CN116737842B - Entity relationship display method and device, electronic equipment and computer storage medium - Google Patents
Entity relationship display method and device, electronic equipment and computer storage mediumInfo
- Publication number
- CN116737842B CN116737842B CN202310547717.7A CN202310547717A CN116737842B CN 116737842 B CN116737842 B CN 116737842B CN 202310547717 A CN202310547717 A CN 202310547717A CN 116737842 B CN116737842 B CN 116737842B
- Authority
- CN
- China
- Prior art keywords
- entity
- client
- semantic
- text data
- span
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
本发明涉及大数据技术领域，揭露了一种实体关系展现方法，包括：获取每个客户的文本资料，提取文本资料中的实体属性信息；对实体属性信息进行语义识别，得到语义表征信息，对语义表征信息进行跨度划分，得到文本资料的跨度语义序列；确定跨度语义序列对应的实体类型，将实体类型与文本资料进行融合，得到文本资料的融合关系特征；利用融合关系特征对每个客户进行实体关系分类，得到客户分类集；根据客户分类集构建每个客户的实体关系图谱。本发明还提出一种实体关系展现装置、电子设备以及存储介质。本发明可以提高实体关系展现的精确度。
The present invention relates to the field of big data technology, and discloses an entity relationship display method, including: obtaining text data of each customer, extracting entity attribute information from the text data; performing semantic recognition on the entity attribute information to obtain semantic representation information, performing span division on the semantic representation information to obtain a span semantic sequence of the text data; determining the entity type corresponding to the span semantic sequence, fusing the entity type with the text data to obtain a fusion relationship feature of the text data; using the fusion relationship feature to classify the entity relationship of each customer to obtain a customer classification set; and constructing an entity relationship map of each customer based on the customer classification set. The present invention also proposes an entity relationship display device, an electronic device, and a storage medium. The present invention can improve the accuracy of entity relationship display.
Description
Technical Field
The present invention relates to the field of big data technologies, and in particular, to a method and apparatus for displaying entity relationships, an electronic device, and a computer readable storage medium.
Background
The entity refers to objects or things which exist in the real world in an objective manner and can be distinguished from each other, including personal names, place names, organization names or other proper nouns, and the entity relationship represents the internal connection between each entity, and the relationship between the entities can be displayed to obtain the association degree between different entities, so that the entity expansion can be performed, for example, an enterprise can search potential clients of the enterprise through the entity relationship of clients, and the business scope of the enterprise is expanded.
The research of the existing entity relation display method mainly focuses on interaction between two subtasks, but has the problem of insufficient attention to the context, and excessively depends on coding capability of pre-training language models such as ELMo (Embeddings from Language Models), BERT (Bidirectional Encoder Representation from Transformers) and the like, so that text breadth semantics are insufficient, for example Eberts and the like directly use [ CLS ] information in BERT and adopt simple maximum pooling to integrate text information into entity and relation representation, potential information in the context cannot be focused well, and further the degree of association between the entities cannot be deeply mined, and finally the accuracy of entity relation display is poor.
Disclosure of Invention
The invention provides a method, a device, electronic equipment and a computer readable storage medium for displaying entity relations, and mainly aims to solve the problem of lower accuracy in entity relation display.
In order to achieve the above object, the present invention provides a method for displaying entity relationships, including:
Acquiring text data of each client in a client set, and extracting entity attribute information in the text data;
carrying out semantic recognition on the entity attribute information to obtain semantic representation information in the text data, and carrying out span division on the semantic representation information according to the entity attribute information to obtain a span semantic sequence of the text data;
Determining an entity type sequence corresponding to the span semantic sequence by using preset entity type information, and fusing the entity type sequence with the text data to obtain fusion relation characteristics of the text data;
classifying entity relations of each client of the client set by utilizing the fusion relation characteristics to obtain a client classification set;
And constructing an entity relationship graph of each client in the client set according to the client classification set.
Optionally, the performing semantic recognition on the entity attribute information to obtain semantic representation information in the text data includes:
word embedding is carried out on the entity attribute information to obtain an attribute vector of the entity attribute information;
And carrying out semantic coding on the attribute vector by utilizing the pre-trained language characterization model to obtain semantic characterization information in the text data.
Optionally, the span division is performed on the semantic representation information according to the entity attribute information to obtain a span semantic sequence of the text material, which includes:
Performing word segmentation on the entity attribute information to obtain a word segmentation sequence of the entity attribute information;
Performing initial span division on the semantic characterization information according to the proportion of each word in the word segmentation sequence to obtain an initial span semantic sequence;
and adjusting the initial span semantic sequence by using a preset span value threshold value to obtain the span semantic sequence of the text data.
Optionally, the determining, by using preset entity type information, the entity type sequence corresponding to the span semantic sequence includes:
Carrying out convolution pooling on each span semantic in the span semantic feature sequence in sequence to obtain a pooled feature map;
fully connecting the pooled feature graphs to obtain feature information corresponding to each span semantic;
and calculating the feature similarity between the feature information and the entity type information, and determining an entity type sequence corresponding to the span semantic sequence according to the feature similarity.
Optionally, the fusing the entity type sequence and the text material to obtain a fusion relationship feature of the text material includes:
Converting the text data into text vectors, and constructing a vector matrix of the text vectors;
and respectively carrying out dot multiplication on the vector matrix and the entity types in the entity type sequence to obtain the fusion relation characteristic of the text data.
Optionally, the classifying the entity relationship of each client in the client set by using the fusion relationship feature to obtain a client classification set includes:
Calculating forward propagation characteristics and backward propagation characteristics corresponding to the fusion relation characteristics by using a pre-constructed two-way long-short time memory network;
Performing feature stitching on the forward propagation features and the backward propagation features to obtain stitching features of the fusion relation features;
and performing an activation operation on the spliced features to obtain entity categories corresponding to the fusion relation features, and performing entity category classification on each client in the client set according to the entity categories to obtain a client classification set.
Optionally, the building the entity relationship graph of each client in the client set according to the client classification set includes:
taking each client in the client set as a graph node in the entity relation graph;
determining association relations between the map nodes according to the client classification sets, and constructing edges of the map nodes according to the association relations;
And generating an entity relationship graph of each client in the client set according to the graph nodes and the edges of the graph nodes.
In order to solve the above problems, the present invention further provides an entity relationship display apparatus, which includes:
the entity attribute information extraction module is used for acquiring text data of each client in the client set and extracting entity attribute information in the text data;
The span semantic sequence generation module is used for carrying out semantic recognition on the entity attribute information to obtain semantic representation information in the text data, and carrying out span division on the semantic representation information according to the entity attribute information to obtain a span semantic sequence of the text data;
The fusion relation feature generation module is used for determining an entity type sequence corresponding to the span semantic sequence by utilizing preset entity type information, and fusing the entity type sequence with the text data to obtain fusion relation features of the text data;
the entity relation classification module is used for classifying the entity relation of each client of the client set by utilizing the fusion relation characteristics to obtain a client classification set;
And the entity relationship graph construction module is used for constructing an entity relationship graph of each client in the client set according to the client classification set.
In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:
At least one processor, and
A memory communicatively coupled to the at least one processor, wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the entity relationship presentation method described above.
In order to solve the above-mentioned problems, the present invention also provides a computer-readable storage medium having stored therein at least one computer program that is executed by a processor in an electronic device to implement the above-mentioned entity relationship presentation method.
According to the embodiment of the invention, the text data of each client is obtained, the entity attribute information in the text data is extracted, attribute identification can be carried out on each client by utilizing the attribute information, so that entity attribute association between each client is calculated, semantic representation information in the text data is identified, span division is carried out by combining upper and lower Wen Duiyu semantic representation information, the breadth of semantic representation can be increased, the breadth of entity types corresponding to the semantic representation information is further increased, the entity types and the text data are fused to obtain fusion relation characteristics, potential information of the text data can be increased, the association degree between each client is deeply mined, so that clients are classified to obtain a client classification set, and the entity map of each client in the client classification set is displayed, so that the accuracy of entity relation display can be effectively improved. Therefore, the entity relationship display method, the entity relationship display device, the electronic equipment and the computer readable storage medium can solve the problem of lower accuracy in entity relationship display.
Drawings
FIG. 1 is a flow chart of a method for displaying entity relationships according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of span division of semantic representation information according to an embodiment of the present invention;
FIG. 3 is a flow chart illustrating determining an entity class sequence according to an embodiment of the present invention;
FIG. 4 is a functional block diagram of an entity relationship display device according to an embodiment of the present invention;
Fig. 5 is a schematic structural diagram of an electronic device for implementing the entity relationship display method according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the application provides an entity relationship display method. The execution subject of the entity relationship presentation method includes, but is not limited to, at least one of a server, a terminal, and the like, which can be configured to execute the method provided by the embodiment of the application. In other words, the entity relationship presentation method may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The server side comprises, but is not limited to, a single server, a server cluster, a cloud server or a cloud server cluster and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (ContentDelivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Referring to fig. 1, a flow chart of a method for displaying entity relationships according to an embodiment of the present invention is shown. In this embodiment, the entity relationship display method includes:
s1, acquiring text data of each client in a client set, and extracting entity attribute information in the text data;
In the embodiment of the invention, the client set is a set of historical clients of the enterprise, each client of the enterprise is included in the client set, and the basic situation of each client can be determined through text data of each client in the enterprise, wherein the text data can include event instances of each client in the enterprise, for example, each consumption event, after-sales event and the like of the enterprise.
In the embodiment of the present invention, the entity attribute information is an entity attribute of each client, for example, attribute information contained in text data acquired by enterprises such as client consumption time, client gender, client work, etc.
In the embodiment of the present invention, the extracting entity attribute information in the text material includes:
Extracting event examples of each client in the data in the text, and acquiring event data in the event examples;
And determining the entity attribute corresponding to the event data by using a preset entity attribute set to obtain entity attribute information in the text data.
In the embodiment of the invention, the event instance is the data of each customer in the enterprise consumption situation, such as time, consumption situation, customer information, employee evaluation and the like, obtained by the enterprise record, so that the event data can be obtained from each event instance of the customer.
In the embodiment of the invention, the entity attribute set is a set of all entity attributes included in the text data of the client, and the entity attribute set can determine the corresponding entity attribute in each event data, for example, the time in the event data is used for obtaining the client consumption time attribute information, and the client information is used for obtaining the entity attribute information such as the client sex attribute information and the like, thereby obtaining the entity attribute information in the text data.
S2, carrying out semantic recognition on the entity attribute information to obtain semantic representation information in the text data, and carrying out span division on the semantic representation information according to the entity attribute information to obtain a span semantic sequence of the text data;
In the embodiment of the invention, the semantic representation information is the semantic feature of each entity attribute, and the semantic information of the entity attribute information can be expanded by dividing the semantic representation information span.
In the embodiment of the present invention, the semantic recognition is performed on the entity attribute information to obtain semantic representation information in the text data, including:
word embedding is carried out on the entity attribute information to obtain an attribute vector of the entity attribute information;
And carrying out semantic coding on the attribute vector by utilizing the pre-trained language characterization model to obtain semantic characterization information in the text data.
In the embodiment of the invention, the Word embedding (Word Embedding) is to convert words in the entity attribute information into digital vectors, and to embed a high-dimensional space with all Word numbers into a continuous vector space with lower dimension, wherein each Word or phrase is mapped into a vector on a real number domain to obtain the attribute vector of the entity attribute information so as to be capable of inputting the entity attribute information in a digital form.
In the embodiment of the invention, the pre-trained language characterization model is bert (Bidirectional Encoder Representation from Transformers) model, the pre-trained bert model is utilized to carry out semantic coding on the attribute vector to obtain semantic characterization information in the text data, specifically, the semantic coding comprises word vector and position coding, multi-head self-attention mechanism, residual connection and feedforward network, the invention utilizes the attribute vector and the position coding to provide the position information of each word in the short text, the dependency relationship and the time sequence relationship of each word in the entity attribute information can be identified, the correlation between each word in the entity attribute information and the other words in the sentence is calculated by utilizing a multi-head self-attention mechanism, each attribute vector contains the information of all attribute vectors in the entity attribute information, residual connection is performed, the problems of gradient disappearance and network degradation are solved, and finally the attribute vectors after semantic coding are activated and calculated, so that semantic representation information in text data is obtained.
In the embodiment of the present invention, referring to fig. 2, the span division is performed on the semantic representation information according to the entity attribute information to obtain a span semantic sequence of the text material, which includes:
s21, word segmentation is carried out on the entity attribute information, and a word segmentation sequence of the entity attribute information is obtained;
S22, carrying out initial span division on the semantic characterization information according to the proportion of each word in the word segmentation sequence to obtain an initial span semantic sequence;
s23, adjusting the initial span semantic sequence by using a preset span value threshold value to obtain the span semantic sequence of the text data.
In the embodiment of the invention, the entity attribute information is segmented, the semantic representation information is initially divided according to the proportion of each segmented word, the integrity of semantic information in an initial span semantic sequence is ensured, and the initial span semantic sequence is adjusted according to the preset span value threshold value, so that the span value in the span semantic sequence does not exceed the preset threshold value, the problem of limiting the semantic long-distance dependence among entities is reduced, the depth of the semantic representation information is improved, and the semantic feature information is expanded.
S3, determining an entity type sequence corresponding to the span semantic sequence by using preset entity type information, and fusing the entity type sequence with the text data to obtain fusion relation characteristics of the text data;
In the embodiment of the invention, the entity type information is the entity characteristics corresponding to the semantic characterization information contained in the span semantic sequence, and the entity type corresponding to the span semantic sequence is further determined through the entity characteristics so as to increase the characteristic range of the text data.
In the embodiment of the present invention, referring to fig. 3, the determining, by using preset entity type information, the entity type sequence corresponding to the span semantic sequence includes:
S31, carrying out convolution pooling on each span semantic in the span semantic feature sequence in sequence to obtain a pooled feature map;
S32, performing full connection on the pooled feature graphs to obtain feature information corresponding to each span semantic;
S33, calculating the feature similarity between the feature information and the entity type information, and determining an entity type sequence corresponding to the span semantic sequence according to the feature similarity.
In the embodiment of the invention, the preset convolutional neural network can be utilized to carry out convolutional pooling on each span semantic in sequence, the corresponding feature of each span semantic can be further extracted, meanwhile, the pooled feature images are fully connected, the feature images can be unfolded and paved to obtain the feature information of each span semantic, then the feature similarity between the feature information and the entity type information is calculated, the entity type information with the largest similarity is selected by each span semantic as the corresponding entity type, and further the entity type sequence of the span semantic sequence can be determined.
In the embodiment of the invention, the entity type sequence and the text data are fused, namely entity types possibly included in the text data are added into the text data, so that the text data contain corresponding entity types, and the potential information of the text data is increased.
In the embodiment of the present invention, the fusing the entity type sequence and the text data to obtain the fusion relationship feature of the text data includes:
Converting the text data into text vectors, and constructing a vector matrix of the text vectors;
and respectively carrying out dot multiplication on the vector matrix and the entity types in the entity type sequence to obtain the fusion relation characteristic of the text data.
In the embodiment of the invention, each entity type in the entity type sequence can be added into the text data by constructing the vector matrix of the text data, so that the fusion of the text data and the entity type sequence is realized, the characteristic depth of the text data is enlarged, the depth entity relationship of each client can be deeply mined, and the entity relationship is accurately displayed.
S4, classifying entity relations of each client of the client set by utilizing the fusion relation characteristics to obtain a client classification set;
In the embodiment of the invention, the entity relationship classification is to classify each client according to the corresponding fusion relationship characteristic in each client text data, classify the clients with similar entity classification categories, and obtain the client classification sets of different entity categories, thereby determining the entity relationship of each client.
In the embodiment of the present invention, the classifying the entity relationship of each client in the client set by using the fusion relationship feature to obtain a client classification set includes:
Calculating forward propagation characteristics and backward propagation characteristics corresponding to the fusion relation characteristics by using a pre-constructed two-way long-short time memory network;
Performing feature stitching on the forward propagation features and the backward propagation features to obtain stitching features of the fusion relation features;
and performing an activation operation on the spliced features to obtain entity categories corresponding to the fusion relation features, and performing entity category classification on each client in the client set according to the entity categories to obtain a client classification set.
In the embodiment of the invention, the pre-constructed long-short-time Memory network is a Bi-directional Long Short-Term Memory network, and is composed of a forward Memory network and a backward reverse Memory network, the forward Memory network processes the input fusion relation characteristic in a forward direction, the backward Memory network processes the fusion relation characteristic in a reverse direction, and the forward and backward characteristic information of the fusion relation characteristic can be obtained, so that the information of the splicing characteristic can be increased, and the accuracy of entity relation classification (accuracy) is improved.
In the embodiment of the invention, the entity class is a classification class corresponding to the client, for example, the entity class can be classified into a high-intention client, a low-intention client, a key client and the like according to the cooperation level of an enterprise, the probability of the splicing feature in each entity class is obtained by activating the splicing feature, the entity class with the highest probability is selected as the entity class corresponding to the splicing feature, and then the entity relation classification is carried out on each client, so that an entity client set is obtained.
In the embodiment of the invention, the clients in the client classification set are clients with consistent entity categories, so that the client entity with higher correlation degree of each client can be determined through the client classification set, the entity relationship of each client can be determined, and the business range of enterprise clients can be enlarged.
S5, constructing an entity relationship map of each client in the client set according to the client classification set.
In the embodiment of the invention, the entity relationship graph is a graph-based data structure, each client is used as a node in the graph, and the relationship between each client is used as an edge for connecting nodes, so that the entity relationship of each client can be displayed, and the associated client of each client can be intuitively determined.
In the embodiment of the present invention, the building of the entity relationship graph of each client in the client set according to the client classification set includes:
taking each client in the client set as a graph node in the entity relation graph;
determining association relations between the map nodes according to the client classification sets, and constructing edges of the map nodes according to the association relations;
And generating an entity relationship graph of each client in the client set according to the graph nodes and the edges of the graph nodes.
In the embodiment of the invention, each client in the client set is used as a map node of the entity relationship map, other clients in the client classification set where each client is located are used as associated clients, the association relationship between each client is further determined, the associated clients are connected, and the edge of each map node is constructed.
In the embodiment of the invention, the association degree between each customer is deeply mined through the customer classification set, and the association degree between each customer is intuitively displayed by constructing the entity relationship graph, so that other customers with high association degree can be found through one customer, and the accuracy of entity relationship display is effectively improved.
According to the embodiment of the invention, the text data of each client is obtained, the entity attribute information in the text data is extracted, attribute identification can be carried out on each client by utilizing the attribute information, so that entity attribute association between each client is calculated, semantic representation information in the text data is identified, span division is carried out by combining upper and lower Wen Duiyu semantic representation information, the breadth of semantic representation can be increased, the breadth of entity types corresponding to the semantic representation information is further increased, the entity types and the text data are fused to obtain fusion relation characteristics, potential information of the text data can be increased, the association degree between each client is deeply mined, so that clients are classified to obtain a client classification set, and the entity map of each client in the client classification set is displayed, so that the accuracy of entity relation display can be effectively improved. Therefore, the entity relationship display method provided by the invention can solve the problem of lower accuracy in entity relationship display.
Fig. 4 is a functional block diagram of an entity relationship display apparatus according to an embodiment of the present invention.
The entity relationship display apparatus 400 of the present invention may be installed in an electronic device. The entity relationship presentation apparatus 400 may include an entity attribute information extraction module 401, a span semantic sequence generation module 402, a fusion relationship feature generation module 403, an entity relationship classification module 404, and an entity relationship graph construction module 405 according to the implemented functions. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
The entity attribute information extraction module 401 is configured to obtain text data of each client in the client set, and extract entity attribute information in the text data;
The span semantic sequence generating module 402 is configured to perform semantic recognition on the entity attribute information to obtain semantic representation information in the text material, and perform span division on the semantic representation information according to the entity attribute information to obtain a span semantic sequence of the text material;
The fusion relation feature generation module 403 is configured to determine an entity type sequence corresponding to the span semantic sequence by using preset entity type information, and fuse the entity type sequence with the text material to obtain a fusion relation feature of the text material;
the entity relationship classification module 404 is configured to classify an entity relationship of each client in the client set by using the fused relationship feature to obtain a client classification set;
The entity relationship graph construction module 405 is configured to construct an entity relationship graph of each client in the client set according to the client classification set.
In detail, each module in the entity relationship display apparatus 400 in the embodiment of the present invention adopts the same technical means as the entity relationship display method described in fig. 1 to 3, and can produce the same technical effects, which is not described herein.
Fig. 5 is a schematic structural diagram of an electronic device for implementing a method for displaying entity relationships according to an embodiment of the present invention.
The electronic device 500 may comprise a processor 501, a memory 502, a communication bus 503 and a communication interface 504, and may further comprise a computer program stored in the memory 502 and executable on the processor 501, such as a physical relationship presentation program.
The processor 501 may be formed by an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be formed by a plurality of integrated circuits packaged with the same function or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 501 is a Control Unit (Control Unit) of the electronic device, connects various components of the entire electronic device using various interfaces and lines, and executes various functions of the electronic device and processes data by running or executing programs or modules (e.g., executing an entity relationship presentation program, etc.) stored in the memory 502, and calling data stored in the memory 502.
The memory 502 includes at least one type of readable storage medium including flash memory, a removable hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 502 may in some embodiments be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory 502 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like. Further, the memory 502 may also include both internal storage units and external storage devices of the electronic device. The memory 502 may be used to store not only application software installed in an electronic device and various data, such as code of an entity relationship presentation program, but also temporarily store data that has been output or is to be output.
The communication bus 503 may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable connected communication between the memory 502 and the at least one processor 501 etc.
The communication interface 504 is used for communication between the electronic device and other devices, including network interfaces and user interfaces. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), or alternatively a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device and for displaying a visual user interface.
Only an electronic device having components is shown, and it will be understood by those skilled in the art that the structures shown in the figures do not limit the electronic device, and may include fewer or more components than shown, or may combine certain components, or a different arrangement of components.
For example, although not shown, the electronic device may further include a power source (such as a battery) for supplying power to the respective components, and preferably, the power source may be logically connected to the at least one processor 501 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device may further include various sensors, bluetooth modules, wi-Fi modules, etc., which are not described herein.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The physical relationship presentation program stored by the memory 502 in the electronic device 500 is a combination of instructions that, when executed in the processor 501, may implement:
Acquiring text data of each client in a client set, and extracting entity attribute information in the text data;
carrying out semantic recognition on the entity attribute information to obtain semantic representation information in the text data, and carrying out span division on the semantic representation information according to the entity attribute information to obtain a span semantic sequence of the text data;
Determining an entity type sequence corresponding to the span semantic sequence by using preset entity type information, and fusing the entity type sequence with the text data to obtain fusion relation characteristics of the text data;
classifying entity relations of each client of the client set by utilizing the fusion relation characteristics to obtain a client classification set;
And constructing an entity relationship graph of each client in the client set according to the client classification set.
In particular, the specific implementation method of the above instruction by the processor 501 may refer to the description of the relevant steps in the corresponding embodiment of the drawings, which is not repeated herein.
Further, the modules/units integrated with the electronic device 500 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as a stand alone product. The computer readable storage medium may be volatile or nonvolatile. For example, the computer readable medium may include any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, can implement:
Acquiring text data of each client in a client set, and extracting entity attribute information in the text data;
carrying out semantic recognition on the entity attribute information to obtain semantic representation information in the text data, and carrying out span division on the semantic representation information according to the entity attribute information to obtain a span semantic sequence of the text data;
Determining an entity type sequence corresponding to the span semantic sequence by using preset entity type information, and fusing the entity type sequence with the text data to obtain fusion relation characteristics of the text data;
classifying entity relations of each client of the client set by utilizing the fusion relation characteristics to obtain a client classification set;
And constructing an entity relationship graph of each client in the client set according to the client classification set.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Wherein artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) is the theory, method, technique, and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain optimal results.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the system claims can also be implemented by means of software or hardware by means of one unit or means. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (9)
1. A method for displaying an entity relationship, the method comprising:
Acquiring text data of each client in a client set, and extracting entity attribute information in the text data;
carrying out semantic recognition on the entity attribute information to obtain semantic characterization information in the text data;
Performing word segmentation on the entity attribute information to obtain a word segmentation sequence of the entity attribute information;
Performing initial span division on the semantic characterization information according to the proportion of each word in the word segmentation sequence to obtain an initial span semantic sequence;
Adjusting the initial span semantic sequence by using a preset span value threshold value to obtain a span semantic sequence of the text data;
Determining an entity type sequence corresponding to the span semantic sequence by using preset entity type information, and fusing the entity type sequence with the text data to obtain fusion relation characteristics of the text data;
classifying entity relations of each client of the client set by utilizing the fusion relation characteristics to obtain a client classification set;
And constructing an entity relationship graph of each client in the client set according to the client classification set.
2. The method for displaying entity relationships according to claim 1, wherein said performing semantic recognition on the entity attribute information to obtain semantic representation information in the text material includes:
word embedding is carried out on the entity attribute information to obtain an attribute vector of the entity attribute information;
And carrying out semantic coding on the attribute vector by utilizing the pre-trained language characterization model to obtain semantic characterization information in the text data.
3. The method for displaying entity relationships according to claim 1, wherein determining the entity type sequence corresponding to the span semantic sequence by using preset entity type information includes:
Carrying out convolution pooling on each span semantic in the span semantic sequence in sequence to obtain a pooling feature map;
fully connecting the pooled feature graphs to obtain feature information corresponding to each span semantic;
and calculating the feature similarity between the feature information and the entity type information, and determining an entity type sequence corresponding to the span semantic sequence according to the feature similarity.
4. The method for displaying entity relationships according to claim 1, wherein the fusing the entity type sequence and the text material to obtain the fused relationship feature of the text material includes:
Converting the text data into text vectors, and constructing a vector matrix of the text vectors;
and respectively carrying out dot multiplication on the vector matrix and the entity types in the entity type sequence to obtain the fusion relation characteristic of the text data.
5. The method for displaying entity relationships according to claim 1, wherein the step of classifying the entity relationships of each client in the client set by using the fused relationship features to obtain a client classification set includes:
Calculating forward propagation characteristics and backward propagation characteristics corresponding to the fusion relation characteristics by using a pre-constructed two-way long-short time memory network;
Performing feature stitching on the forward propagation features and the backward propagation features to obtain stitching features of the fusion relation features;
and performing an activation operation on the spliced features to obtain entity categories corresponding to the fusion relation features, and performing entity category classification on each client in the client set according to the entity categories to obtain a client classification set.
6. The entity relationship presentation method of claim 1, wherein said constructing an entity relationship graph for each client in said set of clients from said set of client classifications comprises:
taking each client in the client set as a graph node in the entity relation graph;
determining association relations between the map nodes according to the client classification sets, and constructing edges of the map nodes according to the association relations;
And generating an entity relationship graph of each client in the client set according to the graph nodes and the edges of the graph nodes.
7. An entity relationship presentation apparatus for implementing the entity relationship presentation method according to any one of claims 1 to 6, the apparatus comprising:
the entity attribute information extraction module is used for acquiring text data of each client in the client set and extracting entity attribute information in the text data;
The span semantic sequence generation module is used for carrying out semantic recognition on the entity attribute information to obtain semantic representation information in the text data, and carrying out span division on the semantic representation information according to the entity attribute information to obtain a span semantic sequence of the text data;
The fusion relation feature generation module is used for determining an entity type sequence corresponding to the span semantic sequence by utilizing preset entity type information, and fusing the entity type sequence with the text data to obtain fusion relation features of the text data;
the entity relation classification module is used for classifying the entity relation of each client of the client set by utilizing the fusion relation characteristics to obtain a client classification set;
And the entity relationship graph construction module is used for constructing an entity relationship graph of each client in the client set according to the client classification set.
8. An electronic device, the electronic device comprising:
At least one processor, and
A memory communicatively coupled to the at least one processor, wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the entity relationship presentation method of any one of claims 1 to 6.
9. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the entity relationship presentation method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310547717.7A CN116737842B (en) | 2023-05-16 | 2023-05-16 | Entity relationship display method and device, electronic equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310547717.7A CN116737842B (en) | 2023-05-16 | 2023-05-16 | Entity relationship display method and device, electronic equipment and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116737842A CN116737842A (en) | 2023-09-12 |
| CN116737842B true CN116737842B (en) | 2025-07-15 |
Family
ID=87901988
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310547717.7A Active CN116737842B (en) | 2023-05-16 | 2023-05-16 | Entity relationship display method and device, electronic equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116737842B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117785868A (en) * | 2023-11-30 | 2024-03-29 | 江西元通新材料有限公司 | Data storage method and system applied to preparation of glass sand inclusion pipe |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114022246A (en) * | 2021-11-05 | 2022-02-08 | 平安科技（深圳）有限公司 | Product information pushing method and device, terminal equipment and storage medium |
| CN114881038A (en) * | 2022-07-12 | 2022-08-09 | 之江实验室 | Chinese entity and relation extraction method and device based on span and attention mechanism |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10606853B2 (en) * | 2016-12-22 | 2020-03-31 | Aon Global Operations Ltd (Singapore Branch) | Systems and methods for intelligent prospect identification using online resources and neural network processing to classify organizations based on published materials |
| CN119397032A (en) * | 2018-06-25 | 2025-02-07 | 硕动力公司 | System and method for investigating relationships between entities |
| CN109754012A (en) * | 2018-12-29 | 2019-05-14 | 新华三大数据技术有限公司 | Entity Semantics relationship classification method, model training method, device and electronic equipment |
| EP3923206A1 (en) * | 2020-06-10 | 2021-12-15 | Naver Corporation | A method and system for fine-grained information extraction and annotation using semantic attribute paths |
| CN113051929A (en) * | 2021-03-23 | 2021-06-29 | 电子科技大学 | Entity relationship extraction method based on fine-grained semantic information enhancement |
| CN113051356B (en) * | 2021-04-21 | 2023-05-30 | 深圳壹账通智能科技有限公司 | Open relation extraction method and device, electronic equipment and storage medium |
| CN115357723A (en) * | 2022-07-18 | 2022-11-18 | 华南师范大学 | Entity relationship extraction method and device, electronic equipment and storage medium |
| CN115391557B (en) * | 2022-08-26 | 2025-12-12 | 电子科技大学 | A relation extraction method that integrates entity type representation and relation representation |
-
2023
- 2023-05-16 CN CN202310547717.7A patent/CN116737842B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114022246A (en) * | 2021-11-05 | 2022-02-08 | 平安科技（深圳）有限公司 | Product information pushing method and device, terminal equipment and storage medium |
| CN114881038A (en) * | 2022-07-12 | 2022-08-09 | 之江实验室 | Chinese entity and relation extraction method and device based on span and attention mechanism |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116737842A (en) | 2023-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113157927B (en) | Text classification method, device, electronic device and readable storage medium | |
| CN113449187B (en) | Product recommendation method, device, equipment and storage medium based on double images | |
| CN115114408B (en) | Multimodal sentiment classification method, device, equipment and storage medium | |
| CN113378970B (en) | Sentence similarity detection method and device, electronic equipment and storage medium | |
| CN113157739B (en) | Cross-modal retrieval methods, devices, electronic equipment and storage media | |
| CN114398557B (en) | Information recommendation method and device based on double images, electronic equipment and storage medium | |
| CN113887941B (en) | Business process generation method, device, electronic equipment and medium | |
| CN113360654B (en) | Text classification method, apparatus, electronic device and readable storage medium | |
| CN114708461B (en) | Classification method, device, equipment and storage medium based on multimodal learning model | |
| CN112347739B (en) | Applicable rule analysis method, device, electronic device and storage medium | |
| CN112214556B (en) | Label generation method, device, electronic equipment and computer-readable storage medium | |
| CN114840684A (en) | Map construction method, device and equipment based on medical entity and storage medium | |
| CN116737842B (en) | Entity relationship display method and device, electronic equipment and computer storage medium | |
| CN116340538A (en) | Entity relationship pair identification method, device, equipment and computer-readable storage medium | |
| CN113723114A (en) | Semantic analysis method, device and equipment based on multi-intent recognition and storage medium | |
| CN116701680B (en) | Intelligent matching methods, devices, and equipment based on text and images | |
| CN117271709B (en) | Corpus expansion method and device, electronic equipment and storage medium | |
| CN116166858B (en) | Information recommendation method, device, equipment and storage medium based on artificial intelligence | |
| CN116644208B (en) | Video retrieval method, device, electronic equipment and computer readable storage medium | |
| CN116306656B (en) | Entity relation extraction method, device, equipment and storage medium | |
| CN115544282B (en) | Data processing methods, apparatus, equipment, and storage media based on graph databases | |
| CN114840560B (en) | Unstructured data conversion and storage method and device | |
| CN116468025A (en) | Electronic medical record structuring method and device, electronic equipment and storage medium | |
| CN116755688A (en) | Component processing method, device, computer equipment and storage medium | |
| CN114708073A (en) | Intelligent detection method and device for surrounding mark and serial mark, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |