CN110728516A - Method, device and equipment for updating wind control model - Google Patents
Method, device and equipment for updating wind control model Download PDFInfo
- Publication number
- CN110728516A CN110728516A CN201910955003.3A CN201910955003A CN110728516A CN 110728516 A CN110728516 A CN 110728516A CN 201910955003 A CN201910955003 A CN 201910955003A CN 110728516 A CN110728516 A CN 110728516A
- Authority
- CN
- China
- Prior art keywords
- control model
- wind control
- local area
- area network
- terminal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 84
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 12
- 230000006399 behavior Effects 0.000 claims description 9
- 239000000126 substance Substances 0.000 claims description 3
- 230000008569 process Effects 0.000 description 23
- 238000010586 diagram Methods 0.000 description 17
- 230000006872 improvement Effects 0.000 description 9
- 230000001276 controlling effect Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012954 risk control Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 229920001296 polysiloxane Polymers 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012549 training Methods 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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/382—Payment protocols; Details thereof insuring higher security of transaction
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Computer Security & Cryptography (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the specification provides a method, a device and equipment for updating a wind control model. The scheme comprises the following steps: a terminal with a first wind control model is deployed to obtain trigger information for indicating that additional equipment is added to a local area network where the terminal is located; a second wind control model is deployed on other equipment added in the local area network; judging whether the updating time of the second wind control model is later than that of the first wind control model or not to obtain a first judgment result; and when the first judgment result shows that the updating time of the second wind control model is later than that of the first wind control model, updating the first wind control model based on the second wind control model.
Description
Technical Field
One or more embodiments of the present disclosure relate to the field of computer technologies, and in particular, to a method, an apparatus, and a device for updating a wind control model.
Background
At present, along with the popularization of mobile payment, more and more users adopt electronic equipment such as smart phones and the like as payment tools. Since the payment process involves economic benefits to the user, if the payment process is not regulated, the assets of the user may be lost. For example, some users may maliciously misappropriate third party users' devices for making payments, some users may utilize collection functions with electronic devices for fraud, and so on. Therefore, it is important to control the risk of the payment process.
In the prior art, the payment process is generally subjected to risk control through a wind control model. The wind control model is deployed on the cloud server. And the terminal sends the payment related information to the cloud server in the payment process. And the cloud server carries out risk identification according to the data reported by the terminal and the wind control model.
In the above manner, the calculation process related to the whole wind control process is basically performed in the cloud server, and the resource consumption of the cloud server is very large. In addition, when the wind control model is updated, resource consumption of the cloud server is further increased.
Disclosure of Invention
In view of this, one or more embodiments of the present disclosure provide a method, an apparatus, and a device for updating a wind control model, which are used to reduce resource consumption of a cloud server.
In order to solve the above technical problem, the embodiments of the present specification are implemented as follows:
an update method for a wind control model provided in an embodiment of the present specification includes:
the terminal acquires trigger information; the triggering information is used for indicating that other equipment is added to the local area network where the terminal is located; a first wind control model is deployed on the terminal, and a second wind control model is deployed on the other equipment;
judging whether the updating time of the second wind control model is later than that of the first wind control model or not to obtain a first judgment result;
and when the first judgment result shows that the updating time of the second wind control model is later than that of the first wind control model, updating the first wind control model based on the second wind control model.
An embodiment of the present specification provides a method for triggering update of a wind control model, including:
accessing a terminal with a first wind control model into a local area network;
broadcasting the version information of the first wind control model to the equipment in the local area network so as to trigger the equipment in the local area network to update the wind control model by adopting the method in the embodiment of the specification.
An embodiment of the present specification provides a method for triggering update of a wind control model, including:
accessing a terminal with a first wind control model into a local area network;
judging whether the updating time of a second wind control model in the local area network is earlier than that of the first wind control model or not to obtain a first judgment result;
and when the first judgment result shows that the updating time of the second wind control model is earlier than that of the first wind control model, sending black sample data of the first wind control model to online equipment in the local area network, so that the online equipment can update the wind control model of the online equipment on line according to the black sample data.
An update device of a wind control model provided by an embodiment of this specification includes:
a trigger information acquisition unit for acquiring trigger information; the triggering information is used for indicating that other equipment is added to the local area network where the terminal is located; a first wind control model is deployed on the terminal, and a second wind control model is deployed on the other equipment;
the judging unit is used for judging whether the updating time of the second wind control model is later than that of the first wind control model or not to obtain a first judging result;
and the wind control model updating unit is used for updating the first wind control model based on the second wind control model when the first judgment result shows that the updating time of the second wind control model is later than that of the first wind control model.
An update device of a wind control model provided by an embodiment of this specification includes:
the local area network access unit is used for enabling the terminal with the first wind control model to be accessed into a local area network;
and the version information broadcasting unit is configured to broadcast the version information of the first wind control model to the devices in the local area network so as to trigger the devices in the local area network to update the wind control model by using the method described in the embodiment of the present specification.
An embodiment of the present specification provides a trigger device for updating a wind control model, including:
the local area network access unit is used for accessing the terminal with the first wind control model into the local area network;
the judging unit is used for judging whether the updating time of the second wind control model in the local area network is earlier than that of the first wind control model to obtain a first judging result;
and a black sample data sending unit, configured to send the black sample data of the first wind control model to an online device in the local area network when the first determination result indicates that the update time of the second wind control model is earlier than the update time of the first wind control model, so that the online device updates the wind control model of the online device on line according to the black sample data.
An electronic device with a function of updating a wind-control model provided by an embodiment of the present specification includes:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring trigger information; the trigger information is used for indicating that another device is added to the local area network where the electronic device is located; a first wind control model is deployed on the electronic equipment, and a second wind control model is deployed on the other equipment;
judging whether the updating time of the second wind control model is later than that of the first wind control model or not to obtain a first judgment result;
when the first judgment result shows that the updating time of the second wind control model is later than that of the first wind control model, updating the first wind control model based on the second wind control model;
alternatively, the instructions are executable by the at least one processor to enable the at least one processor to:
controlling the electronic equipment with the first wind control model to access a local area network;
controlling the electronic device to broadcast the version information of the first wind control model to devices in the local area network so as to trigger the devices in the local area network to update the wind control model by adopting the method in the embodiment of the specification;
alternatively, the instructions are executable by the at least one processor to enable the at least one processor to:
controlling the electronic equipment with the first wind control model to access a local area network;
judging whether the updating time of a second wind control model in the local area network is earlier than that of the first wind control model or not to obtain a first judgment result;
and when the first judgment result shows that the updating time of the second wind control model is earlier than that of the first wind control model, controlling the electronic equipment to send black sample data of the first wind control model to online equipment in the local area network, so that the online equipment can update the wind control model of the online equipment on line according to the black sample data.
An embodiment of this specification provides a wind control system, includes:
the system comprises a cloud server, a first terminal and a second terminal;
the cloud server is used for generating a wind control model and issuing the wind control model to the terminals, determining black sample data based on user behavior data reported by each terminal, and issuing the black sample data to the terminals;
the first terminal is deployed with a first version of the wind control model, and is configured to:
when the second terminal is accessed to the local area network where the first terminal is located, the wind control model of the first terminal is updated on line based on black sample data of the wind control model of the second version of the second terminal;
acquiring the black sample data issued by the cloud server; and updating the wind control model of the first terminal on line based on the black sample data issued by the cloud server.
One embodiment of the present description achieves the following advantageous effects: the method comprises the steps of comparing the updating time of a wind control model deployed on newly-accessed network equipment with the updating time of a wind control model deployed by an online terminal in a local area network by acquiring the trigger information of adding other equipment into the local area network where the terminal is located, and updating the wind control model with the early updating time based on the wind control model with the late updating time. The updating model is deployed on the terminal, and the updating process of the wind control model is also performed in the terminal, so that the resource consumption of the cloud server is reduced, and the operating pressure of the cloud server is reduced.
Drawings
The accompanying drawings, which are included to provide a further understanding of one or more embodiments of the disclosure and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the disclosure and together with the description serve to explain the embodiments of the disclosure and not to limit the embodiments of the disclosure. In the drawings:
fig. 1 is a schematic overall architecture diagram of an update system of a wind control model in an embodiment of the present disclosure;
FIG. 2 is a schematic diagram illustrating an online learning principle of a wind control model in an embodiment of the present disclosure;
fig. 3 is a schematic flowchart of a method for updating a wind control model according to an embodiment of the present disclosure;
fig. 4 is a schematic diagram illustrating a structure and an operation principle of a wind control model according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an updating apparatus of a wind control model corresponding to fig. 3 provided in an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of an updating apparatus corresponding to one of the wind control models of fig. 3, provided in an embodiment of the present specification.
Detailed Description
To make the objects, technical solutions and advantages of one or more embodiments of the present disclosure more apparent, the technical solutions of one or more embodiments of the present disclosure will be described in detail and completely 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 specification, and not all embodiments. All other embodiments that can be derived by a person skilled in the art from the embodiments given herein without making any creative effort fall within the scope of protection of one or more embodiments 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 the prior art, when risk control is performed on payment transactions through a wind control model, the wind control model is mainly deployed on a cloud server. The cloud server is generally required to update the model according to the acquired data, and the updated risk model is issued to each mobile terminal device connected to the local area network so as to replace the risk model on each mobile terminal device, so that the resource consumption of the cloud server is increased, and the operating pressure of the cloud server is increased.
In order to solve the defects in the prior art, the scheme provides the following embodiments:
fig. 1 is a schematic overall architecture diagram of an update system of a wind control model in an embodiment of the present disclosure. As shown in fig. 1, the system may include:
the system comprises a cloud server 101, a first terminal 102 and a second terminal 103; the cloud server 101 may be configured to generate a wind control model and issue the wind control model to the terminals, or determine black sample data based on user behavior data reported by each terminal, and then issue the black sample data to the terminals; the first terminal 102 may be deployed with a first version of the wind control model, and it should be noted that the first terminal 102 may be configured to perform online update on the wind control model of the first terminal 102 based on black sample data of the second version of the wind control model of the second terminal 103 when the second terminal 103 is accessed to the local area network where the first terminal 102 is located; the first terminal 102 may also be configured to obtain black sample data sent by the cloud server 101; and updating the wind control model of the first terminal 102 on line based on the black sample data issued by the cloud server 101.
It should be noted that, when the cloud server 101 issues the wind control model or the black sample data to the terminal, the wind control model or the black sample data may be issued through the edge device 104, and the edge device 104 may be a network access device of a local area network, for example: a router. In the embodiments of the present specification, black sample data may represent involved transactions, such as: there are transactions in which the user complains and determines that the complaint is established, such as transactions in which the account is stolen, cash-out, etc. In the system shown in fig. 1, the first terminal 102 and the second terminal 103 are specifically shown for illustrative purposes only, and the system may further include another plurality of terminal devices.
It should be further noted that the model issued to each terminal in the lan may be learned online on the terminal side, where the principle process of online learning is shown in fig. 2.
Fig. 2 is a schematic diagram of an online learning principle of a wind control model in an embodiment of this specification, and as shown in fig. 2, when the model is online learned, the model can be online learned according to black sample data 201 in a device newly accessed to a local area network, and the model is updated.
Fig. 3 is a schematic flow chart of an updating method of a wind control model according to an embodiment of the present disclosure. From the viewpoint of a program, the execution subject of the flow may be a program installed in an application server or an application client.
As shown in fig. 3, the process may include the following steps:
step 302: the terminal acquires trigger information; the triggering information is used for indicating that other equipment is added to the local area network where the terminal is located; and a first wind control model is deployed on the terminal, and a second wind control model is deployed on the other equipment.
A Terminal (Terminal), also called a Terminal device, may refer to a device located at the outermost periphery of a network in a computer network, and is mainly used for inputting user information and outputting a processing result. The terminal can be a mobile phone, a tablet personal computer, an intelligent television, a computer and the like. The terminal in step 302 in this embodiment may be a terminal that has access to a local area network.
The trigger information may be information indicating that another device is newly accessed in the local area network in which the terminal is located. Such as: when the device 1 and the device 2 originally exist in the local area network, when the device 3 is accessed in the local area network, the device 1 and the device 2 originally existing in the local area network can acquire the notification information of the access device 3 in the local area network forwarded by the router, and the notification information can be used as trigger information.
The terminal is provided with a first wind control model, and other newly accessed devices in the local area network can be provided with a second wind control model. It should be noted that the wind control model mentioned here can be used for predictive control of the risk of the transaction. The local area network may include a plurality of terminals, and the wind control model deployed on each terminal may be regarded as a model with a consistent version.
Step 304: and judging whether the updating time of the second wind control model is later than that of the first wind control model or not to obtain a first judgment result.
In practical application, when the wind control model in the terminal is updated, the update time of the wind control model can be recorded in the terminal. After the terminal acquires the trigger information of the new device access in the local area network, the update time of the wind control model deployed on the newly accessed device and the update time of the wind control model deployed on the terminal can be acquired and determined.
The update time may include a timestamp recorded in the terminal when the server issues the new model to the terminal, and may also include other information that can determine the model update time, such as: the version number of the model, from which the old and new version of the model can be seen, is as follows: the version 1.0 and the version 2.0, it can be considered that the version 2.0 belongs to the new version and the update time is later than the version 1.0.
Step 306: and when the first judgment result shows that the updating time of the second wind control model is later than that of the first wind control model, updating the first wind control model based on the second wind control model.
And when the update time of the first wind control model is compared with that of the second wind control model, the model with the later update time is a new model. For example: the local area network comprises a terminal 1 and a terminal 2, the equipment newly accessed into the local area network is a terminal 3, the wind control models deployed on the terminal 1 and the terminal 2 are both a model 1, and the updating time of the model 1 is as follows: 5 months and 4 days in 2019; the wind control model deployed on the terminal 3 is the model 2, and the update time of the model 2 is as follows: 6 months and 4 days in 2019; at this time, it can be determined that the update time of model 2 is later than that of model 1, and therefore model 2 can be considered as a new model with respect to model 1.
It should be understood that the order of some of the steps of the method described in one or more embodiments of the present disclosure may be changed as desired.
In practical application, the initial wind control model and the updated model can be generated by the cloud server and issued to each terminal device. However, when a part of terminal devices are not online when the cloud server issues the model, the online terminal devices acquire the latest wind control model, but the offline terminal devices do not acquire the latest wind control model. If the method of the embodiment of the present specification is adopted, after the terminal device with the latest wind control model is accessed to a local area network, the terminal device may communicate with the on-network device in the local area network for the update time information of the wind control model, and when the wind control model on the newly-accessed terminal is new to the wind control model on the device in the local area network, the newly-accessed terminal may update the wind control model on the device in the local area network with the device in the local area network. The updating process of the wind control model in the local area network basically does not need the intervention of the cloud server, so that the operating pressure of the cloud server can be reduced to a great extent, and the resource consumption of the cloud server is reduced.
In summary, in the method in fig. 3, by acquiring the trigger information of adding another device to the local area network where the terminal is located, the update times of the wind control model deployed on the newly added device and the wind control model deployed by the terminal are compared, and the wind control model with the earlier update time is updated based on the wind control model with the later update time. The updating model is deployed on the terminal, and the updating process of the wind control model is also performed in the terminal, so that the resource consumption of the cloud server is reduced, and the operating pressure of the cloud server is reduced.
It should be further noted that, because the wind control model is deployed at the terminal, each risk identification process can be completed by the terminal itself, and the cloud server is not required to participate in each risk identification process, so that the resource occupation of the cloud server is further reduced. In addition, when the terminal itself adopts the wind control model to carry out risk identification, the operation behavior data of the user and the privacy protection data which can be obtained by the terminal can be obtained most directly, and the performance of the wind control model can be utilized to the greatest extent by adopting the wind control model based on the data. The cloud server is difficult to acquire the data. Therefore, the wind control model is deployed at the terminal, and the following beneficial effects are also achieved: the data required by the wind control model can be acquired in a relatively short time; the operation behavior data of the user and part of the privacy protection data can be fully utilized.
Based on the method of fig. 3, the embodiments of the present specification also provide some specific implementations of the method, which are described below.
Optionally, the acquiring of the trigger information specifically may include: and acquiring the equipment network access information forwarded by the network access equipment of the local area network. The acquiring of the trigger information may specifically include: and acquiring version information of the second wind control model broadcasted by the other equipment in the local area network.
It should be noted that the network entry Device may be an Edge Device (Edge Device), such as: the network entry device may be a switch, router, routing switch, Integrated Access Device (IAD) installed on the edge network.
Each local area network may be connected through a network entry device, for example, a Router (Router), and when a new device is accessed in the local area network, the Router may forward information of accessing the new device in the local area network to each device in the local area network.
The acquisition trigger information may be: acquiring device access information forwarded by an entry device of the local area network, for example, information of a new device accessing the local area network forwarded by a router connected to the local area network. In addition, after the new device is accessed to the local area network, the version information corresponding to the risk model deployed in the new device may also be broadcast in the local area network, and therefore, the acquiring of the trigger information may also be: and acquiring version information of the wind control model which is broadcasted in the local area network by the new equipment accessed into the local area network and is deployed by the new equipment.
When the obtaining manner of the trigger information is that the access device of the local area network forwards the network access information of the new device to the network terminal, the determining whether the update time of the second wind control model is later than the update time of the first wind control model may further include:
the on-line terminal sends a version acquisition request to the other equipment according to the equipment network access information;
and obtaining the version information of the second wind control model fed back by the other equipment based on the version obtaining request.
By the method, the equipment in the local area network can acquire the version information of the model deployed on the terminal newly added in the local area network, and the terminal equipment in the local area network can conveniently judge whether the deployed model needs to be updated or not.
The determining whether the update time of the second wind control model is later than the update time of the first wind control model may specifically include:
and judging whether the version of the second wind control model is newer than the version of the first wind control model or not according to the version information.
In practical application, after the device in the local area network receives the version information of the wind control model deployed on the terminal newly added to the local area network, whether the wind control model deployed on the device newly added to the local area network is a new model or not can be judged according to the version information of the wind control model. Specifically, whether the wind control model deployed on the device newly accessed to the local area network is a new model or not can be judged according to the version number of the model or the timestamp of the model update. The following can be described for these two determination methods:
and judging whether the wind control model deployed on the equipment newly accessed into the local area network is a new model according to the version number of the model.
The determining, according to the version number information of the model, whether the wind control model deployed on the device newly accessed to the local area network is a new model may specifically include:
judging whether the model in the new equipment is a new model relative to the model per se according to the version number corresponding to the model in the newly accessed equipment to obtain a judgment result;
when the model in the new device is judged to be a new model or not relative to the model of the model, the model on the new device can be obtained, and the model of the model is updated to the model with the same version number as the model deployed on the new device.
It should be noted that the version number (version number) may be an identification number of a version, one model may correspond to one model version number, and the update time of the model may be determined according to the version number of the model, for example: version 1.0 of the model, version 2.0 of the model is a new version relative to version 1.0.
And judging whether the wind control model deployed on the equipment newly accessed into the local area network is a new model according to the timestamp updated by the model.
Specifically, it may be determined whether the timestamp updated by the wind control model deployed on the device newly accessing the local area network is later than the timestamp corresponding to the wind control model deployed by the terminal itself.
And when the timestamp of the update of the wind control model deployed on the equipment newly accessed into the local area network is later than the timestamp corresponding to the wind control model deployed on the terminal, updating the model deployed on the terminal into a model with the version number consistent with the version number of the model deployed on the new equipment. For example: before the new device is accessed, the device 2 and the device 3 exist in the local area network, the update timestamp of the model deployed on the device 2 and the device 3 is 2019, 5, month and 4, the terminal 1 newly added into the local area network exists, the update timestamp of the model deployed on the terminal 1 is 2019, 6, month and 4, and at the moment, the model on the terminal newly added into the local area network can be judged to be a new model.
It should be noted that the timestamp of the model update described above may indicate a time record when the server issues the new model to the terminal device.
By the method, the equipment in the local area network judges whether the model deployed on the terminal newly added into the local area network is a new model or not according to the version number corresponding to the model deployed on the terminal newly added into the local area network or the timestamp for updating the model, so that the equipment in the local area network can quickly know whether the model of the new equipment added into the local area network is the new model or not.
In practical application, the wind control model can be a model with online learning capability, and self-learning can be performed according to black sample data so as to update the wind control model. Therefore, the latest black sample data can be sent to the terminal equipment with the wind control model, so that the terminal equipment can automatically complete the updating process of the wind control model according to the latest black sample data.
Specifically, the updating the first wind control model based on the second wind control model may include:
acquiring first black sample data of the second wind control model;
and performing self-learning by adopting an online learning algorithm based on the first black sample data to update the first wind control model, so as to obtain the updated first wind control model.
When the wind control model deployed on each device in the local area network is updated, self-learning may be performed by using an online learning algorithm using black sample data in a terminal newly accessed to the local area network, so as to update the model, and further, the self-learning may be performed by using the online learning algorithm to update the first wind control model, which may specifically include:
and updating the first wind control model by adopting an FTRL algorithm.
The FTRL (Follow-the-regularized-Leader) algorithm is an online learning algorithm, which can ensure higher accuracy and can generate better sparsity under the condition of losing a certain accuracy. The FTRL algorithm is adopted in the scheme, so that an online updating model can be realized.
The black sample data can be wholly sent to the equipment with the deployed model by the cloud server, the equipment can perform online learning according to the black sample data, and the server side does not need to send the updated whole model to the terminal equipment. After the server side issues the black sample data to the terminal equipment in the local area network, the terminal equipment updates the wind control model deployed by the terminal equipment according to the black sample data, and online updating of the model on the Internet of Things (Internet of Things, referred to as IOT for short) is achieved.
By the method, the wind control model can rapidly cope with risks, and resource consumption of the server can be reduced.
In practical application, the specific manner of updating the model by the terminal may further include:
acquiring second black sample data sent by the cloud server;
and updating the updated first wind control model again by adopting an online learning algorithm based on the second black sample data.
By the method, the model can be deployed on the edge equipment, the model can be updated on the Internet of things on line, the model can be guaranteed to deal with risks quickly, and system resources are greatly saved.
Fig. 4 is a schematic view of a structure and an operation principle of a wind control model provided in an embodiment of the present specification, and as shown in fig. 4, the model includes a data layer and a model layer, and in the data layer, rich information can be obtained at a terminal device, for example: transaction information, Remote Procedure Call (RPC) data, gyroscope sensing data, touch screen behavior data, and the like. The global model can be established and the model can be updated by using data in the data layer, and more specifically, the model can be developed and a model file can be generated by relying on a machine learning Platform (PAI) during training. After the model is trained, the model may be delivered to each terminal in the local area network. The gyroscope can be used for acquiring the gesture of a user for terminal operation, the touch screen behavior can represent the finger and stroke operation or the stroke and rotation action and the like of the user on a terminal interface, and according to the acquired transaction information, the historical operation behavior of the user, the recognition gesture of the user, the touch screen behavior of the user and the like, the feature vector with better coverage and accuracy can be acquired, so that the trained model has better performance and more accurate prediction effect.
Based on the same idea, an embodiment of the present specification further provides a method for triggering update of a wind control model, which may include:
accessing a terminal with a first wind control model into a local area network;
broadcasting the version information of the first wind control model to the devices in the local area network so as to trigger the devices in the local area network to update the wind control model by adopting the method according to the embodiment of the specification.
It should be noted that, the device newly accessing the local area network may broadcast version information of the model deployed by the device in the local area network, and each device networked in the local area network may receive the model version information broadcast by the new device and determine whether to update the model of the device according to the version information.
By the method, the equipment accessed into the local area network can spontaneously broadcast the version information of the model of the equipment, so that the efficiency of acquiring the version information of the new equipment model by other equipment in the local area network is improved.
Based on the same idea, an embodiment of the present specification further provides a method for triggering update of a wind control model, which may include:
accessing a terminal with a first wind control model into a local area network;
judging whether the updating time of a second wind control model in the local area network is earlier than that of the first wind control model or not to obtain a first judgment result;
and when the first judgment result shows that the updating time of the second wind control model is earlier than that of the first wind control model, sending black sample data of the first wind control model to online equipment in the local area network, so that the online equipment can update the wind control model of the online equipment on line according to the black sample data.
In the actual application process, the new device newly added into the local area network can judge whether the updating time of the model is earlier than that of the model deployed on the original device in the local area network, if so, the model deployed by the new device can be regarded as the new model, and black sample data corresponding to the model is broadcasted in the local area network or sent to each device in the local area network, so that the original device in the local area network can update the model according to the black sample data.
By the method, the newly-accessed equipment can send the black sample data to other equipment in the local area network, so that the other equipment in the local area network can update the model according to the black sample data, the cloud server is not required to send the black sample data, and the resource consumption of the server is reduced.
Based on the same idea, the embodiment of the present specification further provides a device corresponding to the above method. Fig. 5 is a schematic structural diagram of an updating apparatus of a wind control model corresponding to fig. 3 provided in an embodiment of the present disclosure. As shown in fig. 5, the apparatus may include:
a trigger information acquiring unit 502 configured to acquire trigger information; the triggering information is used for indicating that other equipment is added to the local area network where the terminal is located; a first wind control model is deployed on the terminal, and a second wind control model is deployed on the other equipment;
a determining unit 504, configured to determine whether an update time of the second wind control model is later than an update time of the first wind control model, to obtain a first determination result;
a wind control model updating unit 506, configured to update the first wind control model based on the second wind control model when the first determination result indicates that the update time of the second wind control model is later than the update time of the first wind control model.
Based on the device of fig. 5, the embodiments of the present specification also provide some specific implementations of the method, which are described below.
Optionally, the trigger information obtaining unit 502 may specifically include:
and the equipment network access information acquisition subunit is used for acquiring the equipment network access information forwarded by the network access equipment of the local area network.
Optionally, the apparatus may further include:
a version acquisition request sending unit, configured to send a version acquisition request to the other device according to the device network access information;
a model version information obtaining unit, configured to obtain version information of the second wind control model fed back by the other device based on the version obtaining request.
Optionally, the trigger information obtaining unit 502 may be specifically configured to:
and acquiring version information of the second wind control model broadcasted by the other equipment in the local area network.
Optionally, the determining unit 504 may be specifically configured to:
and judging whether the version of the second wind control model is newer than the version of the first wind control model or not according to the version information.
Optionally, the wind control model updating unit 506 may be specifically configured to:
a first black sample data obtaining subunit, configured to obtain first black sample data of the second wind control model;
and the first model updating subunit is used for performing self-learning by adopting an online learning algorithm based on the first black sample data to update the first wind control model, so as to obtain the updated first wind control model.
Optionally, the model updating subunit may be specifically configured to:
and updating the first wind control model by adopting an FTRL algorithm.
Optionally, the wind control model updating unit 506 may further include:
the second black sample data acquisition subunit is used for acquiring second black sample data sent by the cloud server;
and the second model updating subunit is used for updating the updated first wind control model again by adopting an online learning algorithm based on the second black sample data.
Based on the same idea, embodiments of the present specification further provide an updating apparatus for a wind control model, where the updating apparatus may include:
the local area network access unit is used for enabling the terminal with the first wind control model to be accessed into a local area network;
and the version information broadcasting unit is configured to broadcast the version information of the first wind control model to the devices in the local area network so as to trigger the devices in the local area network to update the wind control model by using the method described in the embodiment of the present specification.
Based on the same idea, an embodiment of the present specification further provides a trigger device for updating a wind control model, where the trigger device may include:
the local area network access unit is used for accessing the terminal with the first wind control model into the local area network;
the judging unit is used for judging whether the updating time of the second wind control model in the local area network is earlier than that of the first wind control model to obtain a first judging result;
and a black sample data sending unit, configured to send the black sample data of the first wind control model to an online device in the local area network when the first determination result indicates that the update time of the second wind control model is earlier than the update time of the first wind control model, so that the online device updates the wind control model of the online device on line according to the black sample data.
Based on the same idea, the embodiment of the present specification further provides a device corresponding to the above method.
Fig. 6 is a schematic structural diagram of an updating apparatus corresponding to one of the wind control models of fig. 3, provided in an embodiment of the present specification. As shown in fig. 6, the apparatus 600 may include:
at least one processor 610; and the number of the first and second groups,
a memory 630 communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory 630 stores instructions 620 executable by the at least one processor 610 to enable the at least one processor 610 to:
acquiring trigger information; the trigger information is used for indicating that another device is added to the local area network where the electronic device is located; a first wind control model is deployed on the electronic equipment, and a second wind control model is deployed on the other equipment;
judging whether the updating time of the second wind control model is later than that of the first wind control model or not to obtain a first judgment result;
when the first judgment result shows that the updating time of the second wind control model is later than that of the first wind control model, updating the first wind control model based on the second wind control model;
alternatively, the instructions are executable by the at least one processor to enable the at least one processor to:
controlling the electronic equipment with the first wind control model to access a local area network;
controlling the electronic device to broadcast the version information of the first wind control model to devices in the local area network so as to trigger the devices in the local area network to update the wind control model by adopting the method in the embodiment of the specification;
alternatively, the instructions are executable by the at least one processor to enable the at least one processor to:
controlling the electronic equipment with the first wind control model to access a local area network;
judging whether the updating time of a second wind control model in the local area network is earlier than that of the first wind control model or not to obtain a first judgment result;
and when the first judgment result shows that the updating time of the second wind control model is earlier than that of the first wind control model, controlling the electronic equipment to send black sample data of the first wind control model to online equipment in the local area network, so that the online equipment can update the wind control model of the online equipment on line according to the black sample data.
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 the 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 modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. 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 making an integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Language Description Language), traffic, pl (core unified Programming Language), HDCal, JHDL (Java Hardware Description Language), langue, Lola, HDL, laspam, hardsradware (Hardware Description Language), vhjhd (Hardware Description Language), and vhigh-Language, which are currently used in most common. 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 as pure computer readable program code, 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 regarded as being both a software module for performing 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 functionality of the various elements may be implemented in the same one or more software and/or hardware implementations in implementing one or more embodiments of the present description.
One skilled in the art will recognize that one or more embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, one or more embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of the present 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.
One or more embodiments of the present description are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to one or more 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 disk storage or other magnetic storage devices, or any other non-transmission medium which can be used to store information that can be accessed by a computing device. 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 phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
One or more embodiments of the present 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. One or more embodiments of 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 merely exemplary of the present disclosure and is not intended to limit one or more embodiments of the present disclosure. Various modifications and alterations to one or more embodiments described herein will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of the present specification should be included in the scope of claims of one or more embodiments of the present specification.
Claims (15)
1. An updating method of a wind control model comprises the following steps:
the terminal acquires trigger information; the triggering information is used for indicating that other equipment is added to the local area network where the terminal is located; a first wind control model is deployed on the terminal, and a second wind control model is deployed on the other equipment;
judging whether the updating time of the second wind control model is later than that of the first wind control model or not to obtain a first judgment result;
and when the first judgment result shows that the updating time of the second wind control model is later than that of the first wind control model, updating the first wind control model based on the second wind control model.
2. The method of claim 1, wherein the acquiring the trigger information specifically includes:
and acquiring the equipment network access information forwarded by the network access equipment of the local area network.
3. The method of claim 2, the determining whether the update time of the second wind control model is later than the update time of the first wind control model, further comprising:
sending a version acquisition request to the other equipment according to the equipment network access information;
and obtaining the version information of the second wind control model fed back by the other equipment based on the version obtaining request.
4. The method of claim 1, wherein the acquiring the trigger information specifically includes:
and acquiring version information of the second wind control model broadcasted by the other equipment in the local area network.
5. The method according to any one of claims 1 to 4, wherein the determining whether the update time of the second wind control model is later than the update time of the first wind control model specifically includes:
and judging whether the version of the second wind control model is newer than the version of the first wind control model or not according to the version information.
6. The method according to claim 1, wherein updating the first wind control model based on the second wind control model specifically includes:
acquiring first black sample data of the second wind control model;
and performing self-learning by adopting an online learning algorithm based on the first black sample data to update the first wind control model, so as to obtain the updated first wind control model.
7. The method of claim 6, wherein the self-learning using an online learning algorithm to update the first wind control model comprises:
and updating the first wind control model by adopting an FTRL algorithm.
8. The method of claim 6, further comprising:
acquiring second black sample data sent by the cloud server;
and updating the updated first wind control model again by adopting an online learning algorithm based on the second black sample data.
9. A method for triggering wind control model updating comprises the following steps:
accessing a terminal with a first wind control model into a local area network;
broadcasting the version information of the first wind control model to the devices in the local area network so as to trigger the devices in the local area network to update the wind control model by using the method according to claim 1.
10. A method for triggering wind control model updating comprises the following steps:
accessing a terminal with a first wind control model into a local area network;
judging whether the updating time of a second wind control model in the local area network is earlier than that of the first wind control model or not to obtain a first judgment result;
and when the first judgment result shows that the updating time of the second wind control model is earlier than that of the first wind control model, sending black sample data of the first wind control model to online equipment in the local area network, so that the online equipment can update the wind control model of the online equipment on line according to the black sample data.
11. An updating device of a wind control model comprises:
a trigger information acquisition unit for acquiring trigger information; the triggering information is used for indicating that other equipment is added to the local area network where the terminal is located; a first wind control model is deployed on the terminal, and a second wind control model is deployed on the other equipment;
the judging unit is used for judging whether the updating time of the second wind control model is later than that of the first wind control model or not to obtain a first judging result;
and the wind control model updating unit is used for updating the first wind control model based on the second wind control model when the first judgment result shows that the updating time of the second wind control model is later than that of the first wind control model.
12. An updating device of a wind control model comprises:
the local area network access unit is used for enabling the terminal with the first wind control model to be accessed into a local area network;
a version information broadcasting unit, configured to broadcast the version information of the first wind control model to devices in the local area network, so as to trigger the devices in the local area network to update the wind control model according to the method recited in claim 1.
13. A triggering device for updating a wind control model comprises:
the local area network access unit is used for accessing the terminal with the first wind control model into the local area network;
the judging unit is used for judging whether the updating time of the second wind control model in the local area network is earlier than that of the first wind control model to obtain a first judging result;
and a black sample data sending unit, configured to send the black sample data of the first wind control model to an online device in the local area network when the first determination result indicates that the update time of the second wind control model is earlier than the update time of the first wind control model, so that the online device updates the wind control model of the online device on line according to the black sample data.
14. An electronic device with a wind-controlled model updating function, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring trigger information; the trigger information is used for indicating that another device is added to the local area network where the electronic device is located; a first wind control model is deployed on the electronic equipment, and a second wind control model is deployed on the other equipment;
judging whether the updating time of the second wind control model is later than that of the first wind control model or not to obtain a first judgment result;
when the first judgment result shows that the updating time of the second wind control model is later than that of the first wind control model, updating the first wind control model based on the second wind control model;
alternatively, the instructions are executable by the at least one processor to enable the at least one processor to:
controlling the electronic equipment with the first wind control model to access a local area network;
controlling the electronic device to broadcast the version information of the first wind control model to devices in the local area network so as to trigger the devices in the local area network to update the wind control model by using the method according to claim 1;
alternatively, the instructions are executable by the at least one processor to enable the at least one processor to:
controlling the electronic equipment with the first wind control model to access a local area network;
judging whether the updating time of a second wind control model in the local area network is earlier than that of the first wind control model or not to obtain a first judgment result;
and when the first judgment result shows that the updating time of the second wind control model is earlier than that of the first wind control model, controlling the electronic equipment to send black sample data of the first wind control model to online equipment in the local area network, so that the online equipment can update the wind control model of the online equipment on line according to the black sample data.
15. A wind control system comprising:
the system comprises a cloud server, a first terminal and a second terminal;
the cloud server is used for generating a wind control model and issuing the wind control model to the terminals, determining black sample data based on user behavior data reported by each terminal, and issuing the black sample data to the terminals;
the first terminal is deployed with a first version of the wind control model, and is configured to:
when the second terminal is accessed to the local area network where the first terminal is located, the wind control model of the first terminal is updated on line based on black sample data of the wind control model of the second version of the second terminal;
acquiring the black sample data issued by the cloud server; and updating the wind control model of the first terminal on line based on the black sample data issued by the cloud server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910955003.3A CN110728516A (en) | 2019-10-09 | 2019-10-09 | Method, device and equipment for updating wind control model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910955003.3A CN110728516A (en) | 2019-10-09 | 2019-10-09 | Method, device and equipment for updating wind control model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110728516A true CN110728516A (en) | 2020-01-24 |
Family
ID=69219863
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910955003.3A Pending CN110728516A (en) | 2019-10-09 | 2019-10-09 | Method, device and equipment for updating wind control model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110728516A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112270478A (en) * | 2020-10-30 | 2021-01-26 | 重庆富民银行股份有限公司 | Management method and platform for wind control model competition |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101183312A (en) * | 2007-12-12 | 2008-05-21 | 中兴通讯股份有限公司 | Method for realizing version upgrade and backup of terminal by switch-in USB memory apparatus |
| CN104899334A (en) * | 2015-06-24 | 2015-09-09 | 惠州华阳通用电子有限公司 | Device and method for updating multimedia play list |
| CN105917613A (en) * | 2014-10-14 | 2016-08-31 | 华为技术有限公司 | Software upgrading method and device |
| CN107360179A (en) * | 2017-07-31 | 2017-11-17 | 腾讯科技（深圳）有限公司 | A kind of risk information shared method, terminal and computer-readable recording medium |
-
2019
- 2019-10-09 CN CN201910955003.3A patent/CN110728516A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101183312A (en) * | 2007-12-12 | 2008-05-21 | 中兴通讯股份有限公司 | Method for realizing version upgrade and backup of terminal by switch-in USB memory apparatus |
| CN105917613A (en) * | 2014-10-14 | 2016-08-31 | 华为技术有限公司 | Software upgrading method and device |
| CN104899334A (en) * | 2015-06-24 | 2015-09-09 | 惠州华阳通用电子有限公司 | Device and method for updating multimedia play list |
| CN107360179A (en) * | 2017-07-31 | 2017-11-17 | 腾讯科技（深圳）有限公司 | A kind of risk information shared method, terminal and computer-readable recording medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112270478A (en) * | 2020-10-30 | 2021-01-26 | 重庆富民银行股份有限公司 | Management method and platform for wind control model competition |
| CN112270478B (en) * | 2020-10-30 | 2023-06-09 | 重庆富民银行股份有限公司 | Management method and platform for competition of wind control model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107450981B (en) | Block chain consensus method and equipment | |
| US10515056B2 (en) | API for resource discovery and utilization | |
| JP2020503601A (en) | Information presentation method and device | |
| US9635129B2 (en) | Automatic application discovery, download, integration and launch | |
| WO2019227994A1 (en) | Method and apparatus for updating application prediction model, storage medium, and terminal | |
| US20150024720A1 (en) | Remote Testing Through Third Party Devices | |
| US20160188895A1 (en) | Electronic system with access management mechanism and method of operation thereof | |
| CN110717536A (en) | Method and device for generating training sample | |
| CN109922142B (en) | File downloading method, device and system | |
| CN111158597A (en) | Metadata reading method and device, electronic equipment and storage medium | |
| CN115203394A (en) | Model training method, service execution method and device | |
| CN108536569B (en) | Business behavior tracking method, device and equipment | |
| CN116542663A (en) | Method, device, equipment and medium for accessing payment page of aggregation code | |
| CN107479868B (en) | Interface loading method, device and equipment | |
| CN109558553B (en) | Method and device for determining style | |
| CN110728516A (en) | Method, device and equipment for updating wind control model | |
| CN115545720B (en) | Model training method, business wind control method and business wind control device | |
| CN113408254A (en) | Page form information filling method, device, equipment and readable medium | |
| CN111767053A (en) | Front-end page data acquisition method and device | |
| CN108133123B (en) | Application program identification method and system | |
| CN110874322A (en) | Test method and test server for application program | |
| CN115563584A (en) | Model training method and device, storage medium and electronic equipment | |
| CN110858238A (en) | Data processing method and device | |
| CN110704742B (en) | Feature extraction method and device | |
| CN115914219A (en) | Task request processing method, device and system, readable 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200124 |
|
| RJ01 | Rejection of invention patent application after publication |