CN115545353A - Method and device for business wind control, storage medium and electronic equipment - Google Patents
Method and device for business wind control, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN115545353A CN115545353A CN202211508341.0A CN202211508341A CN115545353A CN 115545353 A CN115545353 A CN 115545353A CN 202211508341 A CN202211508341 A CN 202211508341A CN 115545353 A CN115545353 A CN 115545353A
- Authority
- CN
- China
- Prior art keywords
- data
- service
- type
- prediction model
- prediction
- 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.)
- Granted
Links
Images
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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The specification discloses a method, a device, a storage medium and an electronic device for business wind control. Secondly, for each type of data contained in the service data, inputting the type of data into a coding layer corresponding to the type in a pre-trained prediction model to obtain data characteristics corresponding to the type of data. Then, various types of data features are input into the influence determination layer to determine the degree of influence of each type of data on the result output by the prediction model. Then, the influence degree and various types of data characteristics are input into the prediction layer to predict the service class of the service executed by the service provider of the service corresponding to the service data according to the service data, and the service class is used as the prediction class. And finally, carrying out service wind control according to the forecast category and the service category of the provided service appointed by the service provider. The method can reduce the cost of manually checking the data, and improve the accuracy of the prediction category.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for controlling a service profile, a storage medium, and an electronic device.
Background
With the development of internet technology, online transactions such as money transfer and online shopping are more and more common through networks, however, the online transactions through networks bring convenience to users, and meanwhile, certain potential safety hazards also exist, and some merchants may make illegal activities by using their own merchant identities, and even may have the situation of revealing user privacy.
Currently, it is usually determined whether a merchant conducts business activities according to an agreed service category by manually checking order information of the merchant. However, manual review requires a high labor cost and a low accuracy.
Therefore, how to improve the accuracy of determining whether the merchant conducts the operation according to the agreed service category is an urgent problem to be solved.
Disclosure of Invention
The specification provides a method, a device, a storage medium and an electronic device for business wind control, so as to solve the problems that manual auditing requires high labor cost and low accuracy.
The technical scheme adopted by the specification is as follows:
the present specification provides a method for service wind control, including:
acquiring service data, wherein the service data comprises different types of data;
inputting the type of data into a coding layer corresponding to the type in a pre-trained prediction model aiming at each type of data contained in the service data to obtain data characteristics corresponding to the type of data, wherein the prediction model comprises a plurality of coding layers, and different coding layers correspond to different types of data;
inputting various types of data features into an influence determination layer included in the prediction model to determine a degree of influence of each type of data on a result output by the prediction model;
inputting the influence degree and the various data characteristics into a data processing layer in the prediction model, so as to perform data processing on the various data characteristics according to the influence degree to obtain processed characteristics, and inputting the processed characteristics into a prediction layer in the prediction model, so as to predict the service type of a service executed by a service provider of a service corresponding to the service data according to the service data, wherein the service type is used as a prediction type;
and carrying out service wind control according to the forecast type and the service type of the provided service appointed by the service provider.
Optionally, the different types of data included in the service data include: the time sequence data is obtained by sequencing the order data of the service provider according to the time sequence;
for each type of data included in the service data, inputting the type of data into a coding layer corresponding to the type in a pre-trained prediction model to obtain data characteristics corresponding to the type of data, specifically including:
inputting the time sequence data into a coding layer corresponding to the time sequence data in a pre-trained prediction model, and determining business characteristics corresponding to the order data at each moment and a weight corresponding to the order data at each moment, wherein the weight corresponding to the order data at the current moment is greater than the weight corresponding to the order data at the historical moment;
and determining the data characteristics corresponding to the time sequence data according to the business characteristics corresponding to the order data at each moment and the weight corresponding to the order data at each moment.
Optionally, the prediction model includes an influence determination layer corresponding to each type of data feature;
inputting various types of data characteristics into an influence determining layer contained in the prediction model to determine the influence degree of each type of data on a result output by the prediction model, wherein the influence degree specifically comprises the following steps:
and for each type of data characteristic, inputting the type of data characteristic into an influence determination layer corresponding to the type of data characteristic, and determining the influence degree of the type of data on the result output by the prediction model.
Optionally, the prediction model comprises a feature extraction layer;
inputting the influence degree and the various types of data characteristics into a data processing layer in the prediction model, performing data processing on the various types of data characteristics according to the influence degree to obtain processed characteristics, inputting the processed characteristics into a prediction layer in the prediction model to predict the service class of a service executed by a service provider of a service corresponding to the service data according to the service data, and taking the service class as a prediction class, specifically comprising:
splicing various types of data features to obtain splicing features, and inputting the splicing features into the feature extraction layer to perform feature crossing on the splicing features to obtain fusion features;
and inputting the influence degree and the various types of data characteristics into a data processing layer in the prediction model, so as to perform data processing on the various types of data characteristics according to the influence degree to obtain processed characteristics, and inputting the processed characteristics and the fusion characteristics into a prediction layer in the prediction model, so as to predict the service category of the service executed by a service provider of the service corresponding to the service data according to the service data, and take the service category as the prediction category.
Optionally, training the predictive model comprises:
acquiring sample service data;
for each type of sample data contained in the sample service data, inputting the type of sample data into a coding layer corresponding to the type in a prediction model to be trained to obtain data characteristics corresponding to the type of sample data;
inputting data characteristics corresponding to various types of sample data into an influence determining layer contained in the prediction model so as to determine the influence degree of each type of sample data on a result output by the prediction model;
inputting the influence degree of the various types of sample data on the result output by the prediction model and the data characteristics corresponding to the various types of sample data into a data processing layer in the prediction model, performing data processing on the data characteristics corresponding to the various types of sample data according to the influence degree of the various types of sample data on the result output by the prediction model to obtain processed sample characteristics, and inputting the processed sample characteristics into a prediction layer in the prediction model to predict the service class of the service executed by the service provider of the service corresponding to the sample service data according to the sample service data as a prediction class;
and training the prediction model by minimizing the deviation between the prediction category corresponding to the sample business data and the label information corresponding to the sample business data.
This specification provides a device of business wind control, including:
the acquisition module is used for acquiring service data, wherein the service data comprises different types of data;
the input module is used for inputting the type of data into a coding layer corresponding to the type in a pre-trained prediction model aiming at each type of data contained in the service data to obtain data characteristics corresponding to the type of data, wherein the prediction model comprises a plurality of coding layers, and different coding layers correspond to different types of data;
the determining module is used for inputting various types of data characteristics into an influence determining layer contained in the prediction model so as to determine the influence degree of each type of data on the result output by the prediction model;
the prediction module is used for inputting the influence degree and the various types of data characteristics into a data processing layer in the prediction model, performing data processing on the various types of data characteristics according to the influence degree to obtain processed characteristics, and inputting the processed characteristics into a prediction layer in the prediction model to predict the service category of a service executed by a service provider of a service corresponding to the service data according to the service data as a prediction category;
and the wind control module is used for carrying out service wind control according to the forecast type and the service type of the provided service appointed by the service provider.
Optionally, the different types of data included in the service data include: the time sequence data is obtained by sequencing the order data of the service provider according to the time sequence;
the input module is specifically configured to input the time series data into a coding layer corresponding to the time series data in a pre-trained prediction model, and determine a business feature corresponding to the order data at each time and a weight corresponding to the order data at each time, where the weight corresponding to the order data at the current time is greater than the weight corresponding to the order data at the historical time; and determining the data characteristics corresponding to the time sequence data according to the business characteristics corresponding to the order data at each moment and the weight corresponding to the order data at each moment.
Optionally, the prediction model includes an influence determination layer corresponding to each type of data feature;
the determining module is specifically configured to, for each type of data feature, input the type of data feature into an influence determining layer corresponding to the type of data feature, and determine a degree of influence of the type of data on a result output by the prediction model.
The present specification provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the above-described method of traffic scheduling.
The present specification provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above-mentioned method of traffic scheduling when executing the program.
The technical scheme adopted by the specification can achieve the following beneficial effects:
in the method for controlling the business wind provided in this specification, first, business data is obtained, where the business data includes different types of data. Secondly, aiming at each type of data contained in the service data, inputting the type of data into a coding layer corresponding to the type in a pre-trained prediction model to obtain data characteristics corresponding to the type of data, wherein the prediction model comprises a plurality of coding layers, and different coding layers correspond to different types of data. Then, various types of data characteristics are input into an influence determination layer included in the prediction model to determine the degree of influence of each type of data on the result output by the prediction model. And then, inputting the influence degree and various types of data characteristics into a data processing layer in a prediction model, performing data processing on the various types of data characteristics according to the influence degree to obtain processed characteristics, and inputting the processed characteristics into a prediction layer in the prediction model to predict the service type of the service executed by a service provider of the service corresponding to the service data according to the service data as the prediction type. And finally, carrying out service wind control according to the forecast category and the service category of the provided service appointed by the service provider.
It can be seen from the above method that, in the method, different types of data can be encoded through encoding layers corresponding to various types of data, so as to obtain data characteristics corresponding to various types of data, and determine the degree of influence of various types of data on the result output by the prediction model, so that the service provider of the service corresponding to the service data predicts the service class of the service executed by the service provider according to the service data as the prediction class. And then, carrying out service wind control according to the forecast category and the service category of the provided service appointed by the service provider. Therefore, the cost of manually checking the data is reduced by applying the pre-trained prediction model, and the accuracy of the judgment result of judging whether the merchant conducts the operation according to the agreed business class is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the specification and are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description serve to explain the specification and not to limit the specification in a non-limiting sense. In the drawings:
fig. 1 is a schematic flowchart of a method for service wind control according to an embodiment of the present disclosure;
FIG. 2 is a diagram illustrating a model structure of a prediction model provided in an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an apparatus for traffic wind control according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an electronic device provided in an embodiment of the present specification.
Detailed Description
In order to make the objects, technical solutions and advantages of the present disclosure more clear, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without making any creative effort belong to the protection scope of the present specification.
The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.
In order to make the objects, technical solutions and advantages of the present disclosure more clear, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without any creative effort belong to the protection scope of the present specification.
The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of a method for service wind control in this specification, which specifically includes the following steps:
s100: and acquiring service data, wherein the service data comprises different types of data.
In the embodiment of the present specification, the execution subject of the method for service scheduling may be an electronic device such as a server or a desktop computer. For convenience of description, the method for service scheduling provided in this specification is described below with reference to only a server as an execution subject.
In this embodiment of the present specification, the server may obtain service data, where the service data includes different types of data, where the types mentioned herein include: image data, text data, video data. The text data referred to herein includes structured data, which may be line data, which is data that can be implemented in a logical representation using a two-dimensional table structure. The structured data has the characteristics of high organization and regular format.
In the business scene of identifying the risk merchant, the image data in the business data may refer to images of a head light of the merchant, a business license of the merchant, and the like. The text data may refer to a business name, a trade name, an address, and the like in the business data. The structured data in the text data may refer to transaction amount, transaction stroke number, and the like. The video data may refer to videos that capture the internal environment of the merchant, advertisement videos of the merchant, and the like.
In practical application, an accurate prediction result cannot be well determined only according to the service data at the current moment. Therefore, the server can acquire the order data in the past period of time and sequence the order data in the past period of time according to the time sequence to obtain time sequence data for subsequent model training and predicting the accurate service class.
In the embodiment of the present specification, the different types of data included in the service data include: time series data. The time sequence data is obtained by sequencing the order data of the service provider according to the time sequence. The order data mentioned herein may refer to order information generated when a transaction is performed between a user and a merchant, for example, an order amount, whether a payment is made by others, a payment method, and the like.
It should be noted that the type of the service data may have more expressions, for example, an image containing a text, a video containing a text, and the like, and the description does not limit the type of the service data.
S102: and inputting the type of data into a coding layer corresponding to the type in a pre-trained prediction model aiming at each type of data contained in the service data to obtain data characteristics corresponding to the type of data, wherein the prediction model comprises a plurality of coding layers, and different coding layers correspond to different types of data.
In practical applications, different types of data cannot be encoded through the same encoding layer, and therefore, for each type of data, the server may encode the type of data through the encoding layer corresponding to the type of data.
In this embodiment, the server may input, for each type of data included in the service data, the type of data into a coding layer corresponding to the type in a pre-trained prediction model, so as to obtain a data feature corresponding to the type of data.
The prediction model comprises a plurality of coding layers, and different coding layers correspond to different types of data. For example, the prediction model may include a coding layer corresponding to image data, a coding layer corresponding to text data, and a coding layer corresponding to video data.
Specifically, for image data included in the service data, the server may input the image data into a coding layer corresponding to the image data in a pre-trained prediction model, so as to obtain data features corresponding to the image data.
The coding layer corresponding to the image data may be a coding layer of a Graph Convolutional Neural Network (GCN), a coding layer of a Graph Neural Network (GNN), a coding layer of a Graph Attention Network (GAT), and the like, and the coding layer corresponding to the image data is not limited in this specification.
Specifically, for text data included in the service data, the server may input the text data into a coding layer corresponding to the text data in a pre-trained prediction model, so as to obtain data characteristics corresponding to the text data.
The coding layer corresponding to the text data may be a Convolutional Neural Network (CNN), a transform model coding layer, or the like, and the coding layer corresponding to the text data is not limited in this specification.
Specifically, for video data included in the service data, the server may input the video data into a coding layer corresponding to the video data in a pre-trained prediction model, so as to obtain data characteristics corresponding to the video data.
The coding layer corresponding to the video data may be a coding layer of a three-dimensional Convolutional network (c 3 d) for Learning spatio-Temporal Features, a coding layer of a Temporal Pyramid pool network (TPP), or the like, and the coding layer corresponding to the video data is not limited in this specification.
It should be noted that the prediction model may include an encoding layer of a graph convolution neural network, an encoding layer of a transform model, and an encoding layer of a time pyramid pool network at the same time, and the combination of the encoding layers of various data types is not limited in this specification. That is, the coding layer corresponding to the image data in the prediction model may be constructed by a network structure of a convolutional neural network. Similarly, the coding layer corresponding to the text data in the prediction model may be constructed by a network structure of a convolutional neural network. Similarly, the coding layer corresponding to the video data in the prediction model may be constructed by a network structure of a three-dimensional convolutional network for learning spatio-temporal features.
In practical application, the influence degrees of the order data at different times in the time series data on the predicted service type are different, so that the server needs to determine the weights corresponding to the order data at different times in the time series data to obtain more accurate data characteristics corresponding to the time series data so as to determine the accurate prediction type.
In this embodiment, the server may input the time series data into a coding layer corresponding to the time series data in a pre-trained prediction model, and determine a business feature corresponding to the order data at each time and a weight corresponding to the order data at each time, where the weight corresponding to the order data at the current time is greater than the weight corresponding to the order data at the historical time.
Secondly, the server can determine the data characteristics corresponding to the time sequence data according to the business characteristics corresponding to the order data at each moment and the weight corresponding to the order data at each moment.
It should be noted that, since the order data in the time series data are arranged in a time sequence, the position of the order data at the current time is fixed, and the server may mark the position of the order data at the current time and determine the weight at the position in advance according to expert experience.
Of course, the weight corresponding to the order data at the current time may also be obtained by training the predictive model.
Further, the type of the service data may have more expressions, for example, an image containing text, a video containing text, and the like, and these types of data all have corresponding coding layers, and the description does not limit the coding layer corresponding to the type of the service data.
Because the data dimensions of different types of data are different, in order to facilitate the processing of subsequent prediction models, the server can align the data features corresponding to each type of data through linear change, that is, the data dimensions of the data features corresponding to each type of data are the same.
S104: various types of data features are input into an influence determination layer included in the prediction model to determine the degree of influence of each type of data on the result output by the prediction model.
In practical applications, different types of data features have different influences on the result output by the prediction model, and if the different types of data features are directly added, partial information loss may occur, so that the accuracy of the result output by the prediction model is low. Based on the data characteristics, the server can determine the influence degree of the data characteristics according to the data characteristics, so as to be used for outputting the result by the subsequent prediction model.
In the embodiments of the present specification, the server may input various types of data characteristics into the influence determination layer included in the prediction model to determine the degree of influence of each type of data on the result output by the prediction model.
In practical applications, the influence degree of each type of data on the result output by the prediction model is usually determined through the same influence determination layer, which may cause the determined influence degree to be inaccurate. Based on this, the prediction model in this specification may include a plurality of influential determination layers, and each type of data feature corresponds to one influential determination layer, so as to improve the accuracy of the determined influence degree.
In the embodiments of the present specification, the prediction model includes an influence determination layer corresponding to various types of data features. For each type of data feature, the server may input the type of data feature into the influence determination layer corresponding to the type of data feature, and determine the influence degree of the type of data on the result output by the prediction model.
Further, the server may normalize the degrees of influence of the various types of data on the result output by the prediction model, and make the sum of the degrees of influence of the various types of data on the result output by the prediction model be one.
It should be noted that, the influence determination layer mentioned herein may be a Gating NetWork (Gating NetWork) in a Multi-head hybrid expert (MMoE), and the like, and the influence determination layer is not limited in this specification.
S106: and inputting the influence degree and the various types of data characteristics into a data processing layer in the prediction model, performing data processing on the various types of data characteristics according to the influence degree to obtain processed characteristics, and inputting the processed characteristics into a prediction layer in the prediction model to predict the service class of the service executed by a service provider of the service corresponding to the service data according to the service data, wherein the service class is used as the prediction class.
In this embodiment, the server may input the influence degree and various types of data features into a data processing layer in the prediction model, perform data processing on the various types of data features according to the influence degree to obtain processed features, and input the processed features into a prediction layer in the prediction model to predict a service class of a service executed by a service provider of a service corresponding to the service data according to the service data, as the prediction class.
Specifically, the server may input the processed features into a prediction layer in the prediction model to predict class probabilities of the services executed by the service providers of the services corresponding to the service data according to the service data under each service class. And selecting the service class with the maximum class probability from the class probabilities under the service classes as a prediction class.
In practical applications, if the depth of the prediction model is increased only to perform feature intersection in the process of performing feature intersection on the prediction model, the initial feature information may be forgotten in the training process due to the deepening of the depth, which may cause a negative effect on the training of the prediction model. Therefore, the server can sum various types of data features before feature crossing and data features after feature crossing to prevent the prediction model from forgetting the initial feature information in the training process.
In the embodiment of the present specification, the prediction model includes a plurality of coding layers, a plurality of influential determination layers, a feature extraction layer, a data processing layer, and a prediction layer. The server can splice various types of data features to obtain splicing features, and the splicing features are input into the feature extraction layer to perform feature crossing on the splicing features to obtain fusion features.
It should be noted that the method for performing feature intersection on the mosaic feature in this specification may be implemented in various ways, for example, a Multilayer Perceptron (MLP), a Convolutional Neural Network (CNN). The present specification does not limit the way in which features are interleaved.
Then, the server may input the influence degree and various types of data features into a data processing layer in the prediction model, perform data processing on the various types of data features according to the influence degree to obtain processed features, and input the processed features and the fusion features into a prediction layer in the prediction model to predict a service class of a service executed by a service provider of a service corresponding to the service data according to the service data as a prediction class.
Specifically, the server may perform linear summation on the processed features and the fusion features to obtain comprehensive features, and input the comprehensive features into a prediction layer in the prediction model to predict a service category of a service executed by a service provider of a service corresponding to the service data according to the service data, as the prediction category.
The server can splice various types of data features and time sequence data to obtain splicing features, and the splicing features are input into the feature extraction layer to perform feature crossing on the splicing features to obtain fusion features.
S108: and carrying out service wind control according to the forecast category and the service category of the provided service appointed by the service provider.
In this embodiment, the server may perform service scheduling according to the predicted category and the service category of the service provided by the service provider. That is, if the determined prediction type is different from the service type of the provided service agreed by the service provider, it is considered that the transaction of the service provider is at risk and service management is required.
In this embodiment of the present specification, before predicting, by using the prediction model, the service provider of the service corresponding to the service data according to the service category of the service executed by the service data, the server needs to train the prediction model first, and then, a training process of the prediction model will be described in detail.
In an embodiment of the present specification, a server may obtain sample traffic data.
Secondly, the server may input, for each type of sample data included in the sample service data, the type of sample data into the coding layer corresponding to the type in the prediction model to be trained, so as to obtain data characteristics corresponding to the type of sample data.
Then, the server may input data features corresponding to various types of sample data into an influence determination layer included in the prediction model to determine a degree of influence of each type of sample data on a result output by the prediction model.
Then, the server can input the influence degree of various types of sample data on the result output by the prediction model and the data characteristics corresponding to various types of sample data into a data processing layer in the prediction model, so as to perform data processing on the data characteristics corresponding to various types of sample data according to the influence degree of various types of sample data on the result output by the prediction model to obtain processed sample characteristics, and input the processed sample characteristics into the prediction layer in the prediction model, so that a service provider of the service corresponding to the predicted sample service data performs the service according to the service type of the service executed by the sample service data as the prediction type.
Finally, the server may train the prediction model with a deviation between the prediction category corresponding to the minimized sample traffic data and the label information corresponding to the sample traffic data. The label information corresponding to the sample service data mentioned herein may refer to an actual service category of the service provider in the sample service data.
In the embodiment of the present specification, the model structure of the prediction model is specifically shown in fig. 2.
Fig. 2 is a schematic diagram of a model structure of a prediction model provided in an embodiment of the present disclosure.
In fig. 2, the server may input image data into an encoding layer corresponding to the image data, determine data characteristics corresponding to the image data, input text data into an encoding layer corresponding to the text data, determine data characteristics corresponding to the text data, and input video data into an encoding layer corresponding to the video data, determine data characteristics corresponding to the video data. Of course, the types of the service data are various, for example, images with characters, time sequence data arranged according to a time sequence, and the like, which are not described herein repeatedly.
Secondly, the server can input the data characteristics corresponding to the data of each type into the characteristic extraction layer, and the characteristics are crossed to obtain the fusion characteristics.
Then, for each type of data feature, the server may input the type of data feature into the influence determination layer corresponding to the type of data feature, and determine the degree of influence of the type of data on the result output by the prediction model.
Then, the server can input the influence degree and various types of data characteristics into a data processing layer in the prediction model, so as to perform data processing on the various types of data characteristics through the influence degree to obtain processed characteristics.
Finally, the server can input the processed features and the fusion features into a prediction layer in the prediction model, and a service provider of a service corresponding to the service data predicts the service class of the service executed by the service data according to the service data, and the service class is used as the prediction class.
It can be seen from the above process that the method can encode different types of data through the encoding layers corresponding to the various types of data to obtain data characteristics corresponding to the various types of data, and determine the degree of influence of the various types of data on the result output by the prediction model, so as to predict the service class of the service executed by the service provider of the service corresponding to the service data according to the service data as the prediction class. And then, carrying out service wind control according to the forecast category and the service category of the provided service appointed by the service provider. Therefore, the cost of manually checking data is reduced by applying the pre-trained prediction model, and the accuracy of the judgment result of judging whether the merchant conducts the operation according to the appointed business category is improved. That is, the accuracy of the prediction categories determined by the prediction model is improved.
In addition, the method improves the model structure of the prediction model, prevents the prediction model from forgetting the initial characteristic information in the training process, and improves the accuracy of the prediction type determined by the prediction model.
Based on the same idea, the present specification further provides a corresponding apparatus, a storage medium, and an electronic device.
Fig. 3 is a schematic structural diagram of an apparatus for traffic wind control provided in an embodiment of the present specification, where the apparatus includes:
an obtaining module 300, configured to obtain service data, where the service data includes different types of data;
an input module 302, configured to input, for each type of data included in the service data, the type of data into a coding layer corresponding to the type in a pre-trained prediction model to obtain data characteristics corresponding to the type of data, where the prediction model includes multiple coding layers, and different coding layers correspond to different types of data;
a determination module 304, configured to input various types of data features into an influence determination layer included in the prediction model to determine a degree of influence of each type of data on a result output by the prediction model;
the prediction module 306 is configured to input the influence degree and the various types of data features into a data processing layer in the prediction model, perform data processing on the various types of data features according to the influence degree to obtain processed features, and input the processed features into a prediction layer in the prediction model to predict a service category of a service executed by a service provider of a service corresponding to the service data according to the service data, where the service category is used as a prediction category;
and a wind control module 308, configured to perform service wind control according to the prediction category and the service category of the service provided by the service provider.
Optionally, the different types of data included in the service data include: the time sequence data is obtained by sequencing the order data of the service provider according to the time sequence;
the input module 302 is specifically configured to input the time series data into a coding layer corresponding to the time series data in a pre-trained prediction model, determine a business feature corresponding to the order data at each time and a weight corresponding to the order data at each time, where the weight corresponding to the order data at the current time is greater than the weight corresponding to the order data at the historical time, and determine a data feature corresponding to the time series data according to the business feature corresponding to the order data at each time and the weight corresponding to the order data at each time.
Optionally, the prediction model includes an influence determination layer corresponding to each type of data feature;
the determining module 304 is specifically configured to, for each type of data feature, input the type of data feature into an influence determining layer corresponding to the type of data feature, and determine a degree of influence of the type of data on a result output by the prediction model.
Optionally, the prediction model comprises a feature extraction layer;
the prediction module 306 is specifically configured to splice various types of data features to obtain spliced features, input the spliced features into the feature extraction layer to perform feature crossing on the spliced features to obtain fused features, input the influence degree and the various types of data features into a data processing layer in the prediction model to perform data processing on the various types of data features according to the influence degree to obtain processed features, and input the processed features and the fused features into a prediction layer in the prediction model to predict a service category of a service executed by a service provider of a service corresponding to the service data according to the service data, as a prediction category.
Optionally, the input module 302 is specifically configured to obtain sample service data, input, for each type of sample data included in the sample service data, the type of sample data into a coding layer corresponding to the type in a prediction model to be trained, obtain data characteristics corresponding to the type of sample data, input, into an influence determining layer included in the prediction model, the degree of influence of each type of sample data on a result output by the prediction model is determined, input, into a data processing layer in the prediction model, the degree of influence of each type of sample data on the result output by the prediction model and the data characteristics corresponding to the various types of sample data, perform data processing on the data characteristics corresponding to the various types of sample data according to the degree of influence of the various types of sample data on the result output by the prediction model, obtain processed sample characteristics, input, into a prediction layer in the prediction model, and predict that a service of a service provider that performs data processing according to the service class of the sample service data corresponding to the sample service data, as a prediction information deviation between the service types of the sample service and the prediction model corresponding to the training data.
The present specification also provides a computer readable storage medium storing a computer program which, when executed by a processor, is operable to perform the method of traffic scheduling provided in fig. 1 above.
The embodiment of the present specification further provides a schematic structural diagram of the electronic device shown in fig. 4. As shown in fig. 4, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, but may also include hardware required for other services. The processor reads a corresponding computer program from the non-volatile memory into the memory and then runs the computer program to implement the method for controlling the service wind provided in fig. 1.
Of course, besides the software implementation, the present specification does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may be hardware or logic devices.
It should be noted that all the actions of acquiring signals, information or data in the present application are performed under the premise of complying with the corresponding data protection regulation policy of the country of the location and obtaining the authorization given by the owner of the corresponding device.
In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain a corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical blocks. For example, a Programmable Logic Device (PLD) (e.g., a Field Programmable Gate Array (FPGA)) is an integrated circuit whose Logic functions are determined by a user programming the Device. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development, but the original code before compiling is also written in a specific Programming Language, which is called Hardware Description Language (HDL), and the HDL is not only one kind but many kinds, such as abll (Advanced boot Expression Language), AHDL (alternate hard Description Language), traffic, CUPL (computer universal Programming Language), HDCal (Java hard Description Language), lava, lola, HDL, PALASM, software, rhydl (Hardware Description Language), and vhul-Language (vhyg-Language), which is currently used in the field. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, atmel AT91SAM, microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller in purely computer readable program code means, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be conceived to be both a software module implementing the method and a structure within a hardware component.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may 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 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 Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or apparatus comprising the element.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present disclosure, and is not intended to limit the present disclosure. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.
Claims (10)
1. A method of traffic scheduling, comprising:
acquiring service data, wherein the service data comprises different types of data;
for each type of data contained in the service data, inputting the type of data into a coding layer corresponding to the type in a pre-trained prediction model to obtain data characteristics corresponding to the type of data, wherein the prediction model comprises a plurality of coding layers, and different coding layers correspond to different types of data;
inputting various types of data features into an influence determination layer included in the prediction model to determine a degree of influence of each type of data on a result output by the prediction model;
inputting the influence degree and the various data characteristics into a data processing layer in the prediction model, so as to perform data processing on the various data characteristics according to the influence degree to obtain processed characteristics, and inputting the processed characteristics into a prediction layer in the prediction model, so as to predict the service type of a service executed by a service provider of a service corresponding to the service data according to the service data, wherein the service type is used as a prediction type;
and carrying out service wind control according to the forecast type and the service type of the provided service appointed by the service provider.
2. The method of claim 1, wherein the different types of data included in the service data comprise: the time sequence data is obtained by sequencing the order data of the service provider according to the time sequence;
for each type of data included in the service data, inputting the type of data into a coding layer corresponding to the type in a pre-trained prediction model to obtain data characteristics corresponding to the type of data, specifically including:
inputting the time sequence data into a coding layer corresponding to the time sequence data in a pre-trained prediction model, and determining business characteristics corresponding to the order data at each moment and a weight corresponding to the order data at each moment, wherein the weight corresponding to the order data at the current moment is greater than the weight corresponding to the order data at the historical moment;
and determining the data characteristics corresponding to the time sequence data according to the business characteristics corresponding to the order data at each moment and the weight corresponding to the order data at each moment.
3. The method of claim 1, wherein the predictive model comprises an impact determination layer corresponding to each type of data feature;
inputting various types of data characteristics into an influence determination layer contained in the prediction model to determine the influence degree of each type of data on a result output by the prediction model, specifically comprising:
and for each type of data characteristic, inputting the type of data characteristic into an influence determination layer corresponding to the type of data characteristic, and determining the influence degree of the type of data on the result output by the prediction model.
4. The method of claim 1, wherein the predictive model comprises a feature extraction layer;
inputting the influence degree and the various types of data characteristics into a data processing layer in the prediction model, performing data processing on the various types of data characteristics according to the influence degree to obtain processed characteristics, inputting the processed characteristics into a prediction layer in the prediction model to predict the service class of a service executed by a service provider of a service corresponding to the service data according to the service data, and taking the service class as a prediction class, specifically comprising:
splicing various types of data features to obtain splicing features, and inputting the splicing features into the feature extraction layer to perform feature crossing on the splicing features to obtain fusion features;
and inputting the influence degree and the various types of data characteristics into a data processing layer in the prediction model, so as to perform data processing on the various types of data characteristics according to the influence degree to obtain processed characteristics, and inputting the processed characteristics and the fusion characteristics into a prediction layer in the prediction model, so as to predict the service category of the service executed by a service provider of the service corresponding to the service data according to the service data, and take the service category as the prediction category.
5. The method of claim 1, training a predictive model, comprising:
acquiring sample service data;
for each type of sample data contained in the sample service data, inputting the type of sample data into a coding layer corresponding to the type in a prediction model to be trained to obtain data characteristics corresponding to the type of sample data;
inputting data characteristics corresponding to various types of sample data into an influence determining layer contained in the prediction model so as to determine the influence degree of each type of sample data on a result output by the prediction model;
inputting the influence degree of the various types of sample data on the result output by the prediction model and the data characteristics corresponding to the various types of sample data into a data processing layer in the prediction model, performing data processing on the data characteristics corresponding to the various types of sample data according to the influence degree of the various types of sample data on the result output by the prediction model to obtain processed sample characteristics, and inputting the processed sample characteristics into a prediction layer in the prediction model to predict the service category of the service executed by a service provider of the service corresponding to the sample service data according to the sample service data as a prediction category;
and training the prediction model by minimizing the deviation between the prediction category corresponding to the sample business data and the label information corresponding to the sample business data.
6. An apparatus for traffic scheduling, comprising:
the acquisition module is used for acquiring service data, wherein the service data comprises different types of data;
an input module, configured to input, for each type of data included in the service data, the type of data into a coding layer corresponding to the type in a pre-trained prediction model to obtain data characteristics corresponding to the type of data, where the prediction model includes multiple coding layers, and different coding layers correspond to different types of data;
the determining module is used for inputting various types of data characteristics into an influence determining layer contained in the prediction model so as to determine the influence degree of each type of data on the result output by the prediction model;
the prediction module is used for inputting the influence degree and the various data characteristics into a data processing layer in the prediction model, performing data processing on the various data characteristics according to the influence degree to obtain processed characteristics, inputting the processed characteristics into a prediction layer in the prediction model, and predicting the service type of a service executed by a service provider of a service corresponding to the service data according to the service data to serve as the prediction type;
and the wind control module is used for carrying out service wind control according to the forecast type and the service type of the provided service appointed by the service provider.
7. The apparatus of claim 6, the different types of data included in the traffic data comprising: the time sequence data is obtained by sequencing the order data of the service provider according to the time sequence;
the input module is specifically configured to input the time series data into a coding layer corresponding to the time series data in a pre-trained prediction model, and determine a business feature corresponding to the order data at each time and a weight corresponding to the order data at each time, where the weight corresponding to the order data at the current time is greater than the weight corresponding to the order data at the historical time; and determining the data characteristics corresponding to the time sequence data according to the business characteristics corresponding to the order data at each moment and the weight corresponding to the order data at each moment.
8. The apparatus of claim 6, wherein the predictive model comprises an influence determination layer corresponding to each type of data feature;
the determining module is specifically configured to, for each type of data feature, input the type of data feature into an influence determining layer corresponding to the type of data feature, and determine a degree of influence of the type of data on a result output by the prediction model.
9. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method of any one of the preceding claims 1 to 5.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any of the preceding claims 1-5 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211508341.0A CN115545353B (en) | 2022-11-29 | 2022-11-29 | Business wind control method, device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211508341.0A CN115545353B (en) | 2022-11-29 | 2022-11-29 | Business wind control method, device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115545353A true CN115545353A (en) | 2022-12-30 |
| CN115545353B CN115545353B (en) | 2023-04-18 |
Family
ID=84722231
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211508341.0A Active CN115545353B (en) | 2022-11-29 | 2022-11-29 | Business wind control method, device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115545353B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116028880A (en) * | 2023-02-07 | 2023-04-28 | 支付宝(杭州)信息技术有限公司 | Method for training behavior intention recognition model, behavior intention recognition method and device |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180053188A1 (en) * | 2016-08-17 | 2018-02-22 | Fair Isaac Corporation | Customer transaction behavioral archetype analytics for cnp merchant transaction fraud detection |
| CN109598597A (en) * | 2018-10-16 | 2019-04-09 | 平安科技（深圳）有限公司 | Business datum classifying method, device and storage medium, server |
| CN110163752A (en) * | 2019-04-16 | 2019-08-23 | 阿里巴巴集团控股有限公司 | A kind of dealing amount of foreign exchange prediction technique, apparatus and system |
| CN110222880A (en) * | 2019-05-20 | 2019-09-10 | 阿里巴巴集团控股有限公司 | Determination method, model training method and the data processing method of business risk |
| CN110503385A (en) * | 2019-07-15 | 2019-11-26 | 招联消费金融有限公司 | Method for processing business, device, computer equipment and storage medium |
| CN111353850A (en) * | 2020-02-26 | 2020-06-30 | 支付宝(杭州)信息技术有限公司 | Risk identification strategy updating method and device and risk merchant identification method and device |
| CN113159213A (en) * | 2021-04-30 | 2021-07-23 | 中国工商银行股份有限公司 | Service distribution method, device and equipment |
| WO2021169115A1 (en) * | 2020-02-29 | 2021-09-02 | 平安科技（深圳）有限公司 | Risk control method, apparatus, electronic device, and computer-readable storage medium |
| CN113672732A (en) * | 2021-08-19 | 2021-11-19 | 胜斗士(上海)科技技术发展有限公司 | Method and device for classifying business data |
| CN114817933A (en) * | 2022-04-29 | 2022-07-29 | 支付宝(杭州)信息技术有限公司 | Method and device for evaluating robustness of business prediction model and computing equipment |
| CN114943307A (en) * | 2022-06-28 | 2022-08-26 | 支付宝(杭州)信息技术有限公司 | Model training method and device, storage medium and electronic equipment |
| CN114998001A (en) * | 2022-07-15 | 2022-09-02 | 中国工商银行股份有限公司 | Service class identification method, device, equipment, storage medium and program product |
| CN115409290A (en) * | 2022-10-31 | 2022-11-29 | 北京领雁科技股份有限公司 | Business data risk model verification method and device, electronic equipment and medium |
-
2022
- 2022-11-29 CN CN202211508341.0A patent/CN115545353B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180053188A1 (en) * | 2016-08-17 | 2018-02-22 | Fair Isaac Corporation | Customer transaction behavioral archetype analytics for cnp merchant transaction fraud detection |
| CN109598597A (en) * | 2018-10-16 | 2019-04-09 | 平安科技（深圳）有限公司 | Business datum classifying method, device and storage medium, server |
| CN110163752A (en) * | 2019-04-16 | 2019-08-23 | 阿里巴巴集团控股有限公司 | A kind of dealing amount of foreign exchange prediction technique, apparatus and system |
| CN110222880A (en) * | 2019-05-20 | 2019-09-10 | 阿里巴巴集团控股有限公司 | Determination method, model training method and the data processing method of business risk |
| CN110503385A (en) * | 2019-07-15 | 2019-11-26 | 招联消费金融有限公司 | Method for processing business, device, computer equipment and storage medium |
| CN111353850A (en) * | 2020-02-26 | 2020-06-30 | 支付宝(杭州)信息技术有限公司 | Risk identification strategy updating method and device and risk merchant identification method and device |
| WO2021169115A1 (en) * | 2020-02-29 | 2021-09-02 | 平安科技（深圳）有限公司 | Risk control method, apparatus, electronic device, and computer-readable storage medium |
| CN113159213A (en) * | 2021-04-30 | 2021-07-23 | 中国工商银行股份有限公司 | Service distribution method, device and equipment |
| CN113672732A (en) * | 2021-08-19 | 2021-11-19 | 胜斗士(上海)科技技术发展有限公司 | Method and device for classifying business data |
| CN114817933A (en) * | 2022-04-29 | 2022-07-29 | 支付宝(杭州)信息技术有限公司 | Method and device for evaluating robustness of business prediction model and computing equipment |
| CN114943307A (en) * | 2022-06-28 | 2022-08-26 | 支付宝(杭州)信息技术有限公司 | Model training method and device, storage medium and electronic equipment |
| CN114998001A (en) * | 2022-07-15 | 2022-09-02 | 中国工商银行股份有限公司 | Service class identification method, device, equipment, storage medium and program product |
| CN115409290A (en) * | 2022-10-31 | 2022-11-29 | 北京领雁科技股份有限公司 | Business data risk model verification method and device, electronic equipment and medium |
Non-Patent Citations (3)
| Title |
|---|
| DONGXU HUANG ET AL: "CoDetect: Financial Fraud Detection With Anomaly Feature Detection" * |
| DR. JYOTINDRA N. DHARWA ET AL: "A Data Mining with Hybrid Approach Based Transaction Risk Score Generation Model (TRSGM) for Fraud Detection of Online Financial Transaction" * |
| 孙权 等: "金融交易数据驱动的图谱网络智能化欺诈侦测" * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116028880A (en) * | 2023-02-07 | 2023-04-28 | 支付宝(杭州)信息技术有限公司 | Method for training behavior intention recognition model, behavior intention recognition method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115545353B (en) | 2023-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113688313A (en) | Training method of prediction model, information pushing method and device | |
| CN115238826B (en) | Model training method and device, storage medium and electronic equipment | |
| CN115759122A (en) | Intention identification method, device, equipment and readable storage medium | |
| CN112966186A (en) | Model training and information recommendation method and device | |
| CN115203394A (en) | Model training method, service execution method and device | |
| CN115545353B (en) | Business wind control method, device, storage medium and electronic equipment | |
| CN113343085B (en) | Information recommendation method and device, storage medium and electronic equipment | |
| CN114331602A (en) | Model training method based on transfer learning, information recommendation method and device | |
| CN116029556B (en) | Service risk assessment method, device, equipment and readable storage medium | |
| CN116308738B (en) | Model training method, business wind control method and device | |
| CN115563584B (en) | Model training method and device, storage medium and electronic equipment | |
| CN116822606A (en) | Training method, device, equipment and storage medium of anomaly detection model | |
| CN115758141A (en) | Method and device for model training and business wind control | |
| CN116824331A (en) | Model training and image recognition method, device, equipment and storage medium | |
| CN116188023A (en) | Method, device, storage medium and equipment for training risk identification model | |
| CN116246276A (en) | Information identification method, device, equipment and readable storage medium | |
| CN115660105A (en) | Model training method, business wind control method and business wind control device | |
| CN114996570A (en) | Information recommendation method and device | |
| CN113344590A (en) | Method and device for model training and complaint rate estimation | |
| CN115017905A (en) | Model training and information recommendation method and device | |
| CN114511376A (en) | Credit data processing method and device based on multiple models | |
| CN117786061B (en) | Large language model prediction method and device based on space-time attention mechanism | |
| CN111104591B (en) | Recommendation information generation method and device | |
| CN117876114A (en) | Method and device for service execution and model training | |
| CN114757713A (en) | Information recommendation method and device, storage medium and electronic 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 |