine missing knowledge information; A knowledge completion instruction is generated according to the knowledge missing information, and the target fusion knowledge data set is completed through the knowledge completion instruction to generate the knowledge completion result.

[0032] Specifically, the target knowledge data set that has been fused is deeply analyzed to identify the potential associations between different knowledge points. By analyzing the co-occurrence relationship, causal relationship, similarity, etc. in the data set, knowledge association factors are extracted. These association factors are the basis for building a knowledge association network. Based on the extracted knowledge association factors, a knowledge association network is constructed. In this network, nodes represent different knowledge points, and edges represent the associations between these knowledge points. The network is optimized, such as removing weakly associated or redundant edges to highlight the core association structure. By traversing the constructed knowledge association network, each node and edge in the network is checked to identify possible knowledge gaps. During the traversal process, if it is found that some key nodes lack necessary connections or some important associations are not established, it is determined to be knowledge missing information. According to the identified knowledge missing information, corresponding knowledge completion instructions are generated. These instructions include adding new associations, improving node information, etc. By executing these knowledge completion instructions, the target fused knowledge data set is completed. After the completion operation, a more complete and more closely associated knowledge base is generated as the final result.

[0033] In summary, the multi-domain knowledge fusion method for intelligent customer service provided by this application has the following technical effects: The method determines a multi-domain data source based on big data, extracts knowledge based on the multi-domain data source, establishes an association mapping rule for multi-domain knowledge based on the extracted information; connects the multi-domain knowledge based on the association mapping rule to construct a first multi-domain knowledge information base; retrieves the conversation data of the intelligent customer service to determine the user's target demand, and formulates a target knowledge fusion strategy based on the user's target demand information; screens the multi-domain knowledge according to the user's target demand to obtain a multi-target domain knowledge set, executes the target knowledge fusion strategy to perform knowledge fusion on the multi-target domain knowledge set, and obtains a target fusion knowledge data set; completes the target fusion knowledge data set based on knowledge association, updates the first multi-domain knowledge information base according to the knowledge completion result, and obtains a second multi-domain knowledge information base; traverses the second multi-domain knowledge information base to adapt the knowledge domain with the intelligent customer service, generates adaptation feedback information, and optimizes the intelligent customer service based on the adaptation feedback information, which effectively solves the limitations of the existing technology in semantic understanding. For complex or ambiguous questions, the user's intention cannot be accurately understood, and the user's questions can be understood more comprehensively, the accuracy and comprehensiveness of the answers can be improved, and the answers can be closer to the level of human customer service.

[0034] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0035] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A multi-domain knowledge fusion method for intelligent customer service, characterized in that: The method comprises: Determine multi-domain data sources based on big data, extract knowledge based on the multi-domain data sources, and establish association mapping rules for multi-domain knowledge based on the extracted information; Connecting the multi-domain knowledge based on the association mapping rule to construct a first multi-domain knowledge information base; Retrieve the conversation data of the intelligent customer service to determine the user's target needs, and formulate a target knowledge fusion strategy based on the user's target demand information; Screening the multi-domain knowledge according to the user's target requirements to obtain a multi-target domain knowledge set, executing the target knowledge fusion strategy to fuse the multi-target domain knowledge set to obtain a target fusion knowledge data set; Performing knowledge completion on the target fusion knowledge data set based on knowledge association, updating the first multi-domain knowledge information base according to the knowledge completion result, and acquiring a second multi-domain knowledge information base; The second multi-domain knowledge information base is traversed to perform knowledge domain adaptation with the intelligent customer service, adaptation feedback information is generated, and the intelligent customer service is optimized according to the adaptation feedback information.

2. The method according to claim 1, characterized in that Determine multi-domain data sources based on big data, extract knowledge based on the multi-domain data sources, and establish association mapping rules for multi-domain knowledge based on the extracted information. The method includes: Use big data technology to screen and identify data sets in multiple fields, and determine multi-field data sources based on the identification results; Integrate the multi-domain data sources to build a multi-domain data lake; Perform entity recognition based on the multi-domain data lake to generate multiple entities, use relationship extraction technology to identify the association relationship between the multiple entities for formal construction, and obtain knowledge triples; Acquire association rules between multi-domain knowledge in the multi-domain knowledge lake by using an association rule mining algorithm according to the knowledge triples; By calculating the similarity of the multi-domain knowledge, a mapping rule between the multi-domain knowledge is formulated according to the association rule.

3. The method according to claim 1, characterized in that Retrieving the conversation data of the intelligent customer service to determine the user's target demand, and formulating a target knowledge fusion strategy according to the user's target demand information, the method includes: Analyze the conversation data to identify multiple user demand information, perform cluster analysis on the multiple user demand information according to the multi-domain knowledge, and extract the largest cluster according to the cluster analysis result; Determine the user target requirement based on the largest cluster, determine multiple knowledge domain fusion levels according to the user target requirement, and define the knowledge domain fusion scope; The knowledge domain fusion range is used as a fusion boundary value, and the target knowledge fusion strategy is formulated according to the multiple knowledge domain fusion levels.

4. The method according to claim 3, characterized in that The method of taking the knowledge domain fusion range as the fusion boundary value and formulating the target knowledge fusion strategy according to the multiple knowledge domain fusion levels includes: Establishing knowledge credibility based on the fusion boundary value, traversing the multiple knowledge domain fusion levels according to the knowledge credibility, and determining in turn whether each knowledge domain fusion level meets a preset credibility threshold; If satisfied, the priority of the target knowledge domain fusion level is assigned; if not satisfied, the priority of the target knowledge domain fusion level is reset, and the process is repeated until each knowledge domain fusion level has a priority; The plurality of knowledge domain fusion levels are arranged in descending order according to the priority, and the target knowledge fusion strategy is formulated according to the priority sequence.

5. The method according to claim 1, characterized in that The multi-domain knowledge is screened according to the user's target requirements to obtain a multi-target domain knowledge set, the method comprising: Analyze the user's target requirements to set an expected threshold, perform knowledge retrieval according to the expected threshold, and obtain a retrieved knowledge set; The retrieval knowledge set is screened based on knowledge timeliness to obtain the multi-target domain knowledge set.

6. The method according to claim 1, characterized in that Executing the target knowledge fusion strategy to fuse the multi-target domain knowledge set to obtain a target fusion knowledge data set, the method includes: Based on the knowledge fusion channel, each target domain knowledge set in the multi-target domain knowledge set is fused through the target knowledge fusion strategy to determine whether there is a fusion conflict in the knowledge fusion; When there is a fusion conflict, the conflict type is identified, a conflict resolution strategy is formulated according to the conflict type, and the conflict resolution strategy is executed to complete the knowledge fusion of the multi-target domain knowledge sets and obtain the target fusion knowledge data set.

7. The method according to claim 6, characterized in that The method also includes: If there is a fusion conflict in the knowledge fusion, the fusion conflict data is recorded and the source of the conflict is analyzed; Perform knowledge tracing based on the conflict source, and generate fusion conflict constraints according to the tracing result; The fusion conflict constraints are integrated and synchronized to the knowledge fusion channel.

8. The method according to claim 1, characterized in that The target fusion knowledge data set is supplemented with knowledge based on knowledge association, the first multi-domain knowledge information base is updated according to the knowledge supplement result, and a second multi-domain knowledge information base is obtained, the method comprising: Performing knowledge association analysis on the target fusion knowledge data set to obtain knowledge association factors; Constructing a knowledge association network based on the knowledge association factors; Traversing the target fusion knowledge data set through the knowledge association network to identify missing information and determine missing knowledge information; A knowledge completion instruction is generated according to the knowledge missing information, and the target fusion knowledge data set is completed through the knowledge completion instruction to generate the knowledge completion result.

Images