CN111460102B - Chart recommendation system and method based on natural language processing - Google Patents
Chart recommendation system and method based on natural language processing Download PDFInfo
- Publication number
- CN111460102B CN111460102B CN202010245843.3A CN202010245843A CN111460102B CN 111460102 B CN111460102 B CN 111460102B CN 202010245843 A CN202010245843 A CN 202010245843A CN 111460102 B CN111460102 B CN 111460102B
- Authority
- CN
- China
- Prior art keywords
- data
- target
- chart
- type
- description text
- 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
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F16/34—Browsing; Visualisation therefor
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a chart recommendation system and method based on natural language processing technology, wherein the chart recommendation system based on the natural language processing technology comprises the following steps: the system comprises a search engine module, a processing module, a calculation module and an output module; the invention adopts a data mining technology, and provides a chart recommendation system and method based on natural language processing for a user; the user can obtain visual chart recommendation only by inputting search sentences in a search engine, so that the system efficiency and the data objectivity are improved, the working efficiency of the user is greatly improved, and the visual experience of the user is improved; the user can select any chart from the recommended charts, and the effectiveness of the initial selection of the user is improved.
Description
Technical Field
The invention relates to the technical field of intelligent manufacturing and image-text generation, in particular to a chart recommendation system and method based on natural language processing.
Background
With the vigorous development of the field of business intelligence, the requirements of chart generation are more and more simplified and intelligentized. In the traditional chart generation method, after a data set is selected, a chart is selected by using experience of business personnel, partial fields are selected as dimensions, partial fields are selected as indexes, and data display is completed. This conventional chart generation requires a user to have a deep knowledge of the data and a knowledge of the extent to which the various charts are suitable for presentation, which poses significant difficulties to the user. Therefore, a new solution is required to solve these difficulties.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the conventional chart recommending method requires a user to have a deep knowledge of data and a knowledge of the range of various charts suitable for display, which causes great difficulty for the user.
To solve the above technical problems.
The invention is realized by the following technical scheme:
the invention provides a chart recommendation system based on natural language processing technology, which comprises: the device comprises a search engine module, a processing module, a computing module, an output module and a storage module;
the processing module is used for identifying the description text input into the search engine module and carrying out natural language processing on the description text to obtain a description text word vector set;
the processing module is also used for determining a target data set which is closest to the description text word vector set in the plurality of data sets, wherein the word vectors in the target data set are the target word vector set, and the processing module extracts target fields in the target word vector set to form a target field set;
the judging module is used for judging the element data type in the target field set; the element data types in the target field set comprise character type data and numerical type data.
The calculation module is used for matching elements in the target field set with data corresponding to the target data set and aggregating the data corresponding to the target field set in the target data set to obtain corresponding target positioning data;
the output module calculates index data according to the element data type in the target field set and the corresponding positioning data of the target field set in each data set, compares the index data with a critical value of a chart type representation range, judges the chart type of a corresponding range value, and feeds the chart type of the corresponding range value back to a user.
The storage module is used for storing the data set.
The working principle of the scheme is that the method is based on a natural language processing technology, and a natural language processing method is utilized to process the description text input into a search engine module by a user to obtain a description text word vector set; determining a target data set, a target word vector set and a target field set which are closest to the description text word vector set in the plurality of data sets; matching elements in the target field set with data corresponding to the target data set, and aggregating the data corresponding to the target field set in the target data set to obtain target positioning data; and comparing the index data with the critical value of the chart type representation range, judging the chart type of the corresponding range value, and feeding the chart type of the corresponding range value back to the user by the output module. In the prior art, corresponding data is usually called from a database directly according to input text data to form a chart for outputting, but in the scheme, a processing module carries out natural language processing on the input content in advance to obtain a description text word vector, and then the description text is subjected to word segmentation, aggregation and calculation according to a natural language processing mode to obtain a target field with the closest combination distance between a data set and the description text word vector. Firstly, carrying out primary processing (natural language processing) on input parameters, then carrying out secondary processing (aggregation and calculation) on data subjected to the primary processing according to a natural language processing mode, and finally judging and outputting all chart types meeting requirements, wherein the matching degree of fields and data in the chart output finally is higher and finer through grading processing.
The invention can obtain visual diagram by inputting search sentence in search engine, the output module of the invention feeds back the diagram type of all corresponding range values to the user, the user selects diagram type, for example, when some factory area counts sales of each area part, the method of the invention is used to recommend diagram, the system builds all fields and corresponding data of the factory area into N data sets, then only needs to input sales of some area in search engine, the diagram recommending system decomposes the input content into some area and sales, then combines these texts into describing text word vector set, matches in system data set according to natural language processing mode, locates to the target data set of some area and sales, judges the index data in the target data set to output multiple diagram types, to a certain extent, the efficiency of the system and the objectivity of data are improved, and the visual experience of the user is improved. The user can select any chart from the recommended charts, the effectiveness of the initial selection of the user is improved, and if the user is not satisfied with the selected chart, other charts can be selected, so that the working fault tolerance and the use experience of the user are improved.
Further preferably, the natural language processing process comprises: the description text is decomposed into a plurality of words by a word segmentation method, each word is mapped into an entity word vector by using the trained word vector, and then the entity word vectors corresponding to all the words are combined to obtain a description text word vector set.
Further preferably, the chart recommendation system based on the natural language processing technology is characterized in that the method for determining the target data set closest to the description text word vector set in the data sets comprises:
and searching fields matched with all words of the description text in the data set, and calculating the distance between all data sets matched with the words of the description text and the word vector of the description text, so that the data set with the minimum distance between the two word vectors is the target data set.
Further preferably, the chart recommendation system based on the natural language processing technology is characterized in that the chart type determination method for the corresponding range value is as follows:
establishing a two-dimensional matrix of the character type target field and the numerical type target field by taking the character type target field as a dimension X and the numerical type target field as a dimension Y, and judging that index data of the two-dimensional matrix meets the optimal range of a diagram when the index data are all in the critical value range of the representation range of the type of the diagram;
and when the index data of the two-dimensional matrix meets the optimal range of the multiple chart types, calculating the distance between the index data value of the current two-dimensional matrix and the edge critical value of each chart, sorting the distances in a descending order, and selecting the first three charts with the farthest distances and the edge critical values.
Further preferably, the chart recommendation system based on the natural language processing technology is characterized in that the index data of the two-dimensional matrix includes:
the index data of dimension X is: the product of the number of character type target fields and the number of different data corresponding to the fields in the target data set;
the index data of dimension Y is: the product of the number of the numeric target fields and the number of different data corresponding to the fields in the target data set.
The invention also provides a chart recommendation method based on the natural language processing technology, which is characterized by comprising the following steps of:
s1, establishing a plurality of data sets by using a public corpus;
s2, representing a description text of the input engine module by using a word vector set;
s3, determining a target word vector set which is closest to the description text word vector set in the data set in a natural language processing mode;
s4, matching elements in the target field set with data in the corresponding data set and collecting matched data;
and S5, judging the chart type of the corresponding range value, and feeding back the chart type to the user in a visual form.
The chart recommendation system and method based on the natural language processing technology can generate the visual chart according to the description text of the user, are beneficial to simplifying the operation flow of the business intelligent software, and reduce the use threshold of the business intelligent software.
A set of data set descriptor vectors is first established.
A word vector model is trained by utilizing a public corpus and is used for mapping each field in a data set into a word vector, and a matrix formed by the word vectors is a description matrix of the data set. If a total of K data sets are set, the description matrix of the kth data set
Where m denotes the number of fields in the kth data set,
a word vector representing the jth field of the kth data set, which isAn n-dimensional vector.
The descriptive text of the user is represented by a set of word vectors.
Decomposing a description text of a user into a plurality of words by a word segmentation method, mapping the words into entity word vectors by using a trained word vector model after filtering stop words, wherein each word is represented by an n-dimensional word vector, all the description texts can form a word vector set, and V is ═ { V ═ V { (V) } is used 1 ,v 2 ,L,v D Denotes, where D denotes the number of words in the user description text, v i A word vector representing the ith word, which is also an n-dimensional vector.
Location data sets and fields.
Most of business intelligence software has a plurality of data sets, the data of which data set a user wants to use is determined based on the obtained data set word vector set and the user description text word vector set, and specific field names of fields in the user description text in the data sets are found through word vector fuzzy matching fields.
From the kth data set S k Find the field number r matched with the ith word ki ：
Here, the
Representing the distance calculation of two word vectors.
Calculating the integral distance d between the kth data set and the user description language k ：
Positioning data sets and fields:
comparing the distance d between the K data sets and the user's language 1 ,d 2 ,L,d K Finding the minimum distance, and taking the corresponding k' data set as the target data set
Meanwhile, the word vector V ═ V in the user description text 1 ,v 2 ,L,v D The corresponding set of word vectors in the data set is
The fields corresponding to these word vectors are target fields, and the set of these target fields is set to M ═ M 1 ,m 2 ,m 3 ,L,m D }。
Chart types are recommended.
Judging the data type of the target field:
according to the located data set and the target field set M ═ { M ═ M 1 ,m 2 ,m 3 ,L,m D Judging the elements M in the target field set M in sequence 1 ,m 2 ,L m D The data type of (2) comprises a character type and a numerical type, wherein the character type comprises: character constants and character variables, the numerical type including: integer, single precision floating point type, double precision floating point type.
Matching data set data:
matching element M in target field set M 1 ,m 2 ,L,m D And sequentially obtaining the data corresponding to the target field set M in the data set with the data in the data set.
And (3) statistical data:
aggregating the data of the target fields to obtain a data matrix of the target fields in the corresponding data set, sequentially counting the number of different data of each data object, and obtaining the following mapping M ═ M 1 ,m 2 ,m 3 ,L,m D }→P＝{p 1 ,p 2 ,p 3 ,L,p D In which p is i (i ═ 1,2, L, D) represents the corresponding object field m i (i is 1,2, L, D) the number of different data in the data set.
And (3) recommending a chart:
calculating the sum of the number of P arrays corresponding to the fields with character types as X 1 Length l, i.e. X 1 L, the product of the number of P rows corresponding to the character-type field is X 2 I.e. X 2 ＝p 1 *p 2 *p 3 *L*p l . The sum of the number of P number sequences corresponding to the field with the type of numerical value is Y 1 I.e. Y 1 N-l. The product of the number of the corresponding P number columns of the count value type field is Y 2 I.e. Y 2 ＝p l+1 *p l+2 *p l+3 *L*p n
According to X 1 ,X 2 ,Y 1 ,Y 2 Determining the type of chart for the respective range value, i.e.
Each chart has characteristics of data type, data range and the like suitable for display, and a critical value of the representation range of each chart type is set to be X min ,X max ,Y min ,Y max According to the above determination rule if X 1 ,X 2 ,Y 1 ,Y 2 And if the data meet the optimal ranges of the graphs, calculating the distance between the current value and each graph edge threshold, sorting the distances in a descending order, selecting the first three graph types with the distances farthest from the edge thresholds, and automatically feeding back the graph types corresponding to the range values to the user in a visual mode by the system.
Compared with the prior art, the invention has the following advantages and beneficial effects:
the invention adopts a data mining technology and provides a chart recommendation system and method based on natural language processing for a user. The user only needs to input search sentences in a search engine to obtain the visual chart, so that the system efficiency and the data objectivity are improved to a certain extent, the working efficiency of the user is greatly improved, and the visual experience of the user is improved. The user can select any chart from the recommended charts, and the effectiveness of the initial selection of the user is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention.
In the drawings:
fig. 1 is a schematic diagram illustrating an overall chart recommendation process of natural language processing provided by the present invention.
Fig. 2 is a flow chart illustrating natural language processing of description text.
FIG. 3 is a schematic flow chart of the output module chart recommendation.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
Examples
As shown in fig. 1, an overall chart recommendation process of natural language processing according to an embodiment of the present invention:
step S101, a user inputs a descriptive sentence which the user wants to search in a search engine of a system;
the embodiment of the invention provides the descriptive sentences which can be arbitrarily filled by the user according to the requirement of the user, can be sentence types such as description and the like, the system can identify the sentences described by the user, and when the system receives the request of the user, the system enters the next step to execute natural language processing.
Step S102, analyzing user language, positioning data set and field through natural language processing;
the embodiment of the invention provides a response to a system when receiving a request of a user, and natural language processing is used for performing word segmentation, aggregation and calculation on a descriptive text of the user to obtain a target field which is closest to a combination distance of a description text word vector in a data set.
As shown in fig. 2, in the natural language processing flow, a user description text is first decomposed into a plurality of words by a word segmentation method, and after stop words are filtered, the words are mapped into vectors; secondly, aggregating words by using the trained word vectors, and respectively calculating the word vector distance from each word vector to the data set; and thirdly, sorting the word vectors according to the ascending order of the distance to obtain the word vectors which are closest to the word of the user in the data set, wherein the fields corresponding to the word vectors are target fields. Finally, the data set and the target field are recorded.
And step S103, obtaining a chart of the optimal representation range through calculation, and feeding the chart back to a user in a visual mode. The recommendation chart flow is shown in fig. 3.
The chart recommendation method provided by the invention comprises the steps of firstly obtaining a target data set and a target field set according to the step S102, and sequentially judging the data types of elements in the field set, wherein the data types are divided into character types and numerical types; and then, establishing a two-dimensional matrix, wherein the dimension X represents the character type field, and comprises two indexes, namely the number of the character type field and the product of the number of the corresponding data of the field in the data set. The dimension Y represents a numeric field and includes two indexes, one is the number of numeric fields and the other is the product of the corresponding data numbers of the fields in the dataset. Each chart type has a specified optimal representation range, namely the representation range of each chart can be represented into a two-dimensional matrix, the data is judged to be the optimal representation range meeting the chart type within the two-dimensional matrix range, finally, the chart type within the range value is determined according to the judgment, and the system automatically feeds back the chart type corresponding to the range value to a user in a visual mode.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (4)
1. A chart recommendation system based on natural language processing techniques, comprising: the device comprises a search engine module, a processing module, a computing module, an output module and a storage module;
the processing module is used for identifying the description text input into the search engine module and carrying out natural language processing on the description text to obtain a description text word vector set;
the processing module is also used for determining a target data set which is closest to the description text word vector set in the plurality of data sets, wherein the word vectors in the target data set are the target word vector set, and the processing module extracts target fields in the target word vector set to form a target field set;
the judging module is used for judging the element data type in the target field set; the element data types in the target field set comprise character type data and numerical type data;
the calculation module is used for matching the elements in the target field set with the data corresponding to the target data set and aggregating the data corresponding to the target field set in the target data set to obtain corresponding target positioning data;
the output module calculates index data according to the element data types in the target field set and the corresponding positioning data of the target field set in each data set, compares the index data with a critical value of a chart type representation range, determines the chart type of a proper range value, and feeds the chart type of the proper range value back to a user;
the storage module is used for storing a data set;
the chart type judgment method for the proper range value comprises the following steps:
establishing a two-dimensional matrix of the character type target field and the numerical type target field by taking the character type target field as a dimension X and the numerical type target field as a dimension Y, and judging that the index data of the two-dimensional matrix meets the optimal range of the chart when the index data of the two-dimensional matrix is in the critical value range of the chart type representation range;
when the index data of the two-dimensional matrix meets the optimal range of a plurality of chart types, calculating the distance between the index data value of the current two-dimensional matrix and the edge critical value of each chart, sorting the distances in a descending order, and selecting the first three charts with the farthest distances and the edge critical values;
the index data of the two-dimensional matrix includes:
the index data of dimension X is: the product of the number of character-type target fields and the corresponding number of different data of the fields in the target data set;
the index data of dimension Y is: the product of the number of numeric target fields and the number of corresponding different data of the fields in the target data set.
2. A chart recommendation system based on natural language processing technology according to claim 1, characterized in that said natural language processing procedure is: the description text is decomposed into a plurality of words through a word segmentation method, each word is mapped into an entity word vector by using the trained word vector, and then the entity word vectors corresponding to all the words are combined to obtain a description text word vector set.
3. The system of claim 1, wherein the target data set of the plurality of data sets closest to the set of descriptive text word vectors is determined by:
and searching fields matched with all words of the description text in the data set, and calculating the distance between all data sets matched with the words of the description text and the word vector of the description text, so that the data set with the minimum distance between the two word vectors is the target data set.
4. A chart recommendation method based on natural language processing technology, which is implemented based on the system of any one of claims 1-3, and is characterized in that the method comprises:
s1, establishing a plurality of data sets by using a public corpus;
s2, representing a description text of the input engine module by using a word vector set;
s3, the chart recommendation system determines a target word vector set which is closest to the description text word vector set in the data set in a natural language processing mode;
s4, matching the elements in the target field set with data in the corresponding data set and collecting matched data;
and S5, judging the chart type of the appropriate range value, and feeding back the chart type to the user in a visual form.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010245843.3A CN111460102B (en) | 2020-03-31 | 2020-03-31 | Chart recommendation system and method based on natural language processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010245843.3A CN111460102B (en) | 2020-03-31 | 2020-03-31 | Chart recommendation system and method based on natural language processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111460102A CN111460102A (en) | 2020-07-28 |
| CN111460102B true CN111460102B (en) | 2022-09-09 |
Family
ID=71683456
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010245843.3A Active CN111460102B (en) | 2020-03-31 | 2020-03-31 | Chart recommendation system and method based on natural language processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111460102B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112445475B (en) * | 2020-11-06 | 2024-07-05 | 杭州讯酷科技有限公司 | System rapid construction method based on data table recommendation |
| CN113761334A (en) * | 2020-11-13 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Visual recommendation method, device, equipment and storage medium |
| CN112597273A (en) * | 2020-12-02 | 2021-04-02 | 国网浙江省电力有限公司台州供电公司 | Power distribution automation chart generation method based on NL2SQL technology |
| CN112749224A (en) * | 2020-12-31 | 2021-05-04 | 清华大学 | Task-oriented visual recommendation method and device |
| CN116126312A (en) * | 2022-12-30 | 2023-05-16 | 北京大学 | Method and system for constructing visual chart based on natural language |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104766101A (en) * | 2015-04-22 | 2015-07-08 | 福州大学 | K-nearest neighbor handwriting recognition system algorithm based on searching for characteristic values |
| CN108287875A (en) * | 2017-12-29 | 2018-07-17 | 东软集团股份有限公司 | Personage's cooccurrence relation determines method, expert recommendation method, device and equipment |
| CN109446277A (en) * | 2018-09-21 | 2019-03-08 | 北京翰云时代数据技术有限公司 | Relational data intelligent search method and system based on Chinese natural language |
| CN109635116A (en) * | 2018-12-17 | 2019-04-16 | 腾讯科技（深圳）有限公司 | Training method, electronic equipment and the computer storage medium of text term vector model |
| CN109766557A (en) * | 2019-01-18 | 2019-05-17 | 河北工业大学 | A kind of sentiment analysis method, apparatus, storage medium and terminal device |
| CN110363194A (en) * | 2019-06-17 | 2019-10-22 | 深圳壹账通智能科技有限公司 | Intelligently reading method, apparatus, equipment and storage medium based on NLP |
| CN110489449A (en) * | 2019-07-30 | 2019-11-22 | 北京百分点信息科技有限公司 | A kind of chart recommended method, device and electronic equipment |
| CN110837545A (en) * | 2019-11-13 | 2020-02-25 | 贵州医渡云技术有限公司 | Interactive data analysis method, device, medium and electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108280061B (en) * | 2018-01-17 | 2021-10-26 | 北京百度网讯科技有限公司 | Text processing method and device based on ambiguous entity words |
-
2020
- 2020-03-31 CN CN202010245843.3A patent/CN111460102B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104766101A (en) * | 2015-04-22 | 2015-07-08 | 福州大学 | K-nearest neighbor handwriting recognition system algorithm based on searching for characteristic values |
| CN108287875A (en) * | 2017-12-29 | 2018-07-17 | 东软集团股份有限公司 | Personage's cooccurrence relation determines method, expert recommendation method, device and equipment |
| CN109446277A (en) * | 2018-09-21 | 2019-03-08 | 北京翰云时代数据技术有限公司 | Relational data intelligent search method and system based on Chinese natural language |
| CN109635116A (en) * | 2018-12-17 | 2019-04-16 | 腾讯科技（深圳）有限公司 | Training method, electronic equipment and the computer storage medium of text term vector model |
| CN109766557A (en) * | 2019-01-18 | 2019-05-17 | 河北工业大学 | A kind of sentiment analysis method, apparatus, storage medium and terminal device |
| CN110363194A (en) * | 2019-06-17 | 2019-10-22 | 深圳壹账通智能科技有限公司 | Intelligently reading method, apparatus, equipment and storage medium based on NLP |
| CN110489449A (en) * | 2019-07-30 | 2019-11-22 | 北京百分点信息科技有限公司 | A kind of chart recommended method, device and electronic equipment |
| CN110837545A (en) * | 2019-11-13 | 2020-02-25 | 贵州医渡云技术有限公司 | Interactive data analysis method, device, medium and electronic equipment |
Non-Patent Citations (3)
| Title |
|---|
| Graph-Based Methods for Natural Language Processing and Understanding—A Survey and Analysis;Michael T. Mills et al.;《IEEE Transactions on Systems, Man, and Cybernetics: Systems》;20130808;第44卷(第1期);59-71 * |
| 大数据背景下的新闻数据可视化分析;陈欣 等;《南方传媒研究》;20190331;52-58 * |
| 电子商务用户反馈信息的可视化研究——以智能手机产品为例;严立军;《中国优秀硕士学位论文全文数据库 经济与管理科学辑》;20200115;J152-1691 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111460102A (en) | 2020-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111460102B (en) | Chart recommendation system and method based on natural language processing | |
| CN108052583B (en) | E-commerce ontology construction method | |
| CN109492077B (en) | Knowledge graph-based petrochemical field question-answering method and system | |
| WO2020108608A1 (en) | Search result processing method, device, terminal, electronic device, and storage medium | |
| CN111949758A (en) | Medical question and answer recommendation method, recommendation system and computer readable storage medium | |
| CN112966091B (en) | Knowledge map recommendation system fusing entity information and heat | |
| US20150199567A1 (en) | Document classification assisting apparatus, method and program | |
| CN112507098B (en) | Question processing method, question processing device, electronic equipment, storage medium and program product | |
| Zul et al. | Social media sentiment analysis using K-means and naïve bayes algorithm | |
| CN117874161A (en) | Form question-answer optimization method and device, electronic equipment and readable storage medium | |
| CN112837820A (en) | Association rule-based traditional Chinese medicine constitution analysis method | |
| CN114239828A (en) | Supply chain affair map construction method based on causal relationship | |
| CN112508726A (en) | False public opinion identification system based on information spreading characteristics and processing method thereof | |
| CN114741471A (en) | Personalized mixed recommendation method based on text mining and multi-view fusion | |
| CN117993772A (en) | Knowledge graph-based crowdsourcing data acquisition method and system and electronic equipment | |
| CN113553326A (en) | Spreadsheet data processing method, device, computer equipment and storage medium | |
| CN112148735A (en) | Construction method for structured form data knowledge graph | |
| CN112905906A (en) | Recommendation method and system fusing local collaboration and feature intersection | |
| CN112270189A (en) | Question type analysis node generation method, question type analysis node generation system and storage medium | |
| Smits et al. | Vocabulary elicitation for informative descriptions of classes | |
| Tripathy et al. | Fuzzy clustering of sequential data | |
| CN118013023B (en) | Scientific and technological literature recommendation method and device, electronic equipment and storage medium | |
| CN112948589B (en) | Text classification method, text classification device and computer-readable storage medium | |
| Zuo et al. | A tag-aware recommendation algorithm based on deep learning and multi-objective optimization | |
| Nayak et al. | A Machine Learning Model to Classify Indian Taxi System in Tourism Industry |
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 | ||
| CB02 | Change of applicant information |
Address after: 610000 No.2, 4th floor, building 1, Jule Road intersection, West 1st section of 1st ring road, Wuhou District, Chengdu City, Sichuan Province Applicant after: Chengdu shuzhilian Technology Co.,Ltd. Address before: 610000 No.2, 4th floor, building 1, Jule Road intersection, West 1st section of 1st ring road, Wuhou District, Chengdu City, Sichuan Province Applicant before: CHENGDU SHUZHILIAN TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |