CN113627186A - Entity relation detection method based on artificial intelligence and related equipment - Google Patents
Entity relation detection method based on artificial intelligence and related equipment Download PDFInfo
- Publication number
- CN113627186A CN113627186A CN202110923984.0A CN202110923984A CN113627186A CN 113627186 A CN113627186 A CN 113627186A CN 202110923984 A CN202110923984 A CN 202110923984A CN 113627186 A CN113627186 A CN 113627186A
- Authority
- CN
- China
- Prior art keywords
- entity
- text
- detected
- relation
- statement
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 94
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 claims abstract description 17
- 239000013598 vector Substances 0.000 claims description 76
- 230000011218 segmentation Effects 0.000 claims description 45
- 230000015654 memory Effects 0.000 claims description 23
- 238000013507 mapping Methods 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 8
- 230000007704 transition Effects 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 10
- 230000006870 function Effects 0.000 description 7
- 238000002372 labelling Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 239000000284 extract Substances 0.000 description 3
- 238000013500 data storage Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- 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
- 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
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/253—Grammatical analysis; Style critique
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- 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)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Machine Translation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to artificial intelligence, and provides an entity relationship detection method based on artificial intelligence and related equipment. The method can obtain the text to be detected according to the entity relationship detection request when receiving the entity relationship detection request; analyzing the text to be detected based on a pre-trained entity relationship recognition model to obtain a recognition result; if the recognition result is a preset result, extracting a relational statement from the text to be detected according to the recognition result; identifying an object entity in the relational statement; if the number of the object entities is multiple, positioning entity relations of the object entities in the relation statement; and detecting the entity relation based on a preset map to obtain a detection result of the text to be detected. The invention can improve the detection accuracy and detection efficiency of the text to be detected. In addition, the invention also relates to a block chain technology, and the detection result can be stored in the block chain.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an entity relation detection method and related equipment based on artificial intelligence.
Background
With the development of artificial intelligence, machine reading understanding can directly extract the cooperative relationship of certain enterprises in a certain text from the text. However, for some disclosures, since the cooperative relationship between the enterprises is not directly described in the text, the entity relationship cannot be extracted by the prior art, and the entity relationship detection is inaccurate.
Disclosure of Invention
In view of the above, it is necessary to provide an entity relationship detection method and related apparatus based on artificial intelligence, which can improve the detection accuracy and detection efficiency of the text to be detected.
In one aspect, the present invention provides an entity relationship detection method based on artificial intelligence, including:
when an entity relationship detection request is received, acquiring a text to be detected according to the entity relationship detection request;
analyzing the text to be detected based on a pre-trained entity relationship recognition model to obtain a recognition result;
if the recognition result is a preset result, extracting a relational statement from the text to be detected according to the recognition result;
identifying an object entity in the relational statement;
if the number of the object entities is multiple, positioning entity relations of the object entities in the relation statement;
and detecting the entity relation based on a preset map to obtain a detection result of the text to be detected.
According to the preferred embodiment of the present invention, analyzing the text to be detected based on the pre-trained entity relationship recognition model to obtain the recognition result includes:
performing word segmentation processing on the text to be detected to obtain a plurality of text word segments;
acquiring a coding mapping table of the entity relationship identification model;
coding the text participles based on the coding mapping table to obtain a plurality of word codes;
splicing the word codes according to the vocabulary positions of the text participles in the text to be detected to obtain a code vector;
generating a position vector of the text to be detected based on the representation sequence of the text participles in the coding vector;
obtaining a semantic generation network and a relation classification network of the entity relation identification model;
analyzing the coding vector and the position vector based on the semantic generation network to obtain a text semantic vector of the text to be detected;
acquiring a weight matrix and a bias vector in the relation classification network;
calculating the product of the text semantic vector and the weight matrix to obtain an operation vector, and calculating the sum of the operation vector and the offset vector to obtain a classification vector;
and determining the category corresponding to the dimension with the largest value in the classification vectors as the identification result.
According to the preferred embodiment of the present invention, the extracting, according to the recognition result, the relational statement from the text to be detected includes:
acquiring a standard vocabulary from a preset lexicon according to the recognition result;
traversing each text statement in the text to be detected based on the standard vocabulary;
and determining the text sentence containing the standard vocabulary as the relational sentence.
According to a preferred embodiment of the present invention, the identifying the object entity in the relational statement includes:
vectorizing the relational statement based on a plurality of statement participles of the relational statement to obtain a statement vector sequence;
inputting the statement vector sequence into a pre-trained entity recognition model, and acquiring the output probability and the transition probability of each statement participle on a plurality of configuration labels of an activation layer;
for each sentence word segmentation, carrying out weighting and operation on the output probability and the transition probability of each configuration label to obtain the label score of each configuration label;
determining the configuration label with the highest label score as an output label of the sentence segmentation;
and matching the output label with a preset entity label, and determining the sentence participle corresponding to the output label successfully matched with the preset entity label as the object entity.
According to a preferred embodiment of the present invention, the locating entity relationships of the plurality of object entities in the relational statement includes:
for an entity pair in a plurality of object entities, detecting whether the object entities in the entity pair are in the same relational statement or not, wherein the entity pair comprises any two object entities;
if the object entities in the entity pair exist in the same relational statement, analyzing the syntactic structure of the object entities in the entity pair in the relational statement;
and if the number of the grammar structures is multiple, determining that the object entity in the entity pair contains the entity relation.
According to the preferred embodiment of the present invention, the method for detecting entity relationship based on artificial intelligence further comprises:
if the entity number of the object entity is smaller than the preset number, acquiring a preset tag, wherein the preset tag is used for indicating a release user;
extracting information corresponding to the preset label from the text to be detected as a text publisher of the text to be detected;
and determining the incidence relation between the text publisher and the object entity as the entity relation.
According to a preferred embodiment of the present invention, the detecting the entity relationship based on the preset map to obtain the detection result of the text to be detected includes:
for each entity relationship, acquiring a plurality of relationship objects of the entity relationship;
for any relation object in the plurality of relation objects, determining the rest relation objects except the any relation object in the plurality of relation objects as target objects;
traversing the preset map based on any relation object to obtain a plurality of associated objects of any relation object;
detecting whether the target object is contained in the plurality of associated objects;
and if the plurality of associated objects contain the target object, determining the detection result as that the entity relationship has authenticity.
On the other hand, the invention also provides an entity relationship detection device based on artificial intelligence, which comprises:
the acquiring unit is used for acquiring a text to be detected according to the entity relationship detection request when the entity relationship detection request is received;
the analysis unit is used for analyzing the text to be detected based on a pre-trained entity relationship recognition model to obtain a recognition result;
the extraction unit is used for extracting the relation sentences from the text to be detected according to the identification result if the identification result is a preset result;
the identification unit is used for identifying the object entity in the relational statement;
a positioning unit, configured to position an entity relationship of the multiple object entities in the relationship statement if there are multiple object entities;
and the detection unit is used for detecting the entity relation based on a preset map to obtain a detection result of the text to be detected.
In another aspect, the present invention further provides an electronic device, including:
a memory storing computer readable instructions; and
a processor executing computer readable instructions stored in the memory to implement the artificial intelligence based entity relationship detection method.
In another aspect, the present invention further provides a computer-readable storage medium, in which computer-readable instructions are stored, and the computer-readable instructions are executed by a processor in an electronic device to implement the artificial intelligence based entity relationship detection method.
According to the technical scheme, the recognition result of the text to be detected is recognized through the entity relationship recognition model, the text which does not contain entity relationship can be prevented from being further analyzed, and further, the relationship sentences can be determined from a plurality of text sentences in the text to be detected and analyzed according to the recognition result, so that the analysis efficiency of the entity relationship is improved, the problem that the entity relationship cannot be extracted can be avoided, the authenticity of the entity relationship can be accurately analyzed through the preset map, the accuracy of the detection result is improved, and whether false propaganda is executed by an enterprise or not can be accurately recognized.
Drawings
FIG. 1 is a flow chart of the method for detecting entity relationship based on artificial intelligence according to the preferred embodiment of the present invention.
FIG. 2 is a functional block diagram of an embodiment of an apparatus for detecting entity relationship based on artificial intelligence.
FIG. 3 is a schematic structural diagram of an electronic device according to a preferred embodiment of the present invention for implementing an artificial intelligence-based entity relationship detection method.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
FIG. 1 is a flow chart of a method for detecting entity relationship based on artificial intelligence according to a preferred embodiment of the present invention. The order of the steps in the flow chart may be changed and some steps may be omitted according to different needs.
The entity relation detection method based on artificial intelligence can be applied to intelligent government affair scenes, and therefore construction of smart cities is promoted.
The entity relation detection method based on artificial intelligence can acquire and process related data based on artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
The entity relationship detection method based on artificial intelligence is applied to one or more electronic devices, which are devices capable of automatically performing numerical calculation and/or information processing according to computer readable instructions set or stored in advance, and the hardware thereof includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.
The electronic device may be any electronic product capable of performing human-computer interaction with a user, for example, a Personal computer, a tablet computer, a smart phone, a Personal Digital Assistant (PDA), a game machine, an interactive Internet Protocol Television (IPTV), a smart wearable device, and the like.
The electronic device may include a network device and/or a user device. Wherein the network device includes, but is not limited to, a single network electronic device, an electronic device group consisting of a plurality of network electronic devices, or a Cloud Computing (Cloud Computing) based Cloud consisting of a large number of hosts or network electronic devices.
The network in which the electronic device is located includes, but is not limited to: the internet, a wide area Network, a metropolitan area Network, a local area Network, a Virtual Private Network (VPN), and the like.
And S10, when receiving the entity relationship detection request, acquiring the text to be detected according to the entity relationship detection request.
In at least one embodiment of the present invention, the entity relationship detection request carries a storage path, a text identifier, and the like.
The text to be detected refers to the text needing entity relationship detection. The entity relationship detection comprises the steps of extracting the entity relationship in the text to be detected and detecting the authenticity of the entity relationship. Further, the entity relationship may refer to a collaborative relationship between multiple enterprises.
In at least one embodiment of the present invention, the acquiring, by the electronic device, the text to be detected according to the entity relationship detection request includes:
analyzing the message of the entity relationship detection request to obtain the data information carried by the message;
extracting a storage path and a text identifier from the data information;
generating a query sentence according to the storage path and the text identifier;
and executing the query statement to obtain the text to be detected.
By the implementation mode, the text to be detected can be quickly acquired.
And S11, analyzing the text to be detected based on the entity relationship recognition model trained in advance to obtain a recognition result.
In at least one embodiment of the invention, the entity relationship recognition model may be generated based on the open document training of the enterprise. Specifically, the electronic device inputs the disclosure file into a pre-constructed learner to obtain a prediction result, obtains a labeling result of the disclosure file, and adjusts the learner according to the similarity between the prediction result and the labeling result until the similarity between the prediction result and the labeling result is not increased, so as to obtain the entity relationship identification model.
The learner comprises an encoding layer, a semantic generation layer and a relation classification layer.
The recognition result may include: the text to be detected contains entity relations, or the text to be detected does not contain entity relations.
In at least one embodiment of the present invention, the analyzing, by the electronic device, the text to be detected based on a pre-trained entity relationship recognition model to obtain a recognition result includes:
performing word segmentation processing on the text to be detected to obtain a plurality of text word segments;
acquiring a coding mapping table of the entity relationship identification model;
coding the text participles based on the coding mapping table to obtain a plurality of word codes;
splicing the word codes according to the vocabulary positions of the text participles in the text to be detected to obtain a code vector;
generating a position vector of the text to be detected based on the representation sequence of the text participles in the coding vector;
obtaining a semantic generation network and a relation classification network of the entity relation identification model;
analyzing the coding vector and the position vector based on the semantic generation network to obtain a text semantic vector of the text to be detected;
acquiring a weight matrix and a bias vector in the relation classification network;
calculating the product of the text semantic vector and the weight matrix to obtain an operation vector, and calculating the sum of the operation vector and the offset vector to obtain a classification vector;
and determining the category corresponding to the dimension with the largest value in the classification vectors as the identification result.
The encoding mapping table stores a plurality of mapping relations between words and encoding values.
The vocabulary position refers to position information of the text to be detected generated by combining the plurality of text word segments.
The representation order refers to an order of encoding and splicing the plurality of words to generate the encoding vector.
The text semantic vector is used for representing semantic information of the text to be detected.
By dividing the text to be detected into the plurality of text participles, the generation efficiency of the coding vector can be improved, the overlong length of the position vector can be avoided, the analysis efficiency of the semantic generation network is improved, meanwhile, the semantics of the text to be detected are analyzed by combining the coding vector and the position vector, and the meanings of the text participles are different at different positions in the sentence, so that the accuracy of the text semantic vector is improved, and the recognition result can be accurately generated based on the weight matrix and the offset vector.
Specifically, the electronic device performs word segmentation processing on the text to be detected to obtain a plurality of text word segments, including:
segmenting the text to be detected based on a preset dictionary to obtain a plurality of segmentation paths and path participles corresponding to each segmentation path;
acquiring a segmentation weight of the path segmentation from the preset dictionary;
for each segmentation path, calculating the sum of the word segmentation weights to obtain the total path score of each segmentation path;
and determining the path participle corresponding to the segmentation path with the maximum total path score as the plurality of text participles.
The preset dictionary stores a plurality of user-defined words and the weight of each user-defined word. The weight value can be determined according to the word frequency and the inverse document frequency of each user-defined vocabulary in a plurality of text data.
The path total score of each segmentation path can be accurately determined through the word segmentation weight, so that the segmentation efficiency of the multiple text word segmentations is improved.
And S12, if the recognition result is a preset result, extracting the relational sentences from the text to be detected according to the recognition result.
In at least one embodiment of the present invention, the preset result indicates that the text to be detected contains an entity relationship.
The relational statement refers to a text statement describing the relationship of the entity.
In at least one embodiment of the present invention, the extracting, by the electronic device, the relational statement from the text to be detected according to the recognition result includes:
acquiring a standard vocabulary from a preset lexicon according to the recognition result;
traversing each text statement in the text to be detected based on the standard vocabulary;
and determining the text sentence containing the standard vocabulary as the relational sentence.
The preset lexicon stores a plurality of standard vocabularies matching the recognition result, and the standard vocabularies are used for indicating that a plurality of target entities contain a cooperative relationship, for example, the standard vocabularies may include: collaboration, etc.
And the relation sentences can be quickly extracted from the text to be detected through the standard vocabularies.
In at least one embodiment of the present invention, if the recognition result is not the preset result, the detection result is determined as that the text to be detected does not contain an entity relationship.
By the implementation mode, the text without entity relation can be prevented from being analyzed, and the utilization rate of the execution thread is improved.
S13, identifying the object entity in the relational statement.
In at least one embodiment of the invention, the object entity refers to a business entity in the relational statement.
In at least one embodiment of the invention, the electronic device identifying the object entity in the relational statement comprises:
vectorizing the relational statement based on a plurality of statement participles of the relational statement to obtain a statement vector sequence;
inputting the statement vector sequence into a pre-trained entity recognition model, and acquiring the output probability and the transition probability of each statement participle on a plurality of configuration labels of an activation layer;
for each sentence word segmentation, carrying out weighting and operation on the output probability and the transition probability of each configuration label to obtain the label score of each configuration label;
determining the configuration label with the highest label score as an output label of the sentence segmentation;
and matching the output label with a preset entity label, and determining the sentence participle corresponding to the output label successfully matched with the preset entity label as the object entity.
Wherein the plurality of sentence segmentations are extracted from the plurality of text segmentations.
The entity identification model includes the active layer, the active layer includes the configuration tags, the configuration tags include tags corresponding to the target entity, for example, the configuration tags may be: businesses, people, etc.
The tag score is used to indicate that the sentence participle is a score of the configuration tag.
The preset entity tag is set according to actual requirements, and it can be understood that the preset entity tag can be set as an enterprise tag because the entity relationship between enterprises is analyzed.
Through the implementation mode, the output label corresponding to each sentence segmentation can be accurately determined, and therefore the identification accuracy of the object entity is improved.
S14, if there are more than one object entities, positioning the entity relations of the object entities in the relation statement.
In at least one embodiment of the present invention, the entity relationship refers to a relationship between a plurality of the object entities, for example, the entity relationship may be a cooperative relationship.
In at least one embodiment of the present invention, the electronic device locating an entity relationship of a plurality of the object entities in the relational statement comprises:
for an entity pair in a plurality of object entities, detecting whether the object entities in the entity pair are in the same relational statement or not, wherein the entity pair comprises any two object entities;
if the object entities in the entity pair exist in the same relational statement, analyzing the syntactic structure of the object entities in the entity pair in the relational statement;
and if the number of the grammar structures is multiple, determining that the object entity in the entity pair contains the entity relation.
Wherein the syntax structure is used to indicate the role that the object entity plays in the relational statement, and the syntax structure may include, but is not limited to: object, subject, etc.
It is understood that there are a plurality of the syntax structures, which is equivalent to that the syntax structures of the object entities in the entity pair in the relational statement are different.
By detecting whether the object entities in the entity pair are in the same relation statement or not, the object entities without the cooperative relation can be preliminarily removed, the number of grammatical structures of any two object entities is further detected, and the entity relation can be rapidly and accurately determined.
In at least one embodiment of the present invention, the method for detecting entity relationship based on artificial intelligence further comprises:
if the entity number of the object entity is smaller than the preset number, acquiring a preset tag, wherein the preset tag is used for indicating a release user;
extracting information corresponding to the preset label from the text to be detected as a text publisher of the text to be detected;
and determining the incidence relation between the text publisher and the object entity as the entity relation.
Wherein, the number of entities refers to the number of the object entities, and the number of entities is usually a positive integer.
The preset number is typically set to 2. It is understood that the number of entities of the target entity is less than the preset number, that is, the target entity does not have a plurality, that is, the number of entities of the target entity is 1.
The text publisher refers to a publishing user of the text to be detected, and the text publisher can be any enterprise.
By the implementation mode, the problem that the entity relation cannot be extracted due to the semantic habit of Chinese can be avoided, and the extraction integrity of the entity relation is improved.
And S15, detecting the entity relation based on a preset map to obtain a detection result of the text to be detected.
In at least one embodiment of the present invention, the preset map stores a plurality of objects and an enterprise object associated with each object.
The detection result may include: the text to be detected does not contain entity relation; the text to be detected contains entity relations, and the entity relations have authenticity; the text to be detected contains entity relations, and the entity relations are not real.
It should be emphasized that, in order to further ensure the privacy and security of the detection result, the detection result may also be stored in a node of a block chain.
In at least one embodiment of the present invention, the detecting, by the electronic device, the entity relationship based on a preset map, and obtaining a detection result of the text to be detected includes:
for each entity relationship, acquiring a plurality of relationship objects of the entity relationship;
for any relation object in the plurality of relation objects, determining the rest relation objects except the any relation object in the plurality of relation objects as target objects;
traversing the preset map based on any relation object to obtain a plurality of associated objects of any relation object;
detecting whether the target object is contained in the plurality of associated objects;
and if the plurality of associated objects contain the target object, determining the detection result as that the entity relationship has authenticity.
By detecting the plurality of relation objects in each entity relation, the unreal entity relation caused by false propaganda of a certain object can be avoided, and the accuracy of the detection result is improved.
According to the technical scheme, the recognition result of the text to be detected is recognized through the entity relationship recognition model, the text which does not contain entity relationship can be prevented from being further analyzed, and further, the relationship sentences can be determined from a plurality of text sentences in the text to be detected and analyzed according to the recognition result, so that the analysis efficiency of the entity relationship is improved, the problem that the entity relationship cannot be extracted can be avoided, the authenticity of the entity relationship can be accurately analyzed through the preset map, the accuracy of the detection result is improved, and whether false propaganda is executed by an enterprise or not can be accurately recognized.
FIG. 2 is a functional block diagram of an embodiment of an artificial intelligence-based entity relationship detection apparatus according to the present invention. The entity relationship detection device 11 based on artificial intelligence comprises an acquisition unit 110, an analysis unit 111, an extraction unit 112, a recognition unit 113, a positioning unit 114, a detection unit 115, an extraction unit 116 and a determination unit 117. The module/unit referred to herein is a series of computer readable instruction segments that can be accessed by the processor 13 and perform a fixed function and that are stored in the memory 12. In the present embodiment, the functions of the modules/units will be described in detail in the following embodiments.
When receiving an entity relationship detection request, the obtaining unit 110 obtains a text to be detected according to the entity relationship detection request.
In at least one embodiment of the present invention, the entity relationship detection request carries a storage path, a text identifier, and the like.
The text to be detected refers to the text needing entity relationship detection. The entity relationship detection comprises the steps of extracting the entity relationship in the text to be detected and detecting the authenticity of the entity relationship. Further, the entity relationship may refer to a collaborative relationship between multiple enterprises.
In at least one embodiment of the present invention, the obtaining unit 110, according to the entity relationship detection request, obtains the text to be detected, including:
analyzing the message of the entity relationship detection request to obtain the data information carried by the message;
extracting a storage path and a text identifier from the data information;
generating a query sentence according to the storage path and the text identifier;
and executing the query statement to obtain the text to be detected.
By the implementation mode, the text to be detected can be quickly acquired.
The analysis unit 111 analyzes the text to be detected based on the entity relationship recognition model trained in advance to obtain a recognition result.
In at least one embodiment of the invention, the entity relationship recognition model may be generated based on the open document training of the enterprise. Specifically, the disclosure file is input into a pre-constructed learner to obtain a prediction result, a labeling result of the disclosure file is obtained, the learner is adjusted according to the similarity between the prediction result and the labeling result until the similarity between the prediction result and the labeling result is not increased any more, and the entity relationship identification model is obtained.
The learner comprises an encoding layer, a semantic generation layer and a relation classification layer.
The recognition result may include: the text to be detected contains entity relations, or the text to be detected does not contain entity relations.
In at least one embodiment of the present invention, the analyzing unit 111 analyzes the text to be detected based on a pre-trained entity relationship recognition model, and obtaining a recognition result includes:
performing word segmentation processing on the text to be detected to obtain a plurality of text word segments;
acquiring a coding mapping table of the entity relationship identification model;
coding the text participles based on the coding mapping table to obtain a plurality of word codes;
splicing the word codes according to the vocabulary positions of the text participles in the text to be detected to obtain a code vector;
generating a position vector of the text to be detected based on the representation sequence of the text participles in the coding vector;
obtaining a semantic generation network and a relation classification network of the entity relation identification model;
analyzing the coding vector and the position vector based on the semantic generation network to obtain a text semantic vector of the text to be detected;
acquiring a weight matrix and a bias vector in the relation classification network;
calculating the product of the text semantic vector and the weight matrix to obtain an operation vector, and calculating the sum of the operation vector and the offset vector to obtain a classification vector;
and determining the category corresponding to the dimension with the largest value in the classification vectors as the identification result.
The encoding mapping table stores a plurality of mapping relations between words and encoding values.
The vocabulary position refers to position information of the text to be detected generated by combining the plurality of text word segments.
The representation order refers to an order of encoding and splicing the plurality of words to generate the encoding vector.
The text semantic vector is used for representing semantic information of the text to be detected.
By dividing the text to be detected into the plurality of text participles, the generation efficiency of the coding vector can be improved, the overlong length of the position vector can be avoided, the analysis efficiency of the semantic generation network is improved, meanwhile, the semantics of the text to be detected are analyzed by combining the coding vector and the position vector, and the meanings of the text participles are different at different positions in the sentence, so that the accuracy of the text semantic vector is improved, and the recognition result can be accurately generated based on the weight matrix and the offset vector.
Specifically, the analyzing unit 111 performs word segmentation processing on the text to be detected to obtain a plurality of text word segmentations, including:
segmenting the text to be detected based on a preset dictionary to obtain a plurality of segmentation paths and path participles corresponding to each segmentation path;
acquiring a segmentation weight of the path segmentation from the preset dictionary;
for each segmentation path, calculating the sum of the word segmentation weights to obtain the total path score of each segmentation path;
and determining the path participle corresponding to the segmentation path with the maximum total path score as the plurality of text participles.
The preset dictionary stores a plurality of user-defined words and the weight of each user-defined word. The weight value can be determined according to the word frequency and the inverse document frequency of each user-defined vocabulary in a plurality of text data.
The path total score of each segmentation path can be accurately determined through the word segmentation weight, so that the segmentation efficiency of the multiple text word segmentations is improved.
If the recognition result is a preset result, the extracting unit 112 extracts the relational statement from the text to be detected according to the recognition result.
In at least one embodiment of the present invention, the preset result indicates that the text to be detected contains an entity relationship.
The relational statement refers to a text statement describing the relationship of the entity.
In at least one embodiment of the present invention, the extracting unit 112, according to the recognition result, extracting the relational statement from the text to be detected includes:
acquiring a standard vocabulary from a preset lexicon according to the recognition result;
traversing each text statement in the text to be detected based on the standard vocabulary;
and determining the text sentence containing the standard vocabulary as the relational sentence.
The preset lexicon stores a plurality of standard vocabularies matching the recognition result, and the standard vocabularies are used for indicating that a plurality of target entities contain a cooperative relationship, for example, the standard vocabularies may include: collaboration, etc.
And the relation sentences can be quickly extracted from the text to be detected through the standard vocabularies.
In at least one embodiment of the present invention, if the recognition result is not the preset result, the detection result is determined as that the text to be detected does not contain an entity relationship.
By the implementation mode, the text without entity relation can be prevented from being analyzed, and the utilization rate of the execution thread is improved.
The identifying unit 113 identifies the object entity in the relational statement.
In at least one embodiment of the invention, the object entity refers to a business entity in the relational statement.
In at least one embodiment of the present invention, the identifying unit 113 identifies the object entity in the relational statement includes:
vectorizing the relational statement based on a plurality of statement participles of the relational statement to obtain a statement vector sequence;
inputting the statement vector sequence into a pre-trained entity recognition model, and acquiring the output probability and the transition probability of each statement participle on a plurality of configuration labels of an activation layer;
for each sentence word segmentation, carrying out weighting and operation on the output probability and the transition probability of each configuration label to obtain the label score of each configuration label;
determining the configuration label with the highest label score as an output label of the sentence segmentation;
and matching the output label with a preset entity label, and determining the sentence participle corresponding to the output label successfully matched with the preset entity label as the object entity.
Wherein the plurality of sentence segmentations are extracted from the plurality of text segmentations.
The entity identification model includes the active layer, the active layer includes the configuration tags, the configuration tags include tags corresponding to the target entity, for example, the configuration tags may be: businesses, people, etc.
The tag score is used to indicate that the sentence participle is a score of the configuration tag.
The preset entity tag is set according to actual requirements, and it can be understood that the preset entity tag can be set as an enterprise tag because the entity relationship between enterprises is analyzed.
Through the implementation mode, the output label corresponding to each sentence segmentation can be accurately determined, and therefore the identification accuracy of the object entity is improved.
If there are multiple object entities, the positioning unit 114 positions entity relationships of the multiple object entities in the relationship statement.
In at least one embodiment of the present invention, the entity relationship refers to a relationship between a plurality of the object entities, for example, the entity relationship may be a cooperative relationship.
In at least one embodiment of the present invention, the positioning unit 114 positions entity relationships of a plurality of the object entities in the relational statement, including:
for an entity pair in a plurality of object entities, detecting whether the object entities in the entity pair are in the same relational statement or not, wherein the entity pair comprises any two object entities;
if the object entities in the entity pair exist in the same relational statement, analyzing the syntactic structure of the object entities in the entity pair in the relational statement;
and if the number of the grammar structures is multiple, determining that the object entity in the entity pair contains the entity relation.
Wherein the syntax structure is used to indicate the role that the object entity plays in the relational statement, and the syntax structure may include, but is not limited to: object, subject, etc.
It is understood that there are a plurality of the syntax structures, which is equivalent to that the syntax structures of the object entities in the entity pair in the relational statement are different.
By detecting whether the object entities in the entity pair are in the same relation statement or not, the object entities without the cooperative relation can be preliminarily removed, the number of grammatical structures of any two object entities is further detected, and the entity relation can be rapidly and accurately determined.
In at least one embodiment of the present invention, if the number of the object entities is less than a preset number, the obtaining unit 110 obtains a preset tag, where the preset tag is used to indicate a publishing user;
the extracting unit 116 extracts information corresponding to the preset tag from the text to be detected as a text publisher of the text to be detected;
the determining unit 117 determines the association relationship of the text publisher and the object entity as the entity relationship.
Wherein, the number of entities refers to the number of the object entities, and the number of entities is usually a positive integer.
The preset number is typically set to 2. It is understood that the number of entities of the target entity is less than the preset number, that is, the target entity does not have a plurality, that is, the number of entities of the target entity is 1.
The text publisher refers to a publishing user of the text to be detected, and the text publisher can be any enterprise.
By the implementation mode, the problem that the entity relation cannot be extracted due to the semantic habit of Chinese can be avoided, and the extraction integrity of the entity relation is improved.
The detecting unit 115 detects the entity relationship based on a preset map to obtain a detection result of the text to be detected.
In at least one embodiment of the present invention, the preset map stores a plurality of objects and an enterprise object associated with each object.
The detection result may include: the text to be detected does not contain entity relation; the text to be detected contains entity relations, and the entity relations have authenticity; the text to be detected contains entity relations, and the entity relations are not real.
It should be emphasized that, in order to further ensure the privacy and security of the detection result, the detection result may also be stored in a node of a block chain.
In at least one embodiment of the present invention, the detecting unit 115 detects the entity relationship based on a preset map, and obtaining a detection result of the text to be detected includes:
for each entity relationship, acquiring a plurality of relationship objects of the entity relationship;
for any relation object in the plurality of relation objects, determining the rest relation objects except the any relation object in the plurality of relation objects as target objects;
traversing the preset map based on any relation object to obtain a plurality of associated objects of any relation object;
detecting whether the target object is contained in the plurality of associated objects;
and if the plurality of associated objects contain the target object, determining the detection result as that the entity relationship has authenticity.
By detecting the plurality of relation objects in each entity relation, the unreal entity relation caused by false propaganda of a certain object can be avoided, and the accuracy of the detection result is improved.
According to the technical scheme, the recognition result of the text to be detected is recognized through the entity relationship recognition model, the text which does not contain entity relationship can be prevented from being further analyzed, and further, the relationship sentences can be determined from a plurality of text sentences in the text to be detected and analyzed according to the recognition result, so that the analysis efficiency of the entity relationship is improved, the problem that the entity relationship cannot be extracted can be avoided, the authenticity of the entity relationship can be accurately analyzed through the preset map, the accuracy of the detection result is improved, and whether false propaganda is executed by an enterprise or not can be accurately recognized.
Fig. 3 is a schematic structural diagram of an electronic device according to a preferred embodiment of the present invention, which implements an artificial intelligence-based entity relationship detection method.
In one embodiment of the present invention, the electronic device 1 includes, but is not limited to, a memory 12, a processor 13, and computer readable instructions stored in the memory 12 and executable on the processor 13, such as an artificial intelligence based entity relationship detection program.
It will be appreciated by a person skilled in the art that the schematic diagram is only an example of the electronic device 1 and does not constitute a limitation of the electronic device 1, and that it may comprise more or less components than shown, or some components may be combined, or different components, e.g. the electronic device 1 may further comprise an input output device, a network access device, a bus, etc.
The Processor 13 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. The processor 13 is an operation core and a control center of the electronic device 1, and is connected to each part of the whole electronic device 1 by various interfaces and lines, and executes an operating system of the electronic device 1 and various installed application programs, program codes, and the like.
Illustratively, the computer readable instructions may be partitioned into one or more modules/units that are stored in the memory 12 and executed by the processor 13 to implement the present invention. The one or more modules/units may be a series of computer readable instruction segments capable of performing specific functions, which are used for describing the execution process of the computer readable instructions in the electronic device 1. For example, the computer readable instructions may be divided into an acquisition unit 110, an analysis unit 111, an extraction unit 112, a recognition unit 113, a positioning unit 114, a detection unit 115, an extraction unit 116, and a determination unit 117.
The memory 12 may be used for storing the computer readable instructions and/or modules, and the processor 13 implements various functions of the electronic device 1 by executing or executing the computer readable instructions and/or modules stored in the memory 12 and invoking data stored in the memory 12. The memory 12 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to use of the electronic device, and the like. The memory 12 may include non-volatile and volatile memories, such as: a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other storage device.
The memory 12 may be an external memory and/or an internal memory of the electronic device 1. Further, the memory 12 may be a memory having a physical form, such as a memory stick, a TF Card (Trans-flash Card), or the like.
The integrated modules/units of the electronic device 1 may be stored in a computer-readable storage medium if they are implemented in the form of software functional units and sold or used as separate products. Based on such understanding, all or part of the flow of the method according to the above embodiments may be implemented by hardware that is configured to be instructed by computer readable instructions, which may be stored in a computer readable storage medium, and when the computer readable instructions are executed by a processor, the steps of the method embodiments may be implemented.
Wherein the computer readable instructions comprise computer readable instruction code which may be in source code form, object code form, an executable file or some intermediate form, and the like. The computer-readable medium may include: any entity or device capable of carrying said computer readable instruction code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM).
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
In conjunction with fig. 1, the memory 12 in the electronic device 1 stores computer readable instructions to implement an artificial intelligence based entity relationship detection method, and the processor 13 can execute the computer readable instructions to implement:
when an entity relationship detection request is received, acquiring a text to be detected according to the entity relationship detection request;
analyzing the text to be detected based on a pre-trained entity relationship recognition model to obtain a recognition result;
if the recognition result is a preset result, extracting a relational statement from the text to be detected according to the recognition result;
identifying an object entity in the relational statement;
if the number of the object entities is multiple, positioning entity relations of the object entities in the relation statement;
and detecting the entity relation based on a preset map to obtain a detection result of the text to be detected.
Specifically, the processor 13 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1 for a specific implementation method of the computer readable instructions, which is not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The computer readable storage medium has computer readable instructions stored thereon, wherein the computer readable instructions when executed by the processor 13 are configured to implement the steps of:
when an entity relationship detection request is received, acquiring a text to be detected according to the entity relationship detection request;
analyzing the text to be detected based on a pre-trained entity relationship recognition model to obtain a recognition result;
if the recognition result is a preset result, extracting a relational statement from the text to be detected according to the recognition result;
identifying an object entity in the relational statement;
if the number of the object entities is multiple, positioning entity relations of the object entities in the relation statement;
and detecting the entity relation based on a preset map to obtain a detection result of the text to be detected.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
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.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. The plurality of units or devices may also be implemented by one unit or device through software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. An entity relationship detection method based on artificial intelligence is characterized in that the entity relationship detection method based on artificial intelligence comprises the following steps:
when an entity relationship detection request is received, acquiring a text to be detected according to the entity relationship detection request;
analyzing the text to be detected based on a pre-trained entity relationship recognition model to obtain a recognition result;
if the recognition result is a preset result, extracting a relational statement from the text to be detected according to the recognition result;
identifying an object entity in the relational statement;
if the number of the object entities is multiple, positioning entity relations of the object entities in the relation statement;
and detecting the entity relation based on a preset map to obtain a detection result of the text to be detected.
2. The method for detecting entity relationship based on artificial intelligence as claimed in claim 1, wherein said analyzing the text to be detected based on the entity relationship recognition model trained in advance to obtain the recognition result comprises:
performing word segmentation processing on the text to be detected to obtain a plurality of text word segments;
acquiring a coding mapping table of the entity relationship identification model;
coding the text participles based on the coding mapping table to obtain a plurality of word codes;
splicing the word codes according to the vocabulary positions of the text participles in the text to be detected to obtain a code vector;
generating a position vector of the text to be detected based on the representation sequence of the text participles in the coding vector;
obtaining a semantic generation network and a relation classification network of the entity relation identification model;
analyzing the coding vector and the position vector based on the semantic generation network to obtain a text semantic vector of the text to be detected;
acquiring a weight matrix and a bias vector in the relation classification network;
calculating the product of the text semantic vector and the weight matrix to obtain an operation vector, and calculating the sum of the operation vector and the offset vector to obtain a classification vector;
and determining the category corresponding to the dimension with the largest value in the classification vectors as the identification result.
3. The method for detecting entity relationship based on artificial intelligence as claimed in claim 1, wherein said extracting relationship statements from said text to be detected according to said recognition result comprises:
acquiring a standard vocabulary from a preset lexicon according to the recognition result;
traversing each text statement in the text to be detected based on the standard vocabulary;
and determining the text sentence containing the standard vocabulary as the relational sentence.
4. The artificial intelligence based entity relationship detection method of claim 1, wherein said identifying object entities in the relational statement comprises:
vectorizing the relational statement based on a plurality of statement participles of the relational statement to obtain a statement vector sequence;
inputting the statement vector sequence into a pre-trained entity recognition model, and acquiring the output probability and the transition probability of each statement participle on a plurality of configuration labels of an activation layer;
for each sentence word segmentation, carrying out weighting and operation on the output probability and the transition probability of each configuration label to obtain the label score of each configuration label;
determining the configuration label with the highest label score as an output label of the sentence segmentation;
and matching the output label with a preset entity label, and determining the sentence participle corresponding to the output label successfully matched with the preset entity label as the object entity.
5. The artificial intelligence based entity relationship detection method of claim 1, wherein said locating entity relationships of a plurality of said object entities in said relationship statement comprises:
for an entity pair in a plurality of object entities, detecting whether the object entities in the entity pair are in the same relational statement or not, wherein the entity pair comprises any two object entities;
if the object entities in the entity pair exist in the same relational statement, analyzing the syntactic structure of the object entities in the entity pair in the relational statement;
and if the number of the grammar structures is multiple, determining that the object entity in the entity pair contains the entity relation.
6. The artificial intelligence based entity relationship detection method of claim 1, wherein the artificial intelligence based entity relationship detection method further comprises:
if the entity number of the object entity is smaller than the preset number, acquiring a preset tag, wherein the preset tag is used for indicating a release user;
extracting information corresponding to the preset label from the text to be detected as a text publisher of the text to be detected;
and determining the incidence relation between the text publisher and the object entity as the entity relation.
7. The method for detecting entity relationship based on artificial intelligence according to claim 1, wherein the detecting the entity relationship based on a preset map to obtain the detection result of the text to be detected comprises:
for each entity relationship, acquiring a plurality of relationship objects of the entity relationship;
for any relation object in the plurality of relation objects, determining the rest relation objects except the any relation object in the plurality of relation objects as target objects;
traversing the preset map based on any relation object to obtain a plurality of associated objects of any relation object;
detecting whether the target object is contained in the plurality of associated objects;
and if the plurality of associated objects contain the target object, determining the detection result as that the entity relationship has authenticity.
8. An artificial intelligence based entity relationship detection apparatus, comprising:
the acquiring unit is used for acquiring a text to be detected according to the entity relationship detection request when the entity relationship detection request is received;
the analysis unit is used for analyzing the text to be detected based on a pre-trained entity relationship recognition model to obtain a recognition result;
the extraction unit is used for extracting the relation sentences from the text to be detected according to the identification result if the identification result is a preset result;
the identification unit is used for identifying the object entity in the relational statement;
a positioning unit, configured to position an entity relationship of the multiple object entities in the relationship statement if there are multiple object entities;
and the detection unit is used for detecting the entity relation based on a preset map to obtain a detection result of the text to be detected.
9. An electronic device, characterized in that the electronic device comprises:
a memory storing computer readable instructions; and
a processor executing computer readable instructions stored in the memory to implement the artificial intelligence based entity relationship detection method of any one of claims 1 to 7.
10. A computer-readable storage medium characterized by: the computer readable storage medium stores computer readable instructions which are executed by a processor in an electronic device to implement the artificial intelligence based entity relationship detection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110923984.0A CN113627186B (en) | 2021-08-12 | 2021-08-12 | Entity relation detection method based on artificial intelligence and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110923984.0A CN113627186B (en) | 2021-08-12 | 2021-08-12 | Entity relation detection method based on artificial intelligence and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113627186A true CN113627186A (en) | 2021-11-09 |
| CN113627186B CN113627186B (en) | 2023-12-22 |
Family
ID=78384990
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110923984.0A Active CN113627186B (en) | 2021-08-12 | 2021-08-12 | Entity relation detection method based on artificial intelligence and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113627186B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114613515A (en) * | 2022-03-28 | 2022-06-10 | 医渡云（北京）技术有限公司 | Medical entity relationship extraction method and device, storage medium and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111625659A (en) * | 2020-08-03 | 2020-09-04 | 腾讯科技（深圳）有限公司 | Knowledge graph processing method, device, server and storage medium |
| CN112579752A (en) * | 2020-12-10 | 2021-03-30 | 上海明略人工智能(集团)有限公司 | Entity relationship extraction method and device, storage medium and electronic equipment |
| US20210117509A1 (en) * | 2019-10-17 | 2021-04-22 | Adobe Inc. | Creating a knowledge graph based on text-based knowledge corpora |
| WO2021151353A1 (en) * | 2020-10-20 | 2021-08-05 | 平安科技（深圳）有限公司 | Medical entity relationship extraction method and apparatus, and computer device and readable storage medium |
-
2021
- 2021-08-12 CN CN202110923984.0A patent/CN113627186B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210117509A1 (en) * | 2019-10-17 | 2021-04-22 | Adobe Inc. | Creating a knowledge graph based on text-based knowledge corpora |
| CN111625659A (en) * | 2020-08-03 | 2020-09-04 | 腾讯科技（深圳）有限公司 | Knowledge graph processing method, device, server and storage medium |
| WO2021151353A1 (en) * | 2020-10-20 | 2021-08-05 | 平安科技（深圳）有限公司 | Medical entity relationship extraction method and apparatus, and computer device and readable storage medium |
| CN112579752A (en) * | 2020-12-10 | 2021-03-30 | 上海明略人工智能(集团)有限公司 | Entity relationship extraction method and device, storage medium and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114613515A (en) * | 2022-03-28 | 2022-06-10 | 医渡云（北京）技术有限公司 | Medical entity relationship extraction method and device, storage medium and electronic equipment |
| CN114613515B (en) * | 2022-03-28 | 2023-02-07 | 医渡云（北京）技术有限公司 | Medical entity relationship extraction method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113627186B (en) | 2023-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112417096B (en) | Question-answer pair matching method, device, electronic equipment and storage medium | |
| CN112686036B (en) | Risk text recognition method and device, computer equipment and storage medium | |
| CN111738016A (en) | Multi-intention recognition method and related equipment | |
| CN111538816B (en) | Question-answering method, device, electronic equipment and medium based on AI identification | |
| CN113656547B (en) | Text matching method, device, equipment and storage medium | |
| CN112989826B (en) | Test question score determining method, device, equipment and medium based on artificial intelligence | |
| CN114090794A (en) | Event map construction method based on artificial intelligence and related equipment | |
| CN113094478B (en) | Expression reply method, device, equipment and storage medium | |
| CN111985241A (en) | Medical information query method, device, electronic equipment and medium | |
| CN114037545A (en) | Client recommendation method, device, equipment and storage medium | |
| CN115222443A (en) | Client group division method, device, equipment and storage medium | |
| CN113342977B (en) | Invoice image classification method, device, equipment and storage medium | |
| CN113705468A (en) | Digital image identification method based on artificial intelligence and related equipment | |
| CN111783425B (en) | Intention identification method based on syntactic analysis model and related device | |
| CN113627186B (en) | Entity relation detection method based on artificial intelligence and related equipment | |
| CN112989820B (en) | Legal document positioning method, device, equipment and storage medium | |
| CN113420545B (en) | Abstract generation method, device, equipment and storage medium | |
| WO2023137903A1 (en) | Reply statement determination method and apparatus based on rough semantics, and electronic device | |
| CN113486680B (en) | Text translation method, device, equipment and storage medium | |
| CN110717029A (en) | Information processing method and system | |
| CN112949305B (en) | Negative feedback information acquisition method, device, equipment and storage medium | |
| CN113420143B (en) | Method, device, equipment and storage medium for generating document abstract | |
| CN113408265B (en) | Semantic analysis method, device and equipment based on human-computer interaction and storage medium | |
| CN113326365A (en) | Reply statement generation method, device, equipment and storage medium | |
| KR20220138960A (en) | Apparatus and metohd for generating named entity recognition model based on knowledge enbedding model |
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 |