CN113590838A

CN113590838A - Customer service enabling method and system based on knowledge graph and storage medium

Info

Publication number: CN113590838A
Application number: CN202110869988.5A
Authority: CN
Inventors: 于皓; 张�杰; 吴信东; 吴明辉; 罗华刚; 邓礼志; 陈栋; 袁杰; 李犇
Original assignee: Shanghai Minglue Artificial Intelligence Group Co Ltd
Current assignee: Shanghai Minglue Artificial Intelligence Group Co Ltd
Priority date: 2021-07-30
Filing date: 2021-07-30
Publication date: 2021-11-02

Abstract

The application relates to a customer service enabling method, a customer service enabling system and a storage medium based on a knowledge graph, wherein the method comprises the following steps: processing the knowledge corpus based on a field by utilizing a pre-established entity relation extraction model to obtain a knowledge set in the knowledge corpus, aligning the knowledge set by using entities, and establishing normalized field knowledge; according to the domain knowledge, a domain knowledge spectrogram is constructed by using an entity linking method, and a knowledge query service interface is established based on the domain knowledge spectrogram; establishing vectorization representation of the products according to the domain knowledge graph, clustering the products to form similar product clusters according to the vectorization representation, and establishing a product cluster query interface; and performing entity extraction on the consultation problems of the customers in real time, calling the interface to inquire according to the extracted entities and/or products, acquiring relevant knowledge and presenting the knowledge to a customer service interface. According to the method, the client service is helped to acquire the knowledge related to the client consultation problem through an automatic knowledge extraction and retrieval method, and the service efficiency of the client service is improved.

Description

Customer service enabling method and system based on knowledge graph and storage medium

Technical Field

The application relates to the technical field of recommendation, in particular to a customer service enabling method, a customer service enabling system and a storage medium based on knowledge graphs.

Background

In the knowledge complexity industry, such as the cosmetics industry, products are full of sight, few products are hundreds of products, many products are thousands of product libraries and various application ranges and functions, in the face of consultation requirements of different clients, domain clients are difficult to master enough knowledge, a query system in an enterprise needs to be combined to inquire and retrieve relevant data, the questions of the clients are answered after manual arrangement and processing, the clients cannot timely feed back, user experience is poor, and rapid development of the enterprises is hindered.

The existing customer service system can arrange and summarize the questions of the customers, form documents for common questions to assist the customer service in answering the questions, form a large amount of data documents for scenes such as numerous products and the like, and the customer service needs to inquire and retrieve and answer the customers, so that a certain time difference still exists, the working efficiency of the customer service is low, and the satisfaction degree of the customers is low.

At present, no effective solution is provided for the problem of low customer service work efficiency in the related technology.

Disclosure of Invention

The embodiment of the application provides a customer service enabling method, a customer service enabling system and a storage medium based on a knowledge graph, and aims to at least solve the problem that the customer service working efficiency is not high in the related technology.

In a first aspect, an embodiment of the present application provides a customer service enabling method based on a knowledge-graph, which is characterized by including:

a domain knowledge establishing step, namely processing the knowledge corpus based on a domain by utilizing a pre-established entity relationship extraction model to obtain a knowledge set in the knowledge corpus, aligning the entities of the knowledge set and establishing normalized domain knowledge;

a knowledge query service interface construction step, namely constructing a domain knowledge spectrogram by using an entity link method according to domain knowledge, and establishing a knowledge query service interface based on the domain knowledge spectrogram;

a product cluster query interface construction step, namely establishing vectorization representation of products according to the domain knowledge graph, clustering the products to form similar product clusters according to the vectorization representation, and constructing a product cluster query interface;

and a query result display step, namely performing entity extraction on the consultation problems of the customers in real time, calling the interface to perform query according to the extracted entities and/or products, and acquiring related knowledge and presenting the related knowledge to the customer service interface.

In some embodiments, the method further comprises a KOL grass seed retrieval step, specifically comprising:

a corpus marking step, marking the corpus by using an entity relation extraction model based on KOL corpus in the social corpus;

and a KOL original corpus retrieval interface construction step, wherein the obtained tags and the KOL corpus are subjected to associated storage, an index is built based on the tags, and accordingly the KOL original corpus retrieval interface based on the tags is constructed.

In some embodiments, the step of building the entity relationship extraction model includes:

a labeling expectation obtaining step, namely labeling knowledge corpora in the field and constructing the relation between corresponding related entities to obtain a labeling corpora for training;

and an extraction model establishing step, namely performing deep learning by utilizing a Bert algorithm based on the labeled expectation to establish a physical relation extraction model.

In some embodiments, the domain knowledge graph can be supplemented based on knowledge of distance and semantics, and the domain knowledge graph is expanded.

In some embodiments, the step of building the product cluster query interface further comprises:

a product vectorization expression step, namely vectorizing the entity and the entity relation based on the domain knowledge graph, and establishing vectorization expression of the product according to the vectorization expression;

a similar product cluster establishing step, namely calculating the vectorization distance between products according to the vectorization expression of the products, clustering the products and establishing a similar product cluster;

and a query interface construction step, namely constructing a product cluster query interface based on keyword matching according to the similar product clusters.

In a second aspect, the present application provides a knowledge-graph-based customer service enabling system, configured to execute the knowledge-graph-based customer service enabling method according to the first aspect, including:

the domain knowledge establishing module is used for processing the knowledge corpus based on a domain by utilizing a pre-established entity relationship extraction model to obtain a knowledge set in the knowledge corpus, aligning the entities of the knowledge set and establishing normalized domain knowledge;

the knowledge query service interface construction module is used for constructing a domain knowledge spectrogram by using an entity link method according to domain knowledge and establishing a knowledge query service interface based on the domain knowledge spectrogram;

the product cluster query interface construction module is used for establishing vectorization representation of products according to the domain knowledge graph, clustering the products to form similar product clusters according to the vectorization representation, and constructing a product cluster query interface;

the KOL grass retrieval module is used for marking the social linguistic data by using an entity relation extraction model based on the KOL linguistic data in the social linguistic data, performing associated storage on the obtained labels and the KOL linguistic data, establishing indexes based on the labels, and accordingly constructing a KOL original linguistic data retrieval interface based on the labels;

and the query result display module is used for extracting entities from the consultation problems of the customers in real time, querying through the interface according to the extracted entities and/or products, acquiring relevant knowledge and presenting the knowledge to the customer service interface.

In some embodiments, the domain knowledge building module further comprises:

a labeling expectation obtaining unit, labeling knowledge corpora of the field and constructing the relation between corresponding related entities to obtain a labeling corpora for training;

and the extraction model establishing unit is used for carrying out deep learning by utilizing a Bert algorithm based on the labeled expectation and establishing an entity relation extraction model.

And the knowledge map expanding unit is used for completing the domain knowledge map based on the knowledge of distance and semantics and expanding the domain knowledge map.

In some embodiments, the product cluster query interface construction module further comprises:

the product vectorization representation unit is used for vectorizing the entity and the entity relation based on the domain knowledge graph and establishing vectorization representation of the product according to the vectorization representation;

the similar product cluster establishing unit is used for calculating the vectorization distance between the products according to the vectorization expression of the products, clustering the products and establishing a similar product cluster;

and the query interface construction unit is used for constructing a product cluster query interface based on keyword matching according to the similar product clusters.

In a third aspect, the present application provides a computer device, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the computer program, implements the knowledgegraph-based customer service enabling method as described in the first aspect.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements a method for knowledgegraph-based customer service enablement as described in the first aspect above.

Compared with the related technology, the customer service enabling method, the customer service enabling system and the storage medium based on the knowledge graph can be applied to the technical field of the knowledge graph and the technical field of knowledge reasoning, normalized domain knowledge is established for knowledge corpora in a certain field, a knowledge query service interface is established, a product cluster query interface is provided for customer service query, customer service is helped to acquire knowledge related to customer consultation problems, errors caused by insufficient knowledge of the customer service are solved, and the service efficiency and the customer satisfaction of the customer service are improved.

The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the application.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:

FIG. 1 is a flow diagram of a method for knowledgegraph-based customer service enablement in accordance with an embodiment of the present application;

FIG. 2 is a flowchart of steps for building an entity relationship extraction model according to an embodiment of the present application;

FIG. 3 is a flowchart of a product cluster query interface construction step according to an embodiment of the present application;

FIG. 4 is a flow diagram of a knowledge-graph based customer service enablement method in accordance with a preferred embodiment of the present application;

FIG. 5 is a block diagram of a knowledge-graph based customer service enabling system according to an embodiment of the present application;

fig. 6 is a hardware structure diagram of a computer device according to an embodiment of the present application.

Description of the drawings:

a domain knowledge building module 1; a knowledge inquiry service interface construction module 2;

a product cluster query interface construction module 3; a KOL grass planting retrieval module 4; a query result display module 5;

labeling the expectation obtaining unit 11; an extraction model establishing unit 12; a knowledge map expanding unit 13;

a product vectorization representation unit 31; a similar product cluster establishing unit 32; query interface construction unit 33

A processor 81; a memory 82; a communication interface 83; a bus 80.

Detailed Description

In order to make the purpose, technical solution and advantages of the present application more apparent, the present application will be described and illustrated with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application.

It is obvious that the drawings in the following description are only examples or embodiments of the present application, and that it is also possible for a person skilled in the art to apply the present application to other similar contexts on the basis of these drawings without inventive effort. Moreover, it should be further appreciated that such a development effort might be complex and tedious, but would nevertheless be a routine undertaking of design, fabrication, and manufacture for those of ordinary skill having the benefit of this disclosure, and it should be understood that such a development effort might be complex and tedious.

Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.

Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar words throughout this application are not to be construed as limiting in number, and may refer to the singular or the plural. The present application is directed to the use of the terms "including," "comprising," "having," and any variations thereof, which are intended to cover non-exclusive inclusions; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or elements, but may include additional steps or elements not listed, or may include additional steps or elements inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as referred to herein means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the front and back associated objects are in an "or" relationship. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.

The embodiment provides a customer service enabling method based on a knowledge graph. FIG. 1 is a flow chart of a method for service energization based on knowledge-graph according to an embodiment of the present application, as shown in FIG. 1, the flow chart includes the following steps:

a domain knowledge establishing step S1, processing the knowledge corpus based on a domain by using a pre-established entity relationship extraction model to obtain a knowledge set in the knowledge corpus, aligning the knowledge set by using entities, and establishing normalized domain knowledge;

a knowledge inquiry service interface construction step S2, constructing a domain knowledge map by using an entity linking method according to domain knowledge, and establishing a knowledge inquiry service interface based on the domain knowledge map;

a product cluster query interface construction step S3, wherein vectorization representation of the products is established according to the domain knowledge graph, and the products are clustered to form similar product clusters according to the vectorization representation, so that a product cluster query interface is constructed;

and a query result display step S5, wherein the query question of the customer is extracted in real time, the interface is called to query according to the extracted entity and/or product, and relevant knowledge is obtained and presented to the customer service interface.

Through the steps, the normalized domain knowledge is obtained by processing the domain knowledge, so that the subsequent construction of the knowledge map is convenient to prepare; establishing a domain knowledge graph by using an entity linking method according to the domain knowledge, and establishing a domain knowledge graph to establish a knowledge query service interface; and constructing a product cluster query interface according to the domain knowledge graph, providing an interface, performing entity extraction on the questions proposed by the client, calling the interface to perform query based on an entity extraction result, returning and presenting the query result to the client interface, and assisting the client to answer the questions proposed by the client. Through the automatic knowledge extraction and retrieval method, the customer service is helped to acquire knowledge related to customer consultation problems, and the service efficiency and the customer satisfaction of the customer service are improved.

The entity linking method comprises two steps, namely a nominal identification process and an entity disambiguation process (or candidate entity generation process and candidate entity sorting process), and different research division modes are slightly different.

The first step of entity linking is to carry out designation recognition, wherein a designation-entity dictionary is firstly constructed, most researchers extract the titles of the entity pages, disambiguation pages and redirection pages of Wikipedia as entity designations, and establish the designation-entity dictionary, and other establishing modes such as extracting the standard names and the alias names of the entities in Freebase. And then, identifying the entity designation according to a certain rule, for example, carrying out designation identification by utilizing case rule and first-check statistical information, and selecting an entity sequence with the highest consistency between the entity context and the entity Wikipedia homepage and the candidate entity. And identifying the index by using the link probability, and determining a final entity sequence by comprehensively using a knowledge engineering method and a naive Bayes classification method.

Since one reference may point to multiple entities, there is a need to determine the entity to which the reference points in some way, i.e., entity disambiguation. The existing entity disambiguation method mainly comprises machine learning, sequencing learning, graph model, unsupervised method, integration method and the like.

The above-mentioned method for constructing the knowledge graph is through an entity linking method, but the present invention is not limited to the method for constructing the knowledge graph.

In some embodiments, the method further includes a KOL grass seed retrieval step S4, specifically including:

a corpus marking step S41, marking the KOL corpus in the social corpus by using an entity relation extraction model based on the KOL corpus;

and a KOL original corpus retrieval interface construction step S42, performing association storage on the obtained tags and the KOL corpus, and establishing an index based on the tags, thereby constructing a tag-based KOL original corpus retrieval interface.

Through the steps, another retrieval interface is provided for customer query, and in the embodiment of the application, retrieval directions of a plurality of interfaces in a plurality of angles are provided, so that query is comprehensive, a theoretical basis of customer service is provided, and better customer service energization is facilitated.

In some embodiments, fig. 2 is a flowchart of steps of building an entity relationship extraction model according to an embodiment of the present application, and as shown in fig. 2, the steps of building the entity relationship extraction model include:

a labeling expectation obtaining step S11, labeling knowledge corpora in the field and constructing a relation between corresponding related entities to obtain a labeling corpora for training;

and an extraction model establishing step S12, based on the labeled expectation, performing deep learning by using a Bert algorithm, and establishing an entity relationship extraction model.

The knowledge corpus of the annotation field in the annotation expectation obtaining step S11 may include entities such as brands, categories, achievements, efficacies, and the like, which are annotated to the corpus related to the makeup in the microblog.

In some embodiments, fig. 3 is a flowchart of a product cluster query interface constructing step according to an embodiment of the present application, and as shown in fig. 3, the product cluster query interface constructing step S3 further includes:

a product vectorization representation step S31, wherein the entity and the entity relation are vectorized and represented based on the domain knowledge graph, and the vectorization representation of the product is established according to the entity and the entity relation;

a similar product cluster establishing step S32, calculating the vectorization distance between products according to the vectorization expression of the products, clustering the products and establishing a similar product cluster;

and a query interface construction step S33, wherein a product cluster query interface based on keyword matching is constructed according to the similar product clusters.

The embodiments of the present application are described and illustrated below by means of preferred embodiments.

FIG. 4 is a flow chart of a method for knowledgegraph-based customer service enablement in accordance with a preferred embodiment of the present application.

S401, a domain knowledge extraction step

Step 1: labeling domain knowledge corpora, for example, labeling entities such as brands, categories, achievements, efficacies and the like of the corpora related to the makeup in the microblog, constructing the relationship among the related entities, and constructing a labeled corpora for training;

step 2: deep learning is carried out on the labeled corpus in the step 1 by utilizing a Bert algorithm, and an extraction model of entities and relations is established;

and step 3: processing a large number of linguistic data in the field by using the model in the step 2 to obtain a knowledge set in the linguistic data in the field;

and 4, step 4: and (4) carrying out entity alignment on the knowledge set in the domain linguistic data obtained in the step (3) and establishing normalized domain knowledge.

S402, establishing and inquiring a domain map

And 5: constructing a domain knowledge graph by using an entity linking method based on the domain knowledge obtained in the step (4);

step 6: performing knowledge completion based on distance and semantics on the knowledge obtained in the step (5), and establishing a relatively complete domain knowledge map;

and 7: establishing a knowledge query service interface based on the step 6.

S403, similarity product calculation and query steps

And 8: vectorizing and representing the network structure of the entity of the domain knowledge graph constructed in the step 6;

and step 9: vectorizing and representing the attributes of the product entities in the domain knowledge graph in the step 6;

step 10: combining and representing the vectorization constructed in the steps 8 and 9, and establishing vectorization representation of the product;

step 11: clustering the products by calculating vectorization distance between the products to establish a similar product cluster;

step 12: and constructing a product cluster query interface based on keyword matching.

S404, KOL grass search step

Step 13: labeling all KOL corpora in the social corpora according to the language materials by using the extraction model in the step 2;

step 14: performing associated storage on the tags and the original corpus acquired in the step 13, and establishing indexes aiming at the tags;

step 15: and constructing a KOL original corpus retrieval interface based on the label.

S405, customer service knowledge enabling step

Step 16: the consultation problems of the customers are extracted in real time;

and step 17: querying the entity associated knowledge from S402 according to the entity of step 16;

step 18: according to the product of step 16, similar products are inquired from S403;

step 19: according to the entity in the step 16, related KOL original linguistic data are inquired from the S404;

step 20: and presenting the knowledge related to the problems of the step 16 to the step 19 to a customer service interface.

It should be noted that the steps illustrated in the above-described flow diagrams or in the flow diagrams of the figures may be performed in a computer system such as a set of computer-executable instructions and that, while the logic order is illustrated in the flow diagrams, in some cases, the steps illustrated or described may be performed in an order different than here. For example, the order between steps 17, 18 and 19 is not fixed and may be reversed.

The embodiment also provides a customer service enabling system based on the knowledge graph, and the device is used for realizing the embodiment and the preferred embodiment, which have already been described and are not repeated. As used below, the terms "module," "unit," "subunit," and the like may implement a combination of software and/or hardware for a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.

FIG. 5 is a block diagram of a knowledge-graph based customer service enabling system according to an embodiment of the present application, as shown in FIG. 5, comprising:

the domain knowledge establishing module 1 is used for processing the knowledge corpus based on a domain by utilizing a pre-established entity relationship extraction model to obtain a knowledge set in the knowledge corpus, aligning the entities of the knowledge set and establishing normalized domain knowledge;

the knowledge inquiry service interface construction module 2 is used for constructing a domain knowledge spectrogram by using an entity link method according to domain knowledge and establishing a knowledge inquiry service interface based on the domain knowledge spectrogram;

the product cluster query interface construction module 3 is used for establishing vectorization representation of products according to the domain knowledge graph, clustering the products to form similar product clusters according to the vectorization representation, and constructing a product cluster query interface;

the KOL grass retrieval module 4 is used for marking the social linguistic data by using an entity relation extraction model based on the KOL linguistic data in the social linguistic data, performing associated storage on the obtained labels and the KOL linguistic data, establishing indexes based on the labels, and accordingly establishing a KOL original linguistic data retrieval interface based on the labels;

and the query result display module 5 is used for extracting entities from the consultation problems of the customers in real time, querying through the interface according to the extracted entities and/or products, acquiring relevant knowledge and presenting the knowledge to the customer service interface.

In some of these embodiments, the domain knowledge building module 1 further comprises:

a labeling expectation obtaining unit 11 for labeling knowledge corpora in the field and constructing a relation between corresponding related entities to obtain a labeling corpora for training;

the labeling expectation obtaining unit 11 may label entities such as brands, categories, fruits, efficacies, and the like, on the corpora related to the makeup in the microblog, and may label corpora in other fields.

The extraction model establishing unit 12 is used for deep learning by using a Bert algorithm based on the labeled expectation and establishing an entity relationship extraction model.

And the knowledge map expanding unit 13 completes the domain knowledge map based on the knowledge of the distance and the semantics, and expands the domain knowledge map.

In some embodiments, the product cluster query interface building module 3 further includes:

the product vectorization representation unit 31 is used for vectorizing and representing the entity and the entity relation based on the domain knowledge graph, and accordingly establishing vectorization representation of the product;

a similar product cluster establishing unit 32, which calculates the vectorization distance between products according to the vectorization representation of the products, clusters the products, and establishes a similar product cluster;

the query interface construction unit 33 constructs a product cluster query interface based on keyword matching according to the similar product clusters.

The modules may be functional modules or program modules, and may be implemented by software or hardware. For a module implemented by hardware, the modules may be located in the same processor; or the modules can be respectively positioned in different processors in any combination.

In addition, the method for enabling customer service based on knowledge-graph of the embodiment of the application described in conjunction with fig. 1 can be realized by computer equipment. Fig. 6 is a hardware structure diagram of a computer device according to an embodiment of the present application.

The computer device may comprise a processor 81 and a memory 82 in which computer program instructions are stored.

Specifically, the processor 81 may include a Central Processing Unit (CPU), or A Specific Integrated Circuit (ASIC), or may be configured as one or more Integrated circuits for implementing the embodiments of the present Application.

Memory 82 may include, among other things, mass storage for data or instructions. By way of example, and not limitation, memory 82 may include a Hard Disk Drive (Hard Disk Drive, abbreviated HDD), a floppy Disk Drive, a Solid State Drive (SSD), flash memory, an optical Disk, a magneto-optical Disk, magnetic tape, or a Universal Serial Bus (USB) Drive, or a combination of two or more of these. Memory 82 may include removable or non-removable (or fixed) media, where appropriate. The memory 82 may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory 82 is a Non-Volatile (Non-Volatile) memory. In particular embodiments, Memory 82 includes Read-Only Memory (ROM) and Random Access Memory (RAM). The ROM may be mask-programmed ROM, Programmable ROM (abbreviated PROM), Erasable PROM (abbreviated EPROM), Electrically Erasable PROM (abbreviated EEPROM), Electrically rewritable ROM (abbreviated EEPROM), or FLASH Memory (FLASH), or a combination of two or more of these, where appropriate. The RAM may be a Static Random-Access Memory (SRAM) or a Dynamic Random-Access Memory (DRAM), where the DRAM may be a Fast Page Mode DRAM (Fast Page Mode Dynamic Random Access Memory, FPMDRAM), an Extended data output DRAM (Extended data Out Dynamic Random Access Memory, EDODRAM), a Synchronous DRAM (Synchronous Dynamic Random-Access Memory, SDRAM), and the like.

The memory 82 may be used to store or cache various data files for processing and/or communication use, as well as possible computer program instructions executed by the processor 81.

The processor 81 implements any of the above-described embodiments of the knowledgegraph-based customer service enabling methods by reading and executing computer program instructions stored in the memory 82.

In some of these embodiments, the computer device may also include a communication interface 83 and a bus 80. As shown in fig. 6, the processor 81, the memory 82, and the communication interface 83 are connected via the bus 80 to complete communication therebetween.

The communication interface 83 is used for implementing communication between modules, devices, units and/or equipment in the embodiment of the present application. The communication port 83 may also be implemented with other components such as: the data communication is carried out among external equipment, image/data acquisition equipment, a database, external storage, an image/data processing workstation and the like.

Bus 80 includes hardware, software, or both to couple the components of the computer device to each other. Bus 80 includes, but is not limited to, at least one of: data Bus (Data Bus), Address Bus (Address Bus), Control Bus (Control Bus), Expansion Bus (Expansion Bus), and Local Bus (Local Bus). By way of example, and not limitation, Bus 80 may include an Accelerated Graphics Port (AGP) or other Graphics Bus, an Enhanced Industry Standard Architecture (EISA) Bus, a Front-Side Bus (Front Side Bus, abbreviated FSB), a Hyper Transport (HT) Interconnect, an Industry Standard Architecture (ISA) Bus, an InfiniBand Interconnect, a Low Pin Count (LPC) Bus, a memory Bus, a microchannel Architecture (MCA) Bus, a Peripheral Component Interconnect (PCI) Bus, a PCI-Express (PCI-X) Bus, a Serial Advanced Technology Attachment (SATA) Bus, a Local audio Architecture (SATA) Bus, abbreviated VLB) bus or other suitable bus or a combination of two or more of these. Bus 80 may include one or more buses, where appropriate. Although specific buses are described and shown in the embodiments of the application, any suitable buses or interconnects are contemplated by the application.

The computer device can perform entity extraction based on the obtained questions asked by the client, and execute the steps of constructing the knowledge query service interface, constructing the product cluster query interface and retrieving KOL planting grass in the embodiment of the application, so that the service energizing method based on the knowledge base described in the figure 1 is realized.

In addition, in combination with the method for enabling customer service based on knowledge-graph in the above embodiments, the embodiments of the present application may be implemented by providing a computer-readable storage medium. The computer readable storage medium having stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement any of the above-described embodiments of a knowledgegraph-based customer service enabling method.

The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent application shall be subject to the appended claims.

Claims

1. A customer service enabling method based on knowledge graph is characterized by comprising the following steps:

a knowledge query service interface construction step, namely constructing a domain knowledge spectrogram by using an entity link method according to the domain knowledge, and establishing a knowledge query service interface based on the domain knowledge spectrogram;

2. The customer service enabling method based on the knowledge-graph as claimed in claim 1, further comprising a KOL weed searching step, specifically comprising:

a corpus marking step, marking the corpus by using the entity relation extraction model based on KOL corpus in social corpus;

and a KOL original corpus retrieval interface construction step, wherein the obtained tags and the KOL corpus are subjected to associated storage, an index is built based on the tags, and accordingly, a tag-based KOL original corpus retrieval interface is constructed.

3. The knowledgegraph-based customer service enabling method according to claim 1, wherein the step of building the entity relationship extraction model comprises:

a labeling expectation obtaining step, namely labeling the knowledge linguistic data of the field and constructing the relation between corresponding related entities to obtain a labeling linguistic data for training;

and an extraction model establishing step, namely performing deep learning by utilizing a Bert algorithm based on the labeled expectation and establishing an entity relationship extraction model.

4. The customer service enabling method based on knowledge-graph according to claim 3, wherein the domain knowledge-graph can be complemented based on knowledge of distance and semantics to expand the domain knowledge-graph.

5. The knowledgegraph-based customer service enabling method according to claim 1, wherein the product cluster query interface constructing step further comprises:

a product vectorization representation step, wherein the entity and the entity relation are vectorized and represented based on the domain knowledge graph, and the vectorization representation of the product is established according to the entity and the entity relation;

a similar product cluster establishing step, namely calculating vectorization distance between products according to the vectorization representation of the products, clustering the products and establishing a similar product cluster;

and a query interface construction step, namely constructing a product cluster query interface based on keyword matching according to the similar product cluster.

6. A knowledgegraph-based customer service enabling system for performing a knowledgegraph-based customer service enabling method according to any one of claims 1 to 5, comprising:

the domain knowledge establishing module is used for processing the knowledge corpus based on a domain by utilizing a pre-established entity relationship extraction model to obtain a knowledge set in the knowledge corpus, aligning the knowledge set by using entities and establishing normalized domain knowledge;

the knowledge query service interface construction module is used for constructing a domain knowledge spectrogram by using an entity link method according to the domain knowledge and establishing a knowledge query service interface based on the domain knowledge spectrogram;

the KOL grass retrieval module is used for marking the KOL corpus by using the entity relation extraction model based on the KOL corpus in the social corpus, performing associated storage on the obtained label and the KOL corpus, establishing an index based on the label, and accordingly establishing a KOL original corpus retrieval interface based on the label;

7. The knowledgegraph-based customer service enabling system of claim 6, wherein the domain knowledge building module further comprises:

a labeling expectation obtaining unit for labeling the knowledge corpus of the field and constructing the relationship between corresponding related entities to obtain a labeling corpus for training;

and the extraction model establishing unit is used for carrying out deep learning by utilizing a Bert algorithm based on the labeled expectation and establishing an entity relationship extraction model.

And the knowledge map expansion unit is used for completing the domain knowledge map based on the knowledge of distance and semantics and expanding the domain knowledge map.

8. The knowledgegraph-based customer service enabling system of claim 7, wherein the product cluster query interface building module further comprises:

the similar product cluster establishing unit is used for calculating the vectorization distance between products according to the vectorization representation of the products, clustering the products and establishing a similar product cluster;

9. A computer device comprising a memory, a processor, and a method of service enablement based on a knowledgegraph of any of computations 5 stored on the memory and executable on the processor.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a method for knowledgegraph-based customer service enablement as claimed in any one of claims 1 to 5.