CN115330487A - Product recommendation method and device, computer equipment and storage medium - Google Patents
Product recommendation method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN115330487A CN115330487A CN202210987661.2A CN202210987661A CN115330487A CN 115330487 A CN115330487 A CN 115330487A CN 202210987661 A CN202210987661 A CN 202210987661A CN 115330487 A CN115330487 A CN 115330487A
- Authority
- CN
- China
- Prior art keywords
- product recommendation
- leaf node
- decision tree
- user information
- branch
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Abstract
The application discloses a product recommendation method, which is applied to the field of intelligent recommendation. The method provided by the application comprises the following steps: acquiring a user information label generated according to user information in a target system and an intelligent recommendation model in the target system; generating a target product recommendation decision tree by using the user information label and the intelligent recommendation model, wherein the target product recommendation decision tree comprises user information type leaf nodes and intelligent recommendation model type leaf nodes; adding a product recommendation screening condition to each user information type leaf node; obtaining a decision tree branch product recommendation result according to the user information type leaf node and the intelligent recommendation model type leaf node on each branch; and adding the decision tree branch product recommendation results to a product recommendation set, and sequencing the decision tree branch product recommendation results in the product recommendation set to obtain target product recommendation results.
Description
Technical Field
The present application relates to the field of intelligent recommendation, and in particular, to a method and an apparatus for recommending a product, a computer device, and a storage medium.
Background
In the existing product recommendation method, generally, a recommendation screening rule is generated according to data attributes in the system, which have an association relationship with a product, to obtain a product recommendation result, or an intelligent recommendation model is constructed and trained by using data in the system, which have an association relationship with a product. Meanwhile, association relations cannot be established between different recommendation screening rules and different intelligent recommendation models, and product recommendation results are screened through the association relations.
Disclosure of Invention
The embodiment of the application provides a product recommendation method, a product recommendation device, computer equipment and a storage medium, and aims to solve the problem that an association relation between a recommendation screening rule and an intelligent recommendation model cannot be established for product recommendation in the existing product recommendation technology.
In a first aspect of the present application, a product recommendation method is provided, including:
acquiring a user information label generated according to user information in a target system and an intelligent recommendation model in the target system;
generating a target product recommendation decision tree by using the user information label and the intelligent recommendation model according to a preset product recommendation strategy, wherein the target product recommendation decision tree comprises user information type leaf nodes and intelligent recommendation model type leaf nodes;
adding a product recommendation screening condition to each user information type leaf node;
obtaining the user information type leaf node and the intelligent recommendation model type leaf node of each branch on the target product recommendation decision tree, and obtaining a decision tree branch product recommendation result according to the user information type leaf node and the intelligent recommendation model type leaf node on each branch;
and adding the decision tree branch product recommendation results to a product recommendation set, and sequencing the decision tree branch product recommendation results in the product recommendation set according to the preset recommendation result priority to obtain target product recommendation results.
In a second aspect of the present application, there is provided a product recommendation device including:
the data acquisition module is used for acquiring a user information label generated according to user information in a target system and an intelligent recommendation model in the target system;
the decision tree generation module is used for generating a target product recommendation decision tree by using the user information labels and the intelligent recommendation model according to a preset product recommendation strategy, wherein the target product recommendation decision tree comprises user information type leaf nodes and intelligent recommendation model type leaf nodes;
the screening condition module is used for adding a product recommendation screening condition to each user information type leaf node;
the decision operation module is used for acquiring the user information type leaf node and the intelligent recommendation model type leaf node of each branch of the target product recommendation decision tree and acquiring a decision tree branch product recommendation result according to the user information type leaf node and the intelligent recommendation model type leaf node on each branch;
and the set sorting module is used for adding the decision tree branch product recommendation results to a product recommendation set, and sorting the decision tree branch product recommendation results in the product recommendation set according to the preset recommendation result priority to obtain target product recommendation results.
In a third aspect of the present application, a computer device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the above product recommendation method when executing the computer program.
In a fourth aspect of the present application, a computer-readable storage medium is provided, which stores a computer program, and the computer program realizes the steps of the above product recommendation method when executed by a processor.
According to the product recommendation method, the product recommendation device, the computer equipment and the storage medium, the user information label generated according to the user information in the target system and the intelligent recommendation model in the target system are obtained; generating a target product recommendation decision tree by using the user information label and the intelligent recommendation model, wherein the target product recommendation decision tree comprises user information type leaf nodes and intelligent recommendation model type leaf nodes; adding a product recommendation screening condition to each user information type leaf node; and obtaining a decision tree branch product recommendation result according to the user information type leaf node and the intelligent recommendation model type leaf node on each branch, and sequencing the decision tree branch product recommendation results to obtain a target product recommendation result. The method not only establishes the incidence relation between the product screening rule and the intelligent recommendation model, but also obtains different types of product recommendation results through all branches of the target product recommendation decision tree.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the description of the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the description below are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings may be obtained according to these drawings without inventive labor.
FIG. 1 is a schematic diagram of an application environment of a product recommendation method according to an embodiment of the present application;
FIG. 2 is a flowchart of a product recommendation method according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a product recommendation device according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a computer device according to an embodiment of the present application.
Detailed Description
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 some, but not all, embodiments of the present application. 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.
The product recommendation method provided by the application can be applied to an application environment shown in fig. 1, where the computer device may be, but is not limited to, various personal computers and notebook computers, the computer device may also be a server, and the server may be an independent server, or a cloud server that provides basic cloud computing services such as cloud service, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, content Delivery Network (CDN), and big data and artificial intelligence platform. It will be appreciated that the number of computer devices in figure 1 is merely illustrative and any number of extensions may be made according to actual requirements.
In an embodiment, as shown in fig. 2, a product recommendation method is provided, which is described by taking the computer device in fig. 1 as an example, and includes the following steps S101 to S105:
s101, obtaining a user information label generated according to user information in a target system and an intelligent recommendation model in the target system.
The user information tag is generated according to user information contained in the target system, for example, user information such as user gender, user age, user location area and the like acquired from the target system, and a corresponding product recommendation result can be obtained by screening according to requirements of a part of products on the user information, for example, a male user with a certain product having a purchase requirement below 60 years old. The intelligent recommendation model is constructed and trained in the target system, and can be directly used for recommending products, and product recommendation results can be obtained according to the intelligent recommendation model, for example, product recommendation results with product purchase intention scores larger than preset purchase intention scores can be obtained according to a high intention model.
Further, a product information tag generated according to product information in the target system is acquired, and the product information tag is used for generating a product recommendation result, for example, an insurance product whose product guarantee range is fire insurance is acquired as the product recommendation result in a season in which a fire event is high. It should be specially noted that the user information tag and the product information tag may be other types of information tags that can be obtained in the target system in the present application, and the information tag may have an association relationship with a product in the product recommendation result, and the application of the user information tag in this embodiment is only a specific implementation manner of many information tags.
S102, according to a preset product recommendation strategy, generating a target product recommendation decision tree by using the user information labels and the intelligent recommendation model, wherein the target product recommendation decision tree comprises user information type leaf nodes and intelligent recommendation model type leaf nodes.
Further, after the generating a target product recommendation decision tree using the user information tag and the intelligent recommendation model according to a preset product recommendation policy, the method further includes: and graphically displaying the target product recommendation decision tree by using a preset graphic library tool, and receiving leaf node sequence adjustment operation input by a user on a graphical display interface. The target product recommendation decision tree is displayed by using a preset graphic library tool, so that the generation process of the product recommendation result can be displayed more intuitively and clearly, and the efficiency of adjusting the target product decision tree is further improved.
Further, after the generating a target product recommendation decision tree using the user information tag and the intelligent recommendation model according to a preset product recommendation strategy, the method further includes: firstly, acquiring a fifth leaf node of which the types of all leaf nodes on each branch of the target product recommendation decision tree are the leaf nodes of the intelligent recommendation model type, and acquiring a fifth leaf node set. Then, clustering is performed on a fifth leaf node in the fifth set of leaf nodes. And finally, if the clustering result is successfully obtained, marking the fifth leaf node and the branch where the fifth leaf node is located by using a preset fifth graph display strategy on the target product recommendation decision tree which is displayed graphically.
Further, marking the fifth leaf node and the branch where the fifth leaf node is located on the graphically displayed target product recommendation decision tree by using a preset fifth graphical display strategy further includes: first, a first number of branches containing the fifth leaf node is obtained. Then, when the first number is equal to 1, if there is a child node in the fifth leaf node, removing the fifth leaf node from the target product recommendation decision tree, and taking the child node of the fifth leaf node as a new child node of the parent node of the fifth leaf node, if there is no child node in the fifth leaf node, removing the fifth leaf node from the target product recommendation decision tree.
S103, adding a product recommendation screening condition to each user information type leaf node.
If a branch of the target product recommendation decision tree has a user information tag with the same user information, corresponding graphical marking needs to be performed on the branch where the user information tag with the same user information exists to remind a user, so as to avoid that a product recommendation result cannot be obtained according to the branch where the user information tag with the same user information exists, for example, a first user information tag and a second user information tag, where the user information is the user gender, exist on a first branch of the target product recommendation decision tree at the same time, the screening condition of the first user information tag is that the user gender is required to be male, the screening condition of the second user information tag is that the user gender is required to be female, the screening conditions of the first user information tag and the second user information tag conflict with each other, and a corresponding product recommendation result cannot be obtained according to a leaf node on the first branch. The first user information tag and the second user information tag exemplify leaf nodes of which the user information is a category attribute, and the judgment condition of the leaf nodes of which the user information type is a numerical attribute is that no intersection exists in a numerical screening range, for example, if the screening condition of the third user information tag on the second branch of the target product recommendation decision tree is that the user age is less than 18 years old, and the screening condition of the fourth user information tag on the second branch is that the user age is greater than 60 years old, a corresponding product recommendation result cannot be obtained according to the second branch.
Specifically, the adding of the product recommendation filtering condition to each leaf node of the user information type further includes: first, a first leaf node of which the types of all leaf nodes on each branch of the target product recommendation decision tree are the user information type leaf nodes is obtained, and a first leaf node set is obtained. And then, acquiring a second leaf node of which the data type of the user information corresponding to the first leaf node in the first leaf node set is a category attribute, and acquiring a second leaf node set. And finally, clustering second leaf nodes in the second leaf node set according to the user information. And if the clustering result of the second leaf node is successfully obtained, judging whether the screening conditions of the second leaf node in each cluster are the same. And if the screening conditions of the second leaf nodes are the same, marking branches corresponding to the second leaf nodes and the second leaf nodes on the target product recommendation decision tree displayed in the graphical mode by using a preset first graph display strategy. And if the screening conditions of the second leaf nodes are different, marking the corresponding second leaf nodes and the branches where the second leaf nodes are located by using a preset second graph display strategy on the target product recommendation decision tree which is displayed graphically.
Specifically, the adding of the product recommendation filtering condition to each leaf node of the user information type further includes: firstly, obtaining a third leaf node with the types of all leaf nodes on each branch of the target product recommendation decision tree as the user information type leaf nodes, and obtaining a third leaf node set. And then, acquiring a fourth leaf node of which the data type of the user information corresponding to the third leaf node in the third leaf node set is a numerical attribute, and acquiring a fourth leaf node set. And finally, clustering fourth leaf nodes in the fourth leaf node set according to user information. If the clustering result of the fourth leaf node is successfully obtained, judging whether the numerical value screening range of the fourth leaf node in each cluster of the clustering result has an intersection part. If the numerical value screening range of the fourth leaf node has an intersection part, marking the fourth leaf node and a branch where the fourth leaf node is located by using a preset third graph display strategy on the target product recommendation decision tree in the graph display. If the numerical value screening range of the fourth leaf node does not have an intersection part, marking the fourth leaf node and a branch where the fourth leaf node is located by using a preset fourth graph display strategy on the target product recommendation decision tree in the graphical display.
The method and the device have the advantages that the different leaf nodes corresponding to the same user information in the branches of the target product recommendation decision tree are graphically distinguished, so that the user can be helped to further reduce the branch length of the target product recommendation decision tree, and the efficiency of obtaining a product recommendation result through the target product recommendation decision tree can be improved.
S104, obtaining the user information type leaf node and the intelligent recommendation model type leaf node of each branch in the target product recommendation decision tree, and obtaining a decision tree branch product recommendation result according to the user information type leaf node and the intelligent recommendation model type leaf node of each branch.
If a first branch first-level leaf node of the target product recommendation decision tree is a leaf node of the user information type, the first branch first-level leaf node comprises a product recommendation screening condition, a first branch first-level leaf node product recommendation result can be obtained according to the product screening condition, the first branch first-level leaf node product recommendation result is input into a child node (a first branch second-level leaf node) of the first branch first-level leaf node, the first branch second-level leaf node can be a leaf node of the user information type or a leaf node of the intelligent recommendation model type, the first branch second-level leaf node outputs a first branch second-level leaf node product recommendation result, and so on, the last-level leaf node of the first branch outputs a final first branch product recommendation result of the first branch. If the first-level leaf node of the first branch is a leaf node of an intelligent recommendation model type, the execution steps for obtaining the recommendation result of the first branch product are similar to the above steps, and are not described herein again. Further, the execution steps of the other branches of the target product recommendation decision tree for outputting the decision tree branch product recommendation results are similar, and therefore are not described herein again.
Further, if the decision tree branch product recommendation result corresponding to one branch in the target product recommendation decision tree is an empty set, marking the branch with the decision tree branch product recommendation result as an empty set by using a preset fifth graphic display strategy on the graphically displayed target product recommendation decision tree. And highlighting the branch of the empty set of the product recommendation result in the target product recommendation decision tree, so that the user is prompted to construct a simpler and more efficient product recommendation decision tree, and the consumption of system resources can be reduced after the user removes the branch of the empty set of the product recommendation result in the target product recommendation decision tree.
S105, adding the decision tree branch product recommendation results to a product recommendation set, and sequencing the decision tree branch product recommendation results in the product recommendation set according to a preset recommendation result priority to obtain target product recommendation results.
Further, the target product recommendation result is displayed by using the preset graphic library tool, and the adjustment operation of the user on the target product recommendation result on a graphic display interface is received. The adjustment operation on the target product recommendation result includes but is not limited to: adding new products to the target product recommendation result, removing products in the target product recommendation result, and modifying the ranking of the products in the target product recommendation result. The target product recommendation result is displayed by using the preset graphic library tool, so that the target product recommendation result is displayed more visually, and the adjustment operation of the target product recommendation result on the graphic display interface by the receiving user is more efficient.
And further, monitoring profit data of the products in the target product recommendation result, and optimizing the structure of the target product recommendation decision tree according to the profit data. Specifically, profit data of products in the target product recommendation result is obtained, and products with the profit lower than the preset minimum profit are screened out according to the profit data. And then, obtaining the decision tree branch product recommendation result corresponding to the product with the unqualified profit and the unqualified decision tree branch corresponding to the decision tree branch product recommendation result. And finally, marking the branch of the non-standard decision tree and the profit data of the recommended product corresponding to the branch of the non-standard decision tree by using a preset sixth graphic display strategy on the target product recommendation decision tree displayed graphically. The profit data also comprises time units, and because the product also has time periodicity and other factors, the profit data is considered, and meanwhile, the running time of the target product recommendation decision tree is displayed on the graphically displayed target product recommendation decision tree, so that a user can more intuitively obtain the profit data obtained by the target product recommendation decision tree in the past graphical display time period.
According to the product recommendation method, a user information label generated according to user information in a target system and an intelligent recommendation model in the target system are obtained; generating a target product recommendation decision tree by using the user information label and the intelligent recommendation model, wherein the target product recommendation decision tree comprises user information type leaf nodes and intelligent recommendation model type leaf nodes; adding a product recommendation screening condition to each user information type leaf node; and obtaining a decision tree branch product recommendation result according to the user information type leaf node and the intelligent recommendation model type leaf node on each branch, and sequencing the decision tree branch product recommendation results to obtain a target product recommendation result. The association relation between the product screening rule and the intelligent recommendation model is established, and different types of product recommendation results are obtained simultaneously through all branches of the target product recommendation decision tree. Meanwhile, the same nodes on the target product recommendation decision tree are identified and graphically marked, so that a user can timely find out the logic problem of the recommendation screening rule of the target product recommendation decision tree.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
In an embodiment, a product recommendation device 100 is provided, and the product recommendation device 100 is in one-to-one correspondence with the product recommendation method in the above embodiment. As shown in fig. 3, the product recommendation apparatus 100 includes a data acquisition module 11, a decision tree generation module 12, a screening condition module 13, a decision execution module 14, and a set sorting module 15. The detailed description of each functional module is as follows:
the data acquisition module 11 is configured to acquire a user information tag generated according to user information in a target system and an intelligent recommendation model in the target system;
the decision tree generation module 12 is configured to generate a target product recommendation decision tree according to a preset product recommendation policy by using the user information tag and the intelligent recommendation model, where the target product recommendation decision tree includes user information type leaf nodes and intelligent recommendation model type leaf nodes;
a screening condition module 13, configured to add a product recommendation screening condition to each user information type leaf node;
a decision operation module 14, configured to obtain the user information type leaf node and the intelligent recommendation model type leaf node of each branch in the target product recommendation decision tree, and obtain a decision tree branch product recommendation result according to the user information type leaf node and the intelligent recommendation model type leaf node on each branch;
and the set sorting module 15 is configured to add the decision tree branch product recommendation result to a product recommendation set, and sort the decision tree branch product recommendation results in the product recommendation set according to a preset recommendation result priority to obtain a target product recommendation result.
Further, the decision tree generation module 12 further includes:
and the graphical submodule is used for graphically displaying the target product recommendation decision tree by using a preset graphical library tool and receiving leaf node sequence adjustment operation input by a user on a graphical display interface.
Further, the screening condition module 13 further includes:
the first leaf node submodule is used for acquiring first leaf nodes of which the types of all leaf nodes on each branch of the target product recommendation decision tree are the user information type leaf nodes to obtain a first leaf node set;
the second leaf node submodule is used for acquiring a second leaf node of which the data type of the user information corresponding to the first leaf node in the first leaf node set is a category attribute to obtain a second leaf node set;
the second leaf node clustering submodule is used for clustering second leaf nodes in the second leaf node set according to user information;
the first judgment submodule is used for judging whether the screening conditions of the second leaf nodes in each cluster are the same or not if the clustering result is successfully obtained;
the first graph marking submodule is used for marking branches corresponding to the second leaf node and the second leaf node on the target product recommendation decision tree in the graphical display by using a preset first graph display strategy if the branches are the same;
and the second graph marking sub-module is used for marking the corresponding second leaf node and the branch where the second leaf node is located by using a preset second graph display strategy on the target product recommendation decision tree which is displayed graphically if the target product recommendation decision tree is different from the target product recommendation decision tree.
Further, the screening condition module 13 further includes:
the third leaf node submodule is used for acquiring a third leaf node of which the types of all leaf nodes on each branch of the target product recommendation decision tree are the user information type leaf nodes to obtain a third leaf node set;
the fourth leaf node submodule is used for acquiring a fourth leaf node of which the data type of the user information corresponding to the third leaf node in the third leaf node set is a numerical attribute to obtain a fourth leaf node set;
the fourth leaf node clustering submodule is used for clustering fourth leaf nodes in the fourth leaf node set according to user information;
the second judging submodule is used for judging whether an intersection part exists in the numerical value screening range of the fourth leaf node in each cluster if the clustering result is successfully obtained;
a third graph marking sub-module, configured to mark, if the fourth leaf node exists, the fourth leaf node and a branch where the fourth leaf node is located on the target product recommendation decision tree that is graphically displayed by using a preset third graph display policy;
and the fourth graph marking submodule is used for marking the fourth leaf node and the branch where the fourth leaf node is located by using a preset fourth graph display strategy on the target product recommendation decision tree which is displayed graphically if the fourth graph marking submodule does not exist.
Further, the decision tree generating module 12 further includes:
a fifth leaf node submodule, configured to obtain a fifth leaf node in which the types of all leaf nodes on each branch of the target product recommendation decision tree are the intelligent recommendation model type leaf nodes, and obtain a fifth leaf node set;
a fifth leaf node clustering sub-module, configured to cluster fifth leaf nodes in the fifth leaf node set;
and the fifth graph marking sub-module is used for marking the fifth leaf node and the branch where the fifth leaf node is located by using a preset fifth graph display strategy on the target product recommendation decision tree which is displayed graphically if the clustering result is obtained successfully.
Further, the fifth graphic labeling sub-module further includes:
a first number subunit configured to obtain a first number of branches including the fifth leaf node;
a leaf node optimization sub-unit, configured to, when the first number is equal to 1, remove the fifth leaf node from the target product recommendation decision tree if the fifth leaf node has a child node, and use the child node of the fifth leaf node as a new child node of a parent node of the fifth leaf node, and remove the fifth leaf node from the target product recommendation decision tree if the fifth leaf node has no child node.
The meaning of "first" and "second" in the above modules/units is only to distinguish different modules/units, and is not used to define which module/unit has higher priority or other defining meanings. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or modules is not necessarily limited to those steps or modules explicitly listed, but may include other steps or modules not explicitly listed or inherent to such process, method, article, or apparatus, and such that a division of modules presented in this application is merely a logical division and may be implemented in a practical application in a further manner.
For specific limitations of the product recommendation device, reference may be made to the above limitations of the product recommendation method, which are not described herein again. The modules in the product recommending device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure thereof may be as shown in fig. 4. 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 comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing data involved in the product recommendation method. 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 a product recommendation method.
In one embodiment, a computer device is provided, which includes a memory, a processor and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the steps of the product recommendation method in the above embodiments are implemented, such as the steps S101 to S105 shown in fig. 2 and other extensions of the method and related steps. Alternatively, the processor, when executing the computer program, implements the functions of the modules/units of the product recommendation device in the above-described embodiments, such as the functions of the modules 11 to 15 shown in fig. 3. To avoid repetition, further description is omitted here.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like which is the control center for the computer device and which connects the various parts of the overall computer device using various interfaces and lines.
The memory may be used to store the computer programs and/or modules, and the processor may implement various functions of the computer apparatus by executing or executing the computer programs and/or modules stored in the memory and calling data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, video data, etc.) created according to the use of the cellular phone, etc.
The memory may be integrated in the processor or may be provided separately from the processor.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements the steps of the product recommendation method in the above-described embodiments, such as the steps S101 to S105 shown in fig. 2 and extensions of other extensions and related steps of the method. Alternatively, the computer program, when executed by the processor, implements the functions of the modules/units of the product recommendation device in the above-described embodiments, such as the functions of the modules 11 to 15 shown in fig. 3. To avoid repetition, further description is omitted here.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include non-volatile and/or volatile memory. Non-volatile 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 DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (10)
1. A method for recommending products, comprising:
acquiring a user information label generated according to user information in a target system and an intelligent recommendation model in the target system;
generating a target product recommendation decision tree by using the user information label and the intelligent recommendation model according to a preset product recommendation strategy, wherein the target product recommendation decision tree comprises user information type leaf nodes and intelligent recommendation model type leaf nodes;
adding a product recommendation screening condition to each user information type leaf node;
obtaining the user information type leaf node and the intelligent recommendation model type leaf node of each branch on the target product recommendation decision tree, and obtaining a decision tree branch product recommendation result according to the user information type leaf node and the intelligent recommendation model type leaf node on each branch;
and adding the decision tree branch product recommendation results to a product recommendation set, and sequencing the decision tree branch product recommendation results in the product recommendation set according to a preset recommendation result priority to obtain target product recommendation results.
2. The product recommendation method according to claim 1, wherein the generating a target product recommendation decision tree using the user information tag and the intelligent recommendation model according to a preset product recommendation policy further comprises:
and graphically displaying the target product recommendation decision tree by using a preset graphic library tool, and receiving leaf node sequence adjustment operation input by a user on a graphical display interface.
3. The product recommendation method of claim 2, wherein adding a product recommendation filtering condition to each of the user information type leaf nodes further comprises:
acquiring a first leaf node of which the types of all leaf nodes on each branch of the target product recommendation decision tree are the user information type leaf nodes to obtain a first leaf node set;
acquiring a second leaf node of which the data type of the user information corresponding to the first leaf node in the first leaf node set is a category attribute to obtain a second leaf node set;
clustering second leaf nodes in the second leaf node set according to user information;
if the clustering result is successfully obtained, judging whether the screening conditions of the second leaf nodes in each cluster are the same;
if the two leaf nodes are the same, marking branches corresponding to the second leaf node and the second leaf node on the target product recommendation decision tree subjected to graphical display by using a preset first graphical display strategy;
and if the target product recommendation decision tree is different from the first leaf node, marking the corresponding second leaf node and the branch where the second leaf node is located by using a preset second graph display strategy on the target product recommendation decision tree subjected to graphical display.
4. The product recommendation method of claim 2, wherein adding a product recommendation filtering condition to each of the user information type leaf nodes further comprises:
obtaining a third leaf node with the types of all leaf nodes on each branch of the target product recommendation decision tree as the user information type leaf nodes, and obtaining a third leaf node set;
acquiring a fourth leaf node of which the data type of the user information corresponding to the third leaf node in the third leaf node set is a numerical attribute, and acquiring a fourth leaf node set;
clustering fourth leaf nodes in the fourth leaf node set according to user information;
if the clustering result is successfully obtained, judging whether an intersection part exists in the numerical value screening range of the fourth leaf node in each cluster;
if yes, marking the fourth leaf node and a branch where the fourth leaf node is located by using a preset third graph display strategy on the target product recommendation decision tree subjected to graphical display;
if the target product recommendation decision tree does not exist, marking the fourth leaf node and the branch where the fourth leaf node is located by using a preset fourth graph display strategy on the target product recommendation decision tree displayed graphically.
5. The product recommendation method according to claim 2, wherein the generating a target product recommendation decision tree using the user information tag and the intelligent recommendation model according to a preset product recommendation policy further comprises:
acquiring a fifth leaf node of which the types of all leaf nodes on each branch of the target product recommendation decision tree are the intelligent recommendation model type leaf nodes to obtain a fifth leaf node set;
clustering fifth leaf nodes in the fifth leaf node set;
and if the clustering result is successfully obtained, labeling the fifth leaf node and the branch where the fifth leaf node is located by using a preset fifth graph display strategy on the target product recommendation decision tree subjected to graphical display.
6. The product recommendation method according to claim 5, wherein the marking the fifth leaf node and the branch where the fifth leaf node is located on the graphically displayed target product recommendation decision tree by using a preset fifth graphical display strategy further comprises:
obtaining a first number of branches comprising the fifth leaf node;
when the first number is equal to 1, if the fifth leaf node has a child node, removing the fifth leaf node from the target product recommendation decision tree, and taking the child node of the fifth leaf node as a new child node of the parent node of the fifth leaf node, if the fifth leaf node has no child node, removing the fifth leaf node from the target product recommendation decision tree.
7. A product recommendation device, comprising:
the data acquisition module is used for acquiring a user information label generated according to user information in a target system and an intelligent recommendation model in the target system;
the decision tree generation module is used for generating a target product recommendation decision tree by using the user information labels and the intelligent recommendation model according to a preset product recommendation strategy, wherein the target product recommendation decision tree comprises user information type leaf nodes and intelligent recommendation model type leaf nodes;
the screening condition module is used for adding a product recommendation screening condition to each user information type leaf node;
the decision operation module is used for acquiring the user information type leaf node and the intelligent recommendation model type leaf node of each branch in the target product recommendation decision tree and acquiring a decision tree branch product recommendation result according to the user information type leaf node and the intelligent recommendation model type leaf node of each branch;
and the set sorting module is used for adding the decision tree branch product recommendation results to a product recommendation set, and sorting the decision tree branch product recommendation results in the product recommendation set according to the preset recommendation result priority to obtain target product recommendation results.
8. The product recommendation device of claim 7, wherein the decision tree generation module further comprises:
and the graphical submodule is used for graphically displaying the target product recommendation decision tree by using a preset graphical library tool and receiving leaf node sequence adjustment operation input by a user on a graphical display interface.
9. A 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 product recommendation method according to any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the product recommendation method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210987661.2A CN115330487A (en) | 2022-08-17 | 2022-08-17 | Product recommendation method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210987661.2A CN115330487A (en) | 2022-08-17 | 2022-08-17 | Product recommendation method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115330487A true CN115330487A (en) | 2022-11-11 |
Family
ID=83923074
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210987661.2A Pending CN115330487A (en) | 2022-08-17 | 2022-08-17 | Product recommendation method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115330487A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117093781A (en) * | 2023-10-19 | 2023-11-21 | 北京小糖科技有限责任公司 | Recommendation system-oriented sorting and scattering method and device, electronic equipment and medium |
-
2022
- 2022-08-17 CN CN202210987661.2A patent/CN115330487A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117093781A (en) * | 2023-10-19 | 2023-11-21 | 北京小糖科技有限责任公司 | Recommendation system-oriented sorting and scattering method and device, electronic equipment and medium |
| CN117093781B (en) * | 2023-10-19 | 2024-01-23 | 北京小糖科技有限责任公司 | Recommendation system-oriented sorting and scattering method and device, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110352425B (en) | Cognitive regulatory compliance automation for blockchain transactions | |
| CN109634698B (en) | Menu display method and device, computer equipment and storage medium | |
| CN112380213B (en) | Information acquisition method and device, computer equipment and storage medium | |
| CN113379301A (en) | Method, device and equipment for classifying users through decision tree model | |
| CN115330487A (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN110633959A (en) | Method, device, equipment and medium for creating approval task based on graph structure | |
| CN111563218A (en) | Page repairing method and device | |
| CN114995791A (en) | API (application program interface) polymerization method and device, electronic equipment and storage medium | |
| CN112463986A (en) | Information storage method and device | |
| US11194869B2 (en) | Method and apparatus for enriching metadata via a network | |
| CN112149838A (en) | Method, device, electronic equipment and storage medium for realizing automatic model building | |
| CN113743968A (en) | Information delivery method, device and equipment | |
| CN111061529A (en) | Configuration software multi-label page management method, device and storage medium | |
| CN115907826A (en) | Client mining method based on artificial intelligence and related equipment | |
| CN115660451A (en) | Supplier risk early warning method, device, equipment and medium based on RPA | |
| CN113674023A (en) | Rights upgrading method, device, equipment and storage medium based on member level | |
| CN108805716A (en) | A kind of circle recommendation method and device | |
| CN113963093A (en) | Domain relation drawing system and method | |
| CN110533110A (en) | Automatic outer call method and device based on telecommunications customer service | |
| CN111401395A (en) | Data processing method, terminal equipment and storage medium | |
| CN111784390B (en) | Information delivery processing method and device and processing equipment | |
| CN114510555A (en) | Method and device for making business strategy and related equipment | |
| CN113806626A (en) | Method and system for sending push message | |
| CN115023933A (en) | Content pushing method, device, server and storage medium | |
| KR20220141456A (en) | customized real-time financial information providing system that analyzes big data and filters financial information whose source is unknown |
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 |