CN110489520B - Knowledge graph-based event processing method, device, equipment and storage medium - Google Patents
Knowledge graph-based event processing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN110489520B CN110489520B CN201910609478.7A CN201910609478A CN110489520B CN 110489520 B CN110489520 B CN 110489520B CN 201910609478 A CN201910609478 A CN 201910609478A CN 110489520 B CN110489520 B CN 110489520B
- Authority
- CN
- China
- Prior art keywords
- event
- information
- information text
- entity
- knowledge graph
- 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
Images
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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
-
- 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
-
- 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
Abstract
The application relates to an event processing method, device, equipment and storage medium based on a knowledge graph. The method relates to knowledge-graph based event processing, the method comprising: acquiring an information text crawled from an information platform and trigger words in the information text, acquiring a preset target field event template when determining that an event type corresponding to the information text belongs to a target field event according to the trigger words, determining event element roles corresponding to the event types according to the target field event template, extracting event elements corresponding to the event element roles from the information text, and taking structured data generated according to the event element roles and corresponding event elements as event element information corresponding to the information text; matching the event meta-information with the entity in the knowledge graph; and carrying out reasoning according to the matched entity and a reasoning path corresponding to the target domain event in the knowledge graph to obtain a corresponding event analysis result. By adopting the method, the efficiency and accuracy of processing the events in the target field can be improved.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method and apparatus for processing an event based on a knowledge graph, a computer device, and a storage medium.
Background
The event refers to an event which can be processed by the computer equipment, the computer equipment can process and analyze the event through an event processing program, and the events in different fields can be realized through different event processing programs. The computer may datasheet various events and then process the events, for example, the user's behavior on internet products may be converted into user behavior events, investment behavior occurring in the economic field may be converted into investment events, etc.
However, the processing of the event in the target field is usually implemented based on a preset rule, and the processing of the event in the target field is limited to the rule only in the service code due to the fact that the fixed analysis rule is set for the event in the target field and then the fixed analysis rule is embedded into the service code. In addition, when analyzing the target domain event through the service code, a large amount of data of the target domain event needs to be queried to obtain an analysis result, and the processing efficiency is extremely low.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a knowledge-graph-based event processing method, apparatus, computer device, and storage medium that can improve the accuracy and efficiency of processing a target domain event.
A knowledge-graph-based event processing method, the method comprising:
acquiring an information text crawled from an information platform and a trigger word in the information text;
determining an event type corresponding to the content of the information text according to the trigger word;
when the event type belongs to a target field event, acquiring a preset target field event template;
determining an event element role corresponding to the event type according to the target field event template;
extracting event elements corresponding to the determined event element roles from the information text;
structured data generated according to the event element roles and the corresponding event elements;
taking the generated structured data as event meta-information corresponding to the information text;
matching the extracted event meta-information with the entity in the knowledge graph;
and carrying out reasoning according to the matched entity and a reasoning path corresponding to the target domain event in the knowledge graph to obtain a corresponding event analysis result.
In one embodiment, the acquiring the information text crawled from the information platform and the trigger words in the information text includes:
monitoring each information platform;
when the information platform is monitored to generate new target field information, acquiring a corresponding information text;
word segmentation is carried out on the information text to obtain a corresponding word set;
and taking the words belonging to the trigger word library in the word set as trigger words corresponding to the information text.
In one embodiment, the determining the event type corresponding to the content of the information text according to the trigger word includes:
inputting each trigger word into a trained event classification model based on deep learning;
and outputting the event type corresponding to the information text through the event classification model.
In one embodiment, the matching the extracted event meta-information with the entity in the knowledge-graph includes:
determining candidate entities corresponding to event elements in the event element information in the knowledge graph;
calculating the similarity between each candidate entity and the extracted event meta-information;
and screening entities matched with the event element from the candidate entities based on the similarity.
In one embodiment, the reasoning is performed according to the matched entity and the reasoning path corresponding to the target domain event in the knowledge graph, to obtain a corresponding event analysis result, including:
determining an inference path corresponding to the target domain event according to the knowledge graph;
acquiring entity relations corresponding to the matched entities according to the knowledge graph;
and generating event analysis results according to the reasoning paths, the matched entities and the corresponding entity relations.
In one embodiment, the entity types in the knowledge graph include a target domain event, the target domain event corresponding to at least one inference path; the method further comprises the steps of:
adding event attributes corresponding to the target domain event in the knowledge graph;
updating an inference path corresponding to the target domain event according to the event attribute;
and storing the updated reasoning path and the target domain event in a database correspondingly.
An event processing apparatus based on a knowledge graph, the apparatus comprising:
the acquisition module is used for acquiring the information text crawled from the information platform and the trigger words in the information text;
The event type determining module is used for determining the event type corresponding to the content of the information text according to the trigger word;
the event meta-information extraction module is used for acquiring a preset target domain event template when the event type belongs to a target domain event; determining an event element role corresponding to the event type according to the target field event template; extracting event elements corresponding to the determined event element roles from the information text; structured data generated according to the event element roles and the corresponding event elements; taking the generated structured data as event meta-information corresponding to the information text;
the entity matching module is used for matching the extracted event meta-information with the entity in the knowledge graph;
and the event reasoning module is used for reasoning according to the matched entity and a reasoning path corresponding to the target domain event in the knowledge graph to obtain a corresponding event analysis result.
In one embodiment, the acquisition module is specifically further configured to monitor each information platform; when the information platform is monitored to generate new target field information, acquiring a corresponding information text; word segmentation is carried out on the information text to obtain a corresponding word set; and taking the words belonging to the trigger word library in the word set as trigger words corresponding to the information text.
In one embodiment, the event type determining module is specifically further configured to input each trigger word into a trained event classification model based on deep learning; and outputting the event type corresponding to the information text through the event classification model.
In one embodiment, the entity matching module is specifically further configured to determine a candidate entity in the knowledge graph corresponding to the event element in the event meta information; calculating the similarity between each candidate entity and the extracted event meta-information; and screening entities matched with the event element from the candidate entities based on the similarity.
In one embodiment, the event inference module is specifically configured to determine an inference path corresponding to the target domain event according to the knowledge graph; acquiring entity relations corresponding to the matched entities according to the knowledge graph; and generating event analysis results according to the reasoning paths, the matched entities and the corresponding entity relations.
In one embodiment, the entity types in the knowledge graph include a target domain event, the target domain event corresponding to at least one inference path; the device also comprises an inference roadbed updating module which is used for adding event attributes corresponding to the target field event in the knowledge graph; updating an inference path corresponding to the target domain event according to the event attribute; and storing the updated reasoning path and the target domain event in a database correspondingly.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of:
acquiring an information text crawled from an information platform and a trigger word in the information text;
determining an event type corresponding to the content of the information text according to the trigger word;
when the event type belongs to a target field event, acquiring a preset target field event template;
determining an event element role corresponding to the event type according to the target field event template;
extracting event elements corresponding to the determined event element roles from the information text;
structured data generated according to the event element roles and the corresponding event elements;
taking the generated structured data as event meta-information corresponding to the information text;
matching the extracted event meta-information with the entity in the knowledge graph;
and carrying out reasoning according to the matched entity and a reasoning path corresponding to the target domain event in the knowledge graph to obtain a corresponding event analysis result.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
Acquiring an information text crawled from an information platform and a trigger word in the information text;
determining an event type corresponding to the content of the information text according to the trigger word;
when the event type belongs to a target field event, acquiring a preset target field event template;
determining an event element role corresponding to the event type according to the target field event template;
extracting event elements corresponding to the determined event element roles from the information text;
structured data generated according to the event element roles and the corresponding event elements;
taking the generated structured data as event meta-information corresponding to the information text;
matching the extracted event meta-information with the entity in the knowledge graph;
and carrying out reasoning according to the matched entity and a reasoning path corresponding to the target domain event in the knowledge graph to obtain a corresponding event analysis result.
According to the knowledge graph-based event processing method, the knowledge graph-based event processing device, the computer equipment and the storage medium, after the information text is acquired, the event type corresponding to the content of the information text can be determined according to the trigger words in the information text, when the event type belongs to a target field event, the event element role corresponding to the event type can be determined according to the target field event template, then the event elements corresponding to the event element roles are extracted from the information text, the structured data comprising the event element roles and the event elements is obtained and used as the event element information corresponding to the target field event, the target field event described by the information text can be accurately and comprehensively expressed, and the knowledge graph-based event processing method is the basis for accurately processing the target field event through the knowledge graph.
Further, the extracted event meta-information is matched with the entity in the knowledge graph, the corresponding event analysis result can be directly obtained by reasoning according to the matched entity and the reasoning path corresponding to the target field event in the knowledge graph, compared with an event processing mode of embedding a preset fixed rule in a service code, the event analysis mode based on the knowledge graph does not need to inquire a large amount of data for analysis, the efficiency of analyzing the target field event is improved, and the accuracy of analyzing the event can be improved because the reasoning path corresponding to the target field event in the knowledge graph can be updated and expanded.
Drawings
FIG. 1 is an application scenario diagram of an event processing method based on a knowledge graph in one embodiment;
FIG. 2 is a flow chart of a knowledge-graph-based event processing method in one embodiment;
FIG. 3 is a schematic diagram of event reasoning for financing events based on a knowledge graph in one embodiment;
FIG. 4 is a flowchart of an event processing method based on a knowledge graph according to another embodiment;
FIG. 5 is a block diagram of an event processing device based on knowledge-graph in one embodiment;
Fig. 6 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The event processing method based on the knowledge graph can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The server 104 may obtain the information text crawled from the information platform and trigger words in the information text, determine an event type corresponding to the content of the information text according to the trigger words, when the event type belongs to a target domain event, when the event type belongs to the target domain event, obtain a preset target domain event template, determine event element roles corresponding to the event type according to the target domain event template, extract event elements corresponding to the determined event element roles from the information text, take the generated structured data as event element information corresponding to the information text according to the event element roles and the structured data generated by the corresponding event elements, match the extracted event element information with entities in the knowledge graph, and infer according to the matched entities and reasoning paths corresponding to the target domain event in the knowledge graph, thereby obtaining a corresponding event analysis result. The server 104 may also push the obtained event analysis result to the terminal 102. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smartphones, tablet computers, and portable wearable devices, and the server 104 may be implemented by a stand-alone server or a server cluster composed of a plurality of servers.
In one embodiment, as shown in fig. 2, a method for processing an event based on a knowledge graph is provided, and the method is applied to the server 104 in fig. 1 for illustration, and includes the following steps:
The information text is a text corresponding to information content crawled from an information platform on a network, and comprises texts in news, announcement files, supervision files, financing and melting coupons crawled from appointed websites, wherein the appointed websites can be websites related to target fields, such as exchanges, marketing companies or securities companies, for example, a medium financial network. The trigger words are core words capable of indicating the occurrence of an event, for example, the target area event is an investment event of an economic area, and the trigger words indicating the occurrence of the investment event include "loss", "merging", "fake", "buy", "sell", "buy-in", "financing" and the like.
Specifically, a large amount of information texts can be crawled from websites, the occurrence frequency of each word in the information texts is counted, the words with high frequency are used as trigger words in the target field, and the trigger words form a trigger word stock in the target field. For example, when the target domain is a financial domain, then the target domain event is an event occurring during the investment process and the fact that the event consists of the event occurring, the target domain event includes a financing event, a merge reorganization event, a marketing event, and the like.
In one embodiment, obtaining the information text crawled from the information platform and the trigger words in the information text comprises: monitoring an information platform; when the information platform is monitored to generate new target field information, acquiring a corresponding information text; word segmentation is carried out on the information text to obtain a corresponding word set; and taking the words belonging to the trigger word library in the word set as trigger words corresponding to the information text.
The information platform refers to a source of information text, and comprises a website related to a target field, an organization database of the target field and the like. The server can monitor the information platform, when the information platform is monitored to release a new information text, the newly-added information text is obtained, the information text is divided according to sentences to obtain each sentence, each sentence is divided into words to obtain a word set corresponding to the information text, each word in the word set is matched with a word in a preset trigger word bank, and if the word is matched with the word in the preset trigger word bank, the word is used as a trigger word corresponding to the information text.
In one embodiment, the method may further include: according to the determined trigger words, sentences including at least one trigger word in the information text are determined, and event main bodies corresponding to the events are determined according to the sentences. An event subject is an object to which an event relates, including a person or business.
In this embodiment, the event types may be divided into two major categories, one being an event belonging to the target domain event and one being an event not belonging to the target domain event. Since there are many trigger words extracted from the information text, it is necessary to determine the event type corresponding to the acquired information text according to the trigger words.
In one embodiment, an event trigger word list may be preset, in which trigger words corresponding to each event are stored, for example, the event trigger word list is queried to obtain trigger words corresponding to "financing event" belonging to an event in the financial field, including "financing, a-round financing, B-round financing, and investment"; and the trigger words corresponding to the user information leakage event which do not belong to the financial field event comprise leakage, theft, user information theft, authorization and the like. After the trigger words corresponding to the information text are obtained, corresponding event types are determined according to the coincidence degrees between the trigger words and the trigger words corresponding to all the events in the event trigger word list. The overlap ratio can be calculated according to the occurrence ratio of the trigger words corresponding to a certain event in the trigger words corresponding to the information text, for example, the occurrence frequency of the trigger words in the information text is M, wherein N trigger words belong to the trigger words corresponding to the financing event, and the calculation formula of the overlap ratio p is as follows: 
In one embodiment, determining the event type corresponding to the content of the information text according to the trigger word includes: inputting each trigger word into a trained event classification model based on deep learning; and outputting the event type corresponding to the information text through the event classification model.
In this embodiment, the event type corresponding to the information text may be determined by an event classification model based on deep learning. Specifically, each trigger word obtained can be input into a trained event classification model, and the event type corresponding to the most likely event is calculated based on all trigger words through the event classification model. The event classification model can convert each trigger word into a corresponding word vector, analyze the relation among the word vectors through a hidden layer of the model, and output and obtain the event type corresponding to the information text.
In one embodiment, all trigger words and the extracted event main body can be used as the input of the event classification model together, and the corresponding event type can be output through the event classification model. For example, the output may be a "financing event".
Although the trigger words obtained in step 202 are obtained according to the information text, the target domain information describes but is not necessarily a target domain event, that is, the event type obtained in step 204 does not necessarily belong to a target domain event, and when the event type does not belong to a target domain event, it is not necessary to further analyze the event through subsequent steps 208-210, so that the whole process is ended. When the event type determined according to the trigger word belongs to the event in the target field, event meta-information is further extracted from the information text.
The event meta-information includes event meta-roles and event elements, the event meta-roles are all elements participating in the event, such as time, place, related person, participant, reason of occurrence, etc., and the event elements are specific information corresponding to each event meta-role, such as "2018 12 month 20 day", "Shenzhen", "XX company", etc.
Specifically, a target domain event template of the target domain may be preset, and event element roles corresponding to various target domain events are stored in the target domain event template. The event element roles corresponding to different target domain events are different, for example, the event element roles corresponding to the "financing event" include: the investors, the financing time, the rounds and the financing amount, and the event element roles corresponding to the 'merging and recombining event' comprise: combining party, combining time, A company takes up the share, and B company takes up the share.
In one embodiment, named entity recognition may be performed on each word in the information text, and the named entity type obtained may correspond to the event element and the event element role in the event meta information, respectively. Specifically, if the event type is a certain type of event related to the target field, carrying out named entity recognition on each word in the information text, judging whether the named entity type of the word belongs to an event element role corresponding to the event, and if so, extracting the word as an event element.
For example, according to the event type determined by the trigger word being "financing event", according to the preset target field event template, inquiring that the event element roles corresponding to the financing event include "investors, sponsors, financing time, rounds and financing amount", and the corresponding event elements extracted from the information text are "XX fund, YY bicycle, 2018 12 month and 24 days, A round and 3000 ten thousand", respectively, so that the event element roles are obtained: structured data of event element ": "investors: XX foundation "; "financing Agents: YY bicycle "; "financing time: 2018, 12, 24 "; "round: wheel a "; "financing amount: 3000 ten thousand ", for representing event meta information of the information text.
And step 208, matching the extracted event meta-information with the entity in the knowledge graph.
The knowledge graph stores a large amount of knowledge in the target field in the form of graph data, including a large amount of entities, attributes and relationships between the entities. An entity in the knowledge graph refers to something that has a distinguishing independent existence in the target domain knowledge, such as a certain fund manager, a certain city, a certain university, a certain company or a certain investment product, etc.
Because the event element in the extracted event meta information is not completely consistent with the entity in the knowledge graph, for example, the extracted event meta information is "bei da", and the similar entities in the knowledge graph include "beijing university", "beijing university of the worker" and the like, it is necessary to match the event meta information with a certain entity in the knowledge graph.
In one embodiment, matching the extracted event meta-information with the entities in the knowledge-graph includes: determining candidate entities corresponding to event elements in the event element information in the knowledge graph; calculating the similarity between each candidate entity and the extracted event meta-information; and screening entities matched with the event elements from the candidate entities based on the similarity.
In one embodiment, candidate entities related to the extracted event element may be queried in the knowledge graph, and entity disambiguation may be performed on all candidate entities to determine a unique entity. For example, the candidate entity related to the event element "Beijing university" is queried to include "Beijing university", "Beijing university of the worker", the description information related to each candidate entity can be obtained through a search engine, the similarity between the extracted event element "Beijing university" and the description information corresponding to each candidate entity is calculated, and the unique entity "Beijing university" is determined based on the similarity, so that the entity "Beijing university" in the upper knowledge graph is matched.
The inference path is an inference rule formed by the target domain event, the entity related to the target domain event and the relation between the realization in the knowledge graph. The inference paths of the target domain knowledge can be predefined, the inference logic corresponding to the target domain events with different event types can be defined, and the inference paths corresponding to the various target domain events can be stored in the database.
In one embodiment, reasoning is performed according to the matched entity and a reasoning path corresponding to the target domain event in the knowledge graph, and obtaining a corresponding event analysis result includes: determining an inference path corresponding to the target domain event according to the knowledge graph; acquiring entity relations corresponding to the matched entities according to the knowledge graph; and generating event analysis results according to the reasoning paths, the matched entities and the corresponding entity relations.
Specifically, the nodes in the knowledge graph include event types, for example, the event type of "YY bicycle financing round a 3000 ten thousand" is "financing event". After determining the event type corresponding to the target domain event, the inference path corresponding to the target domain event can be obtained, and after matching the event meta-information corresponding to the target domain event with the entity in the knowledge graph, the target domain event can be related to the entity in the knowledge graph according to the entity relationship, so as to obtain the event analysis result corresponding to the target domain event.
For example, for "financing event", the inference path obtained is: financing event-company involved-company with competitive relationship-company, wherein "company involved" is an attribute of "financing event" in a knowledge graph, "company with competitive relationship" is a relationship between "entity" company "and" company "in the knowledge graph.
FIG. 3 is a schematic diagram of event reasoning for financing events based on a knowledge-graph, in one embodiment. Referring to fig. 3, the event elements of the event "YY bicycle obtain a round of financing 3000 ten thousand" include "YY bicycle", the entity matched with the event elements in the knowledge graph is "YY bicycle company", the competitor relationship between the entity "YY bicycle company" and the entity "M company" is recorded in the knowledge graph, and the event type corresponding to the event is the financing event, so according to the reasoning path corresponding to the financing event: financing event-company involved-company in competition-company with-company, the resulting reasoning information includes:
the company involved in 'YY bicycle obtaining A round of financing 3000 ten thousand' is 'YY bicycle company', and the competitor of 'YY bicycle company' is M company.
The event analysis result corresponding to the financing event can be obtained based on the reasoning information: the YY bicycle company obtains 3000 ten thousand of XX fund company A round financing, the YY bicycle company strategically upgrades, and the M company terror is braked.
In one embodiment, the entity types in the knowledge graph include a target domain event, and the target domain event corresponds to at least one inference path; the method further comprises the steps of: adding event attributes corresponding to the target field events in the knowledge graph; updating an inference path corresponding to the target domain event according to the event attribute; and storing the updated reasoning path and the target domain event in a database correspondingly.
For example, for "financing event," add a new event attribute: "higher-level leader corresponding to invested company is" and the new reasoning path added correspondingly is: financing event-the higher level leader to which the invested company corresponds is-the higher level leader-the former-the company, where "former-the former" is an attribute of the entity "higher level leader".
In one embodiment, the inference rule corresponding to the event type may also be modified according to the attribute of each entity in the knowledge graph. For the event with the event type of 'financing event', more reasoning paths can be set, and multidimensional analysis results can be obtained according to the reasoning paths and the knowledge graph. For example, the inference paths of the corresponding investment strategies can be set for different event types according to prior investment knowledge, investment information can be obtained, and the investment information is pushed to the user.
The method may further comprise the steps of: and acquiring an entity related to the event in the target field, determining user characteristics according to the user browsing records, determining a user related to the related entity according to the user characteristics, and pushing the event analysis result to a user terminal corresponding to the user, so that the user receiving the event analysis result pays attention to the corresponding entity.
In the event processing method based on the knowledge graph, after the information text is acquired, the event type corresponding to the content of the information text can be determined according to the trigger words in the information text, when the event type belongs to the target field event, the event element role corresponding to the event type can be determined according to the target field event template, then the event elements corresponding to the event element roles are extracted from the information text, the structured data comprising the event element roles and the event elements is obtained, and the structured data is used as the event element information corresponding to the target field event, so that the target field event described by the information text can be accurately and comprehensively expressed, and the basis of the follow-up accurate processing of the target field event through the knowledge graph is provided.
Further, the extracted event meta-information is matched with the entity in the knowledge graph, the corresponding event analysis result can be directly obtained by reasoning according to the matched entity and the reasoning path corresponding to the target field event in the knowledge graph, compared with an event processing mode of embedding a preset fixed rule in a service code, the event analysis mode based on the knowledge graph does not need to inquire a large amount of data for analysis, the efficiency of analyzing the target field event is improved, and the accuracy of analyzing the event can be improved because the reasoning path corresponding to the target field event in the knowledge graph can be updated and expanded.
As shown in fig. 4, in a specific embodiment, the event processing method based on the knowledge graph specifically includes the following steps:
step 410, inputting each trigger word into a trained event classification model based on deep learning;
step 418, extracting event elements corresponding to the determined event element roles from the information text;
step 424, determining candidate entities corresponding to event elements in the event meta-information in the knowledge graph;
and 434, generating event analysis results according to the reasoning paths, the matched entities and the corresponding entity relations.
It should be understood that, although the steps in the flowchart of fig. 4 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence 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 in fig. 4 may include multiple sub-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 sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
In one embodiment, as shown in fig. 5, there is provided an event processing apparatus 500 based on a knowledge-graph, including: an acquisition module 502, an event type determination module 504, an event meta information extraction module 506, an entity matching module 508, and an event reasoning module 510, wherein:
the acquisition module 502 is used for acquiring the information text crawled from the information platform and the trigger words in the information text;
an event type determining module 504, configured to determine an event type corresponding to the content of the information text according to the trigger word;
the event meta-information extraction module 506 is configured to obtain a preset target domain event template when the event type belongs to a target domain event; determining event element roles corresponding to the event types according to the target field event templates; extracting event elements corresponding to the determined event element roles from the information text; structured data generated according to event element roles and corresponding event elements; the generated structured data is used as event meta information corresponding to the information text;
the entity matching module 508 is configured to match the extracted event meta information with an entity in the knowledge graph;
the event inference module 510 is configured to infer according to the matched entity and an inference path corresponding to the target domain event in the knowledge graph, so as to obtain a corresponding event analysis result.
In one embodiment, the obtaining module 502 is further configured to monitor the information platform; when the information platform is monitored to generate new target field information, acquiring a corresponding information text; word segmentation is carried out on the information text to obtain a corresponding word set; and taking the words belonging to the trigger word library in the word set as trigger words corresponding to the information text.
In one embodiment, the event type determination module 504 is further configured to input each trigger word to a trained deep learning based event classification model; and outputting the event type corresponding to the information text through the event classification model.
In one embodiment, the entity matching module 508 is further configured to determine candidate entities in the knowledge graph corresponding to the event elements in the event meta-information; calculating the similarity between each candidate entity and the extracted event meta-information; and screening entities matched with the event elements from the candidate entities based on the similarity.
In one embodiment, the event inference module 510 is further configured to determine an inference path corresponding to the target domain event according to the knowledge graph; acquiring entity relations corresponding to the matched entities according to the knowledge graph; and generating event analysis results according to the reasoning paths, the matched entities and the corresponding entity relations.
In one embodiment, the entity types in the knowledge graph include a target domain event, and the target domain event corresponds to at least one inference path; the apparatus 500 further includes: the reasoning path updating module is used for adding event attributes corresponding to the target domain events in the knowledge graph; updating an inference path corresponding to the target domain event according to the event attribute; and storing the updated reasoning path and the target domain event in a database correspondingly.
After the information text is acquired, the event processing device 500 based on the knowledge graph needs to determine the event type corresponding to the content of the information text according to the trigger words in the information text, when the event type belongs to the target domain event, extract the event meta information corresponding to the target domain event from the information text, match the extracted event meta information with the entity in the knowledge graph, and infer according to the matched entity and the inference path corresponding to the target domain event in the knowledge graph, thereby directly obtaining the corresponding event analysis result.
For specific limitation of the knowledge-graph-based event processing apparatus 500, reference may be made to the above limitation of the knowledge-graph-based target domain event analysis method, and detailed description thereof will be omitted. The respective modules in the above-described knowledge-graph-based event processing apparatus 500 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 server, the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, and a database 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, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing each entity in the knowledge graph and entity attribute data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a knowledge-graph based event processing method.
It will be appreciated by those skilled in the art that the structure shown in fig. 6 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, the knowledge-graph-based event processing apparatus 500 provided herein may be implemented in the form of a computer program that is executable on a computer device as shown in fig. 6. The memory of the computer device may store various program modules constituting the knowledge-graph-based event processing apparatus 500, such as the acquisition module 502, the event type determination module 504, the event meta information extraction module 506, the entity matching module 508, and the event inference module 510 shown in fig. 5. The computer program constituted by the respective program modules causes the processor to execute the steps in the knowledge-graph-based event processing method of the respective embodiments of the present application described in the present specification.
For example, the computer device shown in fig. 6 may perform step 202 through the acquisition module 502 in the knowledge-graph-based event processing apparatus 500 shown in fig. 5. The computer device may execute step 204 by the event type determination module 504. The computer device may perform step 206 via event meta information extraction module 506. The computer device may perform step 208 through the entity matching module 508. The computer device may perform step 210 through the event inference module 510.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the knowledge-graph based event processing method described above. The steps of the knowledge-graph-based event processing method herein may be the steps in the knowledge-graph-based event processing method of the above-described respective embodiments.
In one embodiment, a computer readable storage medium is provided, storing a computer program which, when executed by a processor, causes the processor to perform the steps of the knowledge-graph based event processing method described above. The steps of the knowledge-graph-based event processing method herein may be the steps in the knowledge-graph-based event processing method of the above-described respective embodiments.
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 the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
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 merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. A knowledge-graph-based event processing method, the method comprising:
acquiring an information text crawled from an information platform and a trigger word in the information text;
determining an event type corresponding to the content of the information text according to the trigger word;
when the event type belongs to a target field event, acquiring a preset target field event template;
Determining an event element role corresponding to the event type according to the target field event template;
extracting event elements corresponding to the determined event element roles from the information text;
structured data generated according to the event element roles and the corresponding event elements;
taking the generated structured data as event meta-information corresponding to the information text;
matching the extracted event meta-information with the entity in the knowledge graph;
and carrying out reasoning according to the matched entity and a reasoning path corresponding to the target domain event in the knowledge graph to obtain a corresponding event analysis result.
2. The method of claim 1, wherein the obtaining the information text crawled from the information platform and the trigger words in the information text comprises:
monitoring each information platform;
when the information platform is monitored to generate new target field information, acquiring a corresponding information text;
word segmentation is carried out on the information text to obtain a corresponding word set;
and taking the words belonging to the trigger word library in the word set as trigger words corresponding to the information text.
3. The method according to claim 1, wherein determining the event type corresponding to the content of the information text according to the trigger word comprises:
Inputting each trigger word into a trained event classification model based on deep learning;
and outputting the event type corresponding to the information text through the event classification model.
4. The method of claim 1, wherein matching the extracted event meta-information with the entities in the knowledge-graph comprises:
determining candidate entities corresponding to event elements in the event element information in the knowledge graph;
calculating the similarity between each candidate entity and the extracted event meta-information;
and screening entities matched with the event element from the candidate entities based on the similarity.
5. The method of claim 1, wherein the performing reasoning according to the matched entity and the reasoning path corresponding to the target domain event in the knowledge graph to obtain a corresponding event analysis result includes:
determining an inference path corresponding to the target domain event according to the knowledge graph;
acquiring entity relations corresponding to the matched entities according to the knowledge graph;
and generating event analysis results according to the reasoning paths, the matched entities and the corresponding entity relations.
6. The method according to any one of claims 1 to 5, wherein the entity types in the knowledge-graph comprise target domain events, the target domain events corresponding to at least one inference path;
the method further comprises the steps of:
adding event attributes corresponding to the target domain event in the knowledge graph;
updating an inference path corresponding to the target domain event according to the event attribute;
and storing the updated reasoning path and the target domain event in a database correspondingly.
7. An event processing device based on a knowledge graph, the device comprising:
the acquisition module is used for acquiring the information text crawled from the information platform and the trigger words in the information text;
the event type determining module is used for determining the event type corresponding to the content of the information text according to the trigger word;
the event meta-information extraction module is used for acquiring a preset target domain event template when the event type belongs to a target domain event; determining an event element role corresponding to the event type according to the target field event template; extracting event elements corresponding to the determined event element roles from the information text; structured data generated according to the event element roles and the corresponding event elements; taking the generated structured data as event meta-information corresponding to the information text;
The entity matching module is used for matching the extracted event meta-information with the entity in the knowledge graph;
and the event reasoning module is used for reasoning according to the matched entity and a reasoning path corresponding to the target domain event in the knowledge graph to obtain a corresponding event analysis result.
8. The apparatus of claim 7, wherein the event inference module is specifically configured to determine an inference path corresponding to the target domain event according to the knowledge-graph; acquiring entity relations corresponding to the matched entities according to the knowledge graph; and generating event analysis results according to the reasoning paths, the matched entities and the corresponding entity relations.
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 6 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 6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910609478.7A CN110489520B (en) | 2019-07-08 | 2019-07-08 | Knowledge graph-based event processing method, device, equipment and storage medium |
| PCT/CN2020/099279 WO2021004333A1 (en) | 2019-07-08 | 2020-06-30 | Knowledge graph-based event processing method and apparatus, device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910609478.7A CN110489520B (en) | 2019-07-08 | 2019-07-08 | Knowledge graph-based event processing method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110489520A CN110489520A (en) | 2019-11-22 |
| CN110489520B true CN110489520B (en) | 2023-05-16 |
Family
ID=68546733
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910609478.7A Active CN110489520B (en) | 2019-07-08 | 2019-07-08 | Knowledge graph-based event processing method, device, equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110489520B (en) |
| WO (1) | WO2021004333A1 (en) |
Families Citing this family (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110489520B (en) * | 2019-07-08 | 2023-05-16 | 平安科技（深圳）有限公司 | Knowledge graph-based event processing method, device, equipment and storage medium |
| CN110955801B (en) * | 2019-12-06 | 2022-10-21 | 中国建设银行股份有限公司 | Knowledge graph analysis method and system for cognos report indexes |
| CN110688495B (en) * | 2019-12-09 | 2020-04-24 | 武汉中科通达高新技术股份有限公司 | Method and device for constructing knowledge graph model of event information and storage medium |
| CN111222305B (en) * | 2019-12-17 | 2024-03-22 | 共道网络科技有限公司 | Information structuring method and device |
| CN111209400B (en) * | 2020-01-03 | 2023-06-16 | 北京明略软件系统有限公司 | Data analysis method and device |
| CN111428049B (en) * | 2020-03-20 | 2023-07-21 | 北京百度网讯科技有限公司 | Event thematic generation method, device, equipment and storage medium |
| CN111400456B (en) * | 2020-03-20 | 2023-09-26 | 北京百度网讯科技有限公司 | Information recommendation method and device |
| CN111522915A (en) * | 2020-04-20 | 2020-08-11 | 北大方正集团有限公司 | Extraction method, device and equipment of Chinese event and storage medium |
| CN111967268B (en) * | 2020-06-30 | 2024-03-19 | 北京百度网讯科技有限公司 | Event extraction method and device in text, electronic equipment and storage medium |
| CN112426726A (en) * | 2020-12-09 | 2021-03-02 | 网易（杭州）网络有限公司 | Game event extraction method, device, storage medium and server |
| CN112559747A (en) * | 2020-12-15 | 2021-03-26 | 北京百度网讯科技有限公司 | Event classification processing method and device, electronic equipment and storage medium |
| CN113822430A (en) * | 2020-12-28 | 2021-12-21 | 京东科技控股股份有限公司 | Event reasoning method and device, computer equipment and storage medium |
| CN112596929B (en) * | 2020-12-28 | 2022-02-11 | 恒生电子股份有限公司 | Micro-service registration and calling method based on command event conversion and related device |
| CN112784591A (en) * | 2021-02-01 | 2021-05-11 | 北京百度网讯科技有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN113806549A (en) * | 2021-02-09 | 2021-12-17 | 京东科技控股股份有限公司 | Method and device for constructing personnel relationship map and electronic equipment |
| CN112906391A (en) * | 2021-03-16 | 2021-06-04 | 合肥讯飞数码科技有限公司 | Meta-event extraction method and device, electronic equipment and storage medium |
| CN113158189B (en) * | 2021-04-28 | 2023-12-26 | 绿盟科技集团股份有限公司 | Method, device, equipment and medium for generating malicious software analysis report |
| CN113177055A (en) * | 2021-05-28 | 2021-07-27 | 北京字节跳动网络技术有限公司 | Information updating method and device and computer storage medium |
| CN115510196A (en) * | 2021-06-07 | 2022-12-23 | 马上消费金融股份有限公司 | Knowledge graph construction method, question answering method, device and storage medium |
| CN113344405A (en) * | 2021-06-18 | 2021-09-03 | 北京百度网讯科技有限公司 | Method, apparatus, device, medium, and product for generating information based on knowledge graph |
| CN113590774B (en) * | 2021-06-22 | 2023-09-29 | 北京百度网讯科技有限公司 | Event query method, device and storage medium |
| CN113407678B (en) * | 2021-06-30 | 2023-08-01 | 竹间智能科技（上海）有限公司 | Knowledge graph construction method, device and equipment |
| CN113343108B (en) * | 2021-06-30 | 2023-05-26 | 中国平安人寿保险股份有限公司 | Recommended information processing method, device, equipment and storage medium |
| CN113569931B (en) * | 2021-07-16 | 2024-04-05 | 中国铁道科学研究院集团有限公司 | Dynamic data fusion method, device, equipment and medium |
| CN113779261B (en) * | 2021-08-19 | 2024-01-30 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Quality evaluation method and device of knowledge graph, computer equipment and storage medium |
| CN113779263B (en) * | 2021-08-24 | 2024-01-05 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Decision engine detection method, device and equipment |
| CN113722461B (en) * | 2021-09-02 | 2022-05-06 | 中科雨辰科技有限公司 | Target event extraction data processing system |
| CN114065069A (en) * | 2021-09-27 | 2022-02-18 | 杭州摸象大数据科技有限公司 | Financial event map construction method and device, computer equipment and storage medium |
| CN113763712B (en) * | 2021-10-19 | 2022-05-10 | 西南交通大学 | Regional traffic jam tracing method based on travel event knowledge graph |
| CN114357197B (en) * | 2022-03-08 | 2022-07-26 | 支付宝(杭州)信息技术有限公司 | Event reasoning method and device |
| CN115238045B (en) * | 2022-09-21 | 2023-01-24 | 北京澜舟科技有限公司 | Method, system and storage medium for extracting generation type event argument |
| CN116341531B (en) * | 2023-02-28 | 2023-10-10 | 人民网股份有限公司 | Knowledge-driven character information extraction and inspection method and device |
| CN116662577B (en) * | 2023-08-02 | 2023-11-03 | 北京网智天元大数据科技有限公司 | Knowledge graph-based large language model training method and device |
| CN117171364B (en) * | 2023-10-30 | 2024-02-02 | 北京华控智加科技有限公司 | Operation and maintenance knowledge graph updating method and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105871628A (en) * | 2016-05-27 | 2016-08-17 | 内蒙古自治区民航机场集团有限责任公司 | Flight information sending method and system |
| CN106776523A (en) * | 2017-01-22 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | News speed report generation method and device based on artificial intelligence |
| CN107480137A (en) * | 2017-08-10 | 2017-12-15 | 北京亚鸿世纪科技发展有限公司 | With semantic iterative extraction network accident and the method that identifies extension event relation |
| CN108153901A (en) * | 2018-01-16 | 2018-06-12 | 北京百度网讯科技有限公司 | The information-pushing method and device of knowledge based collection of illustrative plates |
| CN108596439A (en) * | 2018-03-29 | 2018-09-28 | 北京中兴通网络科技股份有限公司 | A kind of the business risk prediction technique and system of knowledge based collection of illustrative plates |
| CN108763333A (en) * | 2018-05-11 | 2018-11-06 | 北京航空航天大学 | A kind of event collection of illustrative plates construction method based on Social Media |
| CN109299221A (en) * | 2018-09-04 | 2019-02-01 | 广州神马移动信息科技有限公司 | Entity extraction and sort method and device |
| CN109408821A (en) * | 2018-10-22 | 2019-03-01 | 腾讯科技（深圳）有限公司 | A kind of corpus generation method, calculates equipment and storage medium at device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150066985A1 (en) * | 2013-08-27 | 2015-03-05 | Antony Raja T | Retrieving information from social media sites based upon events in an enterprise |
| US20180196814A1 (en) * | 2017-01-12 | 2018-07-12 | International Business Machines Corporation | Qualitative and quantitative analysis of data artifacts using a cognitive approach |
| CN110489520B (en) * | 2019-07-08 | 2023-05-16 | 平安科技（深圳）有限公司 | Knowledge graph-based event processing method, device, equipment and storage medium |
-
2019
- 2019-07-08 CN CN201910609478.7A patent/CN110489520B/en active Active
-
2020
- 2020-06-30 WO PCT/CN2020/099279 patent/WO2021004333A1/en active Application Filing
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105871628A (en) * | 2016-05-27 | 2016-08-17 | 内蒙古自治区民航机场集团有限责任公司 | Flight information sending method and system |
| CN106776523A (en) * | 2017-01-22 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | News speed report generation method and device based on artificial intelligence |
| CN107480137A (en) * | 2017-08-10 | 2017-12-15 | 北京亚鸿世纪科技发展有限公司 | With semantic iterative extraction network accident and the method that identifies extension event relation |
| CN108153901A (en) * | 2018-01-16 | 2018-06-12 | 北京百度网讯科技有限公司 | The information-pushing method and device of knowledge based collection of illustrative plates |
| CN108596439A (en) * | 2018-03-29 | 2018-09-28 | 北京中兴通网络科技股份有限公司 | A kind of the business risk prediction technique and system of knowledge based collection of illustrative plates |
| CN108763333A (en) * | 2018-05-11 | 2018-11-06 | 北京航空航天大学 | A kind of event collection of illustrative plates construction method based on Social Media |
| CN109299221A (en) * | 2018-09-04 | 2019-02-01 | 广州神马移动信息科技有限公司 | Entity extraction and sort method and device |
| CN109408821A (en) * | 2018-10-22 | 2019-03-01 | 腾讯科技（深圳）有限公司 | A kind of corpus generation method, calculates equipment and storage medium at device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110489520A (en) | 2019-11-22 |
| WO2021004333A1 (en) | 2021-01-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110489520B (en) | Knowledge graph-based event processing method, device, equipment and storage medium | |
| CN109272396B (en) | Customer risk early warning method, device, computer equipment and medium | |
| WO2020037942A1 (en) | Risk prediction processing method and apparatus, computer device and medium | |
| CN109829629B (en) | Risk analysis report generation method, apparatus, computer device and storage medium | |
| CN109543925B (en) | Risk prediction method and device based on machine learning, computer equipment and storage medium | |
| CN108491511B (en) | Data mining method and device based on graph data and model training method and device | |
| CN110489561A (en) | Knowledge mapping construction method, device, computer equipment and storage medium | |
| CN109063921B (en) | Optimization processing method and device for client risk early warning, computer equipment and medium | |
| CN110008250B (en) | Social security data processing method and device based on data mining and computer equipment | |
| WO2023124204A1 (en) | Anti-fraud risk assessment method and apparatus, training method and apparatus, and readable storage medium | |
| Nakagawa et al. | Stock price prediction using k‐medoids clustering with indexing dynamic time warping | |
| CN109670837A (en) | Recognition methods, device, computer equipment and the storage medium of bond default risk | |
| CN110458324B (en) | Method and device for calculating risk probability and computer equipment | |
| US10579651B1 (en) | Method, system, and program for evaluating intellectual property right | |
| CN110674131A (en) | Financial statement data processing method and device, computer equipment and storage medium | |
| CN108647281B (en) | Webpage access risk detection and prompting method and device and computer equipment | |
| CN114693192A (en) | Wind control decision method and device, computer equipment and storage medium | |
| CN114298232A (en) | Method, device and storage medium for determining type information of user | |
| US20220229854A1 (en) | Constructing ground truth when classifying data | |
| CN110362798B (en) | Method, apparatus, computer device and storage medium for judging information retrieval analysis | |
| Puri et al. | Survey big data analytics, applications and privacy concerns | |
| Jagdish et al. | Identification of end-user economical relationship graph using lightweight blockchain-based BERT model | |
| CN114579523A (en) | Double-recording file quality inspection method and device, computer equipment and storage medium | |
| CN112288279A (en) | Business risk assessment method and device based on natural language processing and linear regression | |
| CN111160566A (en) | Sample generation method and device, computer readable storage medium and computer equipment |
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 |