CN114036949A - Investment strategy determination method and device based on information analysis - Google Patents
Investment strategy determination method and device based on information analysis Download PDFInfo
- Publication number
- CN114036949A CN114036949A CN202111314123.9A CN202111314123A CN114036949A CN 114036949 A CN114036949 A CN 114036949A CN 202111314123 A CN202111314123 A CN 202111314123A CN 114036949 A CN114036949 A CN 114036949A
- Authority
- CN
- China
- Prior art keywords
- information
- model
- emotion classification
- entity
- investment strategy
- 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
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000004458 analytical method Methods 0.000 title claims abstract description 34
- 230000008451 emotion Effects 0.000 claims abstract description 110
- 238000013145 classification model Methods 0.000 claims abstract description 26
- 238000012549 training Methods 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 15
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000009193 crawling Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 13
- 238000004891 communication Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000002996 emotional effect Effects 0.000 description 4
- 238000004880 explosion Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 102100030988 Angiotensin-converting enzyme Human genes 0.000 description 1
- 101710185050 Angiotensin-converting enzyme Proteins 0.000 description 1
- 101000972273 Homo sapiens Mucin-7 Proteins 0.000 description 1
- 102100022493 Mucin-6 Human genes 0.000 description 1
- 108010008692 Mucin-6 Proteins 0.000 description 1
- 102100022492 Mucin-7 Human genes 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Technology Law (AREA)
- Operations Research (AREA)
- Human Resources & Organizations (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an investment strategy determination method and device based on information analysis, which can be used in the technical field of big data, and comprises the following steps: after the information is obtained, inputting the title of the information into an entity identification model, and identifying an entity object in the information; inputting the questions of the information into the emotion classification model to obtain emotion classification of the consultation information; searching an information base based on the identified entity object to obtain historical information and corresponding emotion classification within a first time length; and determining the investment strategy of the entity object based on the emotion classification of the information and the emotion classification of the historical information. The invention can be used for realizing the comprehensive analysis of the information so as to determine the investment strategy.
Description
Technical Field
The invention relates to the technical field of big data, in particular to an investment strategy determination method and device based on information analysis.
Background
Today of network information explosion, the speed block and the range of information propagation in a network are wide, and the credit rating of a company and an organization has real-time influence on the analysis and judgment of investors. How to use the information in real time to perform efficient analysis to generate an investment strategy for an investment target is still one of the pain points at present. In the prior art, emotion analysis is carried out on information, and the analyzed information cannot visually see which objects are affected and further needs to be statistically checked by people, so that investment strategies cannot be timely and accurately determined on investment objects.
Disclosure of Invention
The embodiment of the invention provides an investment strategy determination method based on information analysis, which is used for comprehensively analyzing information so as to determine an investment strategy, and comprises the following steps:
after the information is obtained, inputting the title of the information into an entity identification model, and identifying an entity object in the information;
inputting the questions of the information into the emotion classification model to obtain emotion classification of the consultation information;
searching an information base based on the identified entity object to obtain historical information and corresponding emotion classification within a first time length;
and determining the investment strategy of the entity object based on the emotion classification of the information and the emotion classification of the historical information.
The embodiment of the invention provides an investment strategy determining device based on information analysis, which is used for comprehensively analyzing information so as to determine an investment strategy, and comprises the following components:
the entity object identification module is used for inputting the title of the information into the entity identification model after the information is obtained, and identifying the entity object in the information;
the emotion classification module is used for inputting the questions of the information into the emotion classification model to obtain emotion classification of the consultation information;
the historical emotion classification obtaining module is used for searching an information base based on the identified entity object to obtain historical information and corresponding emotion classification within a first time length;
and the investment strategy determining module is used for determining an investment strategy for the entity object based on the emotion classification of the information and the emotion classification of the historical information.
The embodiment of the invention also provides computer equipment, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the investment strategy determination method based on information analysis when executing the computer program.
An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program for executing the investment strategy determination method based on information analysis is stored.
In the embodiment of the invention, after the information is obtained, the title of the information is input into the entity identification model, and the entity object in the information is identified; inputting the questions of the information into the emotion classification model to obtain emotion classification of the consultation information; searching an information base based on the identified entity object to obtain historical information and corresponding emotion classification within a first time length; and determining the investment strategy of the entity object based on the emotion classification of the information and the emotion classification of the historical information. In the process, the question of the information is subjected to entity identification, so that the information base is conveniently checked by the bank personnel in a self-defined manner, and the historical information and the corresponding emotion classification within the first time length are obtained. The subject of the information is identified instead of the information content, which facilitates accurate location of the entity without interference from the associated entities mentioned in the information. In addition, during emotion analysis, the question of the information is input into the emotion classification model instead of the information content, and the emotion classification efficiency of the information can be further improved, so that the investment strategy for the entity object can be rapidly judged.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
FIG. 1 is a flow chart of an investment strategy determination method based on information analysis according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating the training of an entity recognition model according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating the training of an emotion classification model according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of an investment strategy determination apparatus based on information analysis according to an embodiment of the present invention;
FIG. 5 is a diagram of a computer device in an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
In the description of the present specification, the terms "comprising," "including," "having," "containing," and the like are used in an open-ended fashion, i.e., to mean including, but not limited to. Reference to the description of the terms "one embodiment," "a particular embodiment," "some embodiments," "for example," etc., means that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. The sequence of steps involved in the embodiments is for illustrative purposes to illustrate the implementation of the present application, and the sequence of steps is not limited and can be adjusted as needed.
Fig. 1 is a flowchart of an investment strategy determination method based on information analysis according to an embodiment of the present invention, as shown in fig. 1, including:
102, inputting the questions of the information into an emotion classification model to obtain emotion classification of the consultation information;
103, searching an information base based on the identified entity object to obtain historical information and corresponding emotion classification within a first time length;
and 104, determining an investment strategy for the entity object based on the emotion classification of the information and the emotion classification of the historical information.
In the embodiment of the invention, the entity identification is carried out on the subject of the information, so as to facilitate the self-defined checking of bank personnel, search the information base and obtain the historical information and the corresponding emotion classification within the first time length. The subject of the information is identified instead of the information content, which facilitates accurate location of the entity without interference from the associated entities mentioned in the information. In addition, during emotion analysis, the question of the information is input into the emotion classification model instead of the information content, and the emotion classification efficiency of the information can be further improved, so that the investment strategy for the entity object can be rapidly judged.
In the implementation, the information title is the core of an information, which can find out which main body the information says, and can also reflect the positive and negative emotions of an information. Therefore, the title of the information is identified physically.
In step 101, after the information is obtained, the title of the information is input to the entity identification model to identify the entity object in the information.
In the specific implementation, if the whole content of the information is analyzed, a plurality of entity objects are identified, so that the key points are easy to be caught, and the processing speed is low. In addition, interference information generated by other physical objects appearing in the information is avoided.
In one embodiment, the entity identification model employs a NER model.
The NER model is based on a Stanford NER system, which is a named entity recognition system developed by Stanford university and based on conditional random fields, and system parameters are trained based on CoNLL, MUC-6, MUC-7 and ACE named entity corpora. The standby ner employs a linear Chain Random Field (CRF) sequence model, and can train its own custom model for various applications using its own labeled data set. But may not be limited to this method.
Fig. 2 is a flowchart illustrating a training process of an entity recognition model according to an embodiment of the present invention, in an embodiment, the training process of the entity recognition model includes:
and step 203, training an NER model based on the documents in the tsv format, and generating the trained NER model.
In the above embodiment, the bank-related entity dictionary file includes company institution names, client names, organization institution names, and the like, which are of interest to the bank staff. In order to obtain more accurate word segmentation effect and named entity recognition effect, an entity dictionary file is constructed manually.
Processing the format of the entity dictionary file based on a stanford ner method to obtain a document in a tsv format, wherein the document comprises:
setting training data in a physical dictionary file to be a first column of object names such as company names or person names, setting a second column of marks of the objects, and separating the first column and the second column by tab to finally form a tsv-format document;
configuring attribute file of standford ner.
During training, in the stanford NER system, the parameters of the attribute file of the stanford NER are applied, the document in the tsv format is input, and the command for operating the training model is executed to generate the NER model.
After the NER model is trained, the title of the information can be input into the entity recognition model, entity objects in the information are recognized, and the entity objects can be added into the entity dictionary file to retrain the NER model, so that the NER model is gradually accurate.
In step 102, the topic of the information is input to the emotion classification model to obtain emotion classification of the consultation information.
In one embodiment, the emotion classification model employs a Fasttext model.
Fastext is a text classification tool for facebook open source, the most common application scenario is text classification with supervision, and a simple and efficient text classification method is provided and is widely applied. When the supervised text classification method is adopted, firstly, the word segmentation processing is carried out on a training sample, then stop words are removed, the random disordering processing is carried out on the training sample, a training sample data set is generated, a Fasttext algorithm frame is applied to train the training sample data set to obtain a classification model, and after the data preprocessing is carried out on the test data, the classification of the test sample is obtained by inputting the test data into the model. The Fasttext algorithm introduces the concept of n-gram to solve the problem of word shape change, scatters words to the character level, captures the sequence relation among characters by using the n-gram information of the character level, avoids the problem that independent words in a vocabulary table are used as basic units for training and some low-frequency words have no corresponding vector representation, obtains word information with larger magnitude after n-gram word processing, and then performs global normalization processing after performing linear and exponential transformation on the input processed word information by using a Hirearchical softmax function to obtain an output item with the maximum probability. The binary huffman tree is adopted before Hieracal softmax, the calculation complexity is reduced, one huffman tree is constructed by all vocabularies and the frequency of all vocabularies, the more frequently appeared vocabularies are closer to the root node, the less the needed judgment times are needed, and the integral judgment efficiency is improved.
Unlike the general text classification by Fasttext, the embodiment of the invention only performs emotion classification on the topics of the information, thereby improving the emotion classification efficiency.
FIG. 3 is a flowchart illustrating an embodiment of a method for training an emotion classification model, where in an embodiment of the present invention, the step of training the emotion classification model includes:
303, carrying out emotion label marking on the text information meeting the requirement of a preset format;
and 304, training a Fasttext model based on the labeled text information to obtain the trained Fasttext model.
The preprocessing comprises the steps of information subject arrangement, space removal, punctuation and escape character, and then jieba word segmentation and stop word processing are carried out. When the emotion label is labeled, the positive emotion is 1, the negative emotion is 0, the larger the labeled data volume is, the higher the accuracy of the finally trained model is. In the emotion classification result, the closer to 1, the closer to the positive emotion is indicated, and the closer to 0, the closer to the negative emotion is indicated.
After emotion label labeling is carried out, labeled text information is randomly scrambled and combined into a text file, so that a Fasttext model is trained.
In step 103, the information database is searched based on the identified entity object to obtain the historical information and the corresponding emotion classification within the first duration.
The first time period can be determined according to actual conditions, for example, a week, the entity object is used as a keyword to search the information base, so that a large amount of information can be obtained, because after the entity object of the title of the information is identified, the index is already established for the information, and positive and negative emotion judgment is carried out, so that the credit rating of companies and clients and whether the companies and the clients can invest as investment objects can be judged by bank staff. If the bank staff wants to see the detailed information, the whole information can be opened by clicking the information subject.
The obtained information and the historical information can be put into a consultation information base by taking an entity object identified by the information as an index, so that the use and the display are convenient.
During display, the entity objects, the consultation information and the emotion classification can be displayed through designing a visual interface and through tables, column diagrams, pie charts and the like.
In step 104, an investment strategy for the entity object is determined based on the emotional category of the information and the emotional category of the historical information.
The investment strategy comprises investment according to different scales, for example, if the consulting information of the positive emotion of a certain entity object is very much, large-scale investment can be carried out; if the positive emotion and negative emotion proportions of a certain entity object are basically consistent, small-scale investment is carried out; the consulting information of negative emotion of a certain entity object is very much, so that investment is not carried out.
In summary, in the method provided in the embodiment of the present invention, after the information is obtained, the title of the information is input to the entity identification model, and the entity object in the information is identified; inputting the questions of the information into the emotion classification model to obtain emotion classification of the consultation information; searching an information base based on the identified entity object to obtain historical information and corresponding emotion classification within a first time length; and determining the investment strategy of the entity object based on the emotion classification of the information and the emotion classification of the historical information. In the process, the question of the information is subjected to entity identification, so that the information base is conveniently checked by the bank personnel in a self-defined manner, and the historical information and the corresponding emotion classification within the first time length are obtained. The subject of the information is identified instead of the information content, which facilitates accurate location of the entity without interference from the associated entities mentioned in the information. In addition, during emotion analysis, the question of the information is input into the emotion classification model instead of the information content, and the emotion classification efficiency of the information can be further improved, so that the investment strategy for the entity object can be rapidly judged. For the current information explosion era, a large amount of information about positive emotion or negative emotion of an entity object concerned and some statistical information can be obtained without clicking the information, which is very helpful for improving the working efficiency of bank workers.
The invention also provides an investment strategy determination device based on information analysis, the principle of which is the same as that of the investment strategy determination method based on information analysis, and the details are not repeated here.
Fig. 4 is a schematic diagram of an investment strategy determination apparatus based on information analysis according to an embodiment of the present invention, as shown in fig. 4, including:
the entity object identification module 401 is configured to, after the information is obtained, input the title of the information into the entity identification model, and identify an entity object in the information;
an emotion classification module 402, configured to input the question of the information to the emotion classification model, and obtain emotion classification of the advisory information;
a historical emotion classification obtaining module 403, configured to search an information base based on the identified entity object, and obtain historical information and corresponding emotion classification within a first duration;
an investment strategy determination module 404, configured to determine an investment strategy for the entity object based on the emotional category of the information and the emotional category of the historical information.
In one embodiment, the entity identification model employs a NER model.
In one embodiment, the training of the entity recognition model comprises:
constructing a bank related entity dictionary file;
processing the format of the entity dictionary file based on a stanford ner method to obtain a document in a tsv format;
and training the NER model based on the documents in the tsv format to generate the trained NER model.
In one embodiment, the emotion classification model employs a Fasttext model.
In one embodiment, the step of training the emotion classification model comprises:
crawling historical information on a network;
preprocessing the question of the crawled historical information to obtain text information meeting the requirement of a preset format;
carrying out emotion label marking on the text information meeting the requirements of the preset format;
and training a Fasttext model based on the labeled text information to obtain the trained Fasttext model.
In summary, in the apparatus provided in the embodiment of the present invention, the entity object identification module is configured to, after the information is obtained, input the title of the information into the entity identification model to identify the entity object in the information; the emotion classification module is used for inputting the questions of the information into the emotion classification model to obtain emotion classification of the consultation information; the historical emotion classification obtaining module is used for searching an information base based on the identified entity object to obtain historical information and corresponding emotion classification within a first time length; and the investment strategy determining module is used for determining an investment strategy for the entity object based on the emotion classification of the information and the emotion classification of the historical information. In the process, the question of the information is subjected to entity identification, so that the information base is conveniently checked by the bank personnel in a self-defined manner, and the historical information and the corresponding emotion classification within the first time length are obtained. The subject of the information is identified instead of the information content, which facilitates accurate location of the entity without interference from the associated entities mentioned in the information. In addition, during emotion analysis, the question of the information is input into the emotion classification model instead of the information content, and the emotion classification efficiency of the information can be further improved, so that the investment strategy for the entity object can be rapidly judged. For the current information explosion era, a large amount of information about positive emotion or negative emotion of an entity object concerned and some statistical information can be obtained without clicking the information, which is very helpful for improving the working efficiency of bank workers.
An embodiment of the present invention further provides a computer device, and fig. 5 is a schematic diagram of the computer device in the embodiment of the present invention, where the computer device is capable of implementing all steps in the investment policy determination method based on information analysis in the foregoing embodiment, and the computer device specifically includes the following contents:
a processor (processor)501, a memory (memory)502, a communication Interface (Communications Interface)503, and a communication bus 504;
the processor 501, the memory 502 and the communication interface 503 complete mutual communication through the communication bus 504; the communication interface 503 is used for implementing information transmission between related devices such as server-side devices, detection devices, and user-side devices;
the processor 501 is used to call the computer program in the memory 502, and when the processor executes the computer program, the processor implements all the steps of the investment strategy determination method based on information analysis in the above embodiments.
An embodiment of the present invention further provides a computer-readable storage medium, which is capable of implementing all the steps of the investment strategy determination method based on information analysis in the above-mentioned embodiment, wherein the computer-readable storage medium has stored thereon a computer program, which, when being executed by a processor, implements all the steps of the investment strategy determination method based on information analysis in the above-mentioned embodiment.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
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 only 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 (12)
1. An investment strategy determination method based on information analysis is characterized by comprising the following steps:
after the information is obtained, inputting the title of the information into an entity identification model, and identifying an entity object in the information;
inputting the questions of the information into the emotion classification model to obtain emotion classification of the consultation information;
searching an information base based on the identified entity object to obtain historical information and corresponding emotion classification within a first time length;
and determining the investment strategy of the entity object based on the emotion classification of the information and the emotion classification of the historical information.
2. The method of claim 1, wherein the entity recognition model employs an NER model.
3. The investment strategy determination method based on information analysis of claim 2 wherein the training of the entity recognition model comprises:
constructing a bank related entity dictionary file;
processing the format of the entity dictionary file based on a stanford ner method to obtain a document in a tsv format;
and training the NER model based on the documents in the tsv format to generate the trained NER model.
4. The investment strategy determination method based on information analysis according to claim 1, wherein the emotion classification model employs a Fasttext model.
5. The investment strategy determination method based on information analysis of claim 4 wherein the step of training the emotion classification model comprises:
crawling historical information on a network;
preprocessing the question of the crawled historical information to obtain text information meeting the requirement of a preset format;
carrying out emotion label marking on the text information meeting the requirements of the preset format;
and training a Fasttext model based on the labeled text information to obtain the trained Fasttext model.
6. An investment strategy determination apparatus based on information analysis, comprising:
the entity object identification module is used for inputting the title of the information into the entity identification model after the information is obtained, and identifying the entity object in the information;
the emotion classification module is used for inputting the questions of the information into the emotion classification model to obtain emotion classification of the consultation information;
the historical emotion classification obtaining module is used for searching an information base based on the identified entity object to obtain historical information and corresponding emotion classification within a first time length;
and the investment strategy determining module is used for determining an investment strategy for the entity object based on the emotion classification of the information and the emotion classification of the historical information.
7. The investment strategy determination apparatus based on information analysis according to claim 6, wherein said entity recognition model employs a NER model.
8. The investment strategy determination apparatus based on information analysis according to claim 7, wherein the training of the entity recognition model comprises:
constructing a bank related entity dictionary file;
processing the format of the entity dictionary file based on a stanford ner method to obtain a document in a tsv format;
and training the NER model based on the documents in the tsv format to generate the trained NER model.
9. The investment strategy determination apparatus according to claim 6, wherein said emotion classification model employs a Fasttext model.
10. The investment strategy determination apparatus based on information analysis according to claim 9, wherein the training of the emotion classification model comprises:
crawling historical information on a network;
preprocessing the question of the crawled historical information to obtain text information meeting the requirement of a preset format;
carrying out emotion label marking on the text information meeting the requirements of the preset format;
and training a Fasttext model based on the labeled text information to obtain the trained Fasttext model.
11. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 5 when executing the computer program.
12. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the method of any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111314123.9A CN114036949A (en) | 2021-11-08 | 2021-11-08 | Investment strategy determination method and device based on information analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111314123.9A CN114036949A (en) | 2021-11-08 | 2021-11-08 | Investment strategy determination method and device based on information analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114036949A true CN114036949A (en) | 2022-02-11 |
Family
ID=80143330
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111314123.9A Pending CN114036949A (en) | 2021-11-08 | 2021-11-08 | Investment strategy determination method and device based on information analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114036949A (en) |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102023967A (en) * | 2010-11-11 | 2011-04-20 | 清华大学 | Text emotion classifying method in stock field |
CN105740353A (en) * | 2016-01-26 | 2016-07-06 | 中国人民解放军国防科学技术大学 | Calculation method and system for relevance degree of individual share and article |
US20170351971A1 (en) * | 2016-06-07 | 2017-12-07 | International Business Machines Corporation | Method and apparatus for informative training repository building in sentiment analysis model learning and customaization |
CN108197113A (en) * | 2018-01-19 | 2018-06-22 | 百度在线网络技术(北京)有限公司 | Article information conversion method, device, equipment and computer-readable medium |
CN109101597A (en) * | 2018-07-31 | 2018-12-28 | 中电传媒股份有限公司 | A kind of electric power news data acquisition system |
CN109271627A (en) * | 2018-09-03 | 2019-01-25 | 深圳市腾讯网络信息技术有限公司 | Text analyzing method, apparatus, computer equipment and storage medium |
CN111143562A (en) * | 2019-12-27 | 2020-05-12 | 中国银行股份有限公司 | Information emotion analysis method and device and storage medium |
CN111414754A (en) * | 2020-03-19 | 2020-07-14 | 中国建设银行股份有限公司 | Emotion analysis method and device of event, server and storage medium |
US20200302540A1 (en) * | 2019-03-21 | 2020-09-24 | The University Of Chicago | Applying a trained model to predict a future value using contextualized sentiment data |
CN112528028A (en) * | 2020-12-28 | 2021-03-19 | 北京华彬立成科技有限公司 | Investment and financing information mining method and device, electronic equipment and storage medium |
CN112784580A (en) * | 2021-01-25 | 2021-05-11 | 中国工商银行股份有限公司 | Financial data analysis method and device based on event extraction |
CN113434685A (en) * | 2021-07-06 | 2021-09-24 | 中国银行股份有限公司 | Information classification processing method and system |
CN113535813A (en) * | 2021-06-30 | 2021-10-22 | 北京百度网讯科技有限公司 | Data mining method and device, electronic equipment and storage medium |
-
2021
- 2021-11-08 CN CN202111314123.9A patent/CN114036949A/en active Pending
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102023967A (en) * | 2010-11-11 | 2011-04-20 | 清华大学 | Text emotion classifying method in stock field |
CN105740353A (en) * | 2016-01-26 | 2016-07-06 | 中国人民解放军国防科学技术大学 | Calculation method and system for relevance degree of individual share and article |
US20170351971A1 (en) * | 2016-06-07 | 2017-12-07 | International Business Machines Corporation | Method and apparatus for informative training repository building in sentiment analysis model learning and customaization |
CN108197113A (en) * | 2018-01-19 | 2018-06-22 | 百度在线网络技术(北京)有限公司 | Article information conversion method, device, equipment and computer-readable medium |
CN109101597A (en) * | 2018-07-31 | 2018-12-28 | 中电传媒股份有限公司 | A kind of electric power news data acquisition system |
CN109271627A (en) * | 2018-09-03 | 2019-01-25 | 深圳市腾讯网络信息技术有限公司 | Text analyzing method, apparatus, computer equipment and storage medium |
US20200302540A1 (en) * | 2019-03-21 | 2020-09-24 | The University Of Chicago | Applying a trained model to predict a future value using contextualized sentiment data |
CN111143562A (en) * | 2019-12-27 | 2020-05-12 | 中国银行股份有限公司 | Information emotion analysis method and device and storage medium |
CN111414754A (en) * | 2020-03-19 | 2020-07-14 | 中国建设银行股份有限公司 | Emotion analysis method and device of event, server and storage medium |
CN112528028A (en) * | 2020-12-28 | 2021-03-19 | 北京华彬立成科技有限公司 | Investment and financing information mining method and device, electronic equipment and storage medium |
CN112784580A (en) * | 2021-01-25 | 2021-05-11 | 中国工商银行股份有限公司 | Financial data analysis method and device based on event extraction |
CN113535813A (en) * | 2021-06-30 | 2021-10-22 | 北京百度网讯科技有限公司 | Data mining method and device, electronic equipment and storage medium |
CN113434685A (en) * | 2021-07-06 | 2021-09-24 | 中国银行股份有限公司 | Information classification processing method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110765257B (en) | Intelligent consulting system of law of knowledge map driving type | |
KR102288249B1 (en) | Information processing method, terminal, and computer storage medium | |
CN112667794A (en) | Intelligent question-answer matching method and system based on twin network BERT model | |
CN116911312B (en) | Task type dialogue system and implementation method thereof | |
CN111797214A (en) | FAQ database-based problem screening method and device, computer equipment and medium | |
CN114357117A (en) | Transaction information query method and device, computer equipment and storage medium | |
CN112784591B (en) | Data processing method and device, electronic equipment and storage medium | |
CN114153994A (en) | Medical insurance information question-answering method and device | |
CN113627797A (en) | Image generation method and device for employee enrollment, computer equipment and storage medium | |
CN117609419A (en) | Domain retrieval method based on meta learning and knowledge enhancement | |
CN114398466A (en) | Complaint analysis method and device based on semantic recognition, computer equipment and medium | |
CN114372454B (en) | Text information extraction method, model training method, device and storage medium | |
CN116561288B (en) | Event query method, device, computer equipment, storage medium and program product | |
CN116484021A (en) | Method, device and storage medium for constructing leetcode question bank knowledge graph | |
CN116049376A (en) | Method, device and system for retrieving and replying information and creating knowledge | |
Gurin | Methods for Automatic Sentiment Detection | |
CN112328812B (en) | Domain knowledge extraction method and system based on self-adjusting parameters and electronic equipment | |
WO2022227196A1 (en) | Data analysis method and apparatus, computer device, and storage medium | |
CN114036949A (en) | Investment strategy determination method and device based on information analysis | |
CN117540004B (en) | Industrial domain intelligent question-answering method and system based on knowledge graph and user behavior | |
CN114925185B (en) | Interaction method, model training method, device, equipment and medium | |
CN113064887B (en) | Data management method, device, equipment and storage medium | |
CN118095296B (en) | Semantic analysis method, system and medium based on knowledge graph | |
Bektemyssova et al. | Building a Semantic Knowledge Graph Search Model for Finding a Causal Answer. | |
Amsa–nguan et al. | Development of the Topic Tagging System for Thai and English-Translated Web Contents |
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 |