CN112508692A - Resource recovery risk prediction method and device based on convolutional neural network and electronic equipment - Google Patents
Resource recovery risk prediction method and device based on convolutional neural network and electronic equipment Download PDFInfo
- Publication number
- CN112508692A CN112508692A CN202110155320.4A CN202110155320A CN112508692A CN 112508692 A CN112508692 A CN 112508692A CN 202110155320 A CN202110155320 A CN 202110155320A CN 112508692 A CN112508692 A CN 112508692A
- Authority
- CN
- China
- Prior art keywords
- resource recovery
- user
- neural network
- convolutional neural
- behavior data
- 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
- 238000011084 recovery Methods 0.000 title claims abstract description 106
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 38
- 239000011159 matrix material Substances 0.000 claims abstract description 45
- 238000012549 training Methods 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 24
- 230000006399 behavior Effects 0.000 claims description 93
- 238000004064 recycling Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012954 risk control Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 230000003287 optical effect Effects 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005111 flow chemistry technique Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Accounting & Taxation (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Finance (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a resource recovery risk prediction method, a device, electronic equipment and a computer readable medium based on a convolutional neural network, which comprises the following steps: acquiring a user behavior data matrix of a historical user and a resource recovery label indicating whether resources are recovered; training a user behavior data matrix of a historical user and a resource recovery label as training samples of a convolutional neural network to obtain a convolutional neural network model for predicting the resource recovery probability; inputting the user behavior data matrix of the new user into the convolutional neural network model, and calculating to obtain the full-link layer characteristics and the resource recovery probability of the convolutional neural network of the new user; and predicting the resource recovery risk of the new user according to the full connection layer characteristics or the resource recovery probability of the new user. According to the method and the system, all user behavior data in a specific time period can be selected as convolution kernels according to needs, the corresponding risk control level of the user is accurately positioned, and therefore the processing precision of risk control of the internet service platform is improved.
Description
Technical Field
The invention relates to the field of computer information processing, in particular to a resource recovery risk prediction method and device based on a convolutional neural network, electronic equipment and a computer readable medium.
Background
With the development of big data and artificial intelligence, machine learning models predict the future based on past data. The machine learning technology is widely applied to the financial wind control and marketing fields, and has the characteristics of high credit risk and high safety risk in the financial wind control field, so that a financial institution trains a scoring model by using a large amount of historical sample data to generate the scoring model, such as a credit scoring model. The model serves the business, credit score prediction needs to be carried out on the online customer in the business, and a score prediction result is given by calling the trained model by using the incoming data of the customer.
In the existing credit scoring model, because the dimensionality of input user behavior characteristic data is too much, which data in the user behavior characteristic data is important for evaluating the credit risk of the user cannot be known, and which data is relatively minor, a characteristic data input model with a large specific weight needs to be screened out for training, so that the model training time is long, the efficiency is low, and the output credit scoring result is inaccurate.
Disclosure of Invention
In order to reduce resource recovery risks, the invention provides a resource recovery risk prediction method and device based on a convolutional neural network, electronic equipment and a computer readable medium.
One aspect of the present invention provides a resource recovery risk prediction method based on a convolutional neural network, including:
acquiring a user behavior data matrix of a historical user and a resource recovery label indicating whether resources are recovered or not, wherein the user behavior data matrix comprises a plurality of continuous time points, and each time point is provided with a plurality of behavior data;
training the user behavior data matrix of the historical user and the resource recovery label as training samples of a convolutional neural network to obtain a convolutional neural network model for predicting the resource recovery probability;
inputting the user behavior data matrix of the new user into the convolutional neural network model, and calculating to obtain the full-connection layer characteristics and the resource recovery probability of the convolutional neural network of the new user;
and predicting the resource recovery risk of the new user according to the full connection layer characteristics or the resource recovery probability of the new user.
According to a preferred embodiment of the present invention, the training of the user behavior data matrix resource recycling labels of the historical users as training samples of a convolutional neural network further includes:
and setting a convolution kernel, and performing convolution processing on the user behavior data matrix by using the convolution kernel.
According to a preferred embodiment of the present invention, the setting the convolution kernel includes:
and selecting a convolution kernel with the size of m x n, wherein m is the number of all user behavior characteristics of the historical users at a time point in a preset time period, and n is preset continuous days.
According to the preferred embodiment of the present invention, the user behavior feature is behavior data of a user logging in a specific webpage or APP for operation in one day.
According to a preferred embodiment of the invention, the consecutive days are 3, 5 or 7 consecutive days.
According to a preferred embodiment of the present invention, the preset time period is one month before the current time.
According to a preferred embodiment of the present invention, the predicting the resource recycling risk of the new user according to the full connection layer characteristics or the resource recycling probability of the new user further includes:
and directly predicting the resource recovery risk of the new user according to the resource recovery probability.
According to a preferred embodiment of the present invention, the predicting the resource recycling risk of the new user according to the full connection layer characteristics or the resource recycling probability of the new user further includes:
and training a resource recovery risk model by using the full-connection characteristics of the historical users in the convolutional neural network model as training data, and inputting the full-connection layer characteristics of the new users into the resource recovery risk model to obtain a resource recovery risk prediction value of the new users.
According to a preferred embodiment of the invention, the method further comprises:
acquiring behavior data and resource recovery results of the new user;
and inputting the behavior data of the new user and the resource recovery result into the convolutional neural network model, and updating the parameters of the convolutional neural network model.
A second aspect of the present invention provides a resource recovery risk prediction apparatus based on a convolutional neural network, including:
the information acquisition module is used for acquiring a user behavior data matrix of a historical user and a resource recovery label which represents whether resources are recovered or not, wherein the user behavior data matrix comprises a plurality of continuous time points, and each time point is provided with a plurality of behavior data;
the model training module is used for training the user behavior data matrix of the historical user and the resource recovery label as training samples of a convolutional neural network to obtain a convolutional neural network model for predicting the resource recovery probability;
the calculation module is used for inputting the user behavior data matrix of the new user into the convolutional neural network model and calculating to obtain the full-connection layer characteristics and the resource recovery probability of the convolutional neural network of the new user;
and the risk prediction module is used for predicting the resource recovery risk of the new user according to the full connection layer characteristics or the resource recovery probability of the new user.
According to a preferred embodiment of the present invention, the model training module is further configured to:
and setting a convolution kernel, and performing convolution processing on the user behavior data matrix by using the convolution kernel.
According to a preferred embodiment of the present invention, the setting the convolution kernel includes:
and selecting a convolution kernel with the size of m x n, wherein m is the number of all user behavior characteristics of the historical users at a time point in a preset time period, and n is preset continuous days.
According to the preferred embodiment of the present invention, the user behavior feature is behavior data of a user logging in a specific webpage or APP for operation in one day.
According to a preferred embodiment of the invention, the consecutive days are 3, 5 or 7 consecutive days.
According to a preferred embodiment of the present invention, the preset time period is one month before the current time.
According to a preferred embodiment of the invention, the risk prediction module is further configured to:
and directly predicting the resource recovery risk of the new user according to the resource recovery probability.
According to a preferred embodiment of the invention, the risk prediction module is further configured to:
and training a resource recovery risk model by using the full-connection characteristics of the historical users in the convolutional neural network model as training data, and inputting the full-connection layer characteristics of the new users into the resource recovery risk model to obtain a resource recovery risk prediction value of the new users.
According to a preferred embodiment of the present invention, the apparatus further comprises a model update module for:
acquiring behavior data and resource recovery results of the new user;
and inputting the behavior data of the new user and the resource recovery result into the convolutional neural network model, and updating the parameters of the convolutional neural network model.
A third aspect of the present invention provides an electronic apparatus, wherein the electronic apparatus comprises: a processor; and the number of the first and second groups,
a memory storing computer executable instructions that, when executed, cause the processor to perform any of the methods.
A fourth aspect of the invention provides a computer readable storage medium, wherein the computer readable storage medium stores one or more programs which, when executed by a processor, implement any of the methods.
The technical scheme of the invention has the following beneficial effects:
according to the method and the device, the acquired historical user behavior data and time are input into the convolutional neural network model in a matrix form for training to obtain a model for predicting the resource recovery risk, the resource recovery risk of the new user can be predicted after the user behavior data of the new user and the matrix formed by the specific time are input into the model, all the user behavior data in a specific time period can be selected as a convolution kernel according to needs, all the user behavior characteristics are applied during convolution processing, the output result is more accurate, the risk control level corresponding to the user is accurately positioned, and the processing precision of risk control of an internet service platform is further improved.
Drawings
In order to make the technical problems solved by the present invention, the technical means adopted and the technical effects obtained more clear, the following will describe in detail the embodiments of the present invention with reference to the accompanying drawings. It should be noted, however, that the drawings described below are only drawings of exemplary embodiments of the invention, from which other embodiments can be derived by those skilled in the art without inventive step.
FIG. 1 is a schematic flow chart of a resource recovery risk prediction method based on a convolutional neural network according to the present invention;
FIG. 2 is a schematic diagram of a block architecture of a convolutional neural network-based resource recycling risk prediction apparatus according to the present invention;
FIG. 3 is a schematic diagram of an electronic device architecture for resource recycling risk prediction based on a convolutional neural network according to the present invention;
FIG. 4 is a schematic diagram of a computer readable storage medium of the present invention.
Detailed Description
Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. The exemplary embodiments, however, may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these exemplary embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the invention to those skilled in the art. The same reference numerals denote the same or similar elements, components, or parts in the drawings, and thus their repetitive description will be omitted.
Features, structures, characteristics or other details described in a particular embodiment do not preclude the fact that the features, structures, characteristics or other details may be combined in a suitable manner in one or more other embodiments in accordance with the technical idea of the invention.
In describing particular embodiments, the present invention has been described with reference to features, structures, characteristics or other details that are within the purview of one skilled in the art to provide a thorough understanding of the embodiments. One skilled in the relevant art will recognize, however, that the invention may be practiced without one or more of the specific features, structures, characteristics, or other details.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
It will be understood that, although the terms first, second, third, etc. may be used herein to describe various elements, components, or sections, these terms should not be construed as limiting. These phrases are used to distinguish one from another. For example, a first device may also be referred to as a second device without departing from the spirit of the present invention.
The term "and/or" and/or "includes any and all combinations of one or more of the associated listed items.
In order that the objects, technical solutions and advantages of the present invention will become more apparent, the present invention will be further described in detail with reference to the accompanying drawings in conjunction with the following specific embodiments.
In practical application, a default model is generally adopted to predict default probability at present, a mainstream method for establishing the default model is a Logistic regression model, and the Logistic regression model is an important and basic linear model in machine learning, and has the characteristics of low model complexity, strong interpretability, good generalization performance and the like, but has higher requirement on the refinement of variables. In particular, for some non-linear variables, WOE (weight of evidence) processing is also required, and the processing procedures inevitably introduce some artifacts and bring noise to the modeling process.
Fig. 1 is a schematic flow chart of a resource recovery risk prediction method based on a convolutional neural network according to the present invention. As shown in fig. 1, the method includes:
s101, acquiring a user behavior data matrix of a historical user and a resource recovery label indicating whether resources are recovered, wherein the user behavior data matrix comprises a plurality of continuous time points, and each time point is provided with a plurality of behavior data.
Specifically, after logging in the internet service platform, the user performs various operations based on the internet service platform. Corresponding data, which may be referred to as behavioral data, is generated for these operations. The internet service platform can store various behavior data generated by users, such as: login data, payment data, transaction data, borrowing data, repayment data, etc., collectively referred to herein as user behavior data.
In order to ensure the accuracy of risk control, the solution provided in the embodiment of the present specification may obtain, in addition to the user behavior data of the user, identity data of the user, where the identity data includes but is not limited to: age, occupation, address, income, etc.
Under the condition of acquiring user data of a first user, aiming at the acquired user data, a user behavior data matrix is established, wherein 'rows' in the user behavior data matrix represent user behavior data of all dimensions at the same time point, and 'columns' represent behavior data at different time points in the same dimension.
And S102, training the user behavior data matrix of the historical user and the resource recovery label as training samples of a convolutional neural network to obtain a convolutional neural network model for predicting the resource recovery probability.
Specifically, the preprocessed user data (or referred to as a user behavior data matrix) is input into a convolutional neural network model, convolutional kernels with different sizes are selected from the convolutional neural network model, the user behavior data matrices constructed by the user data are respectively subjected to convolutional processing, when the convolutional kernels are selected conventionally, the sizes of convolution and sizes are determined according to the length of a time window, that is, the number of rows and columns in the convolutional kernels is consistent, the convolutional kernels are in a square shape, and the longer the time contained in the convolutional kernels is, the more the dimensionality of the corresponding contained user behavior data is.
In practical application, because the user behavior data has a large number of dimensions, if the convolution kernel only includes some of the dimensions, it cannot represent all the behavior characteristics of the user, and it is likely that a better effect will occur when the user behavior characteristics of some of the dimensions are combined, but the user behavior characteristics are not all included in the convolution kernel, in the embodiment of the present invention, "rows" in the size of the convolution kernel are set as the number of all the user behavior characteristics at a time point within a preset time period, and "columns" are set as consecutive days, where the time point may be set as one day, the corresponding user behavior characteristics are behavior data in which the user logs in a specific web page or APP to operate within one day, and the consecutive days may be set by itself according to needs, for example, may be set as consecutive 3 days, 5 days, or 7 days.
Because the user behavior data has timeliness, in order to ensure the validity of the user behavior data input into the convolutional neural network model, the preset time period can be set to be the previous month, three months and the like of the current time, and the obtained user behavior data in the preset time period has higher validity compared with other time periods.
After the corresponding convolution kernel is selected, inputting behavior data of a historical user in a preset time period into a convolution neural network model, respectively performing convolution processing on a user characteristic matrix constructed by the user data to obtain characteristic graphs corresponding to different continuous time windows, outputting the characteristic graphs through a full connection layer to obtain full connection characteristics and resource recovery probability, predicting user resource recovery risks through the resource recovery probability, comparing the user resource recovery risks with resource recovery labels of the user, and continuously adjusting parameters of the convolution neural network model until the output resource recovery probability is the same as the resource recovery labels.
S103, inputting the user behavior data matrix of the new user into the convolutional neural network model, and calculating to obtain the full-connection layer characteristics and the resource recovery probability of the convolutional neural network of the new user.
Specifically, according to the acquired user behavior data of the new user, processing the user behavior data into a user behavior data matrix, inputting the trained convolutional neural network model, and calculating to obtain the full connection layer characteristics and the resource recovery probability of the convolutional neural network of the new user. For example, the user behavior data matrix for user a in the last month is as follows:
and selecting all behavior data characteristics of 1-3 days when selecting the convolution kernel, finally obtaining the resource recovery probability of the user to be 0.6 through a convolution neural network model, and judging the resource recovery risk of the user according to a preset risk level.
And S104, predicting the resource recovery risk of the new user according to the full connection layer characteristics or the resource recovery probability of the new user.
Specifically, after the full connection layer feature and the resource recovery probability of the convolutional neural network of the new user are obtained, there may be two options, the first one predicts the resource recovery risk of the new user directly according to the resource recovery probability and the preset risk level, for example, in the above embodiment, the resource recovery probability of the user is obtained to be 0.6, and according to the preset risk level, it is determined that the resource recovery risk of the user is high, and the resource quota of the user may be reduced appropriately.
And secondly, training a resource recovery risk model by taking the full-connection layer characteristics of the historical user in the convolutional neural network model as training data, and inputting the full-connection layer characteristics of the new user into the resource recovery risk model to obtain a resource recovery risk predicted value of the new user.
Preferably, the full link layer features of the historical users in the convolutional neural network model are used as one-dimensional features, a resource recovery risk model is trained together with other identity features, and the full link layer features and the identity features of the new users are input into the trained resource recovery risk model to obtain the resource recovery risk prediction value of the new users.
The method can select all the user behavior data in a specific time period as convolution kernels according to needs, ensures that all the user behavior characteristics are applied during convolution processing, enables output results to be more accurate, accurately positions the risk control level corresponding to the user, and further improves the processing precision of risk control of the internet service platform.
Those skilled in the art will appreciate that all or part of the steps to implement the above-described embodiments are implemented as programs (computer programs) executed by a computer data processing apparatus. When the computer program is executed, the method provided by the invention can be realized. Furthermore, the computer program may be stored in a computer readable storage medium, which may be a readable storage medium such as a magnetic disk, an optical disk, a ROM, a RAM, or a storage array composed of a plurality of storage media, such as a magnetic disk or a magnetic tape storage array. The storage medium is not limited to centralized storage, but may be distributed storage, such as cloud storage based on cloud computing.
Embodiments of the apparatus of the present invention are described below, which may be used to perform method embodiments of the present invention. The details described in the device embodiments of the invention should be regarded as complementary to the above-described method embodiments; reference is made to the above-described method embodiments for details not disclosed in the apparatus embodiments of the invention.
Fig. 2 is a schematic block diagram of a resource recycling risk prediction apparatus based on a convolutional neural network according to the present invention. As shown in fig. 2, the apparatus 200 includes:
the information acquisition module 201 is configured to acquire a user behavior data matrix of a historical user and a resource recovery label indicating whether resources are recovered, where the user behavior data matrix includes a plurality of consecutive time points, and each time point has a plurality of behavior data;
the model training module 202 is configured to train a user behavior data matrix of the historical user and a resource recovery label as training samples of a convolutional neural network to obtain a convolutional neural network model for predicting a resource recovery probability;
the calculation module 203 is configured to input the user behavior data matrix of the new user into the convolutional neural network model, and calculate to obtain the full connection layer characteristics and the resource recovery probability of the convolutional neural network of the new user;
and the risk prediction module 204 is configured to predict the resource recovery risk of the new user according to the full connection layer characteristics or the resource recovery probability of the new user.
According to a preferred embodiment of the present invention, the model training module 202 is further configured to:
and setting a convolution kernel, and performing convolution processing on the user behavior data matrix by using the convolution kernel.
According to a preferred embodiment of the present invention, the setting the convolution kernel includes:
and selecting a convolution kernel with the size of m x n, wherein m is the number of all user behavior characteristics of the historical users at a time point in a preset time period, and n is preset continuous days.
According to the preferred embodiment of the present invention, the user behavior feature is behavior data of a user logging in a specific webpage or APP for operation in one day.
According to a preferred embodiment of the invention, the consecutive days are 3, 5 or 7 consecutive days.
According to a preferred embodiment of the present invention, the preset time period is one month before the current time.
According to a preferred embodiment of the present invention, the risk prediction module 204 is further configured to:
and directly predicting the resource recovery risk of the new user according to the resource recovery probability.
According to a preferred embodiment of the invention, the risk prediction module is further configured to:
and training a resource recovery risk model by using the full-connection characteristics of the historical users in the convolutional neural network model as training data, and inputting the full-connection layer characteristics of the new users into the resource recovery risk model to obtain a resource recovery risk prediction value of the new users.
According to a preferred embodiment of the present invention, the apparatus further comprises a model update module for:
acquiring behavior data and resource recovery results of the new user;
and inputting the behavior data of the new user and the resource recovery result into the convolutional neural network model, and updating the parameters of the convolutional neural network model.
Those skilled in the art will appreciate that the modules in the above-described embodiments of the apparatus may be distributed as described in the apparatus, and may be correspondingly modified and distributed in one or more apparatuses other than the above-described embodiments. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.
In the following, embodiments of the electronic device of the present invention are described, which may be regarded as specific physical implementations for the above-described embodiments of the method and apparatus of the present invention. Details described in the embodiments of the electronic device of the invention should be considered supplementary to the embodiments of the method or apparatus described above; for details which are not disclosed in embodiments of the electronic device of the invention, reference may be made to the above-described embodiments of the method or the apparatus.
FIG. 3 is a schematic diagram of an electronic device architecture for resource recycling risk prediction based on a convolutional neural network according to the present invention. An electronic apparatus 200 according to this embodiment of the present invention is described below with reference to fig. 3. The electronic device 200 shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
FIG. 3 is a schematic diagram of an electronic device architecture for model monitoring according to the present invention. An electronic device 300 according to this embodiment of the invention is described below with reference to fig. 3. The electronic device 300 shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 3, electronic device 300 is embodied in the form of a general purpose computing device. The components of electronic device 300 may include, but are not limited to: at least one processing unit 310, at least one memory unit 320, a bus 330 connecting the various system components (including the memory unit 320 and the processing unit 310), a display unit 340, and the like.
Wherein the storage unit stores program code executable by the processing unit 310, so that the processing unit 310 performs the steps according to various exemplary embodiments of the present invention described in the above-mentioned electronic prescription flow processing method section of the present specification. For example, the processing unit 310 may perform the steps as shown in fig. 1.
The storage unit 320 may include readable media in the form of volatile storage units, such as a random access memory unit (RAM) 3201 and/or a cache storage unit 3202, and may further include a read only memory unit (ROM) 3203.
The storage unit 320 may also include a program/utility 3204 having a set (at least one) of program modules 3205, such program modules 3205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The electronic device 300 may also communicate with one or more external devices 400 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 300, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 300 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 350. Also, the electronic device 300 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) via the network adapter 360. Network adapter 360 may communicate with other modules of electronic device 300 via bus 330. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with electronic device 300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments of the present invention described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to make a computing device (which can be a personal computer, a server, or a network device, etc.) execute the above-mentioned method according to the present invention. The computer program, when executed by a data processing apparatus, enables the computer readable medium to implement the above-described method of the invention, namely: acquiring a user behavior data matrix of a historical user and a resource recovery label indicating whether resources are recovered or not, wherein the user behavior data matrix comprises a plurality of continuous time points, and each time point is provided with a plurality of behavior data; training by taking the user behavior data matrix of the historical user and the resource recovery label as training samples of a convolutional neural network to obtain a convolutional neural network model for predicting the resource recovery probability; inputting the user behavior data matrix of the new user into the convolutional neural network model, and calculating to obtain the full-connection layer characteristics and the resource recovery probability of the convolutional neural network of the new user; and predicting the resource recovery risk of the new user according to the full connection layer characteristics or the resource recovery probability of the new user.
The computer program may be stored on one or more computer readable media, and fig. 4 is a schematic diagram of a computer readable storage medium of the present invention. As shown in fig. 4, the computer readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
In summary, the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functionality of some or all of the components in embodiments in accordance with the invention may be implemented in practice using a general purpose data processing device such as a microprocessor or a Digital Signal Processor (DSP). The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
While the foregoing embodiments have described the objects, aspects and advantages of the present invention in further detail, it should be understood that the present invention is not inherently related to any particular computer, virtual machine or electronic device, and various general-purpose machines may be used to implement the present invention. The invention is not to be considered as limited to the specific embodiments thereof, but is to be understood as being modified in all respects, all changes and equivalents that come within the spirit and scope of the invention.
Claims (10)
1. A resource recovery risk prediction method based on a convolutional neural network is characterized by comprising the following steps:
acquiring a user behavior data matrix of a historical user and a resource recovery label indicating whether resources are recovered or not, wherein the user behavior data matrix comprises a plurality of continuous time points, and each time point is provided with a plurality of behavior data;
training the user behavior data matrix of the historical user and the resource recovery label as training samples of a convolutional neural network to obtain a convolutional neural network model for predicting the resource recovery probability;
inputting the user behavior data matrix of the new user into the convolutional neural network model, and calculating to obtain the full-connection layer characteristics and the resource recovery probability of the convolutional neural network of the new user;
and predicting the resource recovery risk of the new user according to the full connection layer characteristics or the resource recovery probability of the new user.
2. The method of claim 1, wherein the training the user behavior data matrix resource recycling labels of the historical users as training samples of a convolutional neural network, further comprises:
and setting a convolution kernel, and performing convolution processing on the user behavior data matrix by using the convolution kernel.
3. The method of claim 2, wherein the setting the convolution kernel comprises:
and selecting a convolution kernel with the size of m x n, wherein m is the number of all user behavior characteristics of the historical users at a time point in a preset time period, and n is preset continuous days.
4. The method of claim 3, wherein the user behavior characteristic is behavior data of a user logging into a specific webpage or APP for operation in a day.
5. The method of claim 4, wherein the consecutive days are 3, 5, or 7 consecutive days.
6. The method of claim 4, wherein the preset time period is one month prior to the current time.
7. The method of claim 1, wherein predicting the resource recycling risk of the new user according to the full connection layer characteristics or the resource recycling probability of the new user further comprises:
and directly predicting the resource recovery risk of the new user according to the resource recovery probability.
8. A resource recovery risk prediction device based on a convolutional neural network, comprising:
the information acquisition module is used for acquiring a user behavior data matrix of a historical user and a resource recovery label which represents whether resources are recovered or not, wherein the user behavior data matrix comprises a plurality of continuous time points, and each time point is provided with a plurality of behavior data;
the model training module is used for training the user behavior data matrix of the historical user and the resource recovery label as training samples of a convolutional neural network to obtain a convolutional neural network model for predicting the resource recovery probability;
the calculation module is used for inputting the user behavior data matrix of the new user into the convolutional neural network model and calculating to obtain the full-connection layer characteristics and the resource recovery probability of the convolutional neural network of the new user;
and the risk prediction module is used for predicting the resource recovery risk of the new user according to the full connection layer characteristics or the resource recovery probability of the new user.
9. An electronic device, wherein the electronic device comprises:
a processor; and the number of the first and second groups,
a memory storing computer-executable instructions that, when executed, cause the processor to perform the method of any of claims 1-7.
10. A computer readable storage medium, wherein the computer readable storage medium stores one or more programs which, when executed by a processor, implement the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110155320.4A CN112508692A (en) | 2021-02-04 | 2021-02-04 | Resource recovery risk prediction method and device based on convolutional neural network and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110155320.4A CN112508692A (en) | 2021-02-04 | 2021-02-04 | Resource recovery risk prediction method and device based on convolutional neural network and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112508692A true CN112508692A (en) | 2021-03-16 |
Family
ID=74953098
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110155320.4A Pending CN112508692A (en) | 2021-02-04 | 2021-02-04 | Resource recovery risk prediction method and device based on convolutional neural network and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112508692A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570124A (en) * | 2021-07-15 | 2021-10-29 | 上海淇玥信息技术有限公司 | Object assignment method and device and electronic equipment |
| CN113570204A (en) * | 2021-07-06 | 2021-10-29 | 北京淇瑀信息科技有限公司 | User behavior prediction method, system and computer equipment |
-
2021
- 2021-02-04 CN CN202110155320.4A patent/CN112508692A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570204A (en) * | 2021-07-06 | 2021-10-29 | 北京淇瑀信息科技有限公司 | User behavior prediction method, system and computer equipment |
| CN113570124A (en) * | 2021-07-15 | 2021-10-29 | 上海淇玥信息技术有限公司 | Object assignment method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112270547A (en) | Financial risk assessment method and device based on feature construction and electronic equipment | |
| CN111192131A (en) | Financial risk prediction method and device and electronic equipment | |
| CN110796542A (en) | Financial risk control method, financial risk control device and electronic equipment | |
| CN110335140B (en) | Method and device for predicting loan black intermediary based on social relationship, and electronic equipment | |
| CN111145009A (en) | Method and device for evaluating risk after user loan and electronic equipment | |
| CN113177700B (en) | Risk assessment method, system, electronic equipment and storage medium | |
| US10678821B2 (en) | Evaluating theses using tree structures | |
| CN112508692A (en) | Resource recovery risk prediction method and device based on convolutional neural network and electronic equipment | |
| CN111210336A (en) | User risk model generation method and device and electronic equipment | |
| CN110675250A (en) | Credit line management method and device based on user marketing score and electronic equipment | |
| CN111597343B (en) | APP-based intelligent user occupation judgment method and device and electronic equipment | |
| CN114462532A (en) | Model training method, device, equipment and medium for predicting transaction risk | |
| CN111353872A (en) | Credit granting processing method and device based on financial performance value and electronic equipment | |
| CN115345530A (en) | Market address recommendation method, device and equipment and computer readable storage medium | |
| CN110689425A (en) | Method and device for pricing quota based on income and electronic equipment | |
| CN111221881A (en) | User characteristic data synthesis method and device and electronic equipment | |
| CN111582649B (en) | Risk assessment method and device based on user APP single-heat coding and electronic equipment | |
| CN113128773A (en) | Training method of address prediction model, address prediction method and device | |
| CN112348658A (en) | Resource allocation method and device and electronic equipment | |
| CN111445139A (en) | Business process simulation method and device, storage medium and electronic equipment | |
| CN116703466A (en) | System access quantity prediction method based on improved wolf algorithm and related equipment thereof | |
| CN114742645B (en) | User security level identification method and device based on multi-stage time sequence multitask | |
| CN113568739B (en) | User resource quota allocation method and device and electronic equipment | |
| CN112348661B (en) | Service policy distribution method and device based on user behavior track and electronic equipment | |
| CN113988914A (en) | User value prediction method and device 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 |