CN112132690B - Method and device for pushing foreign exchange product information, computer equipment and storage medium - Google Patents
Method and device for pushing foreign exchange product information, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112132690B CN112132690B CN202011050631.6A CN202011050631A CN112132690B CN 112132690 B CN112132690 B CN 112132690B CN 202011050631 A CN202011050631 A CN 202011050631A CN 112132690 B CN112132690 B CN 112132690B
- Authority
- CN
- China
- Prior art keywords
- information
- foreign exchange
- product
- preset number
- known information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000012549 training Methods 0.000 claims abstract description 32
- 239000011159 matrix material Substances 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 8
- 230000009467 reduction Effects 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000012847 principal component analysis method Methods 0.000 claims description 4
- 230000010365 information processing Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 230000006870 function Effects 0.000 description 4
- 238000000513 principal component analysis Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 230000009514 concussion Effects 0.000 description 2
- 230000008451 emotion Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- 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
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Operations Research (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Technology Law (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides a pushing method, a pushing device, computer equipment and a storage medium of foreign exchange product information, wherein the method comprises the following steps: the foreign exchange information in the current preset duration is arranged into information; inputting the information into a prediction model, and outputting a heat product in the next preset time period corresponding to the information by the prediction model, wherein the prediction model is obtained by training with known information and corresponding heat products as samples, and the heat products are determined according to the transaction quantity condition; pushing relevant information of the heat product corresponding to the information. The scheme can provide the relevant information of the foreign exchange products for the user, provide the reference information for the user to perform foreign exchange product operation, avoid or reduce uncertainty and confusing of the user, and is beneficial to improving efficiency and accuracy of the user in foreign exchange product operation and improving user experience.
Description
Technical Field
The present application relates to the field of product recommendation technologies, and in particular, to a method and apparatus for pushing foreign exchange product information, a computer device, and a storage medium.
Background
At present, most people are unknown to foreign exchange products when operating the foreign exchange products, do not know the foreign exchange products and do not operate reference information, so that users are particularly lost, how to select and operate the foreign exchange products is unknown, uncertainty and lost performance exist in the operation process, the operation efficiency is low, the accuracy is low, and the user experience is reduced.
Disclosure of Invention
The embodiment of the application provides a method for pushing foreign exchange product information, which aims to solve the technical problems of low efficiency, low accuracy and poor experience of a user in foreign exchange product operation in the prior art. The method comprises the following steps:
the foreign exchange information in the current preset duration is arranged into information;
inputting the information into a prediction model, and outputting a heat product in the next preset time period corresponding to the information by the prediction model, wherein the prediction model is obtained by training with known information and corresponding heat products as samples, and the heat products are determined according to the transaction quantity condition;
pushing relevant information of the heat product corresponding to the information.
The embodiment of the application also provides a pushing device for the foreign exchange product information, which is used for solving the technical problems of low efficiency, low accuracy and poor experience of a user in the operation of the foreign exchange product in the prior art. The device comprises:
the information processing module is used for sorting the foreign exchange information in the current preset duration into information;
the prediction module is used for inputting the information into a prediction model, and outputting a heat product in the next preset duration corresponding to the information by the prediction model, wherein the prediction model is obtained by training a sample of the known information and the corresponding heat product, and the heat product is determined according to the transaction quantity condition;
and the information pushing module is used for pushing the relevant information of the heat product corresponding to the information.
The embodiment of the application also provides computer equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the pushing method of any foreign exchange product information when executing the computer program, so as to solve the technical problems of low efficiency, low accuracy and poor experience of a user when the foreign exchange product operates in the prior art.
The embodiment of the application also provides a computer readable storage medium which stores a computer program for executing the method for pushing the information of any foreign exchange product, so as to solve the technical problems of low efficiency, low accuracy and poor experience of a user in the operation of the foreign exchange product in the prior art.
In the embodiment of the application, a prediction model is provided, the prediction model is obtained by training known information and corresponding heat products as samples, after the foreign exchange information in the current preset time length is arranged into one piece of information, after the one piece of information is input into the prediction model, the prediction model can output the heat product in the next preset time length corresponding to the information, namely, the heat product in the next preset time length can be predicted based on the foreign exchange information in the current preset time length, and further, the related information of the heat product corresponding to the predicted information is pushed to a user.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate and together with the description serve to explain the application. In the drawings:
fig. 1 is a flowchart of a method for pushing foreign exchange product information according to an embodiment of the present application;
FIG. 2 is a schematic illustration of a sample provided by an embodiment of the present application;
fig. 3 is a flowchart of a pushing method for implementing the above-mentioned foreign exchange product information according to an embodiment of the present application;
FIG. 4 is a block diagram of a computer device according to an embodiment of the present application;
fig. 5 is a block diagram of a push device for foreign exchange product information according to an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the following embodiments and the accompanying drawings, in order to make the objects, technical solutions and advantages of the present application more apparent. The exemplary embodiments of the present application and the descriptions thereof are used herein to explain the present application, but are not intended to limit the application.
In an embodiment of the present application, a method for pushing foreign exchange product information is provided, as shown in fig. 1, where the method includes:
step 102: the foreign exchange information in the current preset duration is arranged into information;
step 104: inputting the information into a prediction model, and outputting a heat product in the next preset time period corresponding to the information by the prediction model, wherein the prediction model is obtained by training with known information and corresponding heat products as samples, and the heat products are determined according to the transaction quantity condition;
step 106: pushing relevant information of the heat product corresponding to the information.
As can be seen from the flow shown in fig. 1, in the embodiment of the present application, a prediction model is provided, the prediction model is obtained by training using known information and corresponding heat products as samples, after finishing the information of the foreign exchange in the current preset duration into one piece of information, after inputting the one piece of information into the prediction model, the prediction model can output the heat product in the next preset duration corresponding to the information, that is, the heat product in the next preset duration can be predicted based on the information of the foreign exchange in the current preset duration, and further, the related information of the heat product corresponding to the predicted information is pushed to the user.
In a specific implementation, in order to implement the above prediction model, the heat product in the next preset duration may be predicted based on the information in the current preset duration, in this embodiment, training with known information and corresponding heat product information as samples is implemented by the following steps to obtain the prediction model:
the known foreign exchange information in the preset time length is arranged into a piece of known information;
taking the foreign exchange product with the difference value between the transaction quantity and the maximum transaction value in the preset time period as a heat product corresponding to the known information in the preset time period; specifically, if the maximum transaction value in the latter preset duration is represented by Q, the foreign exchange products with the difference between the transaction number and Q within the preset range can be regarded as heat products corresponding to the known information in the former preset duration, the specific value in the preset range can be determined according to specific conditions, for example, the application is not specifically limited, and can be 0 to 1 ten thousand; for another example, when the internal and external sink products in the latter preset time period are dollars/yen and pounds/dollars, and the number of times of transactions is 20 ten thousand and 19 ten thousand respectively, the maximum transaction value in the latter preset time period is 20 ten thousand, dollars/yen is the heat product corresponding to the information known in the former preset time period, and the difference between the number of times of transactions of pounds/dollars 19 ten thousand and 20 ten thousand is in the preset range of 0 to 1 ten thousand, pounds/dollar is also used as the heat product corresponding to the information known in the former preset time period;
and converting each piece of known information into a feature matrix form, and training a feature matrix corresponding to each piece of known information and a corresponding heat product as samples to obtain the prediction model.
In particular, each known heat product corresponding to information can be marked by a text description form or a symbol, for convenience of marking or training, each known heat product corresponding to information can be marked by different marking symbols, and different foreign exchange products or foreign exchange product combinations are represented by different symbols, for example, the foreign exchange products take three types of dollars/yen, pound/dollar and euro/dollar as examples, and according to the number of times of transactions of the three types of foreign exchange products, the heat products can be as follows: dollars/yen, pound/dollar, euro/dollar, dollar/yen and pound/dollar, dollar/yen and euro/dollar, pound/dollar and euro/dollar, dollar/yen and pound/dollar and euro/dollar, each hot product case formed by combining a foreign exchange product or foreign exchange products may be marked with a different symbol or label, respectively, as in the case of the seven hot products described above, may be abbreviated as A, B, C, D, E, F, G, respectively. If dollars/yen is a heat product corresponding to a certain piece of known information, the heat product corresponding to the certain piece of known information is marked as A; if dollars/yen and pound/dollars are heat products corresponding to a certain piece of known information, then the heat product corresponding to the certain piece of known information is labeled D.
In particular, in order to further improve accuracy or training efficiency of the prediction model, in this embodiment, after each piece of known information is converted into a feature matrix form, the feature matrix form is used as a sample to perform training:
word segmentation is carried out on the known information aiming at each piece of the known information; for example, jieba (i.e., a Python chinese word segmentation component) may be used to implement word segmentation, and data cleaning may be performed after word segmentation to remove stop words.
Calculating the weight of each word relative to the known information, matching all the words of the known information with preset feature words, and selecting a first preset number of feature words from the successfully matched feature words according to the order of the weight from high to low; for example, a TF-IDF evaluation function may be used to calculate the weight of each word for the known information, as shown in fig. 2, if 1000 feature words are used, then 1000 feature words are calculated for the known information, all the feature words of the known information are matched with preset feature words, a first preset number of feature words are selected from the successfully matched feature words according to the order of the weight from large to small, and the preset feature words may be feature words related to a plurality of foreign exchange extracted based on the historical foreign exchange information, for example, may include feature words such as dollars, japanese, united states, japan, bottom, a strand, lifting, foreign exchange, walking, market, bounces, downslide, callback, concussion, policies, resuscitations, economy, strategies, high-order, resistance, support, index, trade, situation, difficulty weight, shedding, refuge, investor, emotion, and the like.
Respectively calculating expected cross entropy of each feature word in the first preset number of feature words for the known information, and selecting a second preset number of feature words according to the order from the big to the small of the expected cross entropy, wherein the second preset number is smaller than or equal to the first preset number;
performing dimension reduction processing on a matrix formed by the second preset number of feature words and the corresponding weights by adopting a principal component analysis method, and taking the output third preset number of feature words and the corresponding values as the feature matrix of the known information, wherein the third preset number is smaller than or equal to the second preset number; for example, a principal component analysis (i.e., PCA) is used to perform a dimension reduction process on a matrix composed of a second preset number of feature words and corresponding weights thereof, and a third preset number of feature words and corresponding values are output, where the third preset number of feature words and corresponding values are feature matrices of the known information, and the feature matrices can closely and accurately express or represent the known information.
In specific implementation, the specific values of the first preset number, the second preset number and the third preset number can be adjusted appropriately according to the accuracy of the prediction model obtained through training until the accuracy of the prediction model meets the requirement.
In the implementation, after the feature matrix corresponding to each piece of known information is obtained, the feature matrix corresponding to each piece of known information and the corresponding heat product are used as samples to train to obtain a prediction model, 80% of the samples can be used for training the model, and 20% of the samples can be used for testing the model.
In the specific implementation, the predictive model is obtained through training, after the foreign exchange information in the current preset time length is arranged into one piece of information, one piece of information is converted into a feature matrix form, the feature matrix is input into the predictive model, the predictive model can output the heat products in the next preset time length corresponding to the information in the current preset time length, the purpose that the heat products in the next preset time length can be predicted is achieved, and then the related information of the heat products is pushed to a user.
In specific implementation, the related information of the hot product may include information such as a name of the hot product, a product introduction, and the like.
In specific implementation, the value of the preset duration may be determined according to specific requirements, for example, a day, a week, a half month, a month, etc., and in order to embody timeliness and referential of information recommendation, the preset duration may be a week.
In specific implementation, the prediction model may be obtained by training a classifier, a neural network, or other machine training components.
In this embodiment, a process of implementing the method for pushing foreign exchange product information is described in detail, as shown in fig. 3, and the process includes the following steps:
s1: and selecting a plurality of feature words as preset feature words based on the historical foreign exchange information.
30 features are selected from all the history information: dollars, yen, united states, japan, bottom, a-stock, lifting, foreign exchange, walking, marketing, market, rebound, gliding, callback, concussion, policy, resuscitation, economy, strategy, high-end, resistance, support, index, trade, situation, difficulty and weight, unobtainment, risk avoidance, investors, emotion.
S2: the known foreign exchange information in the preset time period is arranged into a piece of known information, and foreign exchange products with the difference value between the transaction quantity and the maximum transaction value in the next preset time period in a preset range are used as heat products corresponding to the known information in the previous preset time period, so that information marking is realized.
For example, integrating all information into one piece of information according to the release time of the information, finding the number of times of exchanges corresponding to foreign exchange products such as dollars/yen, pound/dollars, euro/dollars and the like of the next week, and labeling a piece of known information corresponding to each week: the labels corresponding to the seven hot product cases of dollars/yen, pound/dollar, euro/dollar, dollar/yen and pound/dollar, dollar/yen and euro/dollar, pound/dollar and euro/dollar, dollar/yen and pound/dollar and euro/dollar are respectively abbreviated as A, B, C, D, E, F, G.
S3: converting each piece of known information into a feature matrix form;
data cleaning: and (3) segmenting the text by using jieba for each piece of known information after marking and deactivating the text.
S4: feature extraction
The characteristics of the cleaned data are extracted by the following two methods:
(1)TF-IDF
calculating the weight of each word relative to the known information by using a TF-IDF evaluation function, matching all the words of the known information with preset feature words, and selecting a first preset number of feature words from the successfully matched feature words according to the order of the weight from large to small, for example, selecting the first 25 (i.e. the first preset number) feature words according to the order of the weight from large to small.
(2) Expected cross entropy
And respectively calculating expected cross entropy of each feature word in the first preset number of feature words for the known information by using an expected cross entropy evaluation function, and selecting a second preset number of feature words according to the order from the large expected cross entropy to the small expected cross entropy, for example, selecting the first 20 (namely the second preset number) feature words in the 25 feature words according to the order from the large expected cross entropy to the small expected cross entropy.
S5: dimension reduction treatment
And performing dimension reduction processing on a matrix formed by the second preset number of feature words and corresponding weights by using Principal Component Analysis (PCA), and outputting a third preset number of feature words and corresponding values, wherein 10 feature words and corresponding values are reserved finally.
S6: training and optimizing model
And using a decision tree classification algorithm, taking a feature matrix corresponding to each piece of known information and a corresponding heat product as a sample training model, using 80% of sample data training models, using 20% of sample data to test the correctness of the model, and continuously optimizing to finally obtain a model with higher correctness.
S7: predictive heat product
Acquiring information of the current week, converting the information into a feature matrix form, inputting a prediction model, outputting a predicted heat product of the next week by the prediction model, such as one of dollars/yen, pound/dollar, euro/dollar, dollar/yen and pound/dollar, dollar/yen and euro/dollar, pound/dollar and euro/dollar, dollar/yen and pound/dollar and euro/dollar.
S8: product information recommendation
After the client opens the foreign exchange product APP, the relevant information of the hot product output by the model is pushed to the client in a message mode.
The pushing method of the information of the foreign exchange products realizes the training of the prediction model based on the information and combining with the foreign exchange products with higher historical transaction amount, and the relevant information of the hot products is recommended to the clients after the hot products are predicted by the prediction model, unlike the pushing method of the related product information based on the attribute of the financial products or the behavior characteristics of the users in the prior art.
In this embodiment, a computer device is provided, as shown in fig. 4, including a memory 402, a processor 404, and a computer program stored in the memory and capable of running on the processor, where the processor implements the method for pushing the foreign exchange product information.
In particular, the computer device may be a computer terminal, a server or similar computing means.
In this embodiment, a computer readable storage medium is provided, where a computer program for executing the pushing method of the foreign exchange product information of any of the above is stored.
In particular, computer-readable storage media, including both permanent and non-permanent, removable and non-removable media, may be used to implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer-readable storage media include, but are not limited to, phase-change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable storage media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
Based on the same inventive concept, the embodiment of the application also provides a pushing device for the foreign exchange product information, as described in the following embodiment. Because the principle of the foreign exchange product information pushing device for solving the problem is similar to that of the foreign exchange product information pushing method, the implementation of the foreign exchange product information pushing device can refer to the implementation of the foreign exchange product information pushing method, and the repetition is omitted. As used below, the term "unit" or "module" may be a combination of software and/or hardware that implements the intended function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
Fig. 5 is a block diagram of a structure of a device for pushing foreign exchange product information according to an embodiment of the present application, as shown in fig. 5, the device includes:
the information processing module 502 is configured to sort the foreign exchange information in the current preset duration into a piece of information;
the prediction module 504 is configured to input the information into a prediction model, where the prediction model outputs a heat product in the preset duration corresponding to the information, where the prediction model is obtained by training using known information and a corresponding heat product as samples, and the heat product is determined according to the transaction quantity condition;
and the information pushing module 506 is configured to push information about the hot product corresponding to the information.
In one embodiment, further comprising:
the training module is used for sorting the known foreign exchange information in the preset time length into a piece of known information; taking the foreign exchange product with the difference value between the transaction quantity and the maximum transaction value in the preset time period as a heat product corresponding to the known information in the preset time period; and converting each piece of known information into a feature matrix form, and training a feature matrix corresponding to each piece of known information and a corresponding heat product as samples to obtain the prediction model.
In one embodiment, the training module is further configured to word each piece of known information; calculating the weight of each word relative to the known information, matching all the words of the known information with preset feature words, and selecting a first preset number of feature words from the successfully matched feature words according to the order of the weight from high to low; respectively calculating expected cross entropy of each feature word in the first preset number of feature words for the known information, and selecting a second preset number of feature words according to the order from the big to the small of the expected cross entropy, wherein the second preset number is smaller than or equal to the first preset number; and performing dimension reduction processing on a matrix formed by the second preset number of feature words and the corresponding weights by adopting a principal component analysis method, and taking the output third preset number of feature words and the corresponding values as the feature matrix of the known information, wherein the third preset number is smaller than or equal to the second preset number.
In one embodiment, the preset time period is one week.
The embodiment of the application realizes the following technical effects: the prediction model is provided, the prediction model is obtained by training known information and corresponding heat products as samples, after the foreign exchange information in the current preset duration is arranged into one piece of information, the one piece of information is input into the prediction model, the prediction model can output the heat product in the next preset duration corresponding to the information, namely, the heat product in the next preset duration can be predicted based on the foreign exchange information in the current preset duration, and further, the related information of the heat product corresponding to the predicted information is pushed to a user.
It will be apparent to those skilled in the art that the modules or steps of the embodiments of the application described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may alternatively be implemented in program code executable by computing devices, so that they may be stored in a storage device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than what is shown or described, or they may be separately fabricated into individual integrated circuit modules, or a plurality of modules or steps in them may be fabricated into a single integrated circuit module. Thus, embodiments of the application are not limited to any specific combination of hardware and software.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, and various modifications and variations can be made to the embodiments of the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (6)
1. The pushing method of the foreign exchange product information is characterized by comprising the following steps:
the foreign exchange information in the current preset duration is arranged into information;
inputting the information into a prediction model, and outputting a heat product in the next preset time period corresponding to the information by the prediction model, wherein the prediction model is obtained by training with known information and corresponding heat products as samples, and the heat products are determined according to the transaction quantity condition;
pushing relevant information of the heat product corresponding to the information;
the method for obtaining the prediction model by training the known information and the corresponding heat product information as samples comprises the following steps:
the known foreign exchange information in the preset time length is arranged into a piece of known information;
taking the foreign exchange product with the difference value between the transaction quantity and the maximum transaction value in the preset time period as a heat product corresponding to the known information in the preset time period;
converting each piece of known information into a feature matrix form, and training a feature matrix corresponding to each piece of known information and a corresponding heat product as a sample to obtain a prediction model;
wherein converting each piece of known information into a feature matrix form includes:
word segmentation is carried out on the known information aiming at each piece of the known information;
calculating the weight of each word relative to the known information, matching all the words of the known information with preset feature words, and selecting a first preset number of feature words from the successfully matched feature words according to the order of the weight from high to low;
respectively calculating expected cross entropy of each feature word in the first preset number of feature words for the known information, and selecting a second preset number of feature words according to the order from the big to the small of the expected cross entropy, wherein the second preset number is smaller than or equal to the first preset number;
and performing dimension reduction processing on a matrix formed by the second preset number of feature words and the corresponding weights by adopting a principal component analysis method, and taking the output third preset number of feature words and the corresponding values as the feature matrix of the known information, wherein the third preset number is smaller than or equal to the second preset number.
2. The method for pushing information of foreign exchange products according to claim 1, wherein the preset duration is one week.
3. A push device for foreign exchange product information, comprising:
the information processing module is used for sorting the foreign exchange information in the current preset duration into information;
the prediction module is used for inputting the information into a prediction model, and outputting a heat product in the next preset duration corresponding to the information by the prediction model, wherein the prediction model is obtained by training a sample of the known information and the corresponding heat product, and the heat product is determined according to the transaction quantity condition;
the information pushing module is used for pushing the related information of the heat product corresponding to the information;
further comprises:
the training module is used for sorting the known foreign exchange information in the preset time length into a piece of known information; taking the foreign exchange product with the difference value between the transaction quantity and the maximum transaction value in the preset time period as a heat product corresponding to the known information in the preset time period; converting each piece of known information into a feature matrix form, and training a feature matrix corresponding to each piece of known information and a corresponding heat product as a sample to obtain a prediction model;
the training module is further used for word segmentation of the known information aiming at each piece of the known information; calculating the weight of each word relative to the known information, matching all the words of the known information with preset feature words, and selecting a first preset number of feature words from the successfully matched feature words according to the order of the weight from high to low; respectively calculating expected cross entropy of each feature word in the first preset number of feature words for the known information, and selecting a second preset number of feature words according to the order from the big to the small of the expected cross entropy, wherein the second preset number is smaller than or equal to the first preset number; and performing dimension reduction processing on a matrix formed by the second preset number of feature words and the corresponding weights by adopting a principal component analysis method, and taking the output third preset number of feature words and the corresponding values as the feature matrix of the known information, wherein the third preset number is smaller than or equal to the second preset number.
4. The device for pushing information of a foreign exchange product as claimed in claim 3, wherein the predetermined period of time is one week.
5. 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 pushing the foreign exchange product information according to any of claims 1 to 2 when the computer program is executed.
6. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when executed by a processor, implements the method of pushing foreign exchange product information according to any one of claims 1 to 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011050631.6A CN112132690B (en) | 2020-09-29 | 2020-09-29 | Method and device for pushing foreign exchange product information, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011050631.6A CN112132690B (en) | 2020-09-29 | 2020-09-29 | Method and device for pushing foreign exchange product information, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112132690A CN112132690A (en) | 2020-12-25 |
| CN112132690B true CN112132690B (en) | 2023-10-27 |
Family
ID=73844742
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011050631.6A Active CN112132690B (en) | 2020-09-29 | 2020-09-29 | Method and device for pushing foreign exchange product information, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112132690B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113159959A (en) * | 2021-05-20 | 2021-07-23 | 中国银行股份有限公司 | Foreign exchange product recommendation method and device |
| CN118075347B (en) * | 2024-04-24 | 2024-08-06 | 杭州高能云科技有限公司 | Information data pushing method, system and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106991609A (en) * | 2016-01-21 | 2017-07-28 | 阿里巴巴集团控股有限公司 | The recommendation method and apparatus of investment product |
| CN108665355A (en) * | 2018-05-18 | 2018-10-16 | 深圳壹账通智能科技有限公司 | Financial product recommends method, apparatus, equipment and computer storage media |
| CN110517150A (en) * | 2019-08-29 | 2019-11-29 | 中国银行股份有限公司 | The generation method and device of money market product transaction reporting |
| CN110517149A (en) * | 2019-08-29 | 2019-11-29 | 中国银行股份有限公司 | The method and device of financial market machining information is pushed to user |
| CN110704603A (en) * | 2019-09-12 | 2020-01-17 | 武汉灯塔之光科技有限公司 | Method and device for discovering current hot event through information |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140122174A1 (en) * | 2012-10-31 | 2014-05-01 | Ncr Corporation | Techniques for forecasting retail activity |
-
2020
- 2020-09-29 CN CN202011050631.6A patent/CN112132690B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106991609A (en) * | 2016-01-21 | 2017-07-28 | 阿里巴巴集团控股有限公司 | The recommendation method and apparatus of investment product |
| CN108665355A (en) * | 2018-05-18 | 2018-10-16 | 深圳壹账通智能科技有限公司 | Financial product recommends method, apparatus, equipment and computer storage media |
| CN110517150A (en) * | 2019-08-29 | 2019-11-29 | 中国银行股份有限公司 | The generation method and device of money market product transaction reporting |
| CN110517149A (en) * | 2019-08-29 | 2019-11-29 | 中国银行股份有限公司 | The method and device of financial market machining information is pushed to user |
| CN110704603A (en) * | 2019-09-12 | 2020-01-17 | 武汉灯塔之光科技有限公司 | Method and device for discovering current hot event through information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112132690A (en) | 2020-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104781837B (en) | System and method for forming predictions using event-based sentiment analysis | |
| CN109657696A (en) | Multitask supervised learning model training, prediction technique and device | |
| JP2019519042A (en) | Method and device for pushing information | |
| CN106296195A (en) | A kind of Risk Identification Method and device | |
| CN112132690B (en) | Method and device for pushing foreign exchange product information, computer equipment and storage medium | |
| WO2015112989A1 (en) | Obtaining social relationship type of network subjects | |
| US10671926B2 (en) | Method and system for generating predictive models for scoring and prioritizing opportunities | |
| CN113656699B (en) | User feature vector determining method, related equipment and medium | |
| WO2021177897A1 (en) | Systems and methods for machine numeracy | |
| CN116109373A (en) | Recommendation method and device for financial products, electronic equipment and medium | |
| CN112434884A (en) | Method and device for establishing supplier classified portrait | |
| CN111241258A (en) | Data cleaning method and device, computer equipment and readable storage medium | |
| CN107958346A (en) | The recognition methods of abnormal behaviour and device | |
| CN111538909A (en) | Information recommendation method and device | |
| US20210349920A1 (en) | Method and apparatus for outputting information | |
| CN109344255B (en) | Label filling method and terminal equipment | |
| CN112434862B (en) | Method and device for predicting financial dilemma of marketing enterprises | |
| CN111767474A (en) | Method and equipment for constructing user portrait based on user operation behaviors | |
| CN113554448A (en) | User loss prediction method and device and electronic equipment | |
| CN113849618B (en) | Strategy determination method and device based on knowledge graph, electronic equipment and medium | |
| US20210133853A1 (en) | System and method for deep learning recommender | |
| CN114741501A (en) | Public opinion early warning method and device, readable storage medium and electronic equipment | |
| CN113284027A (en) | Method for training group recognition model, and method and device for recognizing abnormal group | |
| CN114066513A (en) | User classification method and device | |
| CN113934894A (en) | Data display method based on index tree and terminal equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |