CN117648926A - Method and system for automatically creating data model based on natural language - Google Patents
Method and system for automatically creating data model based on natural language Download PDFInfo
- Publication number
- CN117648926A CN117648926A CN202410121874.6A CN202410121874A CN117648926A CN 117648926 A CN117648926 A CN 117648926A CN 202410121874 A CN202410121874 A CN 202410121874A CN 117648926 A CN117648926 A CN 117648926A
- Authority
- CN
- China
- Prior art keywords
- information
- industry
- library
- model
- field
- 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.)
- Pending
Links
- 238000013499 data model Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000011218 segmentation Effects 0.000 claims abstract description 62
- 238000010276 construction Methods 0.000 claims description 12
- 238000013500 data storage Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 4
- 239000008280 blood Substances 0.000 description 3
- 210000004369 blood Anatomy 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
Landscapes
- Machine Translation (AREA)
Abstract
The invention provides a method and a system for automatically creating a data model based on natural language, which relate to the technical field of data processing and comprise the following steps: storing all table names and field names in a data source and an industry model library into a first branch library and a second branch library respectively, and storing the data source and the field names into the first vector database and the second vector database respectively after vectorizing; storing each table in the industry model library into a graph database; the first and second word segmentation libraries are used for respectively carrying out word segmentation processing on the service demand information, extracting keyword information and forming a center word; vectorizing the center word, then respectively searching data source field information and industry model library field information matched with the center word in a first vector database and a second vector database, and finding out table information in the data source and table information in the industry model library; and removing parts which are not related in the graph database based on field information and table information of the industry model library to obtain an industry data model corresponding to the business demand information. The invention improves the efficiency of creating the data model.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a system for automatically creating a data model based on natural language.
Background
At present, people create a data warehouse through a data modeling tool, wherein data items in the data warehouse are all data sources from various systems, and new data tables (indexes or report data) are processed according to service requirements through the data items in the data sources and stored in the data warehouse, as shown in fig. 1.
However, in this process, the data in the data sources of the respective systems must be known, creating a new data table is performed manually, and the new data table is required to have a blood relationship diagram, and the process of manually creating an annual sales report from the data sources of the application system in fig. 1 includes: manually finding required data (table (user information table, commodity information table)/field) from an application system data source according to service requirements; merging the data in the application system data sources into a data set (user order list) according to the service requirement; the source information (data blood relationship) of the data in the annual sales report is recorded.
The manual mode is found in the application system data source, the efficiency is low, and the method is specifically shown in the following steps: the words of the business requirement in writing are inconsistent with the words in the database, for example, the field names in the database are telephone numbers, and the mobile phone numbers used in the requirement are the corresponding fields which cannot be found in a general searching mode, and are often manually read and searched one by one.
Therefore, how to automatically create a data model through natural language processing, improve the efficiency of creating the data model, and quickly output a report model becomes a problem to be solved.
Disclosure of Invention
Aiming at the problems, the invention provides a method and a system for automatically creating a data model based on natural language, which only need to input business demand information into the system, and the system performs semantic search according to key information in business demand description and performs optimization on an existing model library to output a new report model.
In order to achieve the above object, the present invention provides a method for automatically creating a data model based on natural language, comprising:
storing all table names and field names in a data source into a first word segmentation library, vectorizing and storing the table names and field names into a first vector database;
storing all table names and field names in an industry model library into a second branch library, vectorizing and storing the table names and field names in the industry model library into a second vector database, and storing each table in the industry model library into a graph database based on the relation among tables to obtain an industry model library knowledge graph;
the method comprises the steps that a user inputs service requirement information, word segmentation processing is conducted on the service requirement information through a first word segmentation library and a second word segmentation library respectively, keyword information related to table names and field names is extracted according to word segmentation results, and center words are formed;
the center word is vectorized, matched data source field information and industry model library field information are respectively searched in the first vector database and the second vector database based on the vectorized center word, and table information in a data source and table information in an industry model library are reversely searched;
and searching corresponding relations in the industry model library knowledge graph aiming at field information of the industry model library and table information in the industry model library, and removing parts without relations to obtain an industry data model corresponding to the business demand information.
As a further improvement of the present invention,
vectorizing table names and field names stored in a first word segmentation library by adopting a word embedding vector algorithm model;
vectorizing table names and field names stored in a second word stock by adopting a word embedding vector algorithm model;
and vectorizing the center word by adopting a word embedding vector algorithm model.
As a further improvement of the present invention, the word segmentation processing is performed on the service requirement information by the first word segmentation library and the second word segmentation library, respectively, including:
the table names and the field names in the first word segmentation library are used for segmenting the business requirement information;
and using the table names and the field names in the second word segmentation library to segment the business requirement information.
As a further improvement of the invention, the matched data source field information and industry model library field information are retrieved in the first vector database and the second vector database by word sense retrieval based on the vectorized center word.
As a further improvement of the present invention, the back-finding of the table information in the data source and the table information in the industry model library includes:
inquiring a table containing field information in a data source based on the field information of the data source to obtain table information in the data source;
and inquiring a table containing field information in the industry model database based on the field information of the industry model database to obtain table information in the industry model database.
As a further improvement of the present invention, excluding the irrelevant sections includes:
in the industry model library knowledge graph, eliminating the independent table containing the field information of the industry model library and eliminating the table information in the industry model library but the isolated table.
As a further improvement of the invention, an industry data model corresponding to the business demand information is obtained, which comprises the following steps:
and summarizing the business demand information, the tables and fields in the finally obtained data source and the tables and fields in an industry model library by adopting a GPT model to generate the industry data model.
As a further improvement of the invention, an industry data model corresponding to the business demand information is obtained, which comprises the following steps:
and replacing the tables and the fields in the template by adopting the tables and the fields in the finally obtained data source to generate the industry data model by taking the tables and the fields in the finally obtained industry model library as templates.
As a further improvement of the invention, the table and the field in the template are replaced by natural language.
The invention also provides a system for automatically creating a data model based on natural language, which comprises: the system comprises a data storage and vectorization module, an industry model base knowledge graph construction module, a word segmentation and center word extraction module, a related field and table information retrieval module and an industry data model construction module;
the data storage and vectorization module is used for:
storing all table names and field names in a data source into a first word segmentation library, vectorizing and storing the table names and field names into a first vector database;
storing all table names and field names in the industry model library into a second branch library, vectorizing and storing the table names and field names into the second vector database;
the industry model base knowledge graph construction module is used for:
storing all the tables in the industry model library into a graph database based on the relation among the tables to obtain an industry model library knowledge graph;
the word segmentation and center word extraction module is used for:
the method comprises the steps that a user inputs service requirement information, word segmentation processing is conducted on the service requirement information through a first word segmentation library and a second word segmentation library respectively, keyword information related to table names and field names is extracted according to word segmentation results, and center words are formed;
the related field and table information retrieval module is used for:
the center word is vectorized, matched data source field information and industry model library field information are respectively searched in the first vector database and the second vector database based on the vectorized center word, and table information in a data source and table information in an industry model library are reversely searched;
the industry data model construction module is used for:
and searching corresponding relations in the industry model library knowledge graph aiming at field information of the industry model library and table information in the industry model library, and removing parts without relations to obtain an industry data model corresponding to the business demand information.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, through a natural language processing technology, only the business requirement information is required to be input, semantic search can be performed according to the key information in the business requirement description, and the optimization output can be performed on the existing model library, so that the automatic creation of the data model is realized, the efficiency of creating the data model is improved, and then the report model is rapidly output; compared with the prior art that a manual mode is adopted to search the tables and fields in the data source of the application system and manually create the new data table, the method and the device do not need to manually read the tables in the data source one by one to search and manually combine and create the data model, and greatly improve the creation efficiency of the data model.
Drawings
FIG. 1 is a schematic diagram of an application system data source for manually creating annual sales report according to one embodiment of the present invention;
FIG. 2 is a schematic diagram of automatically creating a data model based on natural language in accordance with an embodiment of the present invention;
FIG. 3 is a flow chart of a method for automatically creating a data model based on natural language in accordance with one embodiment of the present invention;
FIG. 4 is a schematic diagram of a system for automatically creating a data model based on natural language according to one embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention is described in further detail below with reference to the attached drawing figures:
as shown in fig. 3, the method for automatically creating a data model based on natural language provided by the invention comprises the following steps:
s1, storing all table names and field names in a data source into a first word segmentation library, vectorizing and storing the table names and field names into a first vector database;
wherein,
the natural language automatic modeling system comprises a word segmentation library, a vector database and a word embedded vector algorithm model, and specifically comprises the following steps: a first sub-word library and a second sub-word library, a first vector database and a second vector database;
further, the method comprises the steps of,
and vectorizing the table names and the field names stored in the first word segmentation library by adopting a word embedding vector algorithm model.
In particular, the method comprises the steps of,
as shown in fig. 2, the data source is data of a plurality of application systems, and table names are as follows: the user information table, the user order table and the commodity information table have correlation before each table.
S2, storing all table names and field names in an industry model library into a second branch library, carrying out vectorization and then storing the table names and field names into a second vector database, wherein each industry model comprises the relation among objects (tables), and storing the relation among the tables in the industry model library into a graph database to obtain an industry model library knowledge graph;
wherein,
vectorizing table names and field names stored in a second word stock by adopting a word embedding vector algorithm model;
s3, inputting service requirement information by a user, performing word segmentation processing on the service requirement information through a first word segmentation library and a second word segmentation library respectively, and extracting keyword information related to table names and field names according to word segmentation results to form center words;
wherein,
when the first word segmentation library is used for carrying out word segmentation on the service demand information, the table names and the field names in the first word segmentation library are preferentially used for carrying out word segmentation on the service demand information, and the rest words which do not belong to the table names and the field names in the first word segmentation library are subjected to AI intelligent word segmentation;
similarly, when the second word stock is used for word segmentation of the service requirement information, the table names and the field names in the second word stock are preferentially used for word segmentation of the service requirement information, and the rest words which do not belong to the table names and the field names in the second word stock are subjected to AI intelligent word segmentation.
S4, vectorizing the center word, respectively searching matched data source field information and industry model library field information in a first vector database and a second vector database based on the vectorized center word, and reversely searching table information in the data source and table information in the industry model library;
wherein,
and vectorizing the center word by adopting a word embedding vector algorithm model.
Further, the method comprises the steps of,
based on the vectorized center word, the matched data source field information and industry model library field information are searched in the first vector database and the second vector database through word sense search.
Still further, the method comprises the steps of,
inquiring a table containing field information in a data source based on the field information of the data source to obtain table information in the data source;
and inquiring a table containing field information in the industry model database based on the field information of the industry model database to obtain table information in the industry model database.
In particular, the method comprises the steps of,
in this case, the searching will search all the data about the central word in the data source, and of course, many are unnecessary or inapplicable, so the data is needed to be removed;
s5, searching corresponding relations in the industry model library knowledge graph aiming at field information of the industry model library and table information in the industry model library, and removing parts without relations to obtain an industry data model corresponding to business demand information, namely: a local industry data model is described in relation to business demand information.
Wherein, reject the part that does not have a relation, include:
in the industry model base knowledge graph, eliminating the independent table containing the field information of the industry model base and eliminating the table information in the industry model base but the isolated table.
Further, an industry data model corresponding to the service demand information is obtained, which comprises two schemes:
scheme one: adopting a GPT model to carry out final model creation by using the GPT model;
and sending the business demand information, the tables and the fields in the data source and the tables and the fields in the industry model library which are finally obtained to the GPT for summarization, and generating an industry data model.
Scheme II: using the industry model as a template, and generating a model of the system by replacing tables and fields in the template through natural language;
replacing the tables and fields in the template by using the tables and fields in the finally obtained data source as templates to generate an industry data model; wherein, the table and the field in the template are replaced by natural language.
In particular, the method comprises the steps of,
as shown in fig. 2, the obtained industry data model is: annual sales report, the industry data model includes fields: user name, user region, order amount, order time, commodity type, commodity name, etc.
The industry data model finally obtained by the invention contains the data blood edges, namely the source information of each data in the industry data model.
As shown in fig. 4, the present invention further provides a system for automatically creating a data model based on natural language, including a word segmentation library, a vector database, and a word embedding vector algorithm model, which specifically includes: a first sub-word library and a second sub-word library, a first vector database and a second vector database; the application angle includes: the system comprises a data storage and vectorization module, an industry model base knowledge graph construction module, a word segmentation and center word extraction module, a related field and table information retrieval module and an industry data model construction module;
the data storage and vectorization module is used for:
storing all table names and field names in a data source into a first word segmentation library, vectorizing and storing the table names and field names into a first vector database;
storing all table names and field names in the industry model library into a second branch library, vectorizing and storing the table names and field names into a second vector database;
the industry model base knowledge graph construction module is used for:
storing each table in the industry model library into a graph database based on the relation among the tables to obtain an industry model library knowledge graph;
the word segmentation and center word extraction module is used for:
the user inputs the service demand information, word segmentation processing is carried out on the service demand information through the first word segmentation library and the second word segmentation library respectively, and keyword information related to the table names and the field names is extracted according to word segmentation results to form center words;
the related field and table information retrieval module is used for:
vectorizing the center word, respectively searching matched data source field information and industry model library field information in a first vector database and a second vector database based on the vectorized center word, and reversely searching table information in the data source and table information in the industry model library;
the industry data model construction module is used for:
and searching corresponding relations in the industry model library knowledge graph aiming at field information of the industry model library and table information in the industry model library, and removing parts without relations to obtain an industry data model corresponding to the business demand information.
The invention has the advantages that:
according to the invention, through a natural language processing technology, only the business requirement information is required to be input, semantic search can be performed according to the key information in the business requirement description, and the optimization output can be performed on the existing model library, so that the automatic creation of the data model is realized, the efficiency of creating the data model is improved, and then the report model is rapidly output; compared with the prior art that a manual mode is adopted to search the tables and fields in the data source of the application system and manually create the new data table, the method and the device do not need to manually read the tables in the data source one by one to search and manually combine and create the data model, and greatly improve the creation efficiency of the data model.
The invention applies the intelligent AI to the whole business process of automatically creating the data model.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for automatically creating a data model based on natural language, comprising:
storing all table names and field names in a data source into a first word segmentation library, vectorizing and storing the table names and field names into a first vector database;
storing all table names and field names in an industry model library into a second branch library, carrying out vectorization, storing the vectorization and the vectorization into a second vector database, and storing all tables in the industry model library into a graph database based on the relation among the tables to obtain an industry model library knowledge graph;
the method comprises the steps that a user inputs service requirement information, word segmentation processing is conducted on the service requirement information through a first word segmentation library and a second word segmentation library respectively, keyword information related to table names and field names is extracted according to word segmentation results, and center words are formed;
the center word is vectorized, matched data source field information and industry model library field information are respectively searched in the first vector database and the second vector database based on the vectorized center word, and table information in a data source and table information in an industry model library are reversely searched;
and searching corresponding relations in the industry model library knowledge graph aiming at field information of the industry model library and table information in the industry model library, and removing parts without relations to obtain an industry data model corresponding to the business demand information.
2. The method for automatically creating a data model based on natural language of claim 1, wherein:
vectorizing table names and field names stored in a first word segmentation library by adopting a word embedding vector algorithm model;
vectorizing table names and field names stored in a second word stock by adopting a word embedding vector algorithm model;
and vectorizing the center word by adopting a word embedding vector algorithm model.
3. The method for automatically creating a data model based on natural language of claim 1, wherein: the word segmentation processing is carried out on the service requirement information through a first word segmentation library and a second word segmentation library respectively, and the method comprises the following steps:
the table names and the field names in the first word segmentation library are used for segmenting the business requirement information;
and using the table names and the field names in the second word segmentation library to segment the business requirement information.
4. The method for automatically creating a data model based on natural language of claim 1, wherein: and searching matched data source field information and industry model library field information in the first vector database and the second vector database through word sense search based on the vectorized center word.
5. The method for automatically creating a data model based on natural language of claim 1, wherein: reversely looking up the table information in the data source and the table information in the industry model library, comprising:
inquiring a table containing field information in a data source based on the field information of the data source to obtain table information in the data source;
and inquiring a table containing field information in the industry model database based on the field information of the industry model database to obtain table information in the industry model database.
6. The method for automatically creating a data model based on natural language of claim 1, wherein: culling out parts that do not have a relationship, including:
in the industry model library knowledge graph, eliminating the independent table containing the field information of the industry model library and eliminating the table information in the industry model library but the isolated table.
7. The method for automatically creating a data model based on natural language of claim 1, wherein: obtaining an industry data model corresponding to the business demand information comprises the following steps:
and summarizing the business demand information, the tables and fields in the finally obtained data source and the tables and fields in an industry model library by adopting a GPT model to generate the industry data model.
8. The method for automatically creating a data model based on natural language of claim 1, wherein: obtaining an industry data model corresponding to the business demand information comprises the following steps:
and replacing the tables and the fields in the template by adopting the tables and the fields in the finally obtained data source to generate the industry data model by taking the tables and the fields in the finally obtained industry model library as templates.
9. The method for automatically creating a data model based on natural language of claim 8, wherein: and replacing the table and the field in the template by adopting natural language.
10. A system for automatically creating a data model based on natural language, for implementing the method for automatically creating a data model based on natural language according to any one of claims 1 to 9, comprising: the system comprises a data storage and vectorization module, an industry model base knowledge graph construction module, a word segmentation and center word extraction module, a related field and table information retrieval module and an industry data model construction module;
the data storage and vectorization module is used for:
storing all table names and field names in a data source into a first word segmentation library, vectorizing and storing the table names and field names into a first vector database;
storing all table names and field names in the industry model library into a second branch library, vectorizing and storing the table names and field names into the second vector database;
the industry model base knowledge graph construction module is used for:
storing all the tables in the industry model library into a graph database based on the relation among the tables to obtain an industry model library knowledge graph;
the word segmentation and center word extraction module is used for:
the method comprises the steps that a user inputs service requirement information, word segmentation processing is conducted on the service requirement information through a first word segmentation library and a second word segmentation library respectively, keyword information related to table names and field names is extracted according to word segmentation results, and center words are formed;
the related field and table information retrieval module is used for:
the center word is vectorized, matched data source field information and industry model library field information are respectively searched in the first vector database and the second vector database based on the vectorized center word, and table information in a data source and table information in an industry model library are reversely searched;
the industry data model construction module is used for:
and searching corresponding relations in the industry model library knowledge graph aiming at field information of the industry model library and table information in the industry model library, and removing parts without relations to obtain an industry data model corresponding to the business demand information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410121874.6A CN117648926A (en) | 2024-01-30 | 2024-01-30 | Method and system for automatically creating data model based on natural language |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410121874.6A CN117648926A (en) | 2024-01-30 | 2024-01-30 | Method and system for automatically creating data model based on natural language |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117648926A true CN117648926A (en) | 2024-03-05 |
Family
ID=90045467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410121874.6A Pending CN117648926A (en) | 2024-01-30 | 2024-01-30 | Method and system for automatically creating data model based on natural language |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117648926A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118070812A (en) * | 2024-04-19 | 2024-05-24 | 深圳市中壬银兴信息技术有限公司 | Industry data analysis method and system based on NLP |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111309877A (en) * | 2018-12-12 | 2020-06-19 | 北京文因互联科技有限公司 | Intelligent question-answering method and system based on knowledge graph |
| CN112001188A (en) * | 2020-10-30 | 2020-11-27 | 北京智源人工智能研究院 | Method and device for rapidly realizing NL2SQL based on vectorization semantic rule |
| CN113407681A (en) * | 2021-08-18 | 2021-09-17 | 国网浙江省电力有限公司信息通信分公司 | Energy industry public data model construction method |
| EP4020253A1 (en) * | 2020-12-23 | 2022-06-29 | Xiamen Meiya Pico Information Co., Ltd | A data model creation method and terminal thereof |
| CN116842076A (en) * | 2023-07-03 | 2023-10-03 | 中移(苏州)软件技术有限公司 | Data analysis method, device, analysis equipment and readable storage medium |
-
2024
- 2024-01-30 CN CN202410121874.6A patent/CN117648926A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111309877A (en) * | 2018-12-12 | 2020-06-19 | 北京文因互联科技有限公司 | Intelligent question-answering method and system based on knowledge graph |
| CN112001188A (en) * | 2020-10-30 | 2020-11-27 | 北京智源人工智能研究院 | Method and device for rapidly realizing NL2SQL based on vectorization semantic rule |
| EP4020253A1 (en) * | 2020-12-23 | 2022-06-29 | Xiamen Meiya Pico Information Co., Ltd | A data model creation method and terminal thereof |
| CN113407681A (en) * | 2021-08-18 | 2021-09-17 | 国网浙江省电力有限公司信息通信分公司 | Energy industry public data model construction method |
| CN116842076A (en) * | 2023-07-03 | 2023-10-03 | 中移(苏州)软件技术有限公司 | Data analysis method, device, analysis equipment and readable storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118070812A (en) * | 2024-04-19 | 2024-05-24 | 深圳市中壬银兴信息技术有限公司 | Industry data analysis method and system based on NLP |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105095195B (en) | Nan-machine interrogation's method and system of knowledge based collection of illustrative plates | |
| CN111191022B (en) | Commodity short header generation method and device | |
| CN102479191B (en) | Method and device for providing multi-granularity word segmentation result | |
| US11907659B2 (en) | Item recall method and system, electronic device and readable storage medium | |
| CN108573045A (en) | A kind of alignment matrix similarity retrieval method based on multistage fingerprint | |
| CN106033416A (en) | A string processing method and device | |
| CN117648926A (en) | Method and system for automatically creating data model based on natural language | |
| CN112507160A (en) | Automatic judgment method and device for trademark infringement, electronic equipment and storage medium | |
| CN114911917B (en) | Asset meta-information searching method and device, computer equipment and readable storage medium | |
| CN108875743B (en) | Text recognition method and device | |
| CN111191051B (en) | Method and system for constructing emergency knowledge map based on Chinese word segmentation technology | |
| CN115329048A (en) | Statement retrieval method and device, electronic equipment and storage medium | |
| Leonandya et al. | A semi-supervised algorithm for Indonesian named entity recognition | |
| CN115858773A (en) | Keyword mining method, device and medium suitable for long document | |
| CN116628173B (en) | Intelligent customer service information generation system and method based on keyword extraction | |
| CN116414872B (en) | Data searching method and system based on natural language identification and knowledge graph | |
| CN113032371A (en) | Database grammar analysis method and device and computer equipment | |
| CN111401056A (en) | Method for extracting keywords from various texts | |
| CN115526601A (en) | File management method and device | |
| CN113836378A (en) | Data processing method and device | |
| CN114281945A (en) | Carbon reduction strategy knowledge base construction method based on green product case base | |
| CN109635075B (en) | Method and device for marking word-dividing marks on text contents | |
| CN111476641A (en) | Method, system and storage medium for automatically placing order on mobile device by voice | |
| CN116975296A (en) | Word vector-based data security classification method and system | |
| CN115858738B (en) | Enterprise public opinion information similarity identification method |
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 |