CN111861569A - Product information recommendation method and device - Google Patents
Product information recommendation method and device Download PDFInfo
- Publication number
- CN111861569A CN111861569A CN202010715579.5A CN202010715579A CN111861569A CN 111861569 A CN111861569 A CN 111861569A CN 202010715579 A CN202010715579 A CN 202010715579A CN 111861569 A CN111861569 A CN 111861569A
- Authority
- CN
- China
- Prior art keywords
- product
- historical
- preference
- customer
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000012549 training Methods 0.000 claims abstract description 77
- 238000003066 decision tree Methods 0.000 claims abstract description 28
- 238000004590 computer program Methods 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 12
- 239000000047 product Substances 0.000 description 307
- 230000000694 effects Effects 0.000 description 19
- 238000004891 communication Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 13
- 238000012545 processing Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 11
- 238000011156 evaluation Methods 0.000 description 10
- 239000000872 buffer Substances 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012854 evaluation process Methods 0.000 description 2
- 239000012467 final product Substances 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000005303 weighing 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a product information recommendation method and device, and the method comprises the following steps: receiving client basic information of a target client; determining preference scores of different product types corresponding to the target customer by applying the customer basic information and a plurality of preset product preference prediction models respectively corresponding to different product types, and taking the product type corresponding to the maximum value of the preference scores as a target recommended product type; sending product purchase information corresponding to the target recommended product type to the target customer; each preset product preference prediction model is an iterative decision tree model obtained by pre-training according to historical customer basic information of a plurality of historical customers and preference scoring labels of the historical customers for the same product type. According to the method and the device, timeliness and intelligent degree of product recommendation can be improved, and then success rate of product recommendation can be improved.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for recommending product information.
Background
With the diversification and complication of bank financing products, the updating speed of the products is faster and faster, and how to quickly insights the requirements of customers and grasp the changes of customer appeal in time under a new situation is a new opportunity and challenge for bank financing business. Meanwhile, the bank faces the large scale of the customer group, the customer requirements are difficult to dig, the maintenance cost is high, most of small and medium-sized enterprise customers are in the state of management and marketing deficiency due to limited human resources, and the marketing management of the long-tailed customers can be carried out only by adopting technical means.
Product recommendation is carried out by adopting a traditional big data analysis or machine learning method, a model is trained by relying on massive historical data, and a rule is obtained by analyzing the historical data. The method has a contradiction in product recommendation under a new situation, namely, a large amount of historical data is adopted for training, although the model has a good fitting condition on the historical rule, the new situation change and the preference of a customer on a new product cannot be considered, and the rule obtained by the model is possibly too old; if only recent data are adopted for training, the training data volume is greatly reduced, the overall fitting effect of the model is reduced, and the rule obtained by the model is possibly too few. The model training is involved in two difficulties, the recommendation effect of the final product cannot be guaranteed, and the requirements of financial and sales under new conditions are difficult to meet.
Disclosure of Invention
Aiming at the problems in the prior art, the application provides a product information recommendation method and device, which can improve the timeliness and the intelligent degree of product recommendation and further improve the success rate of product recommendation.
In order to solve the technical problem, the present application provides the following technical solutions:
in a first aspect, the present application provides a product information recommendation method, including:
receiving client basic information of a target client;
determining preference scores of different product types corresponding to the target customer by applying the customer basic information and a plurality of preset product preference prediction models respectively corresponding to different product types, and taking the product type corresponding to the maximum value of the preference scores as a target recommended product type;
sending product purchase information corresponding to the target recommended product type to the target customer;
each preset product preference prediction model is an iterative decision tree model obtained by pre-training according to historical customer basic information of a plurality of historical customers and preference scoring labels of the historical customers for the same product type.
Further, before the receiving the client basic information of the target client, the method further includes: obtaining a plurality of product preference prediction training sets, wherein each of the product preference prediction training sets comprises: the method comprises the following steps that basic information of historical customers of a plurality of historical customers and preference scoring labels of the historical customers for the same product type are different, and the product types corresponding to historical purchase record groups are different; and respectively training product preference prediction models corresponding to the product types by applying the product preference prediction training groups, wherein each product preference prediction model is an iterative decision model.
Further, before the obtaining the plurality of product preference prediction training sets, the method further comprises: acquiring a plurality of groups of historical transaction record groups, wherein each group of historical transaction record groups comprises the times and time for purchasing products of the same product type by the only corresponding historical client; and generating preference scoring labels of the historical customers for different product types by applying the preset time attenuation coefficient and the historical transaction record group corresponding to each product type.
Further, after the obtaining the plurality of product preference prediction training sets, the method further includes: respectively inputting the historical customer basic information in each group of product preference prediction training groups into respective corresponding product preference prediction models; and adjusting each preset time attenuation coefficient according to the output of each product preference prediction model and the historical transaction record group.
Further, after the determining the preference scores of the target customers corresponding to different product types, the method further comprises: acquiring the purchase times and purchase time of the target customer for purchasing products of different product types; and adjusting each time attenuation coefficient according to the preference scores, purchase times and purchase time of different product types corresponding to the target customer.
In a second aspect, the present application provides a product information recommendation apparatus, including:
the receiving module is used for receiving the client basic information of the target client;
the prediction module is used for applying the client basic information and a plurality of preset product preference prediction models respectively corresponding to different product types, determining preference scores of different product types corresponding to the target client, and taking the product type corresponding to the maximum value of the preference scores as a target recommended product type;
the recommending module is used for sending the product purchasing information corresponding to the target recommended product type to the target customer; each preset product preference prediction model is an iterative decision tree model obtained by pre-training according to historical customer basic information of a plurality of historical customers and preference scoring labels of the historical customers for the same product type.
Further, the product information recommendation device further includes: a first obtaining module, configured to obtain a plurality of product preference prediction training sets, where each of the product preference prediction training sets includes: the method comprises the following steps that basic information of historical customers of a plurality of historical customers and preference scoring labels of the historical customers for the same product type are different, and the product types corresponding to historical purchase record groups are different; and the training module is used for applying each group of product preference prediction training groups to respectively train a product preference prediction model corresponding to each product type, and each product preference prediction model is an iterative decision model.
Further, the product information recommendation device further includes: the second acquisition module is used for acquiring a plurality of groups of historical transaction record groups, and each group of historical transaction record groups contains the times and time for the unique corresponding historical client to purchase the products of the same product type; and the generating module is used for applying a preset time attenuation coefficient and a historical transaction record group corresponding to each product type to generate preference scoring labels of each historical customer for different product types.
Further, the product information recommendation device further includes: the input module is used for respectively inputting the historical customer basic information in each group of product preference prediction training groups into the corresponding product preference prediction models; and the first adjusting module is used for adjusting each preset time attenuation coefficient according to the output of each product preference prediction model and the historical transaction record group.
Further, the product information recommendation device further includes: the third acquisition module is used for acquiring the purchase times and purchase time of the target customer for purchasing the products of different product types; and the second adjusting module is used for adjusting each time attenuation coefficient according to the preference scores, the purchase times and the purchase time of different product types corresponding to the target customer.
In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the product information recommendation method when executing the program.
In a fourth aspect, the present application provides a computer-readable storage medium having stored thereon computer instructions that, when executed, implement the product information recommendation method.
According to the technical scheme, the application provides a product information recommendation method and device, wherein the method comprises the following steps: receiving client basic information of a target client; determining preference scores of different product types corresponding to the target customer by applying the customer basic information and a plurality of preset product preference prediction models respectively corresponding to different product types, and taking the product type corresponding to the maximum value of the preference scores as a target recommended product type; sending product purchase information corresponding to the target recommended product type to the target customer; each preset product preference prediction model is an iterative decision tree model obtained by pre-training respective preference scoring labels of the historical customers for the same product type according to the historical customer basic information of a plurality of historical customers and the historical customers, so that the timeliness and the intelligent degree of product recommendation can be improved, and the success rate of the product recommendation can be further improved; specifically, the timeliness of training data can be considered, the training data volume can be guaranteed, the reliability of product preference prediction model training is improved, the reliable product preference prediction model is applied to improve the reliability of preference scoring, and then the efficiency and the accuracy of product recommendation are improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flowchart of a product information recommendation method in an embodiment of the present application;
FIG. 2 is a schematic flow chart of a product information recommendation method according to another embodiment of the present application;
fig. 3 is a flowchart illustrating steps S301 and S302 of a product information recommendation method in an embodiment of the present application;
fig. 4 is a flowchart illustrating steps S401 and S402 of a product information recommendation method in an embodiment of the present application;
fig. 5 is a flowchart illustrating steps S501 and S502 of a product information recommendation method in an embodiment of the present application;
FIG. 6 is a flowchart illustrating a product information recommendation method in an application example of the present application;
FIG. 7 is a flow chart of a time attenuation process in an application example of the present application;
FIG. 8 is a logic diagram of a model training process in an example application of the present application;
FIG. 9 is a flow chart of an effect evaluation process in an application example of the present application;
fig. 10 is a schematic block diagram of a system configuration of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In order to improve timeliness and intelligent degree of product recommendation and further improve success rate of product recommendation, the method starts with changing an existing product recommendation mode, combines an iterative decision tree and a time attenuation coefficient, takes customer basic information of a customer as sample data, calculates preference scores of the customer on products of the type as a label, and obtains a final product preference prediction model through multiple rounds of sample training and fitting. The p _ score preference score is a score calculated according to the times, time and a time attenuation coefficient of a customer purchasing a product, different weights are given to the sample labels by using time attenuation, the sample with larger time difference is lower in weight, and the sample with smaller time difference is higher in weight, so that a label value for weighing new and old samples is obtained; finally, the time attenuation coefficient can be synchronously adjusted according to the model training effect, the preference rule balance of new and old products is realized, the optimal recommendation effect is achieved, the balance problem of new and old sample data is solved, the model training effect is effectively improved, the deep insight and personalized and intelligent marketing to the product requirements of customers are finally realized, the new investment requirements of customers are met, the rapid propagation and popularization of new products are realized, the viscosity and the product permeability of the customers are improved, and more intelligent and high-efficiency product recommendation service is provided for the customers.
In order to improve timeliness and intelligent degree of product recommendation and further improve success rate of product recommendation, the embodiment of the application provides a product information recommendation device, which may be a server or a client device, where the client device may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a Personal Digital Assistant (PDA), a vehicle-mounted device, an intelligent wearable device, and the like. Wherein, intelligence wearing equipment can include intelligent glasses, intelligent wrist-watch and intelligent bracelet etc..
In practical applications, the part for recommending the product information may be executed on the server side as described in the above, or all operations may be completed in the client device. The selection may be specifically performed according to the processing capability of the client device, the limitation of the user usage scenario, and the like. This is not a limitation of the present application. The client device may further include a processor if all operations are performed in the client device.
The client device may have a communication module (i.e., a communication unit), and may be communicatively connected to a remote server to implement data transmission with the server. The server may include a server on the task scheduling center side, and in other implementation scenarios, the server may also include a server on an intermediate platform, for example, a server on a third-party server platform that is communicatively linked to the task scheduling center server. The server may include a single computer device, or may include a server cluster formed by a plurality of servers, or a server structure of a distributed apparatus.
The server and the client device may communicate using any suitable network protocol, including network protocols not yet developed at the filing date of this application. The network protocol may include, for example, a TCP/IP protocol, a UDP/IP protocol, an HTTP protocol, an HTTPS protocol, or the like. Of course, the network Protocol may also include, for example, an RPC Protocol (Remote Procedure Call Protocol), a REST Protocol (Representational State Transfer Protocol), and the like used above the above Protocol.
The following examples are intended to illustrate the details.
In order to improve timeliness and intelligence of product recommendation and further improve success rate of product recommendation, the present embodiment provides a product information recommendation method in which an execution subject is a product information recommendation device, as shown in fig. 1, the method specifically includes the following contents:
s101: customer basic information of a target customer is received.
Wherein, the client basic information comprises: customer identity information, customer holding other product information, customer assets, customer contributions, settlement business transactions, channel preferences, and the like.
S102: and determining preference scores of the target customer corresponding to different product types by applying the customer basic information and a plurality of preset product preference prediction models respectively corresponding to different product types, and taking the product type corresponding to the maximum value of the preference scores as a target recommended product type.
The product types can be divided into a real-time warranty type, a real-time non-warranty type, a fixed-term non-warranty type, a fixed-term high-risk type and the like according to the term and risk grade of the product. And each preset product preference prediction model corresponds to different product types respectively. For example, the customer basic information of the target customer is input into a preset product preference prediction model corresponding to the real-time warranty type, and the output of the preset product preference prediction model is a preference score of the target customer corresponding to the real-time warranty type.
S103: sending product purchase information corresponding to the target recommended product type to the target customer; each preset product preference prediction model is an iterative decision tree model obtained by pre-training according to historical customer basic information of a plurality of historical customers and preference scoring labels of the historical customers for the same product type.
The iterative Decision Tree (GDBT) model is a concept-integrated Decision Tree model, and the iterative Decision Tree algorithm takes historical data as a sample, sets a label column in the sample data as a training target, and constructs a mapping relation between a Decision Tree fitting feature and a label through iteration. It is understood that each of the historical client basic information is taken as one sample data.
As can be seen from the above description, the product information recommendation method provided in this embodiment applies a plurality of iterative decision tree models pre-trained according to the historical client basic information of a plurality of historical clients and the preference score labels of the historical clients for the same product type to respectively perform product preference scoring, and determines the target recommended product type, so that timeliness and intelligence of product recommendation can be improved, and further, the success rate of product recommendation is improved.
In order to improve timeliness and accuracy of the product preference prediction model training, and further improve timeliness and intelligence of the product recommendation, in an embodiment of the present application, referring to fig. 2, before step S101, the method further includes:
s201: obtaining a plurality of product preference prediction training sets, wherein each of the product preference prediction training sets comprises: the historical customer basic information of a plurality of historical customers and the preference scoring labels of the historical customers for the same product type are different, and the product types corresponding to the historical purchase record groups are different.
S202: and respectively training product preference prediction models corresponding to the product types by applying the product preference prediction training groups, wherein each product preference prediction model is an iterative decision model.
Specifically, the iterative decision tree model may be a machine learning model based on a decision tree algorithm, and is a model formed by integrating multiple tree structures, each branch node represents a distinction of a customer feature, customers are classified through the branch nodes, and finally, leaf nodes represent average preference scores of the categories. The core of the iteration is that a plurality of decision trees are constructed, each tree learns the residual errors of all previous tree conclusions and preference scores, the residual errors are smaller and smaller, the iteration is stopped until the loss errors meet the requirements, and the fitting of the preference scores is realized.
As can be seen from the above description, the product information recommendation method provided in this embodiment can obtain the product preference prediction model corresponding to each product type by applying a plurality of product preference prediction training sets to train the iterative decision tree model, and can improve the reliability of the training of each product preference prediction model.
In order to obtain a reliable preference score label and further apply the preference score label to improve timeliness and accuracy of training the product preference prediction model, in an embodiment of the present application, referring to fig. 3, before step S201, the method further includes:
s301: and acquiring a plurality of sets of historical transaction records, wherein each set of historical transaction record includes the times and time for the uniquely corresponding historical customer to purchase the products of the same product type.
It can be understood that if a product type corresponds to a plurality of sets of historical transaction record groups, which are all marked as first historical transaction record groups, the historical customers corresponding to the first historical transaction record groups are different; and if one historical user corresponds to a plurality of historical transaction record groups which are marked as second historical transaction record groups, the product types corresponding to the second historical transaction record groups are different. The product may be a financial product.
S302: and generating preference scoring labels of the historical customers for different product types by applying the preset time attenuation coefficient and the historical transaction record group corresponding to each product type.
It will be appreciated that the preference score labels for different product types are different for the same history customer; for example, the number and time of the historical customer a purchasing the product of the fixed term warranty type and the preset time attenuation coefficient corresponding to the fixed term warranty type generate the preference score label of the historical customer a for the fixed term warranty type.
Wherein the initial time attenuation coefficient may be preset as required. The time attenuation coefficient is used for assigning values to the label columns of the sample data, and the time attenuation is based on the application of Newton's cooling law in historical data processing. If the time attenuation coefficient is adjusted, the preference scoring tag can be adjusted accordingly, so that timeliness of the preference scoring tag is guaranteed.
Specifically, a historical customer, for any of the product types' preference scoring tags: and traversing the purchase times and purchase time of the product type in the historical transaction record group of the historical user, calculating the preference score of the historical user on the product type according to a time attenuation formula, wherein the time attenuation coefficient can be preset to be 0.1, and the time attenuation coefficient can be flexibly adjusted according to the actual effect evaluation of a product preference prediction model. And traversing all historical clients to perform preference score calculation, and taking the obtained result as a label column of the basic information of the historical clients.
As can be seen from the above description, the product information recommendation method provided in this embodiment can generate the preference score labels of the historical customers for different product types according to the historical transaction record groups and the time decay coefficients, so as to obtain reliable preference score labels, and further improve the timeliness and the accuracy of the training product preference prediction model by applying the preference score labels.
In order to further improve the reliability of the practical attenuation coefficient and further improve the accuracy of obtaining the preference score by applying the time attenuation coefficient, in an embodiment of the present application, referring to fig. 4, after step S201, the method further includes:
s401: and respectively inputting the historical customer basic information in each group of the product preference prediction training group into the corresponding product preference prediction model.
Specifically, according to the product type, determining a product preference prediction model corresponding to each product preference prediction training set, and inputting the historical customer basic information in each product preference prediction training set into the product preference prediction model corresponding to the product preference prediction training set.
S402: and adjusting each preset time attenuation coefficient according to the output of each product preference prediction model and the historical transaction record group.
For example, according to a first product type corresponding to a first product preference prediction model, determining a historical transaction record group corresponding to the first product preference prediction model; and applying the output of the first product preference prediction model and the corresponding historical transaction record group to adjust the preset time attenuation coefficient corresponding to the first product type, wherein the first product preference prediction model can be any one of the product preference prediction models, and the first product type can be any one of the product types.
As can be seen from the above description, according to the product information recommendation method provided in this embodiment, after the preset time attenuation coefficient is adjusted, the preference score label can be correspondingly adjusted, so as to obtain a preference score label capable of balancing new and old sample data, thereby improving timeliness and accuracy of training each product preference prediction model.
In order to further improve the reliability of the practical attenuation coefficient and further improve the accuracy of the obtaining the preference score by applying the time attenuation coefficient, in an embodiment of the present application, referring to fig. 5, after step S102, the method further includes:
s501: and acquiring the purchase times and purchase time of the target customer for purchasing products of different product types.
S502: and adjusting each time attenuation coefficient according to the preference scores, purchase times and purchase time of different product types corresponding to the target customer.
It can be understood that, a product type corresponding to the preference score is determined, and a preset time attenuation coefficient corresponding to the product type is adjusted according to the preference score, the purchase times and the purchase time. The respective purchase times and purchase times of the target customers for purchasing products of different product types may be stored in advance in the target database.
From the above description, based on the preference scores, purchase times and purchase time of the target customer corresponding to different product types in the product information recommendation process, the time attenuation coefficient corresponding to each product type is adjusted, each preference score label is adjusted by applying the adjusted time attenuation coefficient, each product preference prediction model is trained again, and timeliness and accuracy of next product information recommendation can be further improved.
In order to further improve the reliability of the product preference prediction model, in an application example of the present application, after step S202, the method further includes:
s601: and judging whether each preset product preference prediction model passes the preliminary evaluation or not by using preset evaluation indexes.
Specifically, the preset evaluation index includes an MSE mean square error, an R2 decision coefficient evaluation index, and the like.
S602: if the preset product preference prediction models pass the preliminary evaluation, judging whether the success rate of recommending the product by applying each preset product preference prediction model is higher than a recommendation success threshold value or not based on a segmentation test method, and if not, executing the step S202 again.
It can be understood that, if the success rate of recommending the product by applying each preset product preference prediction model is higher than the recommendation success threshold, the current operation is ended.
To further illustrate the present solution, the present application provides an application example of a product information recommendation method, referring to fig. 6, the method includes, step 11: determining a modeling scene; step 12: preparing a sample; step 13: time attenuation treatment; step 14: characteristic engineering; step 15: training a model; step 16: evaluating the effect; and step 17: and (6) deploying the model. The specific description is as follows:
step 11: determining a modeling scene; according to the sales experience of specific products, a modeling scene is determined, the products generally have tendency, and the same type of products are classified for modeling. Taking the recommendation of financial products as an example, the products can be classified according to the time limit and risk level of the products, and are classified into a real-time warranty type, a real-time non-warranty type, a fixed time limit non-warranty type, a fixed time limit high risk type and the like. And (3) respectively establishing a model for each type of product, predicting the preference scores of the type of product by the customer, and finally selecting the type of product with the highest prediction score to recommend to the customer.
Step 12: preparing a sample; the basic information of the client is selected as sample data, and the introduction of a time attenuation coefficient is considered, so that the full amount of historical data can be used as the sample data, sufficient training data amount is included, and the training effect of the model is guaranteed.
Step 13: time attenuation treatment; and introducing a time attenuation coefficient, and assigning values to the label columns of the sample data. The time decay is based on the application of newton's law of cooling to historical data processing, and the specific processing flow is shown in fig. 7, which includes: step 31: traversing all clients; step 32: screening all purchase details of the customer; step 33: acquiring purchase times and purchase dates; step 34: calculating a score according to a time attenuation formula; step 35: updating the preference score to a sample label column; step 36: completing sample preparation; the specific description is as follows:
traversing all the clients in the sample data, determining all the historical records of each client for purchasing the product, recording the purchasing times and the purchasing time of the client, wherein the purchasing time can be the purchasing month or the purchasing date, and calculating the preference score of the client for the product according to a time attenuation formula, wherein the specific formula is as follows:
where α is a time attenuation coefficient, a default value of 0.1 may be set, cust represents a customer, item represents a product type, Sample represents Sample data, T represents a current system time, and T represents a purchase time. The larger the coefficient value is, the higher the attenuation degree is, and the higher the recent sample data weight is; the lower the coefficient value, the lower the degree of attenuation, and the lower the recent sample data weight. In the model construction, the time attenuation coefficient can be flexibly adjusted according to the actual effect evaluation of the model. And traversing all clients to perform preference score calculation, and assigning p _ score to the label column of the sample data to be used as a training target.
Step 14: characteristic engineering; selecting the characteristic information of the client to be supplemented into sample data for model training, wherein the supplemented sample data, namely the basic information of the client comprises: the customer identity information, such as account number and identification card number, and the like, the customer holds other product information, such as product name, code and the like, the customer asset information, the customer contribution information, the settlement business transaction information, the channel preference information and the like.
Step 15: training a model; an iterative decision tree algorithm is adopted for model training, as shown in fig. 8, the iterative decision tree is a model formed by integrating a plurality of tree structures, each branch node represents the distinction of one customer feature, customers are classified through the branch nodes, and finally leaf nodes represent the average preference score of the category. The core of the iteration is to construct a plurality of decision trees, including: decision tree 1 to decision tree n; based on the learning rate weighting, all tree conclusions and preference score residual errors before each decision tree learns are smaller and smaller, and iteration is stopped until loss errors meet requirements, so that the preference score is fitted.
Step 16: evaluating the effect; the model may be initially verified by evaluating metrics such as MSE and R2. The model passing the preliminary verification can be designed into a control group, and the actual effect of the model is evaluated by performing A/B TEST segmentation TEST. If the model recommendation success rate is higher than the success rate in the existing business mode, model deployment and application can be carried out. If the estimated model effect does not meet the expectation, returning to the time attenuation processing step 13, adjusting the time attenuation coefficient and the iterative decision tree model parameters, and performing model training and effect verification again until the effect meets the expectation; as shown in fig. 9, the effect evaluation process specifically includes: step 51: verifying an evaluation index MSE; step 52: a verification evaluation index R2; step 53: setting a comparison group and carrying out A/B Test; step 54: and evaluating the lifting effect of the model group.
And step 17: deploying a model; and performing model deployment application, generating model prediction scores of various products, and selecting the product type with the highest score to recommend to a customer.
In an example of the application, before 2019, a plurality of target enterprises are restricted by own enterprise systems, purchased products are mainly the cost-preserving financial products, and a large amount of sample data reflects the purchasing preference. And after 2019, the money-preserving type financing gradually quits the market, the target enterprise adjusts the relevant system rules, and starts to purchase non-money-preserving type financing products to form a new product purchase trend. Through the application, the preference score of the model evaluation type customers on the non-warranty type products is higher, and finally, the non-warranty type products are recommended to other similar enterprises through model operation more reasonably.
In terms of software, in order to improve timeliness and intelligence of product recommendation and further improve success rate of product recommendation, the present application provides an embodiment of a product information recommendation device for implementing all or part of contents in the product information recommendation method, where the product information recommendation device specifically includes the following contents:
and the receiving module is used for receiving the client basic information of the target client.
And the prediction module is used for applying the client basic information and a plurality of preset product preference prediction models respectively corresponding to different product types, determining preference scores of different product types corresponding to the target client, and taking the product type corresponding to the maximum value of the preference scores as a target recommended product type.
The recommending module is used for sending the product purchasing information corresponding to the target recommended product type to the target customer; each preset product preference prediction model is an iterative decision tree model obtained by pre-training according to historical customer basic information of a plurality of historical customers and preference scoring labels of the historical customers for the same product type.
In an embodiment of the present application, the product information recommending apparatus further includes:
a first obtaining module, configured to obtain a plurality of product preference prediction training sets, where each of the product preference prediction training sets includes: the historical customer basic information of a plurality of historical customers and the preference scoring labels of the historical customers for the same product type are different, and the product types corresponding to the historical purchase record groups are different.
And the training module is used for applying each group of product preference prediction training groups to respectively train a product preference prediction model corresponding to each product type, and each product preference prediction model is an iterative decision model.
In an embodiment of the present application, the product information recommending apparatus further includes:
and the second acquisition module is used for acquiring a plurality of groups of historical transaction record groups, and each group of historical transaction record groups contains the times and time for the uniquely corresponding historical customers to purchase the products of the same product type.
And the generating module is used for applying a preset time attenuation coefficient and a historical transaction record group corresponding to each product type to generate preference scoring labels of each historical customer for different product types.
In an embodiment of the present application, the product information recommending apparatus further includes:
and the input module is used for respectively inputting the historical customer basic information in each group of the product preference prediction training set into the corresponding product preference prediction model.
And the first adjusting module is used for adjusting each preset time attenuation coefficient according to the output of each product preference prediction model and the historical transaction record group.
In an embodiment of the present application, the product information recommending apparatus further includes:
and the third acquisition module is used for acquiring the purchase times and purchase time of the target customer for purchasing the products of different product types.
And the second adjusting module is used for adjusting each time attenuation coefficient according to the preference scores, the purchase times and the purchase time of different product types corresponding to the target customer.
The embodiment of the product information recommendation apparatus provided in this specification may be specifically configured to execute the processing procedure of the embodiment of the product information recommendation method, and the functions of the embodiment are not described herein again, and reference may be made to the detailed description of the embodiment of the product information recommendation method.
From the above description, the product information recommendation method and device provided by the application can solve the balance problem of new and old sample data in model training by combining the iterative decision tree algorithm and the time attenuation coefficient, on one hand, training is introduced through massive historical data to guarantee the fitting effect, on the other hand, the weight of new training data is improved through the time attenuation coefficient, the model training effect is effectively improved, and the accuracy, the novelty and the timeliness of the recommendation result are guaranteed.
In terms of hardware, in order to improve timeliness and intelligence of product recommendation and further improve success rate of product recommendation, the present application provides an embodiment of an electronic device for implementing all or part of contents in the product information recommendation method, where the electronic device specifically includes the following contents:
a processor (processor), a memory (memory), a communication Interface (Communications Interface), and a bus; the processor, the memory and the communication interface complete mutual communication through the bus; the communication interface is used for realizing information transmission among the product information recommendation device, the user terminal and other related equipment; the electronic device may be a desktop computer, a tablet computer, a mobile terminal, and the like, but the embodiment is not limited thereto. In this embodiment, the electronic device may be implemented with reference to the embodiment for implementing the product information recommendation method and the embodiment for implementing the product information recommendation apparatus in the embodiments, and the contents thereof are incorporated herein, and repeated details are not repeated herein.
Fig. 10 is a schematic block diagram of a system configuration of an electronic device 9600 according to an embodiment of the present application. As shown in fig. 10, the electronic device 9600 can include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. Notably, this fig. 10 is exemplary; other types of structures may also be used in addition to or in place of the structure to implement telecommunications or other functions.
In one or more embodiments of the present application, the product information recommendation functionality can be integrated into the central processor 9100. The central processor 9100 may be configured to control as follows:
s101: customer basic information of a target customer is received.
S102: and determining preference scores of the target customer corresponding to different product types by applying the customer basic information and a plurality of preset product preference prediction models respectively corresponding to different product types, and taking the product type corresponding to the maximum value of the preference scores as a target recommended product type.
S103: sending product purchase information corresponding to the target recommended product type to the target customer; each preset product preference prediction model is an iterative decision tree model obtained by pre-training according to historical customer basic information of a plurality of historical customers and preference scoring labels of the historical customers for the same product type.
From the above description, the electronic device provided by the embodiment of the application can improve timeliness and intelligence degree of product recommendation, and further improve success rate of product recommendation.
In another embodiment, the product information recommending apparatus may be configured separately from the central processor 9100, for example, the product information recommending apparatus may be configured as a chip connected to the central processor 9100, and the product information recommending function is realized by the control of the central processor.
As shown in fig. 10, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is noted that the electronic device 9600 also does not necessarily include all of the components shown in fig. 10; in addition, the electronic device 9600 may further include components not shown in fig. 10, which can be referred to in the prior art.
As shown in fig. 10, a central processor 9100, sometimes referred to as a controller or operational control, can include a microprocessor or other processor device and/or logic device, which central processor 9100 receives input and controls the operation of the various components of the electronic device 9600.
The memory 9140 can be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And the central processing unit 9100 can execute the program stored in the memory 9140 to realize information storage or processing, or the like.
The input unit 9120 provides input to the central processor 9100. The input unit 9120 is, for example, a key or a touch input device. Power supply 9170 is used to provide power to electronic device 9600. The display 9160 is used for displaying display objects such as images and characters. The display may be, for example, an LCD display, but is not limited thereto.
The memory 9140 can be a solid state memory, e.g., Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes called an EPROM or the like. The memory 9140 could also be some other type of device. Memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application/function storage portion 9142, the application/function storage portion 9142 being used for storing application programs and function programs or for executing a flow of operations of the electronic device 9600 by the central processor 9100.
The memory 9140 can also include a data store 9143, the data store 9143 being used to store data, such as contacts, digital data, pictures, sounds, and/or any other data used by an electronic device. The driver storage portion 9144 of the memory 9140 may include various drivers for the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, contact book applications, etc.).
The communication module 9110 is a transmitter/receiver 9110 that transmits and receives signals via an antenna 9111. The communication module (transmitter/receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as in the case of a conventional mobile communication terminal.
Based on different communication technologies, a plurality of communication modules 9110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be provided in the same electronic device. The communication module (transmitter/receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby implementing ordinary telecommunications functions. The audio processor 9130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 9130 is also coupled to the central processor 9100, thereby enabling recording locally through the microphone 9132 and enabling locally stored sounds to be played through the speaker 9131.
According to the description, the electronic equipment provided by the embodiment of the application can improve the timeliness and the intelligent degree of product recommendation, and further improve the success rate of product recommendation.
An embodiment of the present application further provides a computer-readable storage medium capable of implementing all the steps in the product information recommendation method in the above embodiment, where the computer-readable storage medium stores a computer program, and the computer program implements all the steps of the product information recommendation method in the above embodiment when executed by a processor, for example, the processor implements the following steps when executing the computer program:
s101: customer basic information of a target customer is received.
S102: and determining preference scores of the target customer corresponding to different product types by applying the customer basic information and a plurality of preset product preference prediction models respectively corresponding to different product types, and taking the product type corresponding to the maximum value of the preference scores as a target recommended product type.
S103: sending product purchase information corresponding to the target recommended product type to the target customer; each preset product preference prediction model is an iterative decision tree model obtained by pre-training according to historical customer basic information of a plurality of historical customers and preference scoring labels of the historical customers for the same product type.
As can be seen from the above description, the computer-readable storage medium provided in the embodiments of the present application can improve timeliness and intelligence of product recommendation, and further improve success rate of product recommendation.
In the present application, each embodiment of the method is 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. Reference is made to the description of the method embodiments.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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 application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. 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.
The principle and the implementation mode of the present application are explained by applying specific embodiments in the present application, and the description of the above embodiments is only used to help understanding the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (12)
1. A product information recommendation method, comprising:
receiving client basic information of a target client;
determining preference scores of different product types corresponding to the target customer by applying the customer basic information and a plurality of preset product preference prediction models respectively corresponding to different product types, and taking the product type corresponding to the maximum value of the preference scores as a target recommended product type;
sending product purchase information corresponding to the target recommended product type to the target customer;
each preset product preference prediction model is an iterative decision tree model obtained by pre-training according to historical customer basic information of a plurality of historical customers and preference scoring labels of the historical customers for the same product type.
2. The product information recommendation method according to claim 1, further comprising, before said receiving the customer basic information of the target customer:
obtaining a plurality of product preference prediction training sets, wherein each of the product preference prediction training sets comprises: the method comprises the following steps that basic information of historical customers of a plurality of historical customers and preference scoring labels of the historical customers for the same product type are different, and the product types corresponding to historical purchase record groups are different;
and respectively training product preference prediction models corresponding to the product types by applying the product preference prediction training groups, wherein each product preference prediction model is an iterative decision model.
3. The product information recommendation method of claim 2, further comprising, prior to said obtaining a plurality of product preference prediction training sets:
acquiring a plurality of groups of historical transaction record groups, wherein each group of historical transaction record groups comprises the times and time for purchasing products of the same product type by the only corresponding historical client;
and generating preference scoring labels of the historical customers for different product types by applying the preset time attenuation coefficient and the historical transaction record group corresponding to each product type.
4. The product information recommendation method of claim 3, further comprising, after said obtaining a plurality of product preference prediction training sets:
respectively inputting the historical customer basic information in each group of product preference prediction training groups into respective corresponding product preference prediction models;
and adjusting each preset time attenuation coefficient according to the output of each product preference prediction model and the historical transaction record group.
5. The product information recommendation method of claim 3, further comprising, after said determining preference scores of said target customers for different product types:
acquiring the purchase times and purchase time of the target customer for purchasing products of different product types;
and adjusting each time attenuation coefficient according to the preference scores, purchase times and purchase time of different product types corresponding to the target customer.
6. A product information recommendation device, comprising:
the receiving module is used for receiving the client basic information of the target client;
the prediction module is used for applying the client basic information and a plurality of preset product preference prediction models respectively corresponding to different product types, determining preference scores of different product types corresponding to the target client, and taking the product type corresponding to the maximum value of the preference scores as a target recommended product type;
the recommending module is used for sending the product purchasing information corresponding to the target recommended product type to the target customer;
each preset product preference prediction model is an iterative decision tree model obtained by pre-training according to historical customer basic information of a plurality of historical customers and preference scoring labels of the historical customers for the same product type.
7. The product information recommendation device of claim 6, further comprising:
a first obtaining module, configured to obtain a plurality of product preference prediction training sets, where each of the product preference prediction training sets includes: the method comprises the following steps that basic information of historical customers of a plurality of historical customers and preference scoring labels of the historical customers for the same product type are different, and the product types corresponding to historical purchase record groups are different;
and the training module is used for applying each group of product preference prediction training groups to respectively train a product preference prediction model corresponding to each product type, and each product preference prediction model is an iterative decision model.
8. The product information recommendation device according to claim 7, further comprising:
the second acquisition module is used for acquiring a plurality of groups of historical transaction record groups, and each group of historical transaction record groups contains the times and time for the unique corresponding historical client to purchase the products of the same product type;
and the generating module is used for applying a preset time attenuation coefficient and a historical transaction record group corresponding to each product type to generate preference scoring labels of each historical customer for different product types.
9. The product information recommendation device according to claim 7, further comprising:
the input module is used for respectively inputting the historical customer basic information in each group of product preference prediction training groups into the corresponding product preference prediction models;
and the first adjusting module is used for adjusting each preset time attenuation coefficient according to the output of each product preference prediction model and the historical transaction record group.
10. The product information recommendation device according to claim 8, further comprising:
the third acquisition module is used for acquiring the purchase times and purchase time of the target customer for purchasing the products of different product types;
and the second adjusting module is used for adjusting each time attenuation coefficient according to the preference scores, the purchase times and the purchase time of different product types corresponding to the target customer.
11. 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 product information recommendation method of any one of claims 1 to 5 when executing the program.
12. A computer-readable storage medium having computer instructions stored thereon, wherein the instructions, when executed, implement the product information recommendation method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010715579.5A CN111861569B (en) | 2020-07-23 | 2020-07-23 | Product information recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010715579.5A CN111861569B (en) | 2020-07-23 | 2020-07-23 | Product information recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111861569A true CN111861569A (en) | 2020-10-30 |
| CN111861569B CN111861569B (en) | 2024-02-02 |
Family
ID=72950434
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010715579.5A Active CN111861569B (en) | 2020-07-23 | 2020-07-23 | Product information recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111861569B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112561709A (en) * | 2020-11-30 | 2021-03-26 | 泰康保险集团股份有限公司 | Product information method, device, equipment and medium |
| CN112561588A (en) * | 2020-12-18 | 2021-03-26 | 中国农业银行股份有限公司 | Product recommendation method and device |
| CN112700043A (en) * | 2020-12-31 | 2021-04-23 | 新奥数能科技有限公司 | Load prediction method and device, computer readable storage medium and electronic equipment |
| CN113129154A (en) * | 2021-05-18 | 2021-07-16 | 中国银行股份有限公司 | Inter-row recommendation method and device for fund product information |
| CN113159959A (en) * | 2021-05-20 | 2021-07-23 | 中国银行股份有限公司 | Foreign exchange product recommendation method and device |
| CN113191821A (en) * | 2021-05-20 | 2021-07-30 | 北京大米科技有限公司 | Data processing method and device |
| CN113344673A (en) * | 2021-06-28 | 2021-09-03 | 平安信托有限责任公司 | Product pushing method and device, electronic equipment and storage medium |
| CN113516511A (en) * | 2021-07-13 | 2021-10-19 | 中国工商银行股份有限公司 | Financial product purchase prediction method and device and electronic equipment |
| CN113592606A (en) * | 2021-08-10 | 2021-11-02 | 平安银行股份有限公司 | Product recommendation method, device, equipment and storage medium based on multiple decisions |
| CN113762392A (en) * | 2021-09-08 | 2021-12-07 | 平安普惠企业管理有限公司 | Financial product recommendation method, device, equipment and medium based on artificial intelligence |
| CN113781246A (en) * | 2021-09-14 | 2021-12-10 | 平安科技（深圳）有限公司 | Policy generation method and device based on preset label and storage medium |
| CN113781098A (en) * | 2021-07-30 | 2021-12-10 | 深圳市思为软件技术有限公司 | Method and device for improving sales efficiency and computer storage medium |
| CN114186024A (en) * | 2021-12-14 | 2022-03-15 | 中国建设银行股份有限公司 | Recommendation method and device |
| CN114219307A (en) * | 2021-12-16 | 2022-03-22 | 中国建设银行股份有限公司 | Product determination method, device, equipment and computer storage medium |
| CN116881853A (en) * | 2023-09-08 | 2023-10-13 | 小舟科技有限公司 | Attention assessment method, system, equipment and medium based on multi-mode fusion |
| CN117874357A (en) * | 2024-03-12 | 2024-04-12 | 中国电子信息产业集团有限公司第六研究所 | Information recommendation method and device for finger display system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109165983A (en) * | 2018-09-04 | 2019-01-08 | 中国平安人寿保险股份有限公司 | Insurance products recommended method, device, computer equipment and storage medium |
-
2020
- 2020-07-23 CN CN202010715579.5A patent/CN111861569B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109165983A (en) * | 2018-09-04 | 2019-01-08 | 中国平安人寿保险股份有限公司 | Insurance products recommended method, device, computer equipment and storage medium |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112561709A (en) * | 2020-11-30 | 2021-03-26 | 泰康保险集团股份有限公司 | Product information method, device, equipment and medium |
| CN112561709B (en) * | 2020-11-30 | 2024-02-02 | 泰康保险集团股份有限公司 | Product information method, device, equipment and medium |
| CN112561588A (en) * | 2020-12-18 | 2021-03-26 | 中国农业银行股份有限公司 | Product recommendation method and device |
| CN112700043A (en) * | 2020-12-31 | 2021-04-23 | 新奥数能科技有限公司 | Load prediction method and device, computer readable storage medium and electronic equipment |
| CN112700043B (en) * | 2020-12-31 | 2024-03-08 | 新奥数能科技有限公司 | Load prediction method, load prediction device, computer readable storage medium and electronic equipment |
| CN113129154A (en) * | 2021-05-18 | 2021-07-16 | 中国银行股份有限公司 | Inter-row recommendation method and device for fund product information |
| CN113159959A (en) * | 2021-05-20 | 2021-07-23 | 中国银行股份有限公司 | Foreign exchange product recommendation method and device |
| CN113191821A (en) * | 2021-05-20 | 2021-07-30 | 北京大米科技有限公司 | Data processing method and device |
| CN113344673A (en) * | 2021-06-28 | 2021-09-03 | 平安信托有限责任公司 | Product pushing method and device, electronic equipment and storage medium |
| CN113516511A (en) * | 2021-07-13 | 2021-10-19 | 中国工商银行股份有限公司 | Financial product purchase prediction method and device and electronic equipment |
| CN113781098A (en) * | 2021-07-30 | 2021-12-10 | 深圳市思为软件技术有限公司 | Method and device for improving sales efficiency and computer storage medium |
| CN113592606A (en) * | 2021-08-10 | 2021-11-02 | 平安银行股份有限公司 | Product recommendation method, device, equipment and storage medium based on multiple decisions |
| CN113592606B (en) * | 2021-08-10 | 2023-08-22 | 平安银行股份有限公司 | Product recommendation method, device, equipment and storage medium based on multiple decisions |
| CN113762392A (en) * | 2021-09-08 | 2021-12-07 | 平安普惠企业管理有限公司 | Financial product recommendation method, device, equipment and medium based on artificial intelligence |
| CN113781246A (en) * | 2021-09-14 | 2021-12-10 | 平安科技（深圳）有限公司 | Policy generation method and device based on preset label and storage medium |
| CN113781246B (en) * | 2021-09-14 | 2024-03-05 | 平安科技（深圳）有限公司 | Strategy generation method and device based on preset label and storage medium |
| CN114186024A (en) * | 2021-12-14 | 2022-03-15 | 中国建设银行股份有限公司 | Recommendation method and device |
| CN114219307A (en) * | 2021-12-16 | 2022-03-22 | 中国建设银行股份有限公司 | Product determination method, device, equipment and computer storage medium |
| CN116881853A (en) * | 2023-09-08 | 2023-10-13 | 小舟科技有限公司 | Attention assessment method, system, equipment and medium based on multi-mode fusion |
| CN116881853B (en) * | 2023-09-08 | 2024-01-05 | 小舟科技有限公司 | Attention assessment method, system, equipment and medium based on multi-mode fusion |
| CN117874357A (en) * | 2024-03-12 | 2024-04-12 | 中国电子信息产业集团有限公司第六研究所 | Information recommendation method and device for finger display system |
| CN117874357B (en) * | 2024-03-12 | 2024-05-24 | 中国电子信息产业集团有限公司第六研究所 | Information recommendation method and device for finger display system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111861569B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111861569B (en) | Product information recommendation method and device | |
| CN112785086A (en) | Credit overdue risk prediction method and device | |
| CN111768231B (en) | Product information recommendation method and device | |
| CN111798244B (en) | Transaction fraud monitoring method and device | |
| CN112232947B (en) | Method and device for predicting risk in lending | |
| CN111369247A (en) | Cross-bank transaction data processing method and device | |
| CN111932267A (en) | Enterprise financial service risk prediction method and device | |
| CN112232546A (en) | Recommendation probability estimation method and device, electronic equipment and storage medium | |
| US20190362354A1 (en) | Real-time updating of predictive analytics engine | |
| CN111815169A (en) | Business approval parameter configuration method and device | |
| CN110992190A (en) | Asset configuration method and device based on user portrait | |
| CN110472798A (en) | Prediction technique, device and the computer readable storage medium of time series data | |
| CN112581226A (en) | Product recommendation method and system | |
| CN115269997A (en) | Financial product recommendation method and device | |
| CN112766825A (en) | Enterprise financial service risk prediction method and device | |
| CN113094284A (en) | Application fault detection method and device | |
| CN111352841B (en) | Quality detection method and device for financial transaction software | |
| CN113011966A (en) | Credit scoring method and device based on deep learning | |
| CN116664227A (en) | Intelligent recommendation method and device for financial products | |
| CN116485527A (en) | Financial credit risk analysis method and device | |
| CN112163861B (en) | Transaction risk factor feature extraction method and device | |
| CN113393320A (en) | Enterprise financial service risk prediction method and device | |
| CN113206998A (en) | Method and device for quality inspection of video data recorded by service | |
| CN110020728A (en) | Business model intensified learning method and device | |
| CN111932018B (en) | Bank business performance contribution information prediction method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |