CN116756425A - Financial website recommendation method and device and financial website recommendation model training method - Google Patents
Financial website recommendation method and device and financial website recommendation model training method Download PDFInfo
- Publication number
- CN116756425A CN116756425A CN202310748214.6A CN202310748214A CN116756425A CN 116756425 A CN116756425 A CN 116756425A CN 202310748214 A CN202310748214 A CN 202310748214A CN 116756425 A CN116756425 A CN 116756425A
- Authority
- CN
- China
- Prior art keywords
- account
- financial
- website
- information
- recommendation model
- 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
- 238000012549 training Methods 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000012795 verification Methods 0.000 claims description 34
- 238000004590 computer program Methods 0.000 claims description 22
- 230000004044 response Effects 0.000 claims description 9
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 230000006399 behavior Effects 0.000 description 6
- 238000007726 management method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Development Economics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a financial website recommendation method and device and a financial website recommendation model training method, and relates to the technical field of artificial intelligence. The method comprises the following steps: responding to a website searching instruction of a website account to be recommended in a financial application program, and acquiring account identification information of the website account to be recommended; inputting account identification information into a pre-trained financial website recommendation model, and acquiring website recommendation results of accounts of the website to be recommended through the financial website recommendation model; the financial website recommendation model is obtained through training of first sample information sent by a financial server and second sample information sent by a map application server; the first sample information is used for representing the financial portrait characteristic information, and the second sample information is used for representing the map characteristic information; and returning the website recommendation result to the financial application program of the website account to be recommended. By adopting the method, the accuracy of recommending the financial website to the website account to be recommended can be improved.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a financial website recommendation method and device and a financial website recommendation model training method.
Background
With the further development of big data, importance of data privacy and security has become a worldwide trend, and each time public data leakage will be a great concern for media and public. The requirements for data security and privacy protection are strict in the face of the increasing strictness of user data privacy and security management, especially in the financial industry, which brings unprecedented challenges to the artificial intelligence field. The financial institutions and other industry institutions cannot share data, so that the value of the data is greatly weakened.
At present, the navigation of the electronic map can only recommend the user to go to the nearby financial website according to the geographical position of the user and the position information of the financial website, but the recommended website can not meet the business requirement of the user due to the fact that the user cannot know the actual requirements of the user. In the existing method, the accuracy of the recommendation method for recommending the financial website through electronic map navigation is low.
Disclosure of Invention
Based on this, it is necessary to provide a financial website recommendation method and device and a financial website recommendation model training method capable of improving the accuracy of the financial website recommendation in order to solve the above technical problems.
In a first aspect, the present application provides a financial website recommendation method, the method comprising:
Responding to a website searching instruction of a website account to be recommended in a financial application program, and acquiring account identification information of the website account to be recommended;
inputting account identification information into a pre-trained financial website recommendation model, and acquiring website recommendation results of accounts of the website to be recommended through the financial website recommendation model; the financial website recommendation model is obtained through training of first sample information sent by a financial server and second sample information sent by a map application server; the first sample information is used for representing the financial portrait characteristic information, and the second sample information is used for representing the map characteristic information;
and returning the website recommendation result to the financial application program of the website account to be recommended.
In one embodiment, acquiring the website recommendation result of the website account to be recommended through the financial website recommendation model includes:
acquiring first account characteristic information sent by a financial server and second account characteristic information sent by a map application server through a financial website recommendation model; the first account feature information is used for representing the financial portrait feature information, and the second account feature information is used for representing the map feature information;
acquiring first account characteristic information associated with the account identification information from the first account characteristic information, and acquiring second account characteristic information associated with the account identification information from the second account characteristic information;
Obtaining account characteristic information associated with the website to be recommended account according to the first account characteristic information associated with the account identification information and the second account characteristic information associated with the account identification information;
and acquiring a website recommendation result of the website account to be recommended according to the account characteristic information associated with the website account to be recommended.
In one embodiment, obtaining the account feature information associated with the website to be recommended account according to the first account feature information associated with the account identification information and the second account feature information associated with the account identification information includes:
acquiring a first hash value of first account feature information associated with account identification information, and acquiring a second hash value of second account feature information associated with the account identification information;
and aligning the first account characteristic information associated with the account identification information and the second account characteristic information associated with the account identification information based on the first hash value and the second hash value to obtain account characteristic information associated with the account of the website to be recommended.
In one embodiment, before entering account identification information into the pre-trained financial website recommendation model, the method comprises:
Encrypting the account identification information to obtain encrypted account identification information;
inputting account identification information into a pre-trained financial website recommendation model, comprising:
and inputting the encrypted account identification information into a pre-trained financial website recommendation model.
In a second aspect, the present application provides a method for training a recommendation model of a financial website, the method comprising:
acquiring first sample information sent by a financial server and second sample information sent by a map application server; the first sample information is used for representing the financial portrait characteristic information; the second sample information is used for representing map feature information;
according to the first sample information and the second sample information, acquiring account characteristic information associated with a sample account, and acquiring an actual access result of the sample account for a financial website, wherein the actual access result is sent by a financial server;
inputting the account characteristic information into a financial website recommendation model to be trained, and obtaining a predicted access result of the sample account for the financial website through the financial website recommendation model;
and training the financial website recommendation model according to the difference between the predicted access result and the actual access result to obtain the trained financial website recommendation model.
In one embodiment, after obtaining the trained financial website recommendation model, the method further includes:
obtaining model verification information for performing model tuning on the trained financial website recommendation model from the account characteristic information;
and inputting the model verification information into a financial website recommendation model, and performing model tuning on the financial website recommendation model by using an actual access result.
In one embodiment, obtaining model verification information for model tuning of a trained financial website recommendation model includes:
splitting account characteristic information according to a preset information splitting proportion to obtain model verification information and model training information for training a financial website recommendation model;
inputting the account feature information into a financial website recommendation model to be trained, comprising:
and inputting the model training information into a financial website recommendation model to be trained.
In a third aspect, the present application also provides a financial website recommendation device, including:
the searching instruction response module is used for responding to the website searching instruction of the website account to be recommended in the financial application program and acquiring account identification information of the website account to be recommended;
The website recommendation result acquisition module is used for inputting account identification information into a pre-trained financial website recommendation model and acquiring website recommendation results of website accounts to be recommended through the financial website recommendation model; the financial website recommendation model is obtained through training of first sample information sent by a financial server and second sample information sent by a map application server; the first sample information is used for representing the financial portrait characteristic information, and the second sample information is used for representing the map characteristic information;
and the website recommendation result returning module is used for returning the website recommendation result to the financial application program of the website account to be recommended.
In a fourth aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the steps of the method described above when the processor executes the computer program.
In a fifth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the method described above.
In a sixth aspect, the application also provides a computer program product. The computer program product comprising a computer program which, when executed by a processor, implements the steps of the method described above.
According to the financial website recommending method and device and the financial website recommending model training method, account identification information of a website account to be recommended is obtained in response to a website searching instruction of the website account to be recommended in a financial application program; inputting account identification information into a pre-trained financial website recommendation model, and acquiring website recommendation results of accounts of the website to be recommended through the financial website recommendation model; the financial website recommendation model is obtained through training of first sample information sent by a financial server and second sample information sent by a map application server; the first sample information is used for representing the financial portrait characteristic information, and the second sample information is used for representing the map characteristic information; and returning the website recommendation result to the financial application program of the website account to be recommended. Compared with the prior art, the method and the device have the advantages that account identification information of the account of the website to be recommended is input into the pre-trained financial website recommendation model, the financial website recommendation model is obtained through training of the first sample information sent by the financial server and the second sample information sent by the map application server, and the website recommendation result aiming at the account of the website to be recommended is obtained through the financial website recommendation model, so that the accuracy of recommending the financial website can be improved through training the financial website recommendation model provided by the financial server and the map application server.
Drawings
FIG. 1 is an application environment diagram of a financial website recommendation method in one embodiment;
FIG. 2 is a flow chart of a financial website recommendation method according to an embodiment;
FIG. 3 is a flowchart illustrating a step of obtaining a website recommendation result of a website account to be recommended in one embodiment;
FIG. 4 is a flowchart illustrating steps for obtaining account feature information associated with a website account to be recommended in one embodiment;
FIG. 5 is a flowchart of a method for training a recommendation model of a financial website in one embodiment;
FIG. 6 is a block diagram of a financial website recommendation device in one embodiment;
fig. 7 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The financial website recommendation model training method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the federal learning platform server 104 communicates with the financial server 106 and the map application server 108, respectively. The data storage system may store data that the federal learning platform server 104, the financial server 106, and the map application server 108 need to process. The data storage system may be integrated on a server or may be placed on a cloud or other network server. The financial server may store the first sample information. The map application server may store the second sample information. The federal learning platform server 104, the financial server 106, and the map application server 108 may each be implemented as a stand-alone server or as a server cluster of multiple servers.
In one embodiment, as shown in fig. 2, a financial website recommendation method is provided, and the method is applied to the financial server 106 in fig. 1 for illustration, and includes the following steps:
s202, acquiring account identification information of the website accounts to be recommended in response to a website search instruction of the website accounts to be recommended in the financial application program.
The website account to be recommended can be an account to be recommended by the financial website for the account. The website search instruction refers to an instruction for searching a financial website, wherein the instruction is triggered by a website account to be recommended in a financial application program. The financial application may be an application for managing account resources of an account, or may be an application for performing resource transfers; the financial application may be used to conduct a fusion business for account transactions. The account identification information of the website to be recommended account can be contact information, identity identification information and the like of the corresponding user of the website to be recommended account. The account identification information can be basic information which can be shared by multiple parties, does not relate to account information which needs to be encrypted, and can ensure the security of the account information of the website accounts to be recommended.
S204, inputting account identification information into a pre-trained financial website recommendation model, and acquiring website recommendation results of accounts of the website to be recommended through the financial website recommendation model; the financial website recommendation model is obtained through training of first sample information sent by a financial server and second sample information sent by a map application server; the first sample information is used for representing the financial portrait characteristic information, and the second sample information is used for representing the map characteristic information.
The financial website recommendation model may be a model for making financial website recommendations. The website recommendation result may be a website that is recommended for the website account to be recommended. The financial server may be a server corresponding to a financial management institution, which may perform a resource exchange business. The first sample information characterizes financial portrait characteristic information, which may be, for example, a financial virtual resource, a financial resource product, or the like. The first sample information may include account identification information of the sample account, e.g., the account identification information may be contact information, identification information, etc. of the user. The map application server may be a server to which the map application program corresponds. The map application may be a map application or an applet in the software. The second sample information characterizes feature information of the map, for example, the feature information of the map may be historical behavior record information of the account, and the historical behavior record information may include historical place searching information, frequently-going financial website information and collection information of the account for the financial website.
S206, returning the website recommendation result to the financial application program of the website account to be recommended.
Illustratively, the financial server 106 may obtain account identification information of the recommended site account to be triggered in response to a site search instruction of the site account to be recommended in the financial application. The financial server 106 may invoke the financial website recommendation model stored on the federal learning platform server 104, and the financial server 106 may input account identification information of the website account to be recommended into the pre-trained financial website recommendation model, and obtain website recommendation results of the website account to be recommended through the financial website recommendation model. The financial server 106 may return the website recommendation results to the financial application of the website account to be recommended.
In the embodiment, account identification information of a website account to be recommended is obtained in response to a website search instruction of the website account to be recommended in a financial application program; inputting account identification information into a pre-trained financial website recommendation model, and acquiring website recommendation results of accounts of the website to be recommended through the financial website recommendation model; the financial website recommendation model is obtained through training of first sample information sent by a financial server and second sample information sent by a map application server; the first sample information is used for representing the financial portrait characteristic information, and the second sample information is used for representing the map characteristic information; and returning the website recommendation result to the financial application program of the website account to be recommended. Compared with the prior art, the method and the device have the advantages that account identification information of the account of the website to be recommended is input into the pre-trained financial website recommendation model, the financial website recommendation model is obtained through training of the first sample information sent by the financial server and the second sample information sent by the map application server, and the website recommendation result aiming at the account of the website to be recommended is obtained through the financial website recommendation model, so that the accuracy of recommending the financial website can be improved through training the financial website recommendation model provided by the financial server and the map application server.
In one embodiment, as shown in fig. 3, obtaining, by a financial website recommendation model, a website recommendation result of a website account to be recommended includes:
s302, acquiring first account characteristic information sent by a financial server and second account characteristic information sent by a map application server through a financial website recommendation model; the first account feature information is used for characterizing financial portrait feature information and the second account feature information is used for characterizing map feature information.
Wherein the second account feature information characterizes financial portrait feature information, e.g., financial virtual resources, financial resource products, etc. The second account characteristic information may include account identification information of the website account to be recommended, for example, the account identification information may be contact information, identity information, and the like of the user. The second account feature information characterizes feature information of the map, for example, the feature information of the map may be historical behavior record information of the website to be recommended, and the historical behavior record information may include historical place search information of the website to be recommended, frequently-used financial website information of the website to be recommended, and collection information of the website to be recommended for the financial website.
S304, acquiring first account characteristic information associated with the account identification information from the first account characteristic information, and acquiring second account characteristic information associated with the account identification information from the second account characteristic information.
S306, obtaining account characteristic information associated with the account of the website to be recommended according to the first account characteristic information associated with the account identification information and the second account characteristic information associated with the account identification information.
S308, acquiring a website recommendation result of the website account to be recommended according to the account characteristic information associated with the website account to be recommended.
For example, contact information corresponding to a website account to be recommended may be obtained for the website account to be recommended, and the first account feature information associated with the website account to be recommended and the second account feature information associated with the website account to be recommended are respectively obtained through the contact information. And aligning the first account characteristic information and the second account characteristic information with the same contact information based on the contact information corresponding to the website accounts to be recommended. And obtaining account characteristic information associated with the website account to be recommended according to the first account characteristic information and the second account characteristic information with the same contact information. For example, the first account feature information and the second account feature information with the same contact information may be combined to obtain account feature information associated with the website account to be recommended. Further, the financial website with the highest matching degree with the account characteristic information can be used as a website recommendation result of the website account to be recommended. The highest matching degree can be understood as that the financial website recommendation model predicts the financial website with the highest account access probability of the website to be recommended.
In this embodiment, first account feature information sent by a financial server and second account feature information sent by a map application server are obtained through a financial website recommendation model, first sample information associated with account identification information is obtained from the first sample information, second sample information associated with account identification information is obtained from the second sample information, account feature information associated with a sample account is obtained according to the first sample information associated with the account identification information and the second sample information associated with the account identification information, and a website recommendation result of a website account to be recommended is obtained according to the account feature information associated with the website account to be recommended. Therefore, the accuracy of acquiring the website recommendation result of the website account to be recommended can be ensured, and the accuracy of recommending the financial website for the website account to be recommended is improved.
In one embodiment, as shown in fig. 4, obtaining the account feature information associated with the website to be recommended account according to the first account feature information associated with the account identification information and the second account feature information associated with the account identification information includes:
s402, acquiring a first hash value of first account feature information associated with account identification information, and acquiring a second hash value of second account feature information associated with the account identification information;
S404, aligning the first account characteristic information associated with the account identification information and the second account characteristic information associated with the account identification information based on the first hash value and the second hash value to obtain account characteristic information associated with the website account to be recommended.
The hash value may be a value calculated by a hash algorithm.
The first account feature information and the second account feature information can be subjected to privacy intersection through a hash algorithm based on account identification information corresponding to the website accounts to be recommended, so that the first account feature information and the second account feature information are aligned, and encryption of the aligned first account feature information and second account feature information can be achieved through privacy intersection, so that encrypted account feature information is obtained. The encrypted account feature information may be used as account feature information associated with the website account to be recommended.
In this embodiment, a first hash value of first account feature information associated with account identification information is obtained, and a second hash value of second account feature information associated with account identification information is obtained; and aligning the first account characteristic information associated with the account identification information and the second account characteristic information associated with the account identification information based on the first hash value and the second hash value to obtain account characteristic information associated with the account of the website to be recommended. In this way, the security of the account information respectively stored by the financial server 106 and the map application server 108 can be ensured, and the accuracy of recommending the financial website for the account of the website to be recommended can be improved.
In one embodiment, before entering account identification information into the pre-trained financial website recommendation model, the method comprises:
encrypting the account identification information to obtain encrypted account identification information;
inputting account identification information into a pre-trained financial website recommendation model, comprising:
and inputting the encrypted account identification information into a pre-trained financial website recommendation model.
Illustratively, the financial server 106 may encrypt the account identification information to obtain encrypted account identification information. And the financial server 106 may input the encrypted account identification information into a pre-trained financial website recommendation model. The website recommendation result of the website account to be recommended is obtained through the financial website recommendation model, and the financial server 106 can return the website recommendation result to the financial application program of the website account to be recommended.
In this embodiment, the account identification information is encrypted to obtain encrypted account identification information, and the encrypted account identification information is input into a pre-trained financial website recommendation model. Thus, the security of account information can be improved.
In one embodiment, as shown in fig. 5, a method for training a recommendation model of a financial website is provided, and the method is applied to the federal learning platform server 104 in fig. 1 for illustration, and includes the following steps:
S502, acquiring first sample information sent by a financial server and second sample information sent by a map application server; the first sample information is used for representing the financial portrait characteristic information; the second sample information is used to characterize map feature information.
The financial server can be a server corresponding to a financial management institution, and the financial management institution can conduct resource exchange business. The first sample information characterizes financial portrait characteristic information, which may be, for example, a financial virtual resource, a financial resource product, or the like. The first sample information may include account identification information of the sample account, e.g., the account identification information may be contact information, identification information, etc. of the user. The map application server may be a server to which the map application program corresponds. The map application may be a map application or an applet in the software. The second sample information characterizes feature information of the map, for example, the feature information of the map may be historical behavior record information of the account, and the historical behavior record information may include historical place searching information, frequently-going financial website information and collection information of the account for the financial website.
Illustratively, the federal learning platform server 104 may issue instructions for sample information collection to the financial server 106 and the map application server 108, respectively. The financial server 106 transmits financial portrait character information and the map application server 108 transmits map character information. The federal learning platform server 104 receives the financial portrait character information transmitted from the financial server 106 and the map character information transmitted from the map application server 108.
S504, according to the first sample information and the second sample information, acquiring account characteristic information associated with the sample account, and acquiring an actual access result of the sample account for the financial network point, wherein the actual access result is sent by the financial server.
The sample account may be an account for conducting a financial website recommendation model. The model training of federal learning can be performed on the financial website recommendation model by using the sample account and the actual access result corresponding to the sample account. The actual access result refers to the website result that the user who owns the sample account actually accesses. The account feature information may be sample feature information for model training.
Illustratively, the federal learning platform server 104 may align the first sample information with the second sample information by the same information features in the first sample information and the second sample information. The account feature information associated with the sample account is feature information associated with the sample account, for example, the feature information may be contact information of the sample account, and the first sample information and the second sample information may be aligned through the contact information of the sample account. And obtaining account characteristic information associated with the sample account through the first sample information and the second sample information after the information alignment. The federal learning platform server 104 can also obtain actual financial site access results for the sample account for the financial site sent by the financial server 106.
S506, inputting the account characteristic information into a financial website recommendation model to be trained, and obtaining a predicted access result of the sample account for the financial website through the financial website recommendation model.
The financial website recommendation model may be a model for making financial website recommendations.
Illustratively, the federal learning platform server 104 may input account feature information into a financial website recommendation model, through which a predicted access result of the sample account to the financial website is predicted. Further, the financial website recommendation model can be trained by using the predicted access result of the sample account to the financial website and the actual access result of the sample account to the financial website, so as to obtain the trained financial website recommendation model.
And S508, training the financial website recommendation model according to the difference between the predicted access result and the actual access result to obtain the trained financial website recommendation model.
Illustratively, the federal learning platform server 104 may obtain a loss value between the predicted access result and the actual access result according to a loss function preset for the financial website recommendation model, and perform iterative training on the financial website recommendation model through the loss value, so that model parameters of the financial website recommendation model can meet preset model parameter conditions, and obtain a trained financial website recommendation model.
In the practical application process, the federal learning modeling of the financial website recommendation model can be developed by utilizing the LightGBM algorithm, and the financial website recommendation model can be stored in a financial federal learning platform node in a ciphertext mode for subsequent recommendation of the financial website of the account.
Further, the training completed financial website recommendation model can be utilized to recommend financial website to the account, so that accuracy of recommending financial website can be improved.
In this embodiment, first sample information sent by a financial server and second sample information sent by a map application server are obtained; the first sample information is used for representing the financial portrait characteristic information; the second sample information is used for representing map feature information; according to the first sample information and the second sample information, acquiring account characteristic information associated with a sample account, and acquiring an actual access result of the sample account for a financial website, wherein the actual access result is sent by a financial server; inputting the account characteristic information into a financial website recommendation model to be trained, and obtaining a predicted access result of the sample account for the financial website through the financial website recommendation model; and training the financial website recommendation model according to the difference between the predicted access result and the actual access result to obtain the trained financial website recommendation model. Compared with the traditional technology, the embodiment performs federal learning through the account feature information acquired from the financial server and the map application server, and can fuse the feature information of the financial server and the map application server to perform financial website recommendation, so that the accuracy of a financial website recommendation model can be improved.
In one embodiment, after obtaining the trained financial website recommendation model, the method further comprises:
obtaining model verification information for performing model tuning on the trained financial website recommendation model from the account characteristic information;
and inputting the model verification information into a financial website recommendation model, and performing model tuning on the financial website recommendation model by using an actual access result.
The model verification information refers to information for performing model tuning on the trained financial website recommendation model.
Illustratively, the federal learning platform server 104 may input the model verification information into the trained financial website recommendation model, predict and obtain the verification access result of the model verification information of the sample account to the financial website through the financial website recommendation model, and perform model tuning on the financial website recommendation model by using the actual access result of the sample account to the financial website and the verification access result of the sample account to the financial website so as to obtain a financial website recommendation model with more accurate prediction recommendation result.
In the actual application process, the account characteristic information can be divided into training set information and verification set information according to a preset proportion. For example, the account feature information of the training set and the account feature information of the verification set may be divided into 70% and 30%. The account feature information of the training set is used for training the model, and the account feature information of the verification set is used for verifying the model effect.
In the embodiment, from account feature information, model verification information for performing model tuning on a trained financial website recommendation model is obtained; and inputting the model verification information into a financial website recommendation model, and performing model tuning on the financial website recommendation model by using an actual access result. Therefore, the financial website recommendation model can be optimized, and the accuracy of the financial website recommendation model is improved.
In one embodiment, obtaining model verification information for model tuning of a trained financial website recommendation model includes:
splitting account characteristic information according to a preset information splitting proportion to obtain model verification information and model training information for training a financial website recommendation model;
inputting the account feature information into a financial website recommendation model to be trained, comprising:
and inputting the model training information into a financial website recommendation model to be trained.
The information splitting ratio can be a preset splitting ratio for model training aiming at a financial website recommendation model. The account feature information may be sample feature information for model training.
Illustratively, the federal learning platform server 104 may split the account feature information according to a preset information splitting ratio to obtain model verification information and model training information for model training of the financial website recommendation model. Further federal learning platform server 104 can input model training information into the financial website recommendation model to be trained. And, the federal learning platform server 104 can perform model tuning on the financial website recommendation model through the model verification information.
For example, the information splitting ratio set in advance is 70% and 30%. The federal learning platform server 104 may split the account feature information to obtain 30% model verification information and 70% model training information. 70% of model training information is used for recommending models by financial websites, and 30% of model verification information is used for verifying model effects.
In one embodiment, a federal learning-based intelligent recommendation method for a financial website is provided, including:
the electronic map platform has a great amount of historical records of users and account characteristic information lacking in a plurality of financial institutions such as frequently-going website information, and the account characteristic information has good value for recommending users to go to the financial website. According to the embodiment, through a federal learning platform of a financial institution, longitudinal federal learning is adopted to align the account feature information of the electronic map and the financial image feature information of a financial institution user through privacy intersection, a customer feature wide table is formed, and training and release of a financial website recommendation model are performed on the basis. The successfully released financial website recommendation model can be combined with the information of the financial portrait characteristic information of the user at the financial institution and the frequently-removed website of the electronic map and the like to intelligently recommend the names of the financial websites to which the user goes.
The financial institution provides tag data that is processed and downloaded from the data lake corresponding to the financial institution, the tag identifying the financial website name that the customer actually visits, e.g., a financial website, B financial website, C financial website, D financial website, etc.
The financial institution provides the data. The financial institution provides the basic information of the account, the financial virtual resource, the region, the account holding financial institution resource, the resource portrait information of resource products and other relevant characteristic data such as site operation information.
The third party map platform provides relevant features such as historical searching records of the account, frequently-removed network point names of the account, collection network point records of the account and the like.
And the financial server and the map application server use the encrypted account contact information to complete data alignment through a federal learning privacy intersection algorithm, and finally, 10 total tens of thousands of pieces of intersection customer data of the two parties are obtained as training samples.
And (5) splitting data. And splitting the data after privacy intersection, and splitting the account characteristic information to obtain 30% of model verification information and 70% of model training information. 70% of model training information is used for recommending models by financial websites, and 30% of model verification information is used for verifying model effects.
And selecting a LightGBM algorithm to develop longitudinal federal learning on the financial institution federal learning platform so as to complete modeling of a financial website recommendation model, wherein the financial website recommendation model is stored in a financial institution federal learning node in a ciphertext mode and is used for recommending accounts for subsequent financial website.
And predicting by using the financial website recommendation model. When a user searches for a website by using a mobile phone bank, the contact information of the user is encrypted and then transmitted into a website intelligent recommendation model in a federal learning platform, and the model can be combined with the account identification information of the current client in a financial institution, resource portrait information of the financial institution, resource products and the like, and a history search record, an account frequently-going website name and an account collection website record in an electronic map to recommend the user to go to the financial website.
After searching nearby network points in the financial application program row, the financial application program encrypts the contact information reserved by the user and calculates the possible banking network points by using the intelligent point intelligent recommendation model.
In the embodiment, in the prior art, the electronic map can only recommend the user to go to the nearby website according to the historical browsing record of the user and the geographical position of the user, and the user can not know the possible appeal, so that the proper financial website can not be effectively recommended to meet the user demand.
Relying on a federal learning platform of a financial institution to cooperate with an electronic map party, introducing characteristic data lacking in a plurality of financial institutions such as historical browsing records of the electronic map, frequently-going website information and the like, combining customer portrait data of the financial institutions, constructing an intelligent financial website recommendation model on the premise of controllable data safety, breaking the problem of data island in website recommendation scenes, eliminating data gap, promoting data circulation and strengthening industry cooperation. On the other hand, through the joint modeling intelligent website recommendation model, personalized website recommendation service can be provided for clients by effectively combining the customer portrait data of the financial institutions, dynamic management and accurate service of the financial websites are realized, and the interaction rate of each financial website and users is further improved.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a financial website recommendation model training device for realizing the related financial website recommendation model training method. The implementation scheme of the solution provided by the device is similar to the implementation scheme recorded in the above-mentioned financial website recommendation model training method, so the specific limitation in the embodiments of the one or more financial website recommendation model training devices provided below can be referred to the limitation of the financial website recommendation model training method hereinabove, and will not be repeated here.
In one embodiment, as shown in fig. 6, there is provided a financial website recommendation device 600 comprising: a search instruction response module 610, a website recommendation result acquisition module 620, and a website recommendation result return module 630, wherein:
the search instruction response module 610 is configured to obtain account identification information of a website account to be recommended in response to a website search instruction of the website account to be recommended in the financial application program.
The website recommendation result obtaining module 620 is configured to input account identification information into a pre-trained financial website recommendation model, and obtain a website recommendation result of a website account to be recommended through the financial website recommendation model; the financial website recommendation model is obtained through training of first sample information sent by a financial server and second sample information sent by a map application server; the first sample information is used for representing the financial portrait characteristic information, and the second sample information is used for representing the map characteristic information.
The website recommendation result returning module 630 is configured to return the website recommendation result to the financial application program of the website account to be recommended.
In one embodiment, the website recommendation result obtaining module includes a feature information receiving unit, an associated feature information unit, an associated information unit to be recommended, and a website recommendation result determining unit.
The account feature information unit is used for acquiring first account feature information sent by the financial server and second account feature information sent by the map application server through the financial network point recommendation model; the first account feature information is used for characterizing financial portrait feature information and the second account feature information is used for characterizing map feature information. The associated feature information unit is used for acquiring first account feature information associated with the account identification information from the first account feature information and acquiring second account feature information associated with the account identification information from the second account feature information. The information unit to be recommended is used for obtaining the account characteristic information associated with the account of the website to be recommended according to the first account characteristic information associated with the account identification information and the second account characteristic information associated with the account identification information. The website recommendation result determining unit is used for obtaining website recommendation results of the website accounts to be recommended according to the account characteristic information associated with the website accounts to be recommended.
In one embodiment, the to-be-recommended association information unit includes a hash value acquisition unit and an account association feature information unit.
The hash value acquisition unit is used for acquiring a first hash value of first account characteristic information associated with the account identification information and acquiring a second hash value of second account characteristic information associated with the account identification information. The account association characteristic information unit is used for aligning the first account characteristic information associated with the account identification information and the second account characteristic information associated with the account identification information based on the first hash value and the second hash value to obtain account characteristic information associated with the website account to be recommended.
In one embodiment, the financial website recommendation device further includes a basic information encryption module. The basic information encryption module is used for encrypting the account identification information to obtain encrypted account identification information. The model recommendation module is used for inputting the encrypted account identification information into a pre-trained financial website recommendation model.
Based on the same inventive concept, the embodiment of the application also provides a financial website recommendation model training device for realizing the related financial website recommendation model training method. The implementation scheme of the solution provided by the device is similar to the implementation scheme recorded in the above-mentioned financial website recommendation model training method, so the specific limitation in the embodiments of the one or more financial website recommendation model training devices provided below can be referred to the limitation of the financial website recommendation model training method hereinabove, and will not be repeated here.
In one embodiment, a financial website recommendation model training apparatus is provided, comprising: the system comprises a sample information acquisition module, an account feature information acquisition module, a prediction access result acquisition module and a model training module, wherein:
the system comprises a sample information acquisition module, a map application server and a map application server, wherein the sample information acquisition module is used for acquiring first sample information sent by the financial server and second sample information sent by the map application server; the first sample information is used for representing the financial portrait characteristic information; the second sample information is used to characterize map feature information.
The account feature information acquisition module is used for acquiring the account feature information associated with the sample account according to the first sample information and the second sample information, and acquiring an actual access result of the sample account for the financial network point, which is sent by the financial server.
The predicted access result acquisition module is used for inputting the account characteristic information into a financial website recommendation model to be trained, and obtaining a predicted access result of the sample account for the financial website through the financial website recommendation model.
And the model training module is used for training the financial website recommendation model according to the difference between the predicted access result and the actual access result to obtain the trained financial website recommendation model.
In one embodiment, the apparatus further comprises a verification information acquisition module and a model tuning module.
The verification information acquisition module is used for acquiring model verification information for performing model tuning on the trained financial website recommendation model from the account characteristic information. The model tuning module is used for inputting the model verification information into the financial website recommendation model, and performing model tuning on the financial website recommendation model by utilizing the actual access result.
In one embodiment, the verification information acquisition module is configured to split the account feature information according to a preset information splitting ratio to obtain model verification information and model training information for performing model training on a recommendation model of the financial website. The prediction access result acquisition module is used for inputting model training information into the financial website recommendation model to be trained.
The above-mentioned financial website recommendation device and each module in the financial website recommendation model training device may be implemented in whole or in part by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing the first sample information and the second sample information. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by the processor is used for realizing a financial website recommendation model training method and a financial website recommendation method.
It will be appreciated by those skilled in the art that the structure shown in FIG. 7 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (11)
1. A method for recommending a financial website, the method comprising:
responding to a website searching instruction of a website account to be recommended in a financial application program, and acquiring account identification information of the website account to be recommended;
inputting the account identification information into a pre-trained financial website recommendation model, and acquiring website recommendation results of the website accounts to be recommended through the financial website recommendation model; the financial website recommendation model is obtained through training of first sample information sent by a financial server and second sample information sent by a map application server; the first sample information is used for representing the financial portrait characteristic information, and the second sample information is used for representing the map characteristic information;
And returning the website recommendation result to the financial application program of the website account to be recommended.
2. The method of claim 1, wherein the obtaining, by the financial website recommendation model, the website recommendation result for the website account to be recommended comprises:
acquiring first account characteristic information sent by a financial server and second account characteristic information sent by a map application server through the financial website recommendation model; the first account feature information is used for representing the financial portrait feature information, and the second account feature information is used for representing the map feature information;
acquiring first account characteristic information associated with the account identification information from the first account characteristic information, and acquiring second account characteristic information associated with the account identification information from the second account characteristic information;
obtaining account characteristic information associated with the website to be recommended account according to the first account characteristic information associated with the account identification information and the second account characteristic information associated with the account identification information;
and acquiring a website recommendation result of the website account to be recommended according to the account characteristic information associated with the website account to be recommended.
3. The method of claim 2, wherein the obtaining the account feature information associated with the website to be recommended account based on the first account feature information associated with the account identification information and the second account feature information associated with the account identification information comprises:
acquiring a first hash value of first account feature information associated with the account identification information, and acquiring a second hash value of second account feature information associated with the account identification information;
and aligning the first account characteristic information associated with the account identification information and the second account characteristic information associated with the account identification information based on the first hash value and the second hash value to obtain the account characteristic information associated with the account of the website to be recommended.
4. The method of claim 1, wherein prior to entering the account identification information into a pre-trained financial website recommendation model, comprising:
encrypting the account identification information to obtain encrypted account identification information;
the inputting the account identification information into a pre-trained financial website recommendation model comprises the following steps:
And inputting the encrypted account identification information into a pre-trained financial website recommendation model.
5. A method for training a recommendation model of a financial website, the method comprising:
acquiring first sample information sent by a financial server and second sample information sent by a map application server; the first sample information is used for representing the financial portrait characteristic information; the second sample information is used for representing map feature information;
according to the first sample information and the second sample information, acquiring account characteristic information associated with a sample account, and acquiring an actual access result of the sample account for a financial website, wherein the actual access result is sent by the financial server;
inputting the account characteristic information into a financial website recommendation model to be trained, and obtaining a predicted access result of the sample account for the financial website through the financial website recommendation model;
and training the financial website recommendation model according to the difference between the predicted access result and the actual access result to obtain a trained financial website recommendation model.
6. The method of claim 5, further comprising, after the obtaining the trained financial website recommendation model:
Obtaining model verification information for performing model tuning on the trained financial website recommendation model from the account characteristic information;
and inputting the model verification information into the financial website recommendation model, and performing model tuning on the financial website recommendation model by utilizing the actual access result.
7. The method of claim 6, wherein the obtaining model verification information for model tuning of the trained financial website recommendation model comprises:
splitting the account characteristic information according to a preset information splitting proportion to obtain the model verification information and model training information for training a financial website recommendation model;
the step of inputting the account characteristic information into a financial website recommendation model to be trained comprises the following steps:
and inputting the model training information into the financial website recommendation model to be trained.
8. A financial website recommendation device, the device comprising:
the searching instruction response module is used for responding to a website searching instruction of a website account to be recommended in a financial application program and acquiring account identification information of the website account to be recommended;
The website recommendation result acquisition module is used for inputting the account identification information into a pre-trained financial website recommendation model, and acquiring website recommendation results of the website accounts to be recommended through the financial website recommendation model; the financial website recommendation model is obtained through training of first sample information sent by a financial server and second sample information sent by a map application server; the first sample information is used for representing the financial portrait characteristic information, and the second sample information is used for representing the map characteristic information;
and the website recommendation result returning module is used for returning the website recommendation result to the financial application program of the website account to be recommended.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
11. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310748214.6A CN116756425A (en) | 2023-06-25 | 2023-06-25 | Financial website recommendation method and device and financial website recommendation model training method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310748214.6A CN116756425A (en) | 2023-06-25 | 2023-06-25 | Financial website recommendation method and device and financial website recommendation model training method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116756425A true CN116756425A (en) | 2023-09-15 |
Family
ID=87958714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310748214.6A Pending CN116756425A (en) | 2023-06-25 | 2023-06-25 | Financial website recommendation method and device and financial website recommendation model training method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116756425A (en) |
-
2023
- 2023-06-25 CN CN202310748214.6A patent/CN116756425A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110245510B (en) | Method and apparatus for predicting information | |
| US11500992B2 (en) | Trusted execution environment-based model training methods and apparatuses | |
| CN113361962A (en) | Method and device for identifying enterprise risk based on block chain network | |
| CN114579584B (en) | Data table processing method and device, computer equipment and storage medium | |
| CN114547204A (en) | Data synchronization method and device, computer equipment and storage medium | |
| CN115150063A (en) | Model encryption method and device and electronic equipment | |
| CN113221153B (en) | Graph neural network training method and device, computing equipment and storage medium | |
| CN111737764B (en) | Method and device for generating description information | |
| CN116800671A (en) | Data transmission method, apparatus, computer device, storage medium, and program product | |
| CN116756425A (en) | Financial website recommendation method and device and financial website recommendation model training method | |
| CN115758271A (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN113674083A (en) | Internet financial platform credit risk monitoring method, device and computer system | |
| CN116846974A (en) | Service request processing method, device, computer equipment and storage medium | |
| CN117151856A (en) | Resource borrowing service handling method, device, computer equipment and storage medium | |
| CN115905340A (en) | User portrait verification method and device, computer equipment and storage medium | |
| CN117391702A (en) | Account data verification method, account data verification device, computer equipment and storage medium | |
| CN116629377A (en) | Federal learning model training method, apparatus, device, medium and product | |
| CN116150188A (en) | Information query method, device, computer equipment and storage medium | |
| CN115630973A (en) | User data processing method, device, computer equipment and storage medium | |
| CN117149371A (en) | Resource borrowing method, resource borrowing device, computer equipment, storage medium and program product | |
| CN117372001A (en) | Resource transfer method, apparatus, device, storage medium, and program product | |
| CN117078386A (en) | Contract signing method, contract signing device, computer equipment and storage medium | |
| CN116595546A (en) | Data encryption method, device, computer equipment and storage medium | |
| CN117132371A (en) | Method, apparatus, computer device and storage medium for predicting risk tolerance level | |
| CN117240578A (en) | Flow integrity verification method and device, computer equipment and storage medium thereof |
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 |