CN112800237B - Prediction method and device based on knowledge graph embedded representation and computer equipment - Google Patents
Prediction method and device based on knowledge graph embedded representation and computer equipment Download PDFInfo
- Publication number
- CN112800237B CN112800237B CN202110070124.7A CN202110070124A CN112800237B CN 112800237 B CN112800237 B CN 112800237B CN 202110070124 A CN202110070124 A CN 202110070124A CN 112800237 B CN112800237 B CN 112800237B
- Authority
- CN
- China
- Prior art keywords
- entity
- mapping
- relation
- target
- embedded
- 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; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a prediction method, a prediction device, computer equipment and a storage medium based on knowledge graph embedded representation. The method comprises the following steps: acquiring a first entity, a second entity and a target relation in a target knowledge graph; acquiring a first normal vector and a second normal vector corresponding to a target relation, and acquiring a relation matrix; determining a first mapping entity according to the first normal vector, determining a second mapping entity according to the second normal vector, and determining an entity relation mapping vector according to a cyclic matrix corresponding to the relation matrix; training the first mapping entity, the second mapping entity and the entity relation mapping vector according to a preset scoring function to obtain a first embedded entity, a second embedded entity and a target embedded relation; and predicting at least one of semantic knowledge and association relation corresponding to the target knowledge graph by applying the first embedding entity, the second embedding entity and the target embedding relation. Thus, semantic knowledge and association relation can be accurately predicted.
Description
Technical Field
The present application relates to the field of knowledge graph technologies, and in particular, to a prediction method, apparatus, computer device, and storage medium based on knowledge graph embedded representation.
Background
With the development of artificial intelligence technology, knowledge-graph technology for semantic analysis and inference prediction functions has emerged. In order to better use the knowledge graph to process the semantics and the relations, the entity and the relation in the knowledge graph are generally required to be embedded and represented, so that the semantics can be rapidly and accurately analyzed and predicted. The traditional prediction method based on knowledge graph embedded representation generally converts and represents entities and relations by transferring a distance model or a semantic matching model, and provides a basis for subsequent semantic analysis and reasoning prediction.
However, in the conventional prediction method based on knowledge graph embedded representation, generally, different entities and relationships are subjected to uniform translation or analysis, when the head entity and the tail entity are not aligned, the characteristics of the head entity, the tail entity and the relationship cannot be considered, and related semantics or relationships cannot be accurately analyzed and predicted.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a knowledge-graph-embedded representation-based prediction method, apparatus, computer device, and storage medium that can accurately analyze and predict related semantics or relationships.
A method of predicting an embedded representation based on a knowledge graph, the method comprising:
acquiring a target knowledge graph based on semantic knowledge and an association relationship, and acquiring a triplet in the target knowledge graph, wherein the triplet comprises a first entity, a second entity and a target relationship;
acquiring a first normal vector and a second normal vector corresponding to the target relationship, and acquiring a relationship matrix formed based on the first entity, the second entity and the target relationship;
determining a first mapping entity corresponding to the first entity according to the first normal vector, determining a second mapping entity corresponding to the second entity according to the second normal vector, and determining an entity relation mapping vector corresponding to the target relation according to a cyclic matrix corresponding to the relation matrix;
training the first mapping entity, the second mapping entity and the entity relation mapping vector according to a preset scoring function to obtain a first embedded entity corresponding to the first mapping entity, a second embedded entity corresponding to the second mapping entity and a target embedded relation corresponding to the target relation;
and predicting at least one of semantic knowledge and association relation corresponding to the target knowledge graph by applying the first embedding entity, the second embedding entity and the target embedding relation.
In one embodiment, the obtaining the target knowledge graph based on the semantic knowledge and the association relationship includes:
and if the reverse relation between the first entity and the second entity is inconsistent with the target relation, or the semantic category corresponding to the first entity is inconsistent with the semantic category corresponding to the second entity, or the output degree or the input degree corresponding to the first entity or the second entity is inconsistent, or the number of the first entities corresponding to the target relation connection is inconsistent with the number of the corresponding second entities, determining the knowledge graph corresponding to the first entity and the second entity as the target knowledge graph.
In one embodiment, the determining, according to the first normal vector, a first mapping entity corresponding to the first entity, determining, according to the second normal vector, a second mapping entity corresponding to the second entity, and determining, according to a cyclic matrix corresponding to the relationship matrix, an entity relationship mapping vector corresponding to the target relationship includes:
mapping the first entity to a first hyperplane corresponding to the first normal vector to obtain a first mapping entity;
mapping the second entity to a second hyperplane corresponding to the second normal vector to obtain a second mapping entity;
And mapping the first entity and the second entity according to the cyclic matrix corresponding to the relation matrix for the target relation to obtain an entity relation mapping vector corresponding to the target relation.
In one embodiment, the method for obtaining the cyclic matrix includes:
and translating the elements in the relation matrix to obtain the circulation matrix.
In one embodiment, the preset scoring function includes a first scoring function and a second scoring function;
training the first mapping entity, the second mapping entity and the entity relation mapping vector according to a preset scoring function to obtain a first embedded entity corresponding to the first mapping entity, a second embedded entity corresponding to the second mapping entity and a target embedded relation corresponding to the target relation, wherein the training comprises the following steps:
training the first mapping entity and the second mapping entity according to the first scoring function to obtain a first embedded entity corresponding to the first mapping entity and a second embedded entity corresponding to the second mapping entity;
and training the target relation and the entity relation mapping vector according to the second scoring function to obtain a target embedded relation corresponding to the target relation.
In one embodiment, training the first mapping entity and the second mapping entity according to the first scoring function to obtain a first embedded entity corresponding to the first mapping entity and a second embedded entity corresponding to the second mapping entity includes:
determining an entity portrait corresponding to the second entity according to the first mapping entity and the target relation;
obtaining the similarity between the second mapping entity and the entity portrait;
training the first mapping entity and the second mapping entity according to the first scoring function and the mapping similarity to obtain a first embedded entity corresponding to the first mapping entity and a second embedded entity corresponding to the second mapping entity.
In one embodiment, the method further comprises:
setting a corresponding time window for the target knowledge graph, and constructing a target knowledge graph based on stream data;
and executing the step of acquiring the target knowledge graph based on the semantic knowledge and the association relation according to the time window until the first embedded entity, the second embedded entity and the target embedded relation are obtained, and predicting at least one of the semantic knowledge and the association relation corresponding to the target knowledge graph based on the streaming data by applying the first embedded entity, the second embedded entity and the target embedded relation.
A knowledge-graph embedded representation-based prediction apparatus, the apparatus comprising:
the first data acquisition module is used for acquiring a target knowledge graph based on semantic knowledge and an association relationship, and acquiring a triplet in the target knowledge graph, wherein the triplet comprises a first entity, a second entity and a target relationship;
the second data acquisition module is used for acquiring a first normal vector and a second normal vector corresponding to the target relationship and acquiring a relationship matrix formed based on the first entity, the second entity and the target relationship;
the mapping data acquisition module is used for determining a first mapping entity corresponding to the first entity according to the first normal vector, determining a second mapping entity corresponding to the second entity according to the second normal vector, and determining an entity relation mapping vector corresponding to the target relation according to a cyclic matrix corresponding to the relation matrix;
the data embedding representation module is used for training the first mapping entity, the second mapping entity and the entity relation mapping vector according to a preset scoring function to obtain a first embedding entity corresponding to the first mapping entity, a second embedding entity corresponding to the second mapping entity and a target embedding relation corresponding to the target relation;
And the embedded prediction module is used for predicting at least one of semantic knowledge and association relation corresponding to the target knowledge graph by applying the first embedded entity, the second embedded entity and the target embedded relation.
A computer device comprising a memory storing a computer program and a processor implementing the method of any of the embodiments described above when the processor executes the computer program.
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements the method of any of the embodiments described above.
According to the knowledge graph embedded representation-based prediction method, the knowledge graph embedded representation-based prediction device, the computer equipment and the storage medium, through determining the first mapping entity corresponding to the first entity according to the first normal vector, determining the second mapping entity corresponding to the second entity according to the second normal vector, determining the entity relation mapping vector corresponding to the target relation according to the cyclic matrix corresponding to the relation matrix, respectively mapping the first entity, the second entity and the target relation independently, taking the characteristics of the first entity, the second entity and the target relation into consideration, training the first mapping entity, the second mapping entity and the entity relation mapping vector according to the preset scoring function, obtaining the first embedding entity corresponding to the first mapping entity, the second embedding entity corresponding to the second mapping entity and the target embedding relation corresponding to the target relation, and applying the first embedding entity, the second embedding entity and the target embedding relation on the basis of considering the characteristics of the first entity, the second entity and the target relation, and accurately predicting at least one of semantic knowledge and the association relation corresponding to the target knowledge graph.
Drawings
FIG. 1 is an application environment diagram of a predictive method based on knowledge-graph embedded representation in one embodiment;
FIG. 2 is a flow diagram of a predictive method based on knowledge-graph embedded representation in one embodiment;
FIG. 3 is a flow chart of one implementation of step S300 in one embodiment;
FIG. 4 is a diagram of an entity individual mapping method in one embodiment;
FIG. 5 is a flow chart of one implementation of step S400 in one example;
FIG. 6 is a flow diagram of a predictive device based on knowledge-graph embedded representation in one embodiment;
fig. 7 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. 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 application.
The prediction method based on the knowledge graph embedded representation provided by the application can be applied to an application environment shown in figure 1. Aiming at real-time big data of multi-source isomerism collected in real time, a knowledge graph is constructed according to semantic knowledge and association relations, entities and relations in the knowledge graph are modeled to obtain a first embedded entity, a second embedded entity and a target embedded relation of the knowledge graph, the first embedded entity, the second embedded entity and the target embedded relation are applied, on the basis of considering the characteristics of the first entity, the second entity and the target relation, at least one of the semantic knowledge and the association relation corresponding to the target knowledge graph is accurately predicted by the first embedded entity, the second embedded entity and the target embedded relation, and risk management is carried out according to a prediction result. Optionally, the specificity of the knowledge graph and the influence on the embedded representation method are dynamically analyzed in terms of semantics, structure, quantity and the like of the entity and the relation. According to unequal characteristics of dynamic changes of a head entity (a first entity) and a tail entity (a second entity) of the flow type knowledge graph, a dynamic cross-correlation knowledge graph embedded representation algorithm based on a sliding window is designed according to interaction of the entities and the relation; and the influence of unequal characteristics on model learning is reduced by adopting the self-adaptive learning rate in the window. For example, the method is applied to the insurance field for explanation, and in order to improve the efficiency and the accuracy of the insurance industry kernel-insurance-verification-approval work, further prevent the moral risk and the reverse selection event, an external data source needs to be fused to construct a knowledge graph of the insurance industry. Firstly, the real-time big data of the multisource isomerization relates to structured, semi-structured and unstructured data, and the real-time incoming data needs to be processed quickly; in addition, a knowledge graph based on semantic knowledge and association relation is required to be constructed, and the reasoning rule of expert decision is dynamically constructed by utilizing different scenerization applications. And according to the interaction of the entity and the relation, the unequal characteristics of the dynamic changes of the head entity and the tail entity are analyzed, and an embedded representation algorithm for independently modeling the head entity and the tail entity and an embedded representation algorithm based on a cyclic matrix are adopted, so that fusion processing for variable data streams can be realized.
In one embodiment, as shown in fig. 2, a prediction method based on knowledge graph embedded representation is provided, and this embodiment is applied to a terminal for illustration by using the method, it can be understood that the method can also be applied to a server, and can also be applied to a system including the terminal and the server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the steps of:
step S100, a target knowledge graph based on semantic knowledge and association relation is obtained, and a triplet in the target knowledge graph is obtained, wherein the triplet comprises a first entity, a second entity and a target relation.
Step S200, a first normal vector and a second normal vector corresponding to the target relationship are obtained, and a relationship matrix formed based on the first entity, the second entity and the target relationship is obtained.
Step S300, determining a first mapping entity corresponding to the first entity according to the first normal vector, determining a second mapping entity corresponding to the second entity according to the second normal vector, and determining an entity relation mapping vector corresponding to the target relation according to a cyclic matrix corresponding to the relation matrix.
Step S400, training the first mapping entity, the second mapping entity and the entity relation mapping vector according to a preset scoring function to obtain a first embedded entity corresponding to the first mapping entity, a second embedded entity corresponding to the second mapping entity and a target embedded relation corresponding to the target relation.
And S500, predicting at least one of semantic knowledge and association relation corresponding to the target knowledge graph by applying the first embedding entity, the second embedding entity and the target embedding relation.
The target knowledge graph refers to a knowledge graph which needs to be subjected to embedded representation and semantic knowledge and/or association relation prediction according to the embedded representation.
Specifically, a target knowledge graph is obtained, and two corresponding normal vectors, namely a first normal vector and a second normal vector, are set for a target relation in the target knowledge graph. And mapping the first entity according to the first normal vector, so as to obtain a first mapping entity. And mapping the second entity according to the second normal vector, and obtaining a second mapping entity. And determining the entity relation mapping vector corresponding to the target relation according to the cyclic matrix corresponding to the relation matrix. The first entity, the second entity and the target relationship are mapped independently, and the obtained mapping vectors of the first mapping entity, the second mapping entity and the entity relationship can give consideration to the respective characteristics of the first entity, the second entity and the target relationship. And training the first mapping entity, the second mapping entity and the entity relation mapping vector according to a preset scoring function, and obtaining a first embedded entity corresponding to the first mapping entity, a second embedded entity corresponding to the second mapping entity and a target embedded relation corresponding to the target relation under the constraint of the scoring function. And finally, predicting at least one of semantic knowledge and association relation corresponding to the target knowledge graph by applying the first embedding entity, the second embedding entity and the target embedding relation.
According to the knowledge graph embedded representation-based prediction method, the first mapping entity corresponding to the first entity is determined according to the first normal vector, the second mapping entity corresponding to the second entity is determined according to the second normal vector, the entity relation mapping vector corresponding to the target relation is determined according to the cyclic matrix corresponding to the relation matrix, independent mapping can be conducted on the first entity, the second entity and the target relation respectively, characteristics of the first entity, the second entity and the target relation are considered, the first mapping entity, the second mapping entity and the entity relation mapping vector are trained according to a preset scoring function, the target embedded relation corresponding to the first embedding entity, the second embedding entity and the target relation corresponding to the first mapping entity is obtained, and on the basis of considering the characteristics of the first entity, the second entity and the target relation, the first embedding entity, the second embedding entity and the target embedding relation are applied, so that at least one of semantic knowledge and association relation corresponding to the target knowledge graph is predicted accurately.
In one embodiment, as an implementation manner of step S100, the method includes:
if the reverse relation between the first entity and the second entity is inconsistent with the target relation, or the semantic category corresponding to the first entity is inconsistent with the semantic category corresponding to the second entity, or the output degree or the input degree corresponding to the first entity or the second entity is inconsistent, or the number of the first entities corresponding to the target relation connection is inconsistent with the number of the corresponding second entities, determining the knowledge graph corresponding to the first entity and the second entity as a target knowledge graph.
Specifically, in this embodiment, the identification is performed on the unequal knowledge patterns of the head entity and the tail entity, and in general, if the reverse relationship between the first entity and the second entity is inconsistent with the target relationship (forward relationship), or the semantic category corresponding to the first entity is inconsistent with the semantic category corresponding to the second entity, or the degree of departure or degree of entrance corresponding to the first entity or the second entity is inconsistent, or the number of first entities corresponding to the target relationship connection is inconsistent with the number of corresponding second entities, the knowledge pattern is considered to be the unequal knowledge pattern of the head entity and the tail entity, and the knowledge pattern is determined to be the target knowledge pattern.
Specifically, the case that the head entity and the tail entity are not equal is as follows: given knowledge graph g= {<h,r,t,τ>H, t E, R E R, τe Ω, where h represents the first entity (head entity), t represents the second entity (tail entity), R represents the target relationship, and τ represents the timestamp. E represents the set of entities, R represents the set of relationships, and Ω represents the window size of the sliding window. Within the window time Ω, let r be -1 Representing the inverse of relationship r, the degree node of entity e is (e i ,r x ) The ingress node of entity e is (r y ,e j )，(e i ,r x ) Is divided into the number of the entity e OD (e)，(r y ,e j ) Is divided into the degree of entry N of entity e IN (e) A. The invention relates to a method for producing a fibre-reinforced plastic composite If the knowledge graph meets one of three conditions, namely, the knowledge graph has unequal characteristics and is a target knowledge graph. Condition one: semantic isomerism of head and tail entities: for the relation r to be defined,or->Semantic category and S representing all head entities linked to relation r Tr Representing the semantic categories of all tail entities linked to the relation r. Condition II: partial knowledge structure isomerism of head and tail entities: for four-tuple<h,r,t,τ>，/>Or-> And (3) a third condition: head entity, tail entity number heterogeneous: for the relation r +.>Or in the knowledge-graph G,wherein, |h r The number of head entities linked by the relation r is represented by the number of tail entities linked by the relation r, the number of all head entities in the knowledge graph is represented by the number of H and the number of all tail entities in the knowledge graph is represented by the number of T. The key of the unequal characteristics of the head entity and the tail entity is that: the head entity and the tail entity are correctly distinguished, and the head entity and the tail entity are distinguished from the whole angle or the individual angle; modeling interactions of entities with relationships captures interactions between entities and relationships.
In the above embodiment, the target knowledge graph with unequal characteristics is determined according to the characteristics of the knowledge graph, and a data basis is provided for the subsequent independent embedding representation of the entities and relations in the target knowledge graph.
In one embodiment, as shown in fig. 3, an implementation manner of step S300 includes:
step 310, mapping the first entity to a first hyperplane corresponding to the first normal vector to obtain a first mapping entity.
And 320, mapping the second entity to a second hyperplane corresponding to the second normal vector to obtain a second mapping entity.
And 330, mapping the first entity and the second entity according to the cyclic matrix corresponding to the relation matrix for the target relation to obtain an entity relation mapping vector corresponding to the target relation.
The hyperplane is a linear subspace with the spare dimension equal to one in the n-dimensional Euclidean space, the first normal vector corresponds to the first hyperplane, and the second normal vector corresponds to the second hyperplane.
Specifically, the determination manner about the first mapping entity and the second mapping entity is as follows:
both entities (first entity or second entity) and relationships (target relationships) have semantics and the semantics have a near-far score. Typically, within a sliding window, the semantics of different relationships are different and the semantics of linked entities are also different, while the semantics of entities linked by the same relationship are close. As shown in equation 1, a head entity (first entity) and a tail entity (second entity) for each relationship are respectively given an action function.
Wherein, the liquid crystal display device comprises a liquid crystal display device,and->Is an action function, which may be a weight, vector, matrix or other function, +.>Representing the correspondingManipulation of h, or->Operation on t. The embedded representation of the entity may be accomplished by the following three steps: 1. unified calculation of entities and relationships>2. By means ofMapping of head entity and relation, preparation for calculating tail entity, i.e. calculating +.>3. Calculating similarity of operations on head entity and tail entity, i.e. setting scoring functionIn a translational model sim () = | i 1 is used to determine, l2 is the first or second order distance.
In order to independently model the head entity and the tail entity, as shown in fig. 4, an entity independent mapping method is shown, the entity independent mapping method has Universality (universal), the translation model can be a TransU, and the TransU model can be applied to unequal knowledge maps of the head entity and the tail entity and can also be applied to equal knowledge maps of the head entity and the tail entity. The TransU model uses 2 normal vectors per relationship r, a first normal vector wrh is assigned to the head entity and a second normal vector wrt is assigned to the tail entity to distinguish the unequal characteristics of the two.
Inside the sliding window, entities (first entity and second entity), relationships (target relationships) are imaged in unison. Based on the hyperplane mapping principle, the image formed by the relation r is an r vector, the image of the head entity h and the tail entity t is a vector obtained by hyperplane mapping, and a calculation formula obtained by the hyperplane mapping principle in fig. 4 is shown as formula 2:
Optionally, the elements in the relation matrix are translated to obtain a cyclic matrix. The determination of the cyclic matrix and entity relationship mapping vector is as follows:
in the sliding window, when the entity and the relation are required to be subjected to fine granularity interaction, the entity and the relation are mainly mapped. Thus, a cyclic matrix is employed as a function to obtain interactions of entities and relationships. Each row in the circulant matrix is shifted one left or right with respect to the previous row vectorAn element. Thus, it can be divided into a left circular matrix and a right circular matrix, which are respectively denoted as A L =circl (a) and a R =circr (a), where a is the first row vector and is the cyclic vector.
The elements of the left circular matrix are represented by formula (3), the elements of the right circular matrix are represented by formula (4), and the conversion relationship between the left circular matrix and the right circular matrix is represented by formula (5).
In the above embodiment, the first entity, the second entity and the target relationship are mapped separately to obtain the mapping vector of the entity relationship corresponding to the first mapping entity, the second mapping entity corresponding to the second entity and the target relationship corresponding to the first entity. The independent mapping mode can reserve the respective characteristics of the first entity, the second entity and the target relationship, and provide a data basis for the subsequent knowledge graph embedding so as to accurately predict at least one of semantic knowledge and association relationship corresponding to the target knowledge graph.
In one embodiment, as shown in fig. 5, an implementation manner of step S400 includes:
step S410, training the first mapping entity and the second mapping entity according to the first scoring function to obtain a first embedded entity corresponding to the first mapping entity and a second embedded entity corresponding to the second mapping entity.
And step S420, training the target relation and the entity relation mapping vector according to the second scoring function to obtain a target embedded relation corresponding to the target relation.
The preset scoring function comprises a first scoring function and a second scoring function.
Optionally, determining an entity representation corresponding to the second entity according to the first mapping entity and the target relationship; obtaining the similarity between the second mapping entity and the entity portrait; training the first mapping entity and the second mapping entity according to the first scoring function and the mapping similarity to obtain a first embedded entity corresponding to the first mapping entity and a second embedded entity corresponding to the second mapping entity.
Specifically, for an entity, first, a mapping of a head entity and a relationship is used to portray a tail entity (entity portraits corresponding to a second entity), h ⊥ And the linear operation of r is taken as t ⊥ Mapping t of (2) mapping The method can be obtained according to the parallelogram rule of vector space:
t mapping ＝h ⊥ +r (6)
wherein h is a first entity, t is a second entity, h ⊥ For the first mapping entity, t ⊥ Is the second mapping entity.
Next, the similarity of operations of the head entity (first entity), the tail entity (second entity), and the entity representation (similarity between the second mapping entity and the entity representation) is calculated. Calculation of the tail entity t Using l1, l2-norm ⊥ And calculated mapping t mapping The similarity is specifically shown in a formula (7):
inside the sliding window, h is needed due to the TransU model ⊥ And t ⊥ The formula (2), the formula (3) and the formula (7) can be satisfied by connecting the relation vectors r on the hyperplane in a low-error mode. Therefore, the scoring function can be expressed as formula (8).
The first scoring function of equation (8) is translated into a minimization problem with constraints, such as equation (9), and then trained.
To address the infrequent problem of longer physical training time, an Adadelta training model with adaptive capabilities may be employed. The model may use the mean value of the exponential decay of the square gradient Eg 2 ]And squared update Edelta 2 ]To increase recent gradients and updates.
For the relationship, an adaptive learning model based on a cyclic matrix is set inside a sliding window. For each quadruple <h,r,t,τ>Setting entity embedding representation e= { h, t } ∈e n Relational embedding is expressed as r.epsilon.R n . For each R, pass through the circulant matrix A εR n×m Or A.epsilon.R m×n (m>n), mapping the entity vector e to obtain a vector e r . Here, let A er For the right circular matrix, the left circular matrix is the same, and the second scoring function is shown in formula (10):
in the training phase, a scoring function f based on a cyclic matrix r (h, t) can be converted into a constrained minimization problem, and an Adadelta model with adaptive capabilities can be chosen to optimize the solution.
Through the optimization of the first scoring function corresponding to the formula (9), a first embedded entity corresponding to the first mapping entity and a second embedded entity corresponding to the second mapping entity can be obtained. And obtaining the target embedding relation corresponding to the target relation through the second scoring function corresponding to the formula (10). The first embedding entity, the second embedding entity and the target embedding relation are embedding representations corresponding to the target knowledge graph, the knowledge graph embedding representations can give consideration to the characteristics of the first entity, the second entity and the target relation, and at least one of semantic knowledge and association relation corresponding to the target knowledge graph is accurately predicted by applying the first embedding entity, the second embedding entity and the target embedding relation.
In the above embodiment, the first embedding entity, the second embedding entity and the target embedding relationship are represented by the knowledge graph embedding by optimizing the scoring function, and the knowledge graph embedding represents the characteristics that can be considered in the first entity, the second entity and the target relationship, and at least one of the semantic knowledge and the association relationship corresponding to the target knowledge graph is accurately predicted by applying the first embedding entity, the second embedding entity and the target embedding relationship.
In an embodiment, the prediction method based on the knowledge-graph embedded representation further comprises:
setting a corresponding time window for the target knowledge graph, and constructing the target knowledge graph based on the streaming data; and executing the step of acquiring the target knowledge graph based on the semantic knowledge and the association relation according to the time window until a first embedded entity, a second embedded entity and the target embedded relation are obtained, and predicting at least one of the semantic knowledge and the association relation corresponding to the target knowledge graph based on the streaming data by applying the first embedded entity, the second embedded entity and the target embedded relation.
Specifically, in order to meet the dynamic change of the data flow corresponding to the knowledge graph, a corresponding time window is set for the target knowledge graph, and the target knowledge graph based on the flow data is constructed. When the knowledge graph is embedded, the step of acquiring a target knowledge graph based on semantic knowledge and an association relationship can be performed according to a time window, a first normal vector and a second normal vector corresponding to the target relationship are acquired, a relationship matrix formed based on the first entity, the second entity and the target relationship is acquired, a first mapping entity corresponding to the first entity is determined according to the first normal vector, a second mapping entity corresponding to the second entity is determined according to the second normal vector, an entity relationship mapping vector corresponding to the target relationship is determined according to a cyclic matrix corresponding to the relationship matrix, training is performed on the first mapping entity, the second mapping entity and the entity relationship mapping vector according to a preset scoring function, a first embedding entity corresponding to the first mapping entity, a second embedding entity corresponding to the second mapping entity and the target embedding relationship corresponding to the target relationship are obtained, and at least one of the semantic knowledge and the association relationship corresponding to the target knowledge graph based on stream data is predicted by applying the first embedding entity, the second embedding entity and the target embedding relationship. τ in the above embodiment represents a time stamp, Ω is a time window. Through the setting of the time window omega, the embedded representation based on the stream knowledge graph can be realized.
In the above embodiment, by means of the setting manner of the time window, the continuously changing data stream may be represented by embedding the knowledge graph, and on the basis of the embedding representation of the knowledge graph, at least one of semantic knowledge and association relationship corresponding to the target knowledge graph based on the stream data may be predicted.
It should be understood that, although the steps in the flowcharts of fig. 1-3 and 5 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps of FIGS. 1-3, 5 may include steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the steps or stages in other steps.
In one embodiment, as shown in fig. 6, there is provided a knowledge-graph embedded representation-based prediction apparatus, including: a first data acquisition module 601, a second data acquisition module 602, a mapping data acquisition module 603, a data embedding representation module 604, and an embedding prediction module 605, wherein:
The first data obtaining module 601 is configured to obtain a target knowledge graph based on semantic knowledge and an association relationship, and obtain a triplet in the target knowledge graph, where the triplet includes a first entity, a second entity, and a target relationship;
a second data obtaining module 602, configured to obtain a first normal vector and a second normal vector corresponding to the target relationship, and obtain a relationship matrix formed based on the first entity, the second entity, and the target relationship;
the mapping data obtaining module 603 is configured to determine a first mapping entity corresponding to the first entity according to a first normal vector, determine a second mapping entity corresponding to the second entity according to a second normal vector, and determine an entity relationship mapping vector corresponding to the target relationship according to a cyclic matrix corresponding to the relationship matrix;
the data embedding representation module 604 is configured to train the first mapping entity, the second mapping entity, and the entity relationship mapping vector according to a preset scoring function, so as to obtain a target embedding relationship corresponding to the first embedding entity corresponding to the first mapping entity, the second embedding entity corresponding to the second mapping entity, and the target relationship;
the embedding prediction module 605 is configured to apply the first embedding entity, the second embedding entity, and the target embedding relationship to predict at least one of semantic knowledge and association relationship corresponding to the target knowledge graph.
In one embodiment, the first data obtaining module 601 is further configured to determine, as the target knowledge graph, the knowledge graph corresponding to the first entity and the second entity if the reverse relationship between the first entity and the second entity is inconsistent with the target relationship, or the semantic category corresponding to the first entity is inconsistent with the semantic category corresponding to the second entity, or the outbound degree or inbound degree corresponding to the first entity or the second entity is inconsistent, or the number of first entities corresponding to the target relationship connection is inconsistent with the number of corresponding second entities.
In one embodiment, the mapping data obtaining module 603 is further configured to map the first entity to a first hyperplane corresponding to the first normal vector, to obtain a first mapped entity; mapping the second entity to a second hyperplane corresponding to the second normal vector to obtain a second mapping entity; and mapping the first entity and the second entity according to the cyclic matrix corresponding to the relation matrix for the target relation to obtain an entity relation mapping vector corresponding to the target relation.
In one embodiment, the mapping data obtaining module 603 is further configured to translate elements in the relationship matrix to obtain a cyclic matrix.
In one embodiment, the preset scoring function includes a first scoring function and a second scoring function; the mapping data obtaining module 603 is further configured to train the first mapping entity and the second mapping entity according to the first scoring function, to obtain a first embedded entity corresponding to the first mapping entity and a second embedded entity corresponding to the second mapping entity; training the mapping vector of the target relation and the entity relation according to the second scoring function to obtain a target embedded relation corresponding to the target relation.
In one embodiment, the data embedding representation module 604 is further configured to determine, according to the first mapping entity and the target relationship, an entity representation corresponding to the second entity; obtaining the similarity between the second mapping entity and the entity portrait; training the first mapping entity and the second mapping entity according to the first scoring function and the mapping similarity to obtain a first embedded entity corresponding to the first mapping entity and a second embedded entity corresponding to the second mapping entity.
In one embodiment, the prediction device based on the knowledge graph embedded representation further comprises a data flow determining module, which is used for setting a corresponding time window for the target knowledge graph to construct the target knowledge graph based on the flow data; and executing the step of acquiring the target knowledge graph based on the semantic knowledge and the association relation according to the time window until a first embedded entity, a second embedded entity and the target embedded relation are obtained, and predicting at least one of the semantic knowledge and the association relation corresponding to the target knowledge graph based on the streaming data by applying the first embedded entity, the second embedded entity and the target embedded relation.
For specific limitations on the prediction apparatus based on the knowledge-graph embedded representation, reference may be made to the above limitation on the prediction method based on the knowledge-graph embedded representation, and no further description is given here. The above-described modules in the knowledge-graph-embedded representation-based prediction apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program, when executed by a processor, implements a predictive method based on knowledge-graph embedded representations. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in FIG. 7 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
acquiring a target knowledge graph based on semantic knowledge and an association relationship, and acquiring a triplet in the target knowledge graph, wherein the triplet comprises a first entity, a second entity and a target relationship;
acquiring a first normal vector and a second normal vector corresponding to a target relationship, and acquiring a relationship matrix formed based on a first entity, a second entity and the target relationship;
determining a first mapping entity corresponding to the first entity according to the first normal vector, determining a second mapping entity corresponding to the second entity according to the second normal vector, and determining an entity relation mapping vector corresponding to the target relation according to a cyclic matrix corresponding to the relation matrix;
Training the first mapping entity, the second mapping entity and the entity relation mapping vector according to a preset scoring function to obtain a first embedded entity corresponding to the first mapping entity, a second embedded entity corresponding to the second mapping entity and a target embedded relation corresponding to the target relation;
and predicting at least one of semantic knowledge and association relation corresponding to the target knowledge graph by applying the first embedding entity, the second embedding entity and the target embedding relation.
In one embodiment, the processor when executing the computer program further performs the steps of: if the reverse relation between the first entity and the second entity is inconsistent with the target relation, or the semantic category corresponding to the first entity is inconsistent with the semantic category corresponding to the second entity, or the output degree or the input degree corresponding to the first entity or the second entity is inconsistent, or the number of the first entities corresponding to the target relation connection is inconsistent with the number of the corresponding second entities, determining the knowledge graph corresponding to the first entity and the second entity as a target knowledge graph.
In one embodiment, the processor when executing the computer program further performs the steps of: mapping the first entity to a first hyperplane corresponding to the first normal vector to obtain a first mapping entity; mapping the second entity to a second hyperplane corresponding to the second normal vector to obtain a second mapping entity; and mapping the first entity and the second entity according to the cyclic matrix corresponding to the relation matrix for the target relation to obtain an entity relation mapping vector corresponding to the target relation.
In one embodiment, the processor when executing the computer program further performs the steps of: and translating the elements in the relation matrix to obtain a cyclic matrix.
In one embodiment, the processor when executing the computer program further performs the steps of: training the first mapping entity and the second mapping entity according to the first scoring function to obtain a first embedded entity corresponding to the first mapping entity and a second embedded entity corresponding to the second mapping entity; training the mapping vector of the target relation and the entity relation according to the second scoring function to obtain a target embedded relation corresponding to the target relation.
In one embodiment, the processor when executing the computer program further performs the steps of: determining an entity portrait corresponding to the second entity according to the relation between the first mapping entity and the target; obtaining the similarity between the second mapping entity and the entity portrait; training the first mapping entity and the second mapping entity according to the first scoring function and the mapping similarity to obtain a first embedded entity corresponding to the first mapping entity and a second embedded entity corresponding to the second mapping entity.
In one embodiment, the processor when executing the computer program further performs the steps of: setting a corresponding time window for the target knowledge graph, and constructing the target knowledge graph based on the streaming data; and executing the step of acquiring the target knowledge graph based on the semantic knowledge and the association relation according to the time window until a first embedded entity, a second embedded entity and the target embedded relation are obtained, and predicting at least one of the semantic knowledge and the association relation corresponding to the target knowledge graph based on the streaming data by applying the first embedded entity, the second embedded entity and the target embedded relation.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a target knowledge graph based on semantic knowledge and an association relationship, and acquiring a triplet in the target knowledge graph, wherein the triplet comprises a first entity, a second entity and a target relationship;
acquiring a first normal vector and a second normal vector corresponding to a target relationship, and acquiring a relationship matrix formed based on a first entity, a second entity and the target relationship;
determining a first mapping entity corresponding to the first entity according to the first normal vector, determining a second mapping entity corresponding to the second entity according to the second normal vector, and determining an entity relation mapping vector corresponding to the target relation according to a cyclic matrix corresponding to the relation matrix;
training the first mapping entity, the second mapping entity and the entity relation mapping vector according to a preset scoring function to obtain a first embedded entity corresponding to the first mapping entity, a second embedded entity corresponding to the second mapping entity and a target embedded relation corresponding to the target relation;
and predicting at least one of semantic knowledge and association relation corresponding to the target knowledge graph by applying the first embedding entity, the second embedding entity and the target embedding relation.
In one embodiment, the computer program when executed by the processor further performs the steps of: if the reverse relation between the first entity and the second entity is inconsistent with the target relation, or the semantic category corresponding to the first entity is inconsistent with the semantic category corresponding to the second entity, or the output degree or the input degree corresponding to the first entity or the second entity is inconsistent, or the number of the first entities corresponding to the target relation connection is inconsistent with the number of the corresponding second entities, determining the knowledge graph corresponding to the first entity and the second entity as a target knowledge graph.
In one embodiment, the computer program when executed by the processor further performs the steps of: mapping the first entity to a first hyperplane corresponding to the first normal vector to obtain a first mapping entity; mapping the second entity to a second hyperplane corresponding to the second normal vector to obtain a second mapping entity; and mapping the first entity and the second entity according to the cyclic matrix corresponding to the relation matrix for the target relation to obtain an entity relation mapping vector corresponding to the target relation.
In one embodiment, the computer program when executed by the processor further performs the steps of: and translating the elements in the relation matrix to obtain a cyclic matrix.
In one embodiment, the computer program when executed by the processor further performs the steps of: training the first mapping entity and the second mapping entity according to the first scoring function to obtain a first embedded entity corresponding to the first mapping entity and a second embedded entity corresponding to the second mapping entity; training the mapping vector of the target relation and the entity relation according to the second scoring function to obtain a target embedded relation corresponding to the target relation.
In one embodiment, the computer program when executed by the processor further performs the steps of: determining an entity portrait corresponding to the second entity according to the relation between the first mapping entity and the target; obtaining the similarity between the second mapping entity and the entity portrait; training the first mapping entity and the second mapping entity according to the first scoring function and the mapping similarity to obtain a first embedded entity corresponding to the first mapping entity and a second embedded entity corresponding to the second mapping entity.
In one embodiment, the computer program when executed by the processor further performs the steps of: setting a corresponding time window for the target knowledge graph, and constructing the target knowledge graph based on the streaming data; and executing the step of acquiring the target knowledge graph based on the semantic knowledge and the association relation according to the time window until a first embedded entity, a second embedded entity and the target embedded relation are obtained, and predicting at least one of the semantic knowledge and the association relation corresponding to the target knowledge graph based on the streaming data by applying the first embedded entity, the second embedded entity and the target embedded relation.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (10)
1. A method of predicting an embedded representation based on a knowledge-graph, the method comprising:
acquiring a target knowledge graph based on semantic knowledge and an association relationship, and acquiring a triplet in the target knowledge graph, wherein the triplet comprises a first entity, a second entity and a target relationship;
acquiring a first normal vector and a second normal vector corresponding to the target relationship, and acquiring a relationship matrix formed based on the first entity, the second entity and the target relationship;
determining a first mapping entity corresponding to the first entity according to the first normal vector, determining a second mapping entity corresponding to the second entity according to the second normal vector, and determining an entity relation mapping vector corresponding to the target relation according to a cyclic matrix corresponding to the relation matrix;
Training the first mapping entity, the second mapping entity and the entity relation mapping vector according to a preset scoring function to obtain a first embedded entity corresponding to the first mapping entity, a second embedded entity corresponding to the second mapping entity and a target embedded relation corresponding to the target relation;
and predicting at least one of semantic knowledge and association relation corresponding to the target knowledge graph by applying the first embedding entity, the second embedding entity and the target embedding relation.
2. The method according to claim 1, wherein the obtaining the target knowledge-graph based on semantic knowledge and association relation comprises:
and if the reverse relation between the first entity and the second entity is inconsistent with the target relation, or the semantic category corresponding to the first entity is inconsistent with the semantic category corresponding to the second entity, or the output degree or the input degree corresponding to the first entity or the second entity is inconsistent, or the number of the first entities corresponding to the target relation connection is inconsistent with the number of the corresponding second entities, determining the knowledge graph corresponding to the first entity and the second entity as the target knowledge graph.
3. The method of claim 1, wherein the determining the first mapping entity corresponding to the first entity according to the first normal vector, determining the second mapping entity corresponding to the second entity according to the second normal vector, and determining the entity relationship mapping vector corresponding to the target relationship according to the cyclic matrix corresponding to the relationship matrix, comprises:
mapping the first entity to a first hyperplane corresponding to the first normal vector to obtain a first mapping entity;
mapping the second entity to a second hyperplane corresponding to the second normal vector to obtain a second mapping entity;
and mapping the first entity and the second entity according to the cyclic matrix corresponding to the relation matrix for the target relation to obtain an entity relation mapping vector corresponding to the target relation.
4. The method according to claim 1, wherein the cyclic matrix obtaining method includes:
and translating the elements in the relation matrix to obtain the circulation matrix.
5. The method of claim 1, wherein the predetermined scoring function comprises a first scoring function and a second scoring function;
Training the first mapping entity, the second mapping entity and the entity relation mapping vector according to a preset scoring function to obtain a first embedded entity corresponding to the first mapping entity, a second embedded entity corresponding to the second mapping entity and a target embedded relation corresponding to the target relation, wherein the training comprises the following steps:
training the first mapping entity and the second mapping entity according to the first scoring function to obtain a first embedded entity corresponding to the first mapping entity and a second embedded entity corresponding to the second mapping entity;
and training the target relation and the entity relation mapping vector according to the second scoring function to obtain a target embedded relation corresponding to the target relation.
6. The method of claim 5, wherein training the first mapping entity and the second mapping entity according to the first scoring function to obtain a first embedded entity corresponding to the first mapping entity and a second embedded entity corresponding to the second mapping entity comprises:
determining an entity portrait corresponding to the second entity according to the first mapping entity and the target relation;
Obtaining the similarity between the second mapping entity and the entity portrait;
training the first mapping entity and the second mapping entity according to the first scoring function and the mapping similarity to obtain a first embedded entity corresponding to the first mapping entity and a second embedded entity corresponding to the second mapping entity.
7. The method according to any one of claims 1 to 6, further comprising:
setting a corresponding time window for the target knowledge graph, and constructing a target knowledge graph based on stream data;
and executing the step of acquiring the target knowledge graph based on the semantic knowledge and the association relation according to the time window until the first embedded entity, the second embedded entity and the target embedded relation are obtained, and predicting at least one of the semantic knowledge and the association relation corresponding to the target knowledge graph based on the streaming data by applying the first embedded entity, the second embedded entity and the target embedded relation.
8. A knowledge-graph embedded representation-based prediction apparatus, the apparatus comprising:
the first data acquisition module is used for acquiring a target knowledge graph based on semantic knowledge and an association relationship, and acquiring a triplet in the target knowledge graph, wherein the triplet comprises a first entity, a second entity and a target relationship;
The second data acquisition module is used for acquiring a first normal vector and a second normal vector corresponding to the target relationship and acquiring a relationship matrix formed based on the first entity, the second entity and the target relationship;
the mapping data acquisition module is used for determining a first mapping entity corresponding to the first entity according to the first normal vector, determining a second mapping entity corresponding to the second entity according to the second normal vector, and determining an entity relation mapping vector corresponding to the target relation according to a cyclic matrix corresponding to the relation matrix;
the data embedding representation module is used for training the first mapping entity, the second mapping entity and the entity relation mapping vector according to a preset scoring function to obtain a first embedding entity corresponding to the first mapping entity, a second embedding entity corresponding to the second mapping entity and a target embedding relation corresponding to the target relation;
and the embedded prediction module is used for predicting at least one of semantic knowledge and association relation corresponding to the target knowledge graph by applying the first embedded entity, the second embedded entity and the target embedded relation.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110070124.7A CN112800237B (en) | 2021-01-19 | 2021-01-19 | Prediction method and device based on knowledge graph embedded representation and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110070124.7A CN112800237B (en) | 2021-01-19 | 2021-01-19 | Prediction method and device based on knowledge graph embedded representation and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112800237A CN112800237A (en) | 2021-05-14 |
| CN112800237B true CN112800237B (en) | 2023-08-11 |
Family
ID=75810470
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110070124.7A Active CN112800237B (en) | 2021-01-19 | 2021-01-19 | Prediction method and device based on knowledge graph embedded representation and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112800237B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113946695B (en) * | 2021-12-20 | 2022-04-22 | 山东新希望六和集团有限公司 | Method and device for generating animal pedigree and computer equipment |
| CN115964504B (en) * | 2021-12-28 | 2023-06-30 | 北方工业大学 | Food safety risk prediction method and system |
| CN115964503B (en) * | 2021-12-28 | 2023-07-07 | 北方工业大学 | Safety risk prediction method and system based on community equipment facilities |
| CN114022058A (en) * | 2022-01-06 | 2022-02-08 | 成都晓多科技有限公司 | Small and medium-sized enterprise confidence loss risk prediction method based on time sequence knowledge graph |
| CN115114411B (en) * | 2022-08-30 | 2022-12-30 | 中国科学院自动化研究所 | Prediction method and device based on knowledge graph and electronic equipment |
| CN116934556B (en) * | 2023-09-08 | 2023-12-26 | 四川三思德科技有限公司 | Target personnel accurate control method based on big data fusion |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106528609A (en) * | 2016-09-28 | 2017-03-22 | 厦门理工学院 | Vector constraint embedded transformation knowledge graph inference method |
| CN111221981A (en) * | 2019-12-31 | 2020-06-02 | 腾讯科技（深圳）有限公司 | Method and device for training knowledge graph embedded model and computer storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190122111A1 (en) * | 2017-10-24 | 2019-04-25 | Nec Laboratories America, Inc. | Adaptive Convolutional Neural Knowledge Graph Learning System Leveraging Entity Descriptions |
-
2021
- 2021-01-19 CN CN202110070124.7A patent/CN112800237B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106528609A (en) * | 2016-09-28 | 2017-03-22 | 厦门理工学院 | Vector constraint embedded transformation knowledge graph inference method |
| CN111221981A (en) * | 2019-12-31 | 2020-06-02 | 腾讯科技（深圳）有限公司 | Method and device for training knowledge graph embedded model and computer storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 融合实体描述及类型的知识图谱表示学习方法;杜文倩;李弼程;王瑞;;中文信息学报(07);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112800237A (en) | 2021-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112800237B (en) | Prediction method and device based on knowledge graph embedded representation and computer equipment | |
| WO2023000574A1 (en) | Model training method, apparatus and device, and readable storage medium | |
| CN113535984B (en) | Knowledge graph relation prediction method and device based on attention mechanism | |
| CN114048331A (en) | Knowledge graph recommendation method and system based on improved KGAT model | |
| US11809966B2 (en) | Computer model machine learning based on correlations of training data with performance trends | |
| Li et al. | Dynamic structure embedded online multiple-output regression for streaming data | |
| CN113780584B (en) | Label prediction method, label prediction device, and storage medium | |
| Lu | CNN Convolutional layer optimisation based on quantum evolutionary algorithm | |
| CN111339724B (en) | Method, apparatus and storage medium for generating data processing model and layout | |
| Xu et al. | Bipolar fuzzy Petri nets for knowledge representation and acquisition considering non-cooperative behaviors | |
| Wang et al. | Neighbor matching for semi-supervised learning | |
| Kalifullah et al. | Retracted: Graph‐based content matching for web of things through heuristic boost algorithm | |
| CN112232360A (en) | Image retrieval model optimization method, image retrieval device and storage medium | |
| CN111062406B (en) | Heterogeneous domain adaptation-oriented semi-supervised optimal transmission method | |
| CN116467466A (en) | Knowledge graph-based code recommendation method, device, equipment and medium | |
| CN114757391A (en) | Service quality prediction method based on network data space design | |
| US20230018525A1 (en) | Artificial Intelligence (AI) Framework to Identify Object-Relational Mapping Issues in Real-Time | |
| CN116802646A (en) | Data processing method and device | |
| Xing et al. | [Retracted] Study about Football Action Recognition Method Based on Deep Learning and Improved Dynamic Time Warping Algorithm | |
| Mendu et al. | Gated linear model induced u-net for surrogate modeling and uncertainty quantification | |
| CN117911418B (en) | Focus detection method, system and storage medium based on improved YOLO algorithm | |
| CN117409209B (en) | Multi-task perception three-dimensional scene graph element segmentation and relationship reasoning method | |
| US11829735B2 (en) | Artificial intelligence (AI) framework to identify object-relational mapping issues in real-time | |
| CN116050640B (en) | Short-time passenger flow prediction method of multi-mode traffic system based on self-adaptive multi-graph convolution | |
| CN113159100B (en) | Circuit fault diagnosis method, circuit fault diagnosis device, 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 |