CN112149422A - Enterprise news dynamic monitoring method based on natural language - Google Patents
Enterprise news dynamic monitoring method based on natural language Download PDFInfo
- Publication number
- CN112149422A CN112149422A CN202011010471.2A CN202011010471A CN112149422A CN 112149422 A CN112149422 A CN 112149422A CN 202011010471 A CN202011010471 A CN 202011010471A CN 112149422 A CN112149422 A CN 112149422A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- news
- entity
- dynamic
- information
- 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
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000012544 monitoring process Methods 0.000 title claims abstract description 18
- 238000012216 screening Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 8
- 238000004140 cleaning Methods 0.000 claims abstract description 7
- 230000000694 effects Effects 0.000 claims description 10
- 230000009193 crawling Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000009960 carding Methods 0.000 claims description 2
- 238000010276 construction Methods 0.000 claims description 2
- 238000003058 natural language processing Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000007115 recruitment Effects 0.000 description 2
- 241000282421 Canidae Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000717 retained 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/258—Heading extraction; Automatic titling; Numbering
-
- 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 Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to an enterprise news dynamic monitoring method based on natural language, and belongs to the field of natural language processing. The method comprises the following steps: step 1: constructing a database; step 2: training a named entity recognition NER model; and step 3: reading news data and performing data cleaning; and 4, step 4: extracting dynamic information of enterprise entities and services from news titles; and 5: extracting enterprise entities from the news body; step 6: screening text enterprise entities; and 7: extracting corresponding business dynamic information from the news body according to the screened enterprise entity; and 8: and writing the result into a database, and establishing an association relation of dynamic dimensions of enterprises, news and services by taking the enterprises as main bodies. The invention can rapidly, massively and automatically acquire news information from the network, and realize the high-efficiency dynamic news monitoring of enterprises; the interference of irrelevant information on the identification result is greatly reduced, and the method has high stability and accuracy.
Description
Technical Field
The invention belongs to the field of natural language processing, and relates to a dynamic enterprise news monitoring method based on natural language.
Background
With the popularization of the internet and the promotion of various internet products, the world has gone into the information explosion era, and the online news becomes an important channel for people to acquire information. A great deal of news is generated on the internet every day, and for the fields of park management, business recruitment, operation and the like which need to quickly grasp the dynamic state of an enterprise, how to extract concerned dynamic information of the enterprise from massive news data is a pain point and a difficulty point in work.
Most of general dynamic enterprise news monitoring methods directly adopt an enterprise keyword matching method, and directly search enterprise names through channels such as a search engine and the like to search related news. The method has a low threshold, can obtain a good effect when the processed news of the enterprise is dynamic, but in the environment with large data volume and high precision requirement on information processing such as park recruitment and management, the classification of the dynamic information dimensionality of the enterprise cannot be rapidly realized by direct search, meanwhile, the identification of the enterprise name keywords is not accurate, news of non-enterprise entities can be identified, invalid information is doped under the condition of large data volume, and the information acquisition efficiency and accuracy are reduced.
Disclosure of Invention
In view of the above, the present invention provides a method for dynamically monitoring enterprise news based on natural language.
In order to achieve the purpose, the invention provides the following technical scheme:
a dynamic enterprise news monitoring method based on natural language comprises the following steps:
step 1: constructing a database; crawling real-time data of a mainstream news website to construct a news database, constructing an enterprise database by methods of industrial and commercial information crawling, manual addition and the like, and constructing a business dynamic keyword database by a manual carding method;
step 2: training a named entity recognition NER model; training a Named Entity Recognition (NER) model by adopting a mature CRF (Conditional Random Field) method and a Chinese language library;
and (3) carrying out the operation of the step (3-8) on each news in the news database:
and step 3: reading news data and performing data cleaning; reading dimension data such as news titles, news source texts and news release time from a news database according to a predetermined method, cleaning the news data and removing invalid characters;
and 4, step 4: extracting dynamic information of enterprise entities and services from news titles; extracting enterprise entities from news headline texts by using a method of named entity identification and enterprise name matching, extracting service dynamic information by using a text matching method, if entities can be extracted from headlines, skipping the step 5, otherwise, turning to the step 5;
and 5: extracting enterprise entities from the news body; extracting enterprise entities from the news text by using a named entity identification method;
step 6: screening text enterprise entities; screening out the enterprise entities with low relevance according to the information such as the number of times of the enterprise entities appearing in the news text, ranking and the like, and keeping the main enterprise entities as the news identification result;
and 7: extracting corresponding business dynamic information from the news body according to the screened enterprise entity; searching the business dynamic keywords appearing in the text, calculating the spatial distance between each business dynamic keyword and the enterprise entity, and extracting business dynamic information according to the distance;
and 8: writing the result into a database; and (4) writing the main enterprise entity and the news data obtained in the step (6) and the dynamic dimension related to the business obtained in the step (4) and the step (7) into a database according to a preset association method for storage, and establishing an association relation among the enterprise, the news and the dynamic dimension of the business by taking the enterprise as a main body.
Optionally, in step 1, the enterprise database information in the step of constructing the database includes data dimensions of enterprise basic information, investment and financing information, business information, judicial debt information, and product technology information; the dynamic key database includes a plurality of levels of keys.
Optionally, in step 4, if an enterprise entity is extracted from the title, it is reasonable to think that the news is definitely associated with the enterprise entity, and the step of searching and screening the enterprise entity from the news body can be omitted;
optionally, in the step 4-6, when determining whether the news data is related to an enterprise, on one hand, the enterprise appearing in the news is identified by using an entity identification and name matching method, and on the other hand, a screening model is constructed by using information such as the number of times, ranking, position and the like of appearance of each enterprise entity, so that the enterprise with poor relevance is removed, and main enterprise entities related to the news are retained;
the method comprises the following steps:
s01: judging whether an enterprise entity appears in the news title or not; because enterprises in a large number of news titles appear in the form of enterprise abbreviation, and the titles have the phenomena of non-strict language structure and poor entity identification effect, the news titles are judged by adopting a method combining text matching and entity identification; searching whether the enterprise name appears in the news title according to a text matching method for the enterprise names in the enterprise database, extracting the title entity by using the NER model, searching the enterprise database to judge whether the entity belongs to the enterprise, and combining the two to obtain an enterprise entity list Y appearing in the news title*(ii) a If Y is*If not, completing enterprise identification, otherwise, going to S02;
s02: judging whether an enterprise entity appears in the news text; and (Y) utilizing the NER model to perform entity identification on the news text, and removing the duplication of the identification result to obtain an entity name list Y ═ Y1,Y2,Y3...Ym) For each entity Y in YiInquiring whether the entity exists in the enterprise database, if so, indicating that the entity belongs toAn enterprise; if the entity does not exist, the entity is discarded, and an enterprise entity list Y' appearing in the news text is obtained (Y)1,Y2,Y3...Yn)；
S03: screening enterprise entities; screening out enterprise entities with low relevance according to information such as the number of times and ranking of each entity in an enterprise entity list Y' appearing in a news text, wherein specific screening logic and dimensionality can be adjusted according to the actual operation effect of a model, and main enterprise entities are reserved as the news identification result;
optionally, in the step 4 and the step 7, when determining whether the news data is related to the business dynamic dimension, on one hand, the business dynamic information is identified by a method of matching the business keyword, on the other hand, the business dynamic dimension is screened by the spatial distance between the business keyword and the main enterprise entity, and the business dynamic dimension with strong association with the enterprise is reserved, wherein a calculation method of the spatial distance between the keyword and the enterprise entity and a threshold value can be adjusted according to the actual operation effect of the model.
The invention has the beneficial effects that: the invention provides a dynamic monitoring method for enterprise news, which can quickly, massively and automatically acquire news information from a network; after entity identification and business dynamic keyword matching processing are carried out on news information, the incidence relation among news, enterprises and dynamic dimensions is established, and efficient news dynamic monitoring and classification of the enterprises are achieved; the news related enterprise identification adopts a method of combining a mature entity identification algorithm and enterprise name matching, so that the interference of irrelevant information on an identification result is greatly reduced, and the stability and the accuracy are higher.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention may be realized and attained by the means of the instrumentalities and combinations particularly pointed out hereinafter.
Drawings
For the purposes of promoting a better understanding of the objects, aspects and advantages of the invention, reference will now be made to the following detailed description taken in conjunction with the accompanying drawings in which:
fig. 1 is a schematic flow chart in the embodiment of the present invention.
FIG. 2 is a flowchart illustrating steps S01-S03 according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention in a schematic way, and the features in the following embodiments and examples may be combined with each other without conflict.
Wherein the showings are for the purpose of illustrating the invention only and not for the purpose of limiting the same, and in which there is shown by way of illustration only and not in the drawings in which there is no intention to limit the invention thereto; to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if there is an orientation or positional relationship indicated by terms such as "upper", "lower", "left", "right", "front", "rear", etc., based on the orientation or positional relationship shown in the drawings, it is only for convenience of description and simplification of description, but it is not an indication or suggestion that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes, and are not to be construed as limiting the present invention, and the specific meaning of the terms may be understood by those skilled in the art according to specific situations.
The invention provides an enterprise news dynamic monitoring method based on natural language processing, which comprises the steps of firstly constructing a news database, a business dynamic keyword database and an enterprise database by a network crawling or manual adding method, then training by using a linear Conditional Random Field (CRF) method to obtain a Named Entity Recognition (NER) model, recognizing and screening enterprise entities in news data by using the NER model and a name matching method, then carrying out dynamic keyword matching on the news data, and finally writing the news data, the dynamic keywords and the enterprise entity names into the database to establish an incidence relation of dynamic dimensions of enterprises, news and businesses by taking the enterprises as a main body. As shown in the attached figure 1, the method comprises the following specific steps:
1. and constructing a database. Crawling the public news data of mainstream news websites, such as the websites of new waves, search foxes, Tencent and the like to construct a news database; the method comprises the steps of crawling open enterprise information, manually adding enterprises and the like to construct an enterprise database; constructing a monitoring dynamic keyword database by manually combing and monitoring dynamic keywords such as 'marketing', 'yield reduction', 'signing' and other fields;
2. training a named entity recognition NER model; training a Named Entity Recognition (NER) model by adopting a mature CRF (Conditional Random Field) method and a Chinese language library;
and (3) carrying out the operation of the step (3-8) on each news in the news database:
3. reading news data and performing data cleaning; reading dimension data such as news titles, news source texts and news release time from a news database according to a predetermined method, cleaning the news data and removing invalid characters;
4. extracting dynamic information of enterprise entities and services from news titles; extracting enterprise entities from news headline texts by using a method of named entity identification and enterprise name matching, extracting service dynamic information by using a text matching method, if entities can be extracted from headlines, skipping the step 5, otherwise, turning to the step 5;
5. extracting enterprise entities from the news body; extracting enterprise entities from the news text by using a named entity identification method;
6. screening text enterprise entities; screening out the enterprise entities with low relevance according to the information such as the number of times of the enterprise entities appearing in the news text, ranking and the like, and keeping the main enterprise entities as the news identification result;
7. extracting corresponding business dynamic information from the news body according to the screened enterprise entity; searching the business dynamic keywords appearing in the text, calculating the spatial distance between each business dynamic keyword and the enterprise entity, and extracting business dynamic information according to the distance;
8. writing the result into a database; writing the main enterprise entity and the news data obtained in the step 6 and the dynamic dimension related to the business obtained in the step 4 and the step 7 into a database according to a preset association method for storage, and establishing an association relation among the enterprise, the news and the dynamic dimension of the business by taking the enterprise as a main body;
further, the enterprise database information in the database construction step includes, but is not limited to, data dimensions such as enterprise basic information, investment and financing information, business information, judicial debt information, product technology information and the like. The dynamic keyword database may include multiple levels of keywords, for example, the first level of keywords is "business dynamic", the second level of keywords is "business cooperation", "capacity dynamic", "research interview", and the like, and the third level of keywords is "visit", "communication", "investigation", and the like.
Further, in the step 4, if an enterprise entity is extracted from the title, it is reasonable to think that the news is definitely associated with the enterprise entity, and the step of searching and screening the enterprise entity from the news body can be omitted;
further, in the step 4-6, when judging whether the news data is related to an enterprise, on one hand, the enterprise appearing in the news is identified by an entity identification and name matching method, on the other hand, a screening model is constructed by information such as the number of times, ranking, position and the like of appearance of each enterprise entity, the enterprise with poor relevance is removed, and main enterprise entities related to the news are reserved;
the method comprises the following steps:
s01: judging whether an enterprise entity appears in the news title or not; because enterprises in a large number of news titles appear in the form of enterprise abbreviation, and the titles have the phenomena of non-strict language structure and poor entity identification effect, the news titles are judged by adopting a method combining text matching and entity identification; searching whether the enterprise name appears in the news title according to a text matching method for the enterprise names in the enterprise database, extracting the title entity by using the NER model, searching the enterprise database to judge whether the entity belongs to the enterprise, and combining the two to obtain an enterprise entity list Y appearing in the news title*(ii) a If Y is*If not, completing enterprise identification, otherwise, going to S02;
s02: judging whether an enterprise entity appears in the news text; and (Y) utilizing the NER model to perform entity identification on the news text, and removing the duplication of the identification result to obtain an entity name list Y ═ Y1,Y2,Y3...Ym) For each entity Y in YiInquiring whether the entity exists in the enterprise database, if so, indicating that the entity belongs to the enterprise; if the entity does not exist, the entity is discarded, and an enterprise entity list Y' appearing in the news text is obtained (Y)1,Y2,Y3...Yn)；
S03: screening enterprise entities; screening out enterprise entities with low relevance according to information such as the number of times and ranking of each entity in an enterprise entity list Y' appearing in a news text, wherein specific screening logic and dimensionality can be adjusted according to the actual operation effect of a model, and main enterprise entities are reserved as the news identification result;
further, in the step 4 and the step 7, when judging whether the news data is related to the business dynamic dimension, on one hand, the business dynamic information is identified by a business keyword matching method, on the other hand, the business dynamic dimension is screened by the space distance between the business keyword and the main enterprise entity, and the business dynamic dimension with strong association with the enterprise is reserved, wherein a calculation method and a threshold value of the space distance between the keyword and the enterprise entity can be adjusted according to the actual operation effect of the model;
finally, the above embodiments are only intended to illustrate the technical solutions of the present invention and not to limit the present invention, and although the present invention has been described in detail with reference to the preferred embodiments, it will 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, and all of them should be covered by the claims of the present invention.
Claims (5)
1. A dynamic enterprise news monitoring method based on natural language is characterized in that: the method comprises the following steps:
step 1: constructing a database; crawling real-time data of a mainstream news website to construct a news database, constructing an enterprise database by industrial and commercial information crawling and manual adding methods, and constructing a business dynamic keyword database by a manual carding method;
step 2: training a named entity recognition NER model; training a named entity recognition NER model by adopting a mature linear chain element random field CRF method and a Chinese language material library;
and (3) carrying out the operation of the step (3-8) on each news in the news database:
and step 3: reading news data and performing data cleaning; reading the dimension data of news titles, news source texts and news release time from a news database according to a preset method, cleaning the news data and removing invalid characters;
and 4, step 4: extracting dynamic information of enterprise entities and services from news titles; extracting enterprise entities from news headline texts by using a method of named entity identification and enterprise name matching, extracting service dynamic information by using a text matching method, if entities can be extracted from headlines, skipping the step 5, otherwise, turning to the step 5;
and 5: extracting enterprise entities from the news body; extracting enterprise entities from the news text by using a named entity identification method;
step 6: screening text enterprise entities; screening out the enterprise entities with low relevance according to the number of times of the enterprise entities appearing in the news text and ranking information, and keeping the main enterprise entities as the news identification result;
and 7: extracting corresponding business dynamic information from the news body according to the screened enterprise entity; searching the business dynamic keywords appearing in the text, calculating the spatial distance between each business dynamic keyword and the enterprise entity, and extracting business dynamic information according to the distance;
and 8: writing the result into a database; and (4) writing the main enterprise entity and the news data obtained in the step (6) and the dynamic dimension related to the business obtained in the step (4) and the step (7) into a database according to a preset association method for storage, and establishing an association relation among the enterprise, the news and the dynamic dimension of the business by taking the enterprise as a main body.
2. The dynamic monitoring method for enterprise news based on natural language as claimed in claim 1, wherein: in the step 1, the enterprise database information in the database construction step comprises data dimensions of enterprise basic information, investment and financing information, operation information, judicial debt information and product technical information; the dynamic key database includes a plurality of levels of keys.
3. The dynamic monitoring method for enterprise news based on natural language as claimed in claim 1, wherein: in the step 4, if the business entity is extracted from the headline, it is reasonable to think that the news is definitely associated with the business entity, and the step of searching and screening the business entity from the news body is omitted.
4. The dynamic monitoring method for enterprise news based on natural language as claimed in claim 1, wherein: in the step 4-6, when judging whether the news data is related to the enterprise, on one hand, the enterprise appearing in the news is identified by an entity identification and name matching method, on the other hand, a screening model is constructed by the appearing times, ranking and position information of each enterprise entity, the enterprise with poor relevance is removed, and the main enterprise entity related to the news is reserved;
the method comprises the following steps:
s01: judging whether an enterprise entity appears in the news title or not; judging news titles by adopting a method combining text matching and entity identification; searching whether the enterprise name appears in the news title according to a text matching method for the enterprise names in the enterprise database, extracting the title entity by using the NER model, searching the enterprise database to judge whether the entity belongs to the enterprise, and combining the two to obtain an enterprise entity list Y appearing in the news title*(ii) a If Y is*If not, completing enterprise identification, otherwise, going to S02;
s02: judging whether an enterprise entity appears in the news text; and (Y) utilizing the NER model to perform entity identification on the news text, and removing the duplication of the identification result to obtain an entity name list Y ═ Y1,Y2,Y3...Ym) For each entity Y in YiInquiring whether the entity exists in the enterprise database, if so, indicating that the entity belongs to the enterprise; if the entity does not exist, the entity is discarded, and an enterprise entity list Y' appearing in the news text is obtained (Y)1,Y2,Y3...Yn)；
S03: screening enterprise entities; and screening out the enterprise entities with low relevance according to the number of times of each entity in the enterprise entity list Y' appearing in the news text and ranking information, wherein the specific screening logic and dimensionality can be adjusted according to the actual operation effect of the model, and main enterprise entities are reserved as the news identification result.
5. The dynamic monitoring method for enterprise news based on natural language as claimed in claim 1, wherein: in the step 4 and the step 7, when judging whether the news data is related to the business dynamic dimension, on one hand, the business dynamic information is identified by a business keyword matching method, on the other hand, the business dynamic dimension is screened by the space distance between the business keyword and the main enterprise entity, and the business dynamic dimension with strong association with the enterprise is reserved, wherein the space distance calculation method and the threshold value of the keyword and the enterprise entity are adjusted according to the actual operation effect of the model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011010471.2A CN112149422B (en) | 2020-09-23 | 2020-09-23 | Dynamic enterprise news monitoring method based on natural language |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011010471.2A CN112149422B (en) | 2020-09-23 | 2020-09-23 | Dynamic enterprise news monitoring method based on natural language |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112149422A true CN112149422A (en) | 2020-12-29 |
| CN112149422B CN112149422B (en) | 2024-04-05 |
Family
ID=73896286
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011010471.2A Active CN112149422B (en) | 2020-09-23 | 2020-09-23 | Dynamic enterprise news monitoring method based on natural language |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112149422B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113129072A (en) * | 2021-04-30 | 2021-07-16 | 上海药慧信息技术有限公司 | Enterprise valuation determination method and device based on investment and financing information |
| CN113689299A (en) * | 2021-05-10 | 2021-11-23 | 深圳价值在线信息科技股份有限公司 | Method for constructing news information index model and news information analysis method |
| CN115357688A (en) * | 2022-10-12 | 2022-11-18 | 北京金堤科技有限公司 | Enterprise list information acquisition method and device, storage medium and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160283876A1 (en) * | 2015-03-24 | 2016-09-29 | Tata Consultancy Services Limited | System and method for providing automomous contextual information life cycle management |
| CN109033200A (en) * | 2018-06-29 | 2018-12-18 | 北京百度网讯科技有限公司 | Method, apparatus, equipment and the computer-readable medium of event extraction |
| CN110516077A (en) * | 2019-08-20 | 2019-11-29 | 北京中亦安图科技股份有限公司 | Knowledge mapping construction method and device towards enterprise's market conditions |
| CN110929134A (en) * | 2019-12-04 | 2020-03-27 | 深圳市新国都金服技术有限公司 | Investment and financing data management method and device, computer equipment and storage medium |
-
2020
- 2020-09-23 CN CN202011010471.2A patent/CN112149422B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160283876A1 (en) * | 2015-03-24 | 2016-09-29 | Tata Consultancy Services Limited | System and method for providing automomous contextual information life cycle management |
| CN109033200A (en) * | 2018-06-29 | 2018-12-18 | 北京百度网讯科技有限公司 | Method, apparatus, equipment and the computer-readable medium of event extraction |
| CN110516077A (en) * | 2019-08-20 | 2019-11-29 | 北京中亦安图科技股份有限公司 | Knowledge mapping construction method and device towards enterprise's market conditions |
| CN110929134A (en) * | 2019-12-04 | 2020-03-27 | 深圳市新国都金服技术有限公司 | Investment and financing data management method and device, computer equipment and storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113129072A (en) * | 2021-04-30 | 2021-07-16 | 上海药慧信息技术有限公司 | Enterprise valuation determination method and device based on investment and financing information |
| CN113689299A (en) * | 2021-05-10 | 2021-11-23 | 深圳价值在线信息科技股份有限公司 | Method for constructing news information index model and news information analysis method |
| CN113689299B (en) * | 2021-05-10 | 2023-10-20 | 深圳价值在线信息科技股份有限公司 | News information index model construction method and news information analysis method |
| CN115357688A (en) * | 2022-10-12 | 2022-11-18 | 北京金堤科技有限公司 | Enterprise list information acquisition method and device, storage medium and electronic equipment |
| CN115357688B (en) * | 2022-10-12 | 2023-02-21 | 北京金堤科技有限公司 | Enterprise list information acquisition method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112149422B (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106649818B (en) | Application search intention identification method and device, application search method and server | |
| CN111353030B (en) | Knowledge question and answer retrieval method and device based on knowledge graph in travel field | |
| CN109885773B (en) | Personalized article recommendation method, system, medium and equipment | |
| CN112149422B (en) | Dynamic enterprise news monitoring method based on natural language | |
| CN106126619A (en) | A kind of video retrieval method based on video content and system | |
| KR20150096295A (en) | System and method for buinding q&as database, and search system and method using the same | |
| CN110543595A (en) | in-station search system and method | |
| CN111104801B (en) | Text word segmentation method, system, equipment and medium based on website domain name | |
| CN110737821B (en) | Similar event query method, device, storage medium and terminal equipment | |
| CN111475625A (en) | News manuscript generation method and system based on knowledge graph | |
| US20150206101A1 (en) | System for determining infringement of copyright based on the text reference point and method thereof | |
| CN107943937B (en) | Debtor asset monitoring method and system based on judicial public information analysis | |
| CN116628173B (en) | Intelligent customer service information generation system and method based on keyword extraction | |
| CN112711716A (en) | Knowledge graph-based marine industry news pushing method and system | |
| CN114238735B (en) | Intelligent internet data acquisition method | |
| US20090234836A1 (en) | Multi-term search result with unsupervised query segmentation method and apparatus | |
| CN102214179A (en) | Method for capturing network information | |
| Chala et al. | A Framework for Enriching Job Vacancies and Job Descriptions Through Bidirectional Matching. | |
| CN115098773A (en) | Big data-based public opinion monitoring and analyzing system and method | |
| CN114706948A (en) | News processing method and device, storage medium and electronic equipment | |
| CN113779981A (en) | Recommendation method and device based on pointer network and knowledge graph | |
| CN113761104A (en) | Method and device for detecting entity relationship in knowledge graph and electronic equipment | |
| CN112597772A (en) | Hotspot information determination method, computer equipment and device | |
| CN110930189A (en) | Personalized marketing method based on user behaviors | |
| CN111444434A (en) | Method and system for generating Internet feedback comments |
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 |