CN110765169B - Information recommendation method, device, computer equipment and storage medium - Google Patents
Information recommendation method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110765169B CN110765169B CN201910842181.5A CN201910842181A CN110765169B CN 110765169 B CN110765169 B CN 110765169B CN 201910842181 A CN201910842181 A CN 201910842181A CN 110765169 B CN110765169 B CN 110765169B
- Authority
- CN
- China
- Prior art keywords
- data
- target
- information
- recommended
- client
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000004891 communication Methods 0.000 claims description 60
- 230000006870 function Effects 0.000 claims description 48
- 238000004590 computer program Methods 0.000 claims description 17
- 238000007619 statistical method Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 230000002452 interceptive effect Effects 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000007477 logistic regression Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000011478 gradient descent method Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an information recommendation method, an information recommendation device, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring target client data and service types in a preset period; inquiring a database based on the service type, and acquiring a target recommendation function corresponding to the service type; processing the target client data by adopting the target recommendation function to obtain data to be recommended corresponding to the target client data; distributing based on target client data, and generating a recommendation task table, wherein each target client data and corresponding data to be recommended are stored in the recommendation task table in an associated mode; and recommending the data to be recommended to the client terminal corresponding to the target client data according to the recommended task list. The information recommendation method can effectively improve information recommendation efficiency and accuracy.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to an information recommendation method, an information recommendation device, a computer device, and a storage medium.
Background
With the rapid development of the economic age and the diversification of the demands of clients, the variety of products with different service types is more and more, the complexity is correspondingly improved, and the selection difficulty of clients is higher. At present, aiming at the situation that the difficulty of selecting the client is high, exhibition industry personnel can conduct product recommendation work according to different client demands so as to pertinently recommend the client, but due to the continuous increase of the product types, the mode relying on manual recommendation is low in efficiency, the manual recommendation mode is subjective, and the accuracy is low.
Disclosure of Invention
The embodiment of the invention provides an information recommendation method, an information recommendation device, computer equipment and a storage medium, which are used for solving the problems that the current information recommendation mode mainly depends on manual recommendation, has low efficiency, is subjective and has low accuracy.
An information recommendation method, comprising:
acquiring target client data and service types in a preset period;
Inquiring a database based on the service type, and acquiring a target recommendation function corresponding to the service type;
processing the target client data by adopting the target recommendation function to obtain data to be recommended corresponding to the target client data;
distributing based on target client data, and generating a recommendation task table, wherein each target client data and corresponding data to be recommended are stored in the recommendation task table in an associated mode;
And recommending the data to be recommended to the client terminal corresponding to the target client data according to the recommended task list.
An information recommendation apparatus, comprising:
the data acquisition module to be processed is used for acquiring target customer data and service types in a preset period;
The target recommendation function acquisition module is used for inquiring a database based on the service type and acquiring a target recommendation function corresponding to the service type;
The data to be recommended acquisition module is used for processing the target client data by adopting the target recommendation function to obtain data to be recommended corresponding to the target client data;
the recommendation task table generation module is used for carrying out distribution based on target client data to generate a recommendation task table, and each target client data and corresponding data to be recommended are stored in the recommendation task table in an associated mode;
And the information recommending module is used for recommending the data to be recommended to the client terminal corresponding to the target client data according to the recommending task list.
A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the information recommendation method described above when the computer program is executed.
A computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the information recommendation method described above.
In the information recommendation method, the information recommendation device, the computer equipment and the storage medium information recommendation, the target client data and the service type in the preset period are acquired, so that a database is queried based on the service type, and a target recommendation function corresponding to the service type is acquired. And then, processing the target client data by adopting a target recommendation function corresponding to the service type to obtain data to be recommended corresponding to the target client data, so as to enhance the pertinence and the accuracy of the data to be recommended. And then, distributing the target client data to generate a recommendation task list so as to recommend the data to be recommended to the client terminal corresponding to the target client data based on the recommendation task list which is associated with and stored with each target client data and the corresponding data to be recommended, thereby achieving the purpose of intelligent information recommendation, and effectively improving the information recommendation efficiency and accuracy without relying on manual information recommendation according to experience.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic view of an application environment of an information recommendation method according to an embodiment of the invention;
FIG. 2 is a flow chart of a method for recommending information according to an embodiment of the invention;
FIG. 3 is a flowchart showing step S40 in FIG. 2;
FIG. 4 is a flowchart showing step S50 in FIG. 2;
FIG. 5 is a flowchart showing step S50 in FIG. 2;
FIG. 6 is a flow chart of a method for recommending information according to an embodiment of the invention;
FIG. 7 is a flowchart showing step S13 in FIG. 6;
FIG. 8 is a flowchart showing step S13 in FIG. 6;
FIG. 9 is a schematic diagram of an information recommendation device according to an embodiment of the invention;
FIG. 10 is a schematic diagram of a computer device in accordance with an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The information recommendation method provided by the embodiment of the invention can be applied to a display industry system to realize intelligent information recommendation without relying on manual information recommendation, and effectively improves the information recommendation efficiency and accuracy. The information recommendation method can be applied in an application environment such as fig. 1. Wherein the computer device communicates with the server over a network. The computer devices may be, but are not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The servers may be implemented by independent servers, or may be implemented by a server cluster, which is not limited herein.
In one embodiment, as shown in fig. 2, an information recommendation method is provided, and the method is applied to the server in fig. 1 for illustration, and includes the following steps:
s10: and acquiring target client data and service types in a preset period.
The target client data refers to client data of a to-be-exhibited business (i.e. an extended business) in a preset period in an enterprise or an organization. The preset period can be set in a self-defined manner according to different recommended demands of different enterprises and institutions, and is not limited herein. In this embodiment, the target customer data includes, but is not limited to, customer basic information and types of services (such as loans or financial transactions) handled by the exhibition staff, and it is understood that different exhibition staff can handle different types of services to service customers in a targeted manner. The customer base information refers to personal information of the customer, such as customer communication identification, customer location, customer grade, customer gender, customer income, etc. Big data platforms include, but are not limited to, the collection of target customer data using a Hadoop big data platform.
The Hadoop big data platform enables a user to develop a distributed program under the condition that the detail of the distributed bottom layer is not known, and high-speed operation and storage are carried out so as to improve the acquisition efficiency of original sample data. The Hadoop refers to a distributed system infrastructure, and implements a distributed file system (Hadoop Distributed FILE SYSTEM, hereinafter referred to as HDFS). The HDFS has the characteristic of high fault tolerance, is designed to be deployed on low-cost hardware, can provide high throughput to access data of an application program, is suitable for the application program with an oversized data set, and has the advantage of high acquisition efficiency when the Hadoop big data platform is adopted to acquire target client data.
S20: and inquiring the database based on the service type, and acquiring a target recommendation function corresponding to the service type.
The target recommendation function is a pre-trained function for analyzing data characteristics of target customer data to obtain product data suitable for customers. Specifically, the target recommendation functions corresponding to different service types are different, and the database is queried to obtain the target recommendation functions corresponding to the service types, so that the product data suitable for different customer recommendations can be pertinently recommended, and the accuracy of information recommendation is improved.
S30: and processing the target client data by adopting a target recommendation function to obtain data to be recommended corresponding to the target client data.
Specifically, the target client data in the preset period is processed by adopting the target exhibition function corresponding to the service type, and the recommended product data (namely the data to be recommended) corresponding to the target client data is obtained, so that the pertinence and the accuracy of the recommended product are enhanced.
S40: and distributing the target client data to generate a recommended task table, wherein each target client data and corresponding data to be recommended are stored in the recommended task table in an associated mode.
The recommended task list is a task list in which a server automatically distributes target clients to corresponding exhibition staff so as to recommend information. Specifically, after the server acquires the data to be recommended, the data to be recommended is associated with the target client data. And then, distributing according to the target client data to generate a recommendation task table so as to recommend information according to the data to be recommended corresponding to the target client data in the recommendation task table, and improving the accuracy of information recommendation without manually recommending according to experience.
S50: and recommending the data to be recommended to the client terminal corresponding to the target client data according to the recommending task list.
The recommending task table comprises target client data and corresponding data to be recommended (namely product data to be recommended). Specifically, the server can recommend the data to be recommended to the client terminal corresponding to the target client data according to different information pushing modes, so that the purpose of intelligent information recommendation is achieved, information recommendation is not needed to be performed manually according to experience, and information recommendation efficiency and accuracy are effectively improved.
In this embodiment, the target client data and the service type in the preset period are acquired, so that the database is queried based on the service type, and the target recommendation function corresponding to the service type is acquired. And then, processing the target client data by adopting a target recommendation function corresponding to the service type to obtain data to be recommended corresponding to the target client data, so as to enhance the pertinence and the accuracy of the data to be recommended. And then, distributing the target client data to generate a recommendation task list so as to recommend the data to be recommended to the client terminal corresponding to the target client data based on the recommendation task list which is associated with and stored with each target client data and the corresponding data to be recommended, thereby achieving the purpose of intelligent information recommendation, and effectively improving the information recommendation efficiency and accuracy without relying on manual information recommendation according to experience.
In one embodiment, the target customer data includes customer locations and customer levels, each customer level corresponding to a target number of customers; as shown in fig. 3, in step S40, that is, allocation is performed based on target client data, a recommended task table is generated, which specifically includes the following steps:
S41: and dividing target client data based on the client location to obtain a group to be allocated, wherein the group to be allocated corresponds to the client location.
S42: inquiring canvasing a personnel library according to the location of the customer, and determining a first exhibition industry personnel group corresponding to the group to be distributed; the first exhibition staff group comprises service grades corresponding to the first exhibition staff, and the service grades correspond to the client grades.
The first exhibition staff group is canvasing staff groups stored in the exhibition staff library, wherein the area of canvasing staff belonging to the first exhibition staff group is the same as the area of a client. The service level is a service level obtained by evaluating in advance according to experience, performance and the like of each exhibition staff, and the server level corresponds to the client level, namely the service level is the client level which can be served by the exhibition staff.
Specifically, dividing target client data based on the client location, namely dividing the target client data with the same client location into a group serving as a group to be allocated according to the client location; then, according to the customer location corresponding to the group to be allocated, inquiring canvasing the area of canvasing personnel corresponding to the exhibition staff in the personnel library, then, distributing the target customer data to a corresponding first canvasing personnel group, wherein the area corresponding to the first exhibition staff in the first exhibition staff group is consistent with the customer location in the group to be allocated, so that canvasing personnel and customers can communicate better, and the effectiveness of information recommendation is ensured.
S43: dividing the first exhibition staff with the service level identical to the client level into a second exhibition staff group corresponding to the client level; the second exhibition staff group comprises the maximum service amount corresponding to the second exhibition staff and the number of the second exhibition staff.
The second exhibition staff group is canvasing staff groups corresponding to the first exhibition staff in the first exhibition staff group, wherein the service level of the first exhibition staff is the same as the client level. The second exhibition staff group includes a maximum service amount corresponding to the second exhibition staff, and the maximum service amount refers to the maximum amount of clients that the exhibition staff can serve in a unit time (such as a day, a week or a month).
Specifically, the server may divide the client level in advance according to the liveness of the client, for example, if the service type is a loan service, the liveness of the client may be determined according to the historical loan amount of the client; if the service type is financial service, the activity of the customer can be determined according to the historical purchase quantity of financial products or the purchase financial amount of the customer. It will be appreciated that the higher the customer liveness, the higher the certification customer rating. And the client grade is determined so as to be distributed according to the service grade and the client grade corresponding to each first exhibition staff, thereby ensuring the effectiveness of information recommendation.
S44: and determining the to-be-serviced amount corresponding to the second exhibition staff based on the target client amount corresponding to the client level and the second exhibition staff amount.
Specifically, based on the number of target clients and the number of second exhibition staff corresponding to the client level, determining the amount of to-be-serviced corresponding to the second exhibition staff, namely, rounding down the ratio of the number of target clients to the number of second exhibition staff to obtain the amount of to-be-serviced corresponding to the second exhibition staff, for example, the target client data amount is 104, and the number of second canvasing staff is 5, and the amount of to-be-serviced corresponding to the second exhibition staff is
S45: and selecting target client data from the to-be-allocated group randomly or sequentially based on the to-be-served amount and the maximum service amount, and allocating the target client data to a second exhibition staff to generate a recommended task list.
Specifically, according to the to-be-served amount and the maximum processing amount, target client data is selected from the to-be-allocated group randomly or sequentially to be allocated to a second exhibition staff, and a recommended task list is generated.
For example, the server levels (from low to high) corresponding to the first exhibition staff are A, B and C, the client levels (from low to high) are a, B and C, the first exhibition staff corresponding to the client level in the second exhibition staff group is taken as the second exhibition staff group corresponding to the client level, that is, a-a, B-B and C-C, since each second exhibition staff group corresponds to a plurality of second exhibition staff, each client level corresponds to a plurality of target clients, the target clients with the client level a need to be allocated according to the number of canvasing staff corresponding to the second exhibition staff group, if the number of canvasing staff corresponding to the second exhibition staff level a is 5, the number of target clients corresponding to the client level a is 104, and the maximum throughput corresponding to each second exhibition staff is 20, the first clients corresponding to the client level a can be randomly selected from the target clients with the client level a, the second exhibition staff corresponding to the client level a 4 can be allocated to the target clients in the second exhibition staff group corresponding to the client level a, and the first and second exhibition staff can be recommended to the target exhibition staff according to the first order, the first and the second exhibition staff can be recommended to the target exhibition staff can be sent to the first and the target exhibition staff according to the recommended task list, and the first and the target exhibition staff can be recommended according to the first and the target data.
Further, for the remaining clients, if the database stores the related data of the candidate exhibition staff (for example, the candidate canvasing staff is identified), the remaining clients may be issued to the candidate canvasing staff (the candidate exhibition staff may be the senior exhibition staff) or if there is no candidate exhibition staff, the remaining clients may be allocated to the task table to be exhibited in the next unit time (for example, the unit time is calculated in weeks, the week is the first week, and the next unit time is the second week). The to-be-exhibited business task list refers to a task list containing client data corresponding to clients of the to-be-exhibited business.
In this embodiment, the target client data is allocated according to the client location and the client level in the target client data, so that the target client data is allocated to the exhibition staff corresponding to the client location and the client level, and the validity of information recommendation is ensured.
In one embodiment, the recommended task list includes an outbound communication identifier and a pending communication identifier; as shown in fig. 4, in step S50, that is, recommending the data to be recommended to the client terminal corresponding to the target client data according to the recommended task table, the method specifically includes the following steps:
s511: and receiving an information recommendation request, wherein the information recommendation request comprises an information pushing mode and a recommendation task list.
The information recommendation request is a request for triggering the server to conduct information recommendation on data in the recommendation task table. The information recommendation request comprises the information pushing mode and the recommendation task list generated in the embodiment. The information pushing mode includes, but is not limited to, a communication pushing mode, a network pushing mode and the like. Specifically, different enterprises or institutions have different information pushing modes (i.e. exhibition modes), so that after acquiring the recommended task list, the information needs to be pushed according to the different information pushing modes.
S512: if the information pushing mode is a communication pushing mode, calling the communication module to carry out batch outbound based on the outbound communication identifier and the to-be-called communication identifier, and receiving a communication feedback result sent by the communication module.
The communication module is a module for automatically carrying out batch outbound according to outbound communication identifiers and to-be-called communication identifiers in canvasing systems. The outbound communication identifier is a communication identifier (such as an extension number) corresponding to canvasing persons. The communication identification to be called is a communication identification (such as a mobile phone number or a base phone number) corresponding to the target client.
Specifically, the server randomly selects target clients from the recommended task list corresponding to each exhibition industry personnel to carry out batch outbound without manual outbound, so that the working efficiency is improved. Further, in this embodiment, a maximum amount of outbound volume needs to be set, so as to avoid the problem that no idle exhibition staff is connected and the waiting time of clients is long when the telephone is connected. Specifically, the maximum number of outgoing calls in a lot is not greater than the number of exhibition staff.
S513: if the communication feedback result is communication failure, acquiring information to be pushed, wherein the information to be pushed comprises an information frame and an original long link corresponding to the data to be recommended.
The information to be pushed refers to information which is not processed before information is pushed. The information to be pushed comprises an information frame and an original long link. The original long link refers to a product detail webpage address corresponding to the information to be pushed. The information frame refers to recommended content for recommended products in the information to be pushed. It is understood that the original long link is a long link (i.e., a link with a longer web page address). Specifically, if the communication feedback result is that the communication fails, the server sends product recommendation information, namely information to be pushed, to the corresponding client identifier, so that the cost of calling out again is reduced. If the communication feedback result is that the outbound is successful, the outbound line is required to be distributed to canvasing persons corresponding to the recommended task list so as to facilitate the exhibition staff to communicate with the clients, and the outbound is not required to be manually performed, so that the workload of the exhibition staff is reduced.
S514: and calling a link conversion interface to convert the original long link to obtain a target short link corresponding to the original long link.
The link conversion interface is an interface which is preconfigured by the system and converts long links into short links. The short link is to convert the web page address corresponding to the original long link (i.e. the target short link) to obtain a shorter web page address. The long link is converted into the short link by adopting a long-chain-short-chain algorithm, so that the phenomenon that the characters of the information to be pushed exceed the limit due to overlong linked address character strings and are often required to be split into two pieces of information to be respectively sent to target clients is avoided, the sending cost is saved, and the user experience is improved.
S515: based on the information frame and the target short link, generating target push information, and sending the target push information to the client terminal corresponding to the to-be-called communication identifier.
In this embodiment, an information template is created in advance, where the information template includes an information content module and a link module. The link module is used for storing the target short links corresponding to the target short links. The information content module is used for storing the information frame. Specifically, the obtained short link is filled into the information content module in the information template, and the target short link is filled into the link module in the information template, so that the target push information is sent to the client terminal corresponding to the to-be-called communication identifier, and the process of obtaining the target push information does not need manual intervention, thereby saving time. It should be noted that, the sending mode of sending the target push information to the client terminal corresponding to the to-be-called communication identifier includes, but is not limited to, a short message form, and the target push information is sent to the client with communication failure, so that the client clicks the target short link (i.e. the target short link) in the target push information to know the product details, thereby further improving the recommending efficiency and the effectiveness of information recommendation.
In this embodiment, if the information pushing manner is a communication pushing manner, the communication module is invoked to perform batch outbound based on the outbound communication identifier and the to-be-called communication identifier, so that manual outbound is not required, the working efficiency is improved, errors caused by manual operation can be effectively avoided, and the validity of information recommendation is ensured. Further, communication monitoring is performed during each outbound to receive a communication feedback result, and if the communication feedback result is a communication failure, target push information is sent to the client terminal corresponding to the to-be-called communication identifier, so that the cost of re-outbound is reduced.
In one embodiment, as shown in fig. 5, in step S50, data to be recommended is recommended to a client terminal corresponding to target client data according to a recommendation task table, and the method specifically includes the following steps:
s521: and receiving an information push request, wherein the information push request comprises an information push mode and a recommended task list.
S522: if the information pushing mode is a network pushing mode, updating an interactive interface corresponding to the client terminal based on the data to be recommended so as to highlight the data to be recommended on a recommendation display module of the interactive interface.
Specifically, the system can also be pushed in a network pushing mode, namely, the exhibition industry is carried out through a network sales channel. The target client data further comprises a client account corresponding to each target client (the client account can also be a to-be-called communication identifier), namely the target short link and the information frame can be sent to a client terminal corresponding to the client account in a message pushing mode. Or the interactive interface corresponding to each client terminal can be updated.
Specifically, a recommendation display module is preset on the interactive interface corresponding to the client terminal, a database is queried based on data to be recommended (i.e. recommended products) corresponding to each target client, a product display page corresponding to the data to be recommended is obtained, and the recommendation display module is updated based on the product display page corresponding to the data to be recommended, so that the recommended product information can be displayed on the interactive interface corresponding to the client terminal. Understandably, the recommendation display module displays the recommended products in a highlighted mode in the interactive interface, so that the clients can visually check the recommended products, and the effectiveness of information recommendation is ensured.
In this embodiment, if the information pushing manner is a network pushing manner, updating the interactive interface corresponding to the client terminal based on the data to be recommended, so as to highlight the data to be recommended on the recommendation display module of the interactive interface, so that the client can intuitively check the recommended product, and the validity of information recommendation is ensured.
In an embodiment, as shown in fig. 6, before step S10, the information recommendation method further includes the following steps:
s11: and acquiring the service type and corresponding original sample data.
Specifically, products corresponding to different business types are different, so that statistical analysis needs to be performed on original sample data of different business types, for example, for loan business, the original sample data corresponding to the loan business is obtained to include customer basic information and historical loan products (to be noted, different historical loan amounts correspond to different loan products); for the financial service, the original sample data corresponding to the financial service includes the customer basic information and the historical purchase products, and the customer basic information refers to customer personal information, such as customer age, customer location, customer gender, customer occupation, customer income, etc. In particular, the raw sample data may be obtained from sales-successful customer data in a large data platform, i.e. the raw sample data refers to sales-successful customer data. The big data platform comprises, but is not limited to, a Hadoop big data platform for collecting original sample data.
S12: and encoding the original sample data according to a preset encoding rule to obtain the sample data to be processed, which is expressed in a vector form.
Specifically, for the convenience of calculation, the original sample data is encoded according to a preset encoding rule, that is, each dimension data in the obtained original sample data is converted into a numerical value to be represented, so that in this embodiment, the original sample data identified in a vector form, that is, the sample data to be processed, is obtained, and each dimension data can be converted into a numerical value according to the following encoding rule: customer gender: 1-male, 0-female; customer age: an integer between 20 and 60; customer occupation: converting the occupation classification value conversion table into a value according to a pre-established occupation classification value conversion table; customer premises: converting the city into a numerical value according to a pre-established city conversion numerical value table; customer income: the numerical value type is normal without conversion; historical purchase products: and converting the product into a numerical value according to a pre-established product numerical value comparison table, and providing technical support for subsequent statistical analysis.
S13: and carrying out data cleaning on the sample data to be processed to obtain target sample data.
Wherein the data cleansing includes, but is not limited to outlier and missing value processing. Specifically, in order to improve the accuracy and efficiency of the subsequent statistical analysis, data cleaning is required to be performed on the sample data to be processed to eliminate interference factors and obtain the target sample data.
S14: and carrying out statistical analysis on the target sample data by adopting a machine learning algorithm to obtain a target exhibition function corresponding to the service type.
Specifically, different service types and corresponding recommended products are different, so that statistical analysis is required to be performed on target customer data corresponding to the different service types to obtain a target exhibition function corresponding to the service type, and the statistical analysis is performed on the target exhibition function in a targeted manner to improve the accuracy of analysis results. Among them, machine learning algorithms include, but are not limited to, decision tree algorithms, random forest algorithms, logistic regression algorithms, naive bayes, and k-nearest neighbor algorithms. In this embodiment, a multiple logistic regression algorithm is used to perform curve fitting on the target customer data, so as to obtain a target exhibition function corresponding to the service type. The multiple logistic regression algorithm is used to estimate the probability of something, or determine the probability that a sample belongs to a certain class.
Specifically, a model of multivariate logistic regression is defined as h θ(x)＝θ0+θ1x1+θ2x2+…+θnxn, where hθ (x) is a hypothetical function, θ is the vector of angles between the input values (i.e., the weight of each vector), and each x is a corresponding plurality of variable vector values. Constructing Cost Function, if the Cost Function is smaller, the fitting degree is better. The Cost Function expression is as follows: Where x (i) represents the ith element in vector x, y (i) represents the ith element in vector y, and as will be appreciated, x (i) corresponds to y (i), h θ(x(i)) represents a known hypothetical function, i.e., product identification of a known customer's historical purchased product, and m is the number of target customer data. Then, finding out the minimum value of the cost function according to the gradient descent method, firstly determining the step size of the next step, then giving an initial value theta 0,θ1 at will, determining a downward direction, descending a preset step, updating theta 0,θ1, and stopping descending when the descending height is smaller than a certain defined value. The specific formula of the gradient descent method is Alpha represents learning rate, and through continuous iteration, when the assumed function converges to a certain degree, the iterative computation is stopped, and the obtained theta j is the final function parameter so as to obtain the target exhibition function.
In this embodiment, a machine learning algorithm is used to perform statistical analysis on the client data, i.e., the original sample data, which is successfully sold, so that the classification result is more targeted, and the accuracy of the classification result is further improved, thereby improving the accuracy of information recommendation.
In one embodiment, as shown in fig. 7, in step S13, data cleaning is performed on sample data to be processed to obtain target sample data, which specifically includes the following steps:
s1311: and judging whether the sample data to be processed has a missing value or not.
S1312: and if the sample data to be processed does not have the missing value, taking the sample data to be processed as target sample data.
The missing value refers to that a part of attribute value is empty due to temporary unavailable part of information in the sample data to be processed, or part of information is lost due to some human factors or some attribute of a part of object is unavailable, such as a spouse name of an unmarrier, or information is missing due to the fact that the cost of acquiring part of information is too high, so that data are not acquired, and the like. In the sample data to be processed, the value corresponding to the age field is null, or the value corresponding to the phone number field is incomplete, the values corresponding to the age field and the phone number field are missing values. Specifically, the server judges each piece of obtained original sample data, and determines whether each piece of original sample data is complete and abnormal, i.e. whether a missing value exists.
S1313: if the sample data to be processed has a missing value, a missing field corresponding to the missing value is obtained.
Specifically, if the server side judges that the sample data to be processed does not have a missing value, that is, the data corresponding to each field in the sample data to be processed is complete data, the sample data to be processed is taken as target sample data. The sample data to be processed without the missing value is used as target sample data, so that the target sample data is complete data. The missing field refers to a field corresponding to a missing value in the sample data to be processed. Specifically, if the server side judges that the missing value exists in the sample data to be processed, the server side acquires the missing field corresponding to each missing value in the sample data to be processed, and determines whether interpolation processing is needed for the missing value or not through determining the missing field corresponding to the missing value.
S1314: and if the missing field is the necessary field corresponding to the service type, carrying out missing value processing on the missing value to obtain target sample data.
Wherein, the database stores the necessary field table corresponding to each service type. The necessary field table stores therein a field of data necessary for statistical analysis, and the necessary field is stored therein as a necessary field. Searching a necessary field table through a field corresponding to the missing value, and determining whether the field is a necessary field, namely determining whether the missing value corresponding to the field is data required by statistical analysis. If the missing field is the necessary field, performing interpolation processing on the missing value corresponding to the missing field to ensure the data quantity, namely the sample quantity.
Specifically, the missing value processing includes directly discarding the sample data to be processed if the missing value in the data is large; if the missing value in the sample data to be processed is smaller, the median is taken for filling. For example, if the missing value of the dimension factor (sex or age) of a certain object in the sample data to be processed is greater than a preset threshold value, directly discarding the data; if the missing value is not greater than the preset threshold, taking the median of all the to-be-processed sample data corresponding to the dimension factor for filling, for example, if the attribute value of the age dimension of a certain object (namely certain target client data) is missing, taking the median of the ages of all the objects corresponding to the age dimension in the to-be-processed sample data for filling.
In this embodiment, whether the missing value exists in the sample data to be processed is determined, so as to determine whether the true field is a necessary field corresponding to the service type according to the missing field corresponding to the missing value, and if the missing field is a necessary field corresponding to the service type, the missing value is processed on the missing value, so as to ensure the effectiveness of the missing value processing.
In one embodiment, as shown in fig. 8, in step S13, data cleaning is performed on sample data to be processed to obtain target sample data, which specifically includes the following steps:
s1321: and identifying whether the attribute value corresponding to each data dimension in the sample data to be processed is an abnormal value.
The outlier refers to an attribute value corresponding to any data dimension (such as age) in the sample data to be processed, which is outside the standard range (i.e. greater than the standard range or less than the standard range), and is an outlier.
S1322: and if the attribute value corresponding to the data dimension is an abnormal value, calculating quantiles based on the attribute value corresponding to the data dimension to obtain the replacement quantiles.
S1323: and replacing the attribute value corresponding to the data dimension with the replacement quantile to obtain the target sample data.
Specifically, the server firstly identifies whether the attribute value corresponding to each data dimension in the target sample data is an abnormal value, if so, quantile calculation is performed based on the attribute value corresponding to the data dimension to obtain a replacement quantile, so that the subsequent statistical analysis has certain fault tolerance. For example, the outlier (data excessively large or excessively small) processing method includes forcibly designating an attribute value of a certain variable (sex or age) of one sample (i.e., sample data to be processed) as a 99-quantile value if the attribute value of the variable is greater than the 99-quantile value of the variable; similarly, if the attribute value of a variable of a sample is less than 1 minute for that variable, then the attribute value of that variable is forcefully specified as1 minute. Wherein, the quantile (Quantile), also called quantile, refers to a numerical point which divides the probability distribution range of a random variable into several equal parts, and the common use is the median (i.e. the quantile), the quartile, the percentile and the like. The quantile is a variable value at each halving position after the whole data (namely, all attribute values of data dimensions corresponding to abnormal values in the sample data to be processed) are arranged in order from small to large.
In this embodiment, the server first identifies whether the attribute value corresponding to each data dimension in the target sample data is an outlier, and if so, performs quantile calculation based on the attribute value corresponding to the data dimension to obtain a replacement quantile, so that the subsequent statistical analysis has a certain fault tolerance.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
In an embodiment, an information recommendation device is provided, where the information recommendation device corresponds to the information recommendation method in the above embodiment one by one. As shown in fig. 9, the information recommending apparatus includes a data to be processed acquiring module 10, a target recommending function acquiring module 20, a data to be recommended acquiring module 30, a recommending task table generating module 40, and an information recommending module 50. The functional modules are described in detail as follows:
The pending data acquisition module 10 is configured to acquire target client data and service types in a preset period.
The objective recommendation function obtaining module 20 is configured to query the database based on the service type, and obtain an objective recommendation function corresponding to the service type.
And the data to be recommended acquisition module 30 is used for processing the target client data by adopting the target recommendation function to obtain data to be recommended corresponding to the target client data.
The recommended task table generating module 40 is configured to generate a recommended task table by allocating target client data, where each target client data and corresponding data to be recommended are stored in association with each other.
The information recommending module 50 is configured to recommend the data to be recommended to the client terminal corresponding to the target client data according to the recommending task table.
Specifically, the target client data includes a client location and a client level, each client level corresponding to a target number of clients; the recommended task table generating module comprises a target client data dividing unit, a first exhibition industry personnel group determining unit, a second exhibition industry personnel group determining unit, a to-be-serviced amount determining unit and a recommended task table generating unit.
The target client data dividing unit is used for dividing target client data based on the client location to obtain a group to be allocated, and the group to be allocated corresponds to the client location.
And the first exhibition industry personnel group determining unit is used for determining a first exhibition industry personnel group corresponding to the group to be allocated according to the inquiry canvasing personnel library of the customer location, wherein the first exhibition industry personnel group comprises a service grade corresponding to the first exhibition industry personnel, and the service grade corresponds to the customer grade.
The second exhibition staff group determining unit is used for dividing the first exhibition staff with the same service level as the client level into second exhibition staff groups corresponding to the client level; the second exhibition staff group comprises the maximum service amount corresponding to the second exhibition staff.
And the to-be-serviced amount determining unit is used for determining the to-be-serviced amount corresponding to the second exhibition staff based on the target customer number and the maximum service amount corresponding to the customer level.
And the recommended task list generation unit is used for randomly or sequentially selecting target client data from the to-be-allocated group based on the to-be-served amount and allocating the target client data to the second exhibition staff to generate a recommended task list.
Specifically, the recommended task list comprises an outbound communication identifier and a waiting communication identifier; the information recommendation module comprises an information push request receiving unit, a communication push unit, an information to be pushed obtaining unit, a target short-chain acquisition unit and a target push information generating unit.
The information push request receiving unit is used for receiving an information push request information recommendation request comprising an information push mode and a recommendation task list.
And the communication pushing unit is used for calling the communication module to carry out batch outbound based on the outbound communication identifier and the to-be-called communication identifier if the information pushing mode is the communication pushing mode, and receiving a communication feedback result sent by the communication module.
The information to be pushed acquisition unit is used for acquiring information to be pushed if the communication feedback result is communication failure, wherein the information to be pushed comprises an information frame and an original long link corresponding to the data to be recommended.
And the target short link acquisition unit is used for calling the link conversion interface to convert the original long link to obtain a target short link corresponding to the original long link.
The target push information generation unit is used for generating target push information based on the information frame and the target short link and sending the target push information to the client terminal corresponding to the waiting communication identifier.
Specifically, the information recommendation device further comprises an information push request receiving unit and a network push unit.
The information push request receiving unit is used for receiving an information recommendation request, wherein the information recommendation request comprises an information push mode and a recommendation task list.
And the network pushing unit is used for updating the interactive interface corresponding to the client terminal based on the data to be recommended if the information pushing mode is a network pushing mode so as to highlight the data to be recommended on a recommendation display module of the interactive interface.
Specifically, the information recommendation device further comprises a sample data acquisition unit, a sample data to be processed acquisition unit, a target client data acquisition unit and a target exhibition function acquisition unit.
The sample data acquisition unit is used for acquiring the service type and the corresponding original sample data.
The sample data to be processed is obtained by the sample data obtaining unit, which is used for encoding the original sample data according to a preset encoding rule to obtain the sample data to be processed which is expressed in a vector form.
The target client data acquisition unit is used for carrying out data cleaning on the sample data to be processed to acquire target client data.
And the target exhibition industry function acquisition unit is used for carrying out statistical analysis on the target client data by adopting a machine learning algorithm to acquire a target exhibition industry function corresponding to the service type.
Specifically, the target client data acquisition unit includes a missing value judgment subunit, a target client data acquisition subunit, a missing field acquisition subunit, and a target client data acquisition subunit.
And the missing value judging subunit is used for judging whether the sample data to be processed has missing values or not.
And the target client data acquisition subunit is used for taking the sample data to be processed as target client data if the sample data to be processed does not have a missing value.
The missing field obtaining subunit is configured to obtain a missing field corresponding to the missing value if the missing value exists in the sample data to be processed.
And the target client data acquisition subunit is used for carrying out missing value processing on the missing value if the missing field is a necessary field corresponding to the service type, and acquiring target client data.
Specifically, the target client data acquisition unit includes an outlier identification subunit, a replacement quantile acquisition subunit, and an attribute value replacement subunit.
And the abnormal value identification subunit is used for identifying whether the attribute value corresponding to each data dimension in the target client data is an abnormal value or not.
And the replacement quantile obtaining subunit is used for calculating quantiles based on the attribute values corresponding to the data dimension if the attribute values corresponding to the data dimension are abnormal values, so as to obtain the replacement quantiles.
And the attribute value replacing subunit is used for replacing the attribute value corresponding to the data dimension with a replacing quantile.
For specific limitations of the information recommendation device, reference may be made to the above limitation of the information recommendation method, and the description thereof will not be repeated here. The respective modules in the information recommendation apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 10. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a computer readable storage medium, an internal memory. The computer readable storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the computer readable storage media. The database of the computer device is used for storing data generated or acquired in the process of executing the information recommending method, such as data to be recommended. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an information recommendation method.
In one embodiment, a computer device is provided that includes a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing steps of the information recommendation method in the above embodiments when the computer program is executed, such as steps S10-S50 shown in fig. 2, or steps shown in fig. 3-8. Or the processor may implement the functions of each module/unit in this embodiment of the information recommendation device when executing the computer program, for example, the functions of each module/unit shown in fig. 9, which are not described herein again for avoiding repetition.
In an embodiment, a computer readable storage medium is provided, and a computer program is stored on the computer readable storage medium, and when the computer program is executed by a processor, the steps of the information recommendation method in the above embodiment, for example, steps S10-S50 shown in fig. 2, or steps shown in fig. 3-8, are implemented, and will not be repeated herein. Or the computer program when executed by the processor implements the functions of the modules/units in this embodiment of the information recommendation device, for example, the functions of the modules/units shown in fig. 9, which are not repeated here.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (9)
1. An information recommendation method, comprising:
Acquiring target client data and service types in a preset period, wherein the target client data comprises a client location and client grades, and each client grade corresponds to a target client number;
Inquiring a database based on the service type, and acquiring a target recommendation function corresponding to the service type;
processing the target client data by adopting the target recommendation function to obtain data to be recommended corresponding to the target client data;
Dividing the target client data based on the client location to obtain a group to be allocated; the group to be allocated corresponds to the location of the customer; inquiring canvasing a personnel library according to the location of the customer, and determining a first exhibition industry personnel group corresponding to the group to be distributed; the first exhibition staff group comprises service grades corresponding to the first exhibition staff, and the service grades correspond to the client grades; dividing the first canvasing persons with the service level being the same as the customer level into a second exhibition staff group corresponding to the customer level; the second exhibition staff group comprises the maximum service amount corresponding to the second exhibition staff; determining the to-be-serviced amount corresponding to the second exhibition staff based on the target customer number corresponding to the customer level and the maximum service amount; based on the to-be-served amount, randomly or sequentially selecting target client data from the to-be-allocated group, allocating the target client data to a second exhibition worker, and generating a recommended task table, wherein each target client data and corresponding to-be-recommended data are stored in an associated mode in the recommended task table;
And recommending the data to be recommended to the client terminal corresponding to the target client data according to the recommended task list.
2. The information recommendation method of claim 1, wherein the recommendation task table includes an outbound communication identifier and a pending communication identifier;
The recommending the data to be recommended to the client terminal corresponding to the target client data according to the recommending task list comprises the following steps:
receiving an information push request, wherein the information recommendation request comprises an information push mode and the recommendation task list;
If the information pushing mode is a communication pushing mode, calling a communication module to carry out batch outbound based on the outbound communication identifier and the to-be-called communication identifier, and receiving a communication feedback result sent by the communication module;
if the communication feedback result is communication failure, acquiring information to be pushed, wherein the information to be pushed comprises an information frame and an original long link corresponding to the data to be recommended;
A link conversion interface is called to convert the original long link to obtain a target short link corresponding to the original long link;
And generating target push information based on the information frame and the target short link, and sending the target push information to the client terminal corresponding to the waiting communication identifier.
3. The information recommendation method of claim 2, wherein after the receiving the information push request, the information recommendation method further comprises:
and if the information pushing mode is a network pushing mode, updating an interactive interface corresponding to the client terminal based on the data to be recommended so as to highlight the data to be recommended on a recommendation display module of the interactive interface.
4. The information recommendation method as claimed in claim 1, wherein prior to said acquiring the target customer data and the corresponding service type within a preset period, the information recommendation method further comprises:
acquiring a service type and corresponding original sample data;
coding the original sample data according to a preset coding rule to obtain sample data to be processed, wherein the sample data to be processed is expressed in a vector form;
Carrying out data cleaning on the sample data to be processed to obtain target customer data;
and carrying out statistical analysis on the target client data by adopting a machine learning algorithm to obtain a target exhibition function corresponding to the service type.
5. The information recommendation method of claim 4, wherein the performing data cleansing on the sample data to be processed to obtain target client data includes:
judging whether the sample data to be processed has a missing value or not;
if the sample data to be processed does not have a missing value, the sample data to be processed is used as target client data;
if the sample data to be processed has a missing value, acquiring a missing field corresponding to the missing value;
And if the missing field is the necessary field corresponding to the service type, carrying out missing value processing on the missing value to acquire the target client data.
6. The information recommendation method of claim 4, wherein the performing data cleansing on the sample data to be processed to obtain target client data includes:
identifying whether the attribute value corresponding to each data dimension in the target client data is an abnormal value;
If the attribute value corresponding to the data dimension is an abnormal value, quantile calculation is carried out based on the attribute value corresponding to the data dimension, and a replacement quantile is obtained;
and replacing the attribute value corresponding to the data dimension with the replacement quantile.
7. An information recommendation device, characterized by comprising:
The system comprises a to-be-processed data acquisition module, a service processing module and a service processing module, wherein the to-be-processed data acquisition module is used for acquiring target client data and service types in a preset period, the target client data comprise client locations and client grades, and each client grade corresponds to a target client number;
The target recommendation function acquisition module is used for inquiring a database based on the service type and acquiring a target recommendation function corresponding to the service type;
The data to be recommended acquisition module is used for processing the target client data by adopting the target recommendation function to obtain data to be recommended corresponding to the target client data;
The recommended task table generation module is used for dividing the target client data based on the client location to obtain a group to be allocated; the group to be allocated corresponds to the location of the customer; inquiring canvasing a personnel library according to the location of the customer, and determining a first exhibition industry personnel group corresponding to the group to be distributed; the first exhibition staff group comprises service grades corresponding to the first exhibition staff, and the service grades correspond to the client grades; dividing the first canvasing persons with the service level being the same as the customer level into a second exhibition staff group corresponding to the customer level; the second exhibition staff group comprises the maximum service amount corresponding to the second exhibition staff; determining the to-be-serviced amount corresponding to the second exhibition staff based on the target customer number corresponding to the customer level and the maximum service amount; based on the to-be-served amount, randomly or sequentially selecting target client data from the to-be-allocated group to be allocated to a second exhibition worker, and generating the recommended task table, wherein each target client data and corresponding to-be-recommended data are stored in an associated mode in the recommended task table;
And the information recommending module is used for recommending the data to be recommended to the client terminal corresponding to the target client data according to the recommending task list.
8. Computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the information recommendation method according to any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the information recommendation method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910842181.5A CN110765169B (en) | 2019-09-06 | 2019-09-06 | Information recommendation method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910842181.5A CN110765169B (en) | 2019-09-06 | 2019-09-06 | Information recommendation method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110765169A CN110765169A (en) | 2020-02-07 |
| CN110765169B true CN110765169B (en) | 2024-07-12 |
Family
ID=69330776
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910842181.5A Active CN110765169B (en) | 2019-09-06 | 2019-09-06 | Information recommendation method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110765169B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112017775A (en) * | 2020-09-09 | 2020-12-01 | 平安科技（深圳）有限公司 | Information recommendation method and device, computer equipment and storage medium |
| CN112307028B (en) * | 2020-10-31 | 2021-11-12 | 海南大学 | Cross-data information knowledge modal differential content recommendation method oriented to essential computation |
| CN112561588B (en) * | 2020-12-18 | 2024-08-09 | 中国农业银行股份有限公司 | Product recommendation method and device |
| CN112637206B (en) * | 2020-12-23 | 2022-08-26 | 光大兴陇信托有限责任公司 | Method and system for actively acquiring service data |
| CN113095945A (en) * | 2021-04-22 | 2021-07-09 | 北京十一贝科技有限公司 | Method and device for determining role of target insurance business |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109064268A (en) * | 2018-07-20 | 2018-12-21 | 中国建设银行股份有限公司 | Business recommended method, apparatus, server-side and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102693498A (en) * | 2012-05-16 | 2012-09-26 | 上海卓达信息技术有限公司 | Accurate recommendation method based on incomplete data |
| CN104951534B (en) * | 2015-06-18 | 2019-07-23 | 百度在线网络技术（北京）有限公司 | Search result optimization method and search engine |
-
2019
- 2019-09-06 CN CN201910842181.5A patent/CN110765169B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109064268A (en) * | 2018-07-20 | 2018-12-21 | 中国建设银行股份有限公司 | Business recommended method, apparatus, server-side and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110765169A (en) | 2020-02-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110765169B (en) | Information recommendation method, device, computer equipment and storage medium | |
| CN109344183B (en) | Data interaction method and device, computer equipment and storage medium | |
| US20220239574A1 (en) | Systems and methods for social graph data analytics to determine connectivity within a community | |
| CN108874968B (en) | Risk management data processing method and device, computer equipment and storage medium | |
| CN115526363A (en) | Business data processing method and device, computer equipment and storage medium | |
| CN110163655B (en) | Agent distribution method, device and equipment based on gradient lifting tree and storage medium | |
| CN109658126B (en) | Data processing method, device, equipment and storage medium based on product popularization | |
| CN107679740A (en) | Business personnel's screening and activating method, electronic installation and computer-readable recording medium | |
| WO2019062000A1 (en) | Incoming call assignment method for attendants, electronic device and computer readable storage medium | |
| CN113225437B (en) | Telephone calling-out method, calling-out device, electronic equipment and storage medium | |
| CN108513020A (en) | A kind of incoming call distribution method, electronic device and computer readable storage medium | |
| CN109492856B (en) | Service request processing method, device, computer equipment and storage medium | |
| CN110083634B (en) | Order processing method, device, equipment and storage medium based on data analysis | |
| CN114244961A (en) | Robot intelligent outbound method and device, computer equipment and storage medium | |
| CN115169906A (en) | Customer service distribution method and device, computer equipment and storage medium | |
| CN112734352A (en) | Document auditing method and device based on data dimensionality | |
| CN113221005A (en) | Customer service pushing method, server and related products | |
| CN110097250B (en) | Product risk prediction method, device, computer equipment and storage medium | |
| CN113553500B (en) | Merchant information recommendation method and device, electronic equipment and storage medium | |
| CN112363831B (en) | Wind control processing method and device, computer equipment and storage medium | |
| US20220318819A1 (en) | Risk clustering and segmentation | |
| CN114090873A (en) | Method, device, equipment and computer readable medium for matching data | |
| CN112163868A (en) | Data processing method, device, equipment and storage medium | |
| CN116562902B (en) | Shop sales strategy recommendation method and device, equipment, medium and product thereof | |
| CN115760287A (en) | Seat recommendation method, device, equipment and storage medium |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240612 Address after: Room 505, 5th Floor, Building 24, Taihu North Lane, Tongzhou District, Beijing, 101149 Applicant after: Jinshanghua (Beijing) Technology Co.,Ltd. Country or region after: China Address before: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Applicant before: PING AN PUHUI ENTERPRISE MANAGEMENT Co.,Ltd. Country or region before: China |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |