CN113222649A - Method and device for recommending service execution mode - Google Patents
Method and device for recommending service execution mode Download PDFInfo
- Publication number
- CN113222649A CN113222649A CN202110467504.4A CN202110467504A CN113222649A CN 113222649 A CN113222649 A CN 113222649A CN 202110467504 A CN202110467504 A CN 202110467504A CN 113222649 A CN113222649 A CN 113222649A
- Authority
- CN
- China
- Prior art keywords
- service
- execution mode
- service execution
- user
- combination
- 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
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0219—Discounts or incentives, e.g. coupons or rebates based on funds or budget
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0213—Consumer transaction fees
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0224—Discounts or incentives, e.g. coupons or rebates based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0239—Online discounts or incentives
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present specification discloses a method and an apparatus for recommending a service execution mode, which respond to a service request of a target user, obtain service data corresponding to the service request, and extract feature data from the service data. Secondly, inputting the characteristic data into a pre-trained prediction model, predicting selection probabilities corresponding to different service execution mode combinations when a target user executes a service corresponding to a service request, determining a service execution mode combination to be recommended, and determining a user group to which the target user belongs from each predetermined user group. And then determining the strategy data corresponding to each service execution mode in the service execution mode combination to be recommended. And finally, recommending the service execution mode combination to be recommended to the target user according to the strategy data. The method pushes the service execution mode combination to the user, so that the user has multiple service execution modes to select, the possibility of the user to participate in the marketing campaign is improved, and the marketing effect of the marketing campaign is improved.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for recommending a service execution mode.
Background
Currently, in the scenario of recommending marketing, in order to prompt users to use products, certain benefits such as coupons, discounts, payment exemptions, etc. are usually provided to users in marketing information. For example, information that a user can get a preference for paying with a certain bank's savings card can be pushed to the user in the process of paying an order to prompt the user to transact the bank's savings card.
In the prior art, generally, only one marketing activity is pushed to a user in one business scene, and the marketing activity may not be the marketing activity in which the user is interested, so that the possibility of the user participating in the marketing activity is reduced, and the single marketing activity push causes the user not to have other marketing activities to select, so that the user cannot determine the marketing activity suitable for the user, and the marketing effect of the activity is possibly reduced.
Therefore, how to recommend the business execution mode to each user more reasonably to ensure the improvement of the marketing effect of the marketing campaign and further improve the business execution efficiency of the user is a problem to be solved urgently.
Disclosure of Invention
The present specification provides a method and an apparatus for recommending a service execution manner, a storage medium, and an electronic device, so as to partially solve the above problems in the prior art.
The technical scheme adopted by the specification is as follows:
the present specification provides a method for recommending a service execution mode, including:
responding to a service request of a target user, and acquiring service data corresponding to the service request;
extracting characteristic data from the service data;
inputting the characteristic data into a pre-trained prediction model, and predicting selection probabilities corresponding to different service execution mode combinations when the target user executes the service corresponding to the service request;
determining a service execution mode combination to be recommended according to the selection probability corresponding to the target user aiming at different service execution mode combinations, and determining a user group to which the target user belongs from each predetermined user group according to the selection probability corresponding to the target user aiming at different service execution mode combinations;
determining strategy data corresponding to each service execution mode in the service execution mode combination to be recommended according to the user group to which the target user belongs;
and recommending the service execution mode combination to be recommended to the target user according to the strategy data.
Optionally, training the prediction model specifically includes:
acquiring historical service data of each user;
extracting historical characteristic data from historical service data of each user;
inputting the historical characteristic data into a prediction model to be trained, and predicting the corresponding prediction selection probability of different service execution modes when the user executes the historical service corresponding to the historical service data;
and training the prediction model by taking the minimized deviation between the prediction selection probability and the actual situation of the historically selected business execution mode of the user as an optimization target.
Optionally, determining a service execution mode combination to be recommended according to the selection probability corresponding to the target user for different service execution mode combinations, specifically including:
determining a service execution mode combination with the selection probability not lower than a set threshold value in each service execution mode combination as an optimal service execution mode combination according to the selection probability corresponding to different service execution mode combinations of the target user;
and determining the service execution mode combination to be recommended according to the preferred service execution mode combination and the service cost corresponding to each service execution mode in the preferred service execution mode combination.
Optionally, determining a service execution mode combination to be recommended according to the service cost corresponding to each service execution mode in the preferred service execution mode combination and the preferred service execution mode combination, specifically including:
determining the sum of the service costs corresponding to the service execution modes in each preferred service execution mode combination aiming at each preferred service execution mode combination to obtain the service cost and value corresponding to the preferred service execution mode combination;
determining the recommendation degree corresponding to the preferred service execution mode combination according to the service cost and the value and the selection probability corresponding to the preferred service execution mode combination;
and determining the service execution mode combination to be recommended according to the recommendation degree corresponding to each preferable service execution mode combination.
Optionally, determining policy data corresponding to each service execution manner in the service execution manner combination to be recommended according to the user group to which the target user belongs, specifically including:
determining a current service period of the target user, and determining policy data corresponding to each service execution mode contained in the service execution mode combination to be recommended in the current service period in a user group to which the target user belongs;
and for each service execution mode contained in the service execution mode combination to be recommended, the strategy data corresponding to the service execution mode in the current service period is determined according to the sum of the service costs of the service execution mode in the last service period and the budget cost corresponding to the service execution mode in the last service period.
Optionally, determining policy data corresponding to the service execution manner in the current service period according to a sum of service costs of the service execution manner in the last service period and a budget cost corresponding to the service execution manner in the last service period, specifically including:
determining the budget cost corresponding to the service execution mode in the current service period according to the sum of the service costs of the service execution mode in the last service period and the budget cost corresponding to the service execution mode in the last service period, if the sum of the service costs of the service execution mode in the last service period is greater than the budget cost corresponding to the service execution mode in the last service period, the budget cost corresponding to the service execution mode in the current service period is less than the determined set budget cost, and if the sum of the service costs of the service execution mode in the last service period is less than the budget cost corresponding to the service execution mode in the last service period, the budget cost corresponding to the service execution mode in the current service period is greater than the set budget cost;
and determining the strategy data corresponding to the service execution mode in the current service period according to the budget cost corresponding to the service execution mode in the current service period.
Optionally, the predetermined user groups specifically include:
acquiring historical service data of each user;
extracting historical characteristic data from historical service data of each user;
inputting the historical characteristic data into the prediction model, predicting selection probabilities corresponding to different service execution mode combinations when the user executes historical services corresponding to the historical service data, and taking the selection probabilities as the historical selection probabilities of the user corresponding to the different service execution mode combinations;
and clustering the users according to the historical selection probability of each user for different service execution mode combinations to obtain each user group and a selection probability interval of each user group for different service execution mode combinations.
This specification provides a service execution mode recommendation apparatus, including:
the acquisition module is used for responding to a service request of a target user and acquiring service data corresponding to the service request;
the extraction module is used for extracting characteristic data from the service data;
the prediction module is used for inputting the characteristic data into a pre-trained prediction model and predicting the selection probability corresponding to different service execution mode combinations when the target user executes the service corresponding to the service request;
the determining module is used for determining a service execution mode combination to be recommended according to the selection probability corresponding to the target user aiming at different service execution mode combinations, and determining a user group to which the target user belongs from each predetermined user group according to the selection probability corresponding to the target user aiming at different service execution mode combinations;
the strategy module is used for determining strategy data corresponding to each service execution mode in the service execution mode combination to be recommended according to the user group to which the target user belongs;
and the recommending module is used for recommending the service execution mode combination to be recommended to the target user according to the strategy data.
The present specification provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the service execution manner recommendation method described above.
The present specification provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, the processor implements the service execution mode recommendation method.
The technical scheme adopted by the specification can achieve the following beneficial effects:
in the method for recommending a service execution manner provided in this specification, a service request of a target user is responded to, service data corresponding to the service request is acquired, and feature data is extracted from the service data. Secondly, inputting the characteristic data into a pre-trained prediction model, predicting selection probabilities corresponding to different service execution mode combinations when a target user executes a service corresponding to a service request, determining a service execution mode combination to be recommended according to the selection probabilities corresponding to the target user aiming at the different service execution mode combinations, and determining a user group to which the target user belongs from the predetermined user groups according to the selection probabilities corresponding to the target user aiming at the different service execution mode combinations. And then, determining strategy data corresponding to each service execution mode in the service execution mode combination to be recommended according to the user group to which the target user belongs. And finally, recommending the service execution mode combination to be recommended to the target user according to the strategy data.
Compared with the prior art that only one marketing activity is pushed to the user, the method determines the service execution mode combination to be recommended according to the selection probability corresponding to different service execution mode combinations of the target user, can push various service execution modes to the user in a combined manner, enables the user to have more service execution modes for selection, improves the possibility of the user to participate in the marketing activity, improves the marketing effect of the marketing activity, and further improves the service execution efficiency of the user.
Drawings
The accompanying drawings, which are included to provide a further understanding of the specification and are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description serve to explain the specification and not to limit the specification in a non-limiting sense. In the drawings:
fig. 1 is a flowchart illustrating a method for recommending a service execution manner according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of a service execution mode recommendation device provided in an embodiment of the present specification;
fig. 3 is a schematic structural diagram of an electronic device provided in an embodiment of this specification.
Detailed Description
In order to make the objects, technical solutions and advantages of the present disclosure more clear, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without any creative effort belong to the protection scope of the present specification.
The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating a method for recommending a service execution manner according to an embodiment of the present specification, which specifically includes the following steps:
s100: and responding to a service request of a target user, and acquiring service data corresponding to the service request.
The execution subject of the recommendation method of the service execution mode provided by the specification can be terminal equipment such as a server, a desktop computer and the like. For convenience of description, the following description will be made of a method for recommending a service execution manner provided in the present specification, with only a server as an execution subject.
In this embodiment, the server may respond to a service request of a target user, and obtain service data corresponding to the service request. The service mentioned herein may refer to any service, such as an order take-out service, a credit card transaction service, a financial service, a travel service, etc., and the description does not specifically limit the service. The service data mentioned herein may refer to at least one of user data of a target user, historical behavior data of the target user, and basic data of a service corresponding to a service request.
The user data of the target user is mainly used for reflecting basic personal conditions of the user, such as the age, the sex and the like of the user. The historical behavior data of the target user may be used to reflect actual operations performed by the user on the service historically, such as historical browsing information of the user, historical order information of the user, and the like, and the basic data of the service corresponding to the service request may refer to relevant information corresponding to the service itself, such as a service type, preference information, a service cost, and the like.
The server can determine whether to recommend the service execution mode to the user according to the acquired service data. For example, the server may determine, according to the user data of the target user, an offer activity that the user may participate in, extract historical order information of the target user, and obtain payment feature data of the target user, and if it is determined that most of the historical order information of the target user is an order related to the offer, consider that the target user is more interested in a marketing activity related to the offer. Thus, the server may push activity information for more favorable coupons, discounts, payment waivers, etc. to users who are more interested in the favorable marketing activity.
S102: and extracting characteristic data from the service data.
In this embodiment, the server may extract feature data from the business data, where the feature data of the user is used to represent some preferred features reflected by the target user. The server can extract data of specified dimensions related to the business from the business data according to actual business requirements, and convert the data into corresponding feature vectors, so that feature data in the form of the feature vectors is obtained. There are various ways for the server to convert the service data into the feature vector, for example, a Word to vector Model (Word to vector), a Continuous Bag of words Model (CBOW), and the like, and the specific way for extracting the feature vector is not limited in this specification.
S104: and inputting the characteristic data into a pre-trained prediction model, and predicting selection probability corresponding to different service execution mode combinations when the target user executes the service corresponding to the service request.
In the embodiment of the present specification, the server inputs the feature data into a pre-trained prediction model, and predicts the selection probability corresponding to different service execution mode combinations when the target user executes the service corresponding to the service request. The service execution manner mentioned here may refer to a preferential manner and a preferential degree selected when the user executes the service, for example, the preferential manner such as a coupon, a discount, payment exemption and the like may be pushed to the user in a payment interface of the payment order, the preferential degrees of different users may be different, and the service execution manner combination may refer to preferential manners such as coupons, discounts, payment exemption and the like from different sources, for example, exemption of payment performed by bank cards of different banking institutions, discounts of different payment manners.
For each service execution mode combination, the selection probability corresponding to the service execution mode combination is used for representing the possibility of selecting any one service execution mode in the service execution mode combination to execute the service, and the higher the selection probability corresponding to the service execution mode combination is, the higher the possibility of selecting any one service execution mode in the service execution mode combination by a user to execute the service is.
In this embodiment of the present specification, the aforementioned recommendation model needs to be trained in advance, specifically, the server may obtain historical service data of each user, extract historical feature data from the historical service data for each user, input the historical feature data into the prediction model to be trained, predict that, when the user executes a historical service corresponding to the historical service data, combine corresponding prediction selection probabilities for different service execution manners, and train the prediction model with a goal of minimizing a deviation between the prediction selection probability and an actual situation of the user selecting a service execution manner historically as an optimization goal. The manner in which the server trains the prediction model may be various, for example, a multitask learning algorithm (multitask learning), a multi-class learning algorithm (Multiclass learning), and the like, and the specification does not limit the specific manner of model training.
In practical application, the server may use an actual situation that the user historically selects a service execution manner as the label information of the training sample, where the server determines the label information of the training sample in various manners, for example, if the user selects any one of service execution manner combinations to be recommended, which are recommended to the user by the server, the label information of the service execution manner combination to be recommended is used to indicate that the user selects the service execution manner combination, and for example, if the user selects any one of the service execution manner combination to be recommended, which is recommended to the user by the server, the label information corresponding to the service execution manner combination is used to indicate that the user selects the service execution manner combination, for any one of the service execution manner combinations including the service execution manner.
S106: determining a service execution mode combination to be recommended according to the selection probability corresponding to the target user aiming at different service execution mode combinations, and determining a user group to which the target user belongs from all predetermined user groups according to the selection probability corresponding to the target user aiming at different service execution mode combinations.
In this embodiment, the server may determine the service execution manner combination to be recommended according to the selection probability corresponding to the target user for different service execution manner combinations. For example, the server may determine, from the service execution manner combinations, a service execution manner combination with the highest selection probability as a service execution manner combination to be recommended.
The server may also determine, as the preferred service execution mode combination, a service execution mode combination having a selection probability not lower than a set threshold in each service execution mode combination, and then determine a service execution mode combination to be recommended according to the preferred service execution mode combination and the service cost corresponding to each service execution mode in the preferred service execution mode combination. For example, the server may determine, from the preferred service execution manner combinations, a service execution manner combination with the lowest service cost as a service execution manner combination to be recommended.
In this embodiment, the server may further determine, for each preferred service execution manner combination, a sum of service costs corresponding to the service execution manners in the preferred service execution manner combination, and obtain a service cost sum value corresponding to the preferred service execution manner combination.
The selection probability corresponding to each service execution mode combination by the user may refer to how many users will select the service execution mode in the service execution mode combination among a certain number of users, that is, the server may multiply the selection probability corresponding to each service execution mode in the preferred service execution mode combination by the service cost corresponding to each service execution mode in the preferred service execution mode combination, and sum the result to obtain the service cost and value corresponding to the preferred service execution mode combination. The server may also multiply the selection probability corresponding to the preferred service execution mode combination by the average service cost corresponding to each service execution mode in the preferred service execution mode combination, and sum the result to obtain the service cost and value corresponding to the preferred service execution mode combination.
The server may determine the recommendation degree corresponding to the preferred service execution mode combination according to the service cost and the value and the selection probability corresponding to the preferred service execution mode combination, and determine the service execution mode combination to be recommended according to the recommendation degree corresponding to each preferred service execution mode combination. The recommendation degree corresponding to the preferred service execution manner combination mentioned herein may refer to a numerical value obtained by dividing the selection probability corresponding to the preferred service execution manner combination by the service cost and the value corresponding to the preferred service execution manner combination, where the larger the numerical value is, the higher the recommendation degree corresponding to the preferred service execution manner combination is, and the smaller the numerical value is, the lower the recommendation degree corresponding to the preferred service execution manner combination is.
Specifically, the server may determine the service execution mode combination to be recommended by referring to the following formula:
the formula shows that the service execution mode combination with the maximum selection probability of each user in different service execution mode combinations is determined, and the sum of the service costs corresponding to the service execution modes in all the users is not more than the set service cost. For example, in different bank marketing activity combinations, the bank marketing activity combination with the maximum selection probability corresponding to each user is determined, and the marketing activity cost of each bank in all users is not much larger than the set marketing activity cost.
Wherein p isnmRepresenting the selection probability, x, of the user n to the mth service execution mode combinationnmWhether the mth service execution mode is shown to the user n is shown as 1 but not shown as 0, moneynmAnd expressing the service cost corresponding to each service execution mode in the service execution mode combination, wherein the Money expresses the total service cost corresponding to each service execution mode.
It should be noted that the optimal service execution mode combination to be recommended obtained according to the above formula may refer to that the recommended service execution mode combination to be recommended is optimal for the entire user in terms of the selection probability and the service cost, rather than being optimal for a single user in terms of the optimal service execution mode combination to be recommended. That is, it may happen that the service execution manner combination to be recommended to the user is not the service execution manner combination with the highest recommendation degree. For example, the recommendation degree of a service execution mode combination to all users is higher than that of other service execution mode combinations, but the service cost corresponding to the service execution mode combination is limited, so that the service execution mode combination can be recommended to some users due to the limitation of the service cost, and other service execution mode combinations with higher recommendation degree can be recommended to other users.
S108: and determining the strategy data corresponding to each service execution mode in the service execution mode combination to be recommended according to the user group to which the target user belongs.
In this embodiment, the server may determine policy data corresponding to each service execution manner in the service execution manner combination to be recommended according to a user group to which the target user belongs. The policy data mentioned here may refer to specific preference information of each service execution manner in the service execution manner combination to be recommended, for example, XX bank credit card immediately subtracts X element, and so on.
Based on this, the server needs to determine the user group in advance. Firstly, the server can obtain historical service data of each user, extract historical characteristic data from the historical service data aiming at the historical service data of each user, secondly, input the historical characteristic data into a prediction model, predict selection probabilities corresponding to different service execution mode combinations when the user executes the historical service corresponding to the historical service data, and serve as the historical selection probabilities of the user aiming at the different service execution mode combinations, and finally, cluster the users according to the historical selection probabilities of the users aiming at the different service execution mode combinations to obtain user groups and selection probability intervals of the user groups aiming at the different service execution mode combinations.
As can be seen from the manner of dividing the user group, the server may determine the user group to which the target user belongs based on the determined selection probability of the target user for different service execution manner combinations. For example, the server may divide users having a selection probability interval of 20% to 25% of a service execution manner combination a, a selection probability interval of 10% to 15% of a service execution manner combination B, and a selection probability interval of 5% to 10% of a service execution manner combination C into a user group a, and if the selection probabilities of the target user for the service execution manner combination a, the service execution manner combination B, and the service execution manner combination C all fall within the selection probability interval of the user group a for the three service execution manner combinations, it may be determined that the target user belongs to the user group a.
In practical applications, the business costs corresponding to different business execution manners may be preset, and since the preferential degrees corresponding to different users are different or the number of users actually participating in the marketing campaign exceeds the expectation, the business costs corresponding to the business execution manners may exceed the budget cost, thereby possibly affecting the marketing effect of the marketing campaign.
In order to avoid the influence of the above situation, the server may equally allocate the service cost corresponding to the service execution manner to a plurality of service cycles, as the budget cost of each service cycle of the service execution manner. The server may determine a current service period of the target user, and determine policy data corresponding to each service execution mode in the current service period, where each service execution mode is included in the service execution mode combination to be recommended in the user group to which the target user belongs. And for each service execution mode contained in the service execution mode combination to be recommended, the strategy data corresponding to the service execution mode in the current service period is determined according to the sum of the service cost of the service execution mode in the last service period and the budget cost corresponding to the service execution mode in the last service period.
Further, the server may determine, according to the sum of the service costs of the service execution manner in the last service period and the budget cost corresponding to the service execution manner in the last service period, a difference between the sum of the service costs of the service execution manner in the last service period and the budget cost. And determining the budget cost corresponding to the service execution mode in the current service period according to the difference between the sum of the service costs and the budget cost in the last service period of the service execution mode and the set budget cost corresponding to the service execution mode in the current service period.
If the sum of the service costs of the service execution mode in the last service period is greater than the budget cost corresponding to the service execution mode in the last service period, the budget cost corresponding to the service execution mode in the current service period should be less than the determined set budget cost, and if the sum of the service costs of the service execution mode in the last service period is less than the budget cost corresponding to the service execution mode in the last service period, the budget cost corresponding to the service execution mode in the current service period should be greater than the set budget cost. For example, the set budget cost corresponding to each service period of the service execution mode is 100 ten thousand, the sum of the service costs in the last service period of the service execution mode is 120 ten thousand, and the budget cost of the service execution mode in the current service period is 80 ten thousand according to the difference between the sum of the service costs in the last service period and the budget cost.
The server may determine the policy data corresponding to the service execution mode in the current service period according to the budget cost corresponding to the service execution mode in the current service period. Specifically, the server may correspondingly adjust the policy data corresponding to the service execution manner in the current service period according to a ratio between the budget cost corresponding to the service execution manner in the current service period and the set budget cost. For example, the budget cost is 80% of the set budget cost, the preferential amount corresponding to the set budget cost of the user in the current service period is changed from 10 yuan to 8 yuan, and the preferential amount of the corresponding proportion is reduced. Of course, the server may also correspondingly adjust the policy data corresponding to the service execution manner in the current service period according to the difference between the budget cost corresponding to the service execution manner in the current service period and the set budget cost. For example, the server reduces the fixed preferential amount of each user according to the difference between the budget cost corresponding to the service execution mode in the current service period and the set budget cost and the estimated number of users.
In practical application, the total service costs corresponding to the service execution manners are different, that is, the budget costs corresponding to different service execution manners in each service period are different, and it may occur that the sum of the service costs corresponding to some service execution manners is greater than the set budget cost, and the sum of the service costs corresponding to some service execution manners is less than the set budget cost, so that the difference between the policy data corresponding to each service execution manner in the current service period and the policy data obtained according to the set budget cost is large, and thus the determined service execution manner combination to be recommended is not the optimal service execution manner combination.
Therefore, the server may determine the policy data corresponding to each service execution mode in the current service period according to the difference between the budget cost of each service execution mode corresponding to the current service period and the set budget cost, and combine the service execution modes with the optimal policy data corresponding to each service execution mode in the service execution mode combination in the current service period as the service execution mode combination to be recommended.
Because the total service costs corresponding to the service execution modes are different, if the total service costs corresponding to the service execution modes are used completely, the service execution mode combination corresponding to the service execution mode is not recommended.
It should be noted that the server may also increase or decrease the policy data corresponding to each service execution mode in the current service period according to the actual amount of the order. For example, if the actual amount of the user's payment order is much larger than the average amount of all the user's historical payment orders, the preferential amount of the preferential activity recommended to the user is increased.
S110: and recommending the service execution mode combination to be recommended to the target user according to the strategy data.
In this embodiment, the server may recommend the service execution mode combination to be recommended to the target user according to the policy data. Then, the server may determine a service execution manner actually selected by the target user from the service execution manner combination to be recommended, and policy data corresponding to the service execution manner, so as to determine a budget cost corresponding to the service execution manner in the next service period.
The method can be seen that the method determines the service execution mode combination to be recommended according to the selection probability corresponding to different service execution mode combinations of the target user, can combine and push multiple service execution modes to the user, so that the user has more service execution modes to select, and the server adjusts the strategy data of each service execution mode in real time according to the service cost corresponding to each service execution mode combination, so as to realize the dynamic balance of the service cost corresponding to the service execution mode of each service cycle, improve the possibility of the user participating in the marketing campaign, improve the marketing effect of the marketing campaign, and further improve the service execution efficiency of the user to a certain extent.
Based on the same idea, the present specification further provides a recommendation apparatus for a service execution manner, as shown in fig. 2.
Fig. 2 is a schematic structural diagram of a service execution mode recommendation apparatus provided in an embodiment of this specification, which specifically includes:
an obtaining module 200, configured to respond to a service request of a target user, and obtain service data corresponding to the service request;
an extraction module 202, configured to extract feature data from the service data;
the prediction module 204 is configured to input the feature data into a pre-trained prediction model, and predict selection probabilities corresponding to different service execution mode combinations when the target user executes a service corresponding to the service request;
a determining module 206, configured to determine a service execution manner combination to be recommended according to the selection probabilities corresponding to the target user for different service execution manner combinations, and determine, from each predetermined user group, a user group to which the target user belongs according to the selection probabilities corresponding to the target user for different service execution manner combinations;
the policy module 208 is configured to determine, according to the user group to which the target user belongs, policy data corresponding to each service execution manner in the service execution manner combination to be recommended;
and the recommending module 210 is configured to recommend the service execution mode combination to be recommended to the target user according to the policy data.
Optionally, the prediction module 204 is specifically configured to obtain historical service data of each user, extract historical feature data from the historical service data for the historical service data of each user, input the historical feature data into a prediction model to be trained, predict that when the user executes a historical service corresponding to the historical service data, combine corresponding prediction selection probabilities for different service execution manners, and train the prediction model with a goal of minimizing a deviation between the prediction selection probability and an actual situation of the historically selected service execution manner of the user as an optimization goal.
Optionally, the determining module 206 is specifically configured to determine, according to the selection probabilities corresponding to different service execution manner combinations by the target user, a service execution manner combination with a selection probability not lower than a set threshold in each service execution manner combination, as a preferred service execution manner combination, and determine a service execution manner combination to be recommended according to the preferred service execution manner combination and a service cost corresponding to each service execution manner in the preferred service execution manner combination.
Optionally, the determining module 206 is specifically configured to, for each preferred service execution manner combination, determine a sum of service costs corresponding to each service execution manner in the preferred service execution manner combination to obtain a service cost sum value corresponding to the preferred service execution manner combination, determine a recommendation degree corresponding to the preferred service execution manner combination according to the service cost sum value and a selection probability corresponding to the preferred service execution manner combination, and determine a service execution manner combination to be recommended according to the recommendation degree corresponding to each preferred service execution manner combination.
Optionally, the policy module 208 is specifically configured to determine a current service period of the target user, as a current service period, and determine policy data corresponding to each service execution manner in the service execution manner combination to be recommended in the user group to which the target user belongs in the current service period, where for each service execution manner in the service execution manner combination to be recommended, the policy data corresponding to the service execution manner in the current service period is determined according to a sum of service costs of the service execution manner in a previous service period and a budget cost corresponding to the service execution manner in the previous service period.
Optionally, the policy module 208 is specifically configured to determine, according to a sum of service costs of the service execution manner in the previous service period and a budget cost corresponding to the service execution manner in the previous service period, a budget cost corresponding to the service execution manner in the current service period, if the sum of the service costs of the service execution manner in the previous service period is greater than the budget cost corresponding to the service execution manner in the previous service period, a budget cost corresponding to the service execution manner in the current service period is less than the determined set budget cost, if the sum of the service costs of the service execution manner in the previous service period is less than the budget cost corresponding to the service execution manner in the previous service period, the budget cost corresponding to the service execution manner in the current service period is greater than the set budget cost, and determining the strategy data corresponding to the service execution mode in the current service period according to the budget cost corresponding to the service execution mode in the current service period.
Optionally, the determining module 206 is specifically configured to obtain historical service data of each user, extract historical feature data from the historical service data for the historical service data of each user, input the historical feature data into the prediction model, predict a selection probability corresponding to a combination of different service execution manners when the user executes a historical service corresponding to the historical service data, serve as a historical selection probability of the user for the combination of different service execution manners, cluster the users according to the historical selection probability of each user for the combination of different service execution manners, and obtain each user group and a selection probability interval of each user group for the combination of different service execution manners.
The present specification also provides a computer-readable storage medium storing a computer program, which can be used to execute the recommendation method of the service execution manner provided in fig. 1.
The present specification also provides a schematic structural diagram of the electronic device shown in fig. 3. As shown in fig. 3, at the hardware level, the device of the method for recommending a service execution mode includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include hardware required by other services. The processor reads a corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to implement the service execution mode recommendation method described in fig. 1. Of course, besides the software implementation, the present specification does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may be hardware or logic devices.
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 Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (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 functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.
Claims (10)
1. A method for recommending service execution modes is characterized by comprising the following steps:
responding to a service request of a target user, and acquiring service data corresponding to the service request;
extracting characteristic data from the service data;
inputting the characteristic data into a pre-trained prediction model, and predicting selection probabilities corresponding to different service execution mode combinations when the target user executes the service corresponding to the service request;
determining a service execution mode combination to be recommended according to the selection probability corresponding to the target user aiming at different service execution mode combinations, and determining a user group to which the target user belongs from each predetermined user group according to the selection probability corresponding to the target user aiming at different service execution mode combinations;
determining strategy data corresponding to each service execution mode in the service execution mode combination to be recommended according to the user group to which the target user belongs;
and recommending the service execution mode combination to be recommended to the target user according to the strategy data.
2. The method of claim 1, wherein training the predictive model comprises:
acquiring historical service data of each user;
extracting historical characteristic data from historical service data of each user;
inputting the historical characteristic data into a prediction model to be trained, and predicting the corresponding prediction selection probability of different service execution modes when the user executes the historical service corresponding to the historical service data;
and training the prediction model by taking the minimized deviation between the prediction selection probability and the actual situation of the historically selected business execution mode of the user as an optimization target.
3. The method according to claim 1, wherein determining a service execution mode combination to be recommended according to the selection probability corresponding to the target user for different service execution mode combinations specifically comprises:
determining a service execution mode combination with the selection probability not lower than a set threshold value in each service execution mode combination as an optimal service execution mode combination according to the selection probability corresponding to different service execution mode combinations of the target user;
and determining the service execution mode combination to be recommended according to the preferred service execution mode combination and the service cost corresponding to each service execution mode in the preferred service execution mode combination.
4. The method according to claim 3, wherein determining the service execution mode combination to be recommended according to the service cost corresponding to each service execution mode in the preferred service execution mode combination and the preferred service execution mode combination specifically comprises:
determining the sum of the service costs corresponding to the service execution modes in each preferred service execution mode combination aiming at each preferred service execution mode combination to obtain the service cost and value corresponding to the preferred service execution mode combination;
determining the recommendation degree corresponding to the preferred service execution mode combination according to the service cost and the value and the selection probability corresponding to the preferred service execution mode combination;
and determining the service execution mode combination to be recommended according to the recommendation degree corresponding to each preferable service execution mode combination.
5. The method according to claim 1, wherein determining policy data corresponding to each service execution manner in the service execution manner combination to be recommended according to the user group to which the target user belongs specifically includes:
determining a current service period of the target user, and determining policy data corresponding to each service execution mode contained in the service execution mode combination to be recommended in the current service period in a user group to which the target user belongs;
and for each service execution mode contained in the service execution mode combination to be recommended, the strategy data corresponding to the service execution mode in the current service period is determined according to the sum of the service costs of the service execution mode in the last service period and the budget cost corresponding to the service execution mode in the last service period.
6. The method according to claim 5, wherein determining the policy data corresponding to the service execution mode in the current service period according to the sum of the service costs of the service execution mode in the previous service period and the budget cost corresponding to the service execution mode in the previous service period specifically includes:
determining the budget cost corresponding to the service execution mode in the current service period according to the sum of the service costs of the service execution mode in the last service period and the budget cost corresponding to the service execution mode in the last service period, if the sum of the service costs of the service execution mode in the last service period is greater than the budget cost corresponding to the service execution mode in the last service period, the budget cost corresponding to the service execution mode in the current service period is less than the determined set budget cost, and if the sum of the service costs of the service execution mode in the last service period is less than the budget cost corresponding to the service execution mode in the last service period, the budget cost corresponding to the service execution mode in the current service period is greater than the set budget cost;
and determining the strategy data corresponding to the service execution mode in the current service period according to the budget cost corresponding to the service execution mode in the current service period.
7. The method of claim 1, wherein predetermining each user group specifically comprises:
acquiring historical service data of each user;
extracting historical characteristic data from historical service data of each user;
inputting the historical characteristic data into the prediction model, predicting selection probabilities corresponding to different service execution mode combinations when the user executes historical services corresponding to the historical service data, and taking the selection probabilities as the historical selection probabilities of the user corresponding to the different service execution mode combinations;
and clustering the users according to the historical selection probability of each user for different service execution mode combinations to obtain each user group and a selection probability interval of each user group for different service execution mode combinations.
8. An apparatus for recommending a service execution mode, comprising:
the acquisition module is used for responding to a service request of a target user and acquiring service data corresponding to the service request;
the extraction module is used for extracting characteristic data from the service data;
the prediction module is used for inputting the characteristic data into a pre-trained prediction model and predicting the selection probability corresponding to different service execution mode combinations when the target user executes the service corresponding to the service request;
the determining module is used for determining a service execution mode combination to be recommended according to the selection probability corresponding to the target user aiming at different service execution mode combinations, and determining a user group to which the target user belongs from each predetermined user group according to the selection probability corresponding to the target user aiming at different service execution mode combinations;
the strategy module is used for determining strategy data corresponding to each service execution mode in the service execution mode combination to be recommended according to the user group to which the target user belongs;
and the recommending module is used for recommending the service execution mode combination to be recommended to the target user according to the strategy data.
9. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1 to 7.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110467504.4A CN113222649A (en) | 2021-04-28 | 2021-04-28 | Method and device for recommending service execution mode |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110467504.4A CN113222649A (en) | 2021-04-28 | 2021-04-28 | Method and device for recommending service execution mode |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113222649A true CN113222649A (en) | 2021-08-06 |
Family
ID=77089710
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110467504.4A Pending CN113222649A (en) | 2021-04-28 | 2021-04-28 | Method and device for recommending service execution mode |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113222649A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114266601A (en) * | 2021-12-24 | 2022-04-01 | 深圳前海微众银行股份有限公司 | Marketing strategy determination method and device, terminal equipment and storage medium |
| CN115828171A (en) * | 2023-02-13 | 2023-03-21 | 支付宝(杭州)信息技术有限公司 | Method, device, medium and equipment for cooperatively executing business by end cloud |
-
2021
- 2021-04-28 CN CN202110467504.4A patent/CN113222649A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114266601A (en) * | 2021-12-24 | 2022-04-01 | 深圳前海微众银行股份有限公司 | Marketing strategy determination method and device, terminal equipment and storage medium |
| CN115828171A (en) * | 2023-02-13 | 2023-03-21 | 支付宝(杭州)信息技术有限公司 | Method, device, medium and equipment for cooperatively executing business by end cloud |
| CN115828171B (en) * | 2023-02-13 | 2023-05-16 | 支付宝(杭州)信息技术有限公司 | Method, device, medium and equipment for executing service cooperatively by end cloud |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110245935B (en) | Payment channel recommendation method, device and equipment | |
| US20200211106A1 (en) | Method, apparatus, and device for training risk management models | |
| CN108460523B (en) | Wind control rule generation method and device | |
| CN108733825B (en) | Object trigger event prediction method and device | |
| CN110020427B (en) | Policy determination method and device | |
| CN110008991B (en) | Risk event identification method, risk identification model generation method, risk event identification device, risk identification equipment and risk identification medium | |
| CN113222649A (en) | Method and device for recommending service execution mode | |
| CN113643119A (en) | Model training method, business wind control method and business wind control device | |
| CN110688974A (en) | Identity recognition method and device | |
| CN110674188A (en) | Feature extraction method, device and equipment | |
| CN110852503A (en) | Method and device for selecting payment channel and payment channel route | |
| CN111047220A (en) | Method, device, equipment and readable medium for determining condition of wind control threshold | |
| CN110134860B (en) | User portrait generation method, device and equipment | |
| CN110033092B (en) | Data label generation method, data label training device, event recognition method and event recognition device | |
| CN113886033A (en) | Task processing method and device | |
| CN112183584A (en) | Method and device for model training and business execution | |
| CN116308738B (en) | Model training method, business wind control method and device | |
| CN112561162A (en) | Information recommendation method and device | |
| CN111325557A (en) | Detection method, device and equipment for merchant risk | |
| CN112016914A (en) | Resource control and fund control method, device and equipment | |
| CN116485391A (en) | Payment recommendation processing method and device | |
| CN113010562B (en) | Information recommendation method and device | |
| CN107392408B (en) | Credit score prompt information output method and device | |
| CN115660105A (en) | Model training method, business wind control method and business wind control device | |
| CN111523995B (en) | Method, device and equipment for determining characteristic value of model migration |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |