CN113312552B - Data processing method, device, electronic device and medium - Google Patents

Abstract

The disclosure provides a data processing method, a data processing device, electronic equipment and a medium, relates to the field of artificial intelligence, and particularly relates to the technical field of deep learning and intelligent recommendation. The implementation scheme is as follows: acquiring sample user data; performing supervised training on sample user data based on a classification algorithm and generating a decision tree; and generating recall rules related to the user attributes based on one or more nodes in the decision tree.

Description

Data processing method, device, electronic device and medium

Technical Field

The present disclosure relates to the field of artificial intelligence, in particular to the field of deep learning and intelligent recommendation technology, and specifically to a data processing method, device, electronic device, computer-readable storage medium and computer program product.

Background Art

Artificial intelligence is a discipline that studies how to use computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.). It includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing. Artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning/deep learning, big data processing technology, knowledge graph technology, and other major directions.

Determining the target user through data processing is conducive to making personalized recommendations to the user. For example, if the user is determined to be a target user through data processing, content or services related to the target can be recommended to the user.

The methods described in this section are not necessarily methods that have been previously conceived or employed. Unless otherwise indicated, it should not be assumed that any method described in this section is considered to be prior art simply because it is included in this section. Similarly, unless otherwise indicated, the issues mentioned in this section should not be considered to have been recognized in any prior art.

Summary of the invention

The present disclosure provides a data processing method, apparatus, electronic device, computer-readable storage medium, and computer program product.

According to one aspect of the present disclosure, a data processing method is provided, including: acquiring sample user data; performing supervised training on the sample user data based on a binary classification algorithm and generating a decision tree; and generating recall rules related to user attributes based on one or more nodes in the decision tree.

According to one aspect of the present disclosure, a data processing device is provided, including: an acquisition module, configured to acquire sample user data; a training module, configured to perform supervised training on the sample user data based on a binary classification algorithm and generate a decision tree; and a recall rule generation module, configured to generate recall rules related to user attributes based on one or more nodes in the decision tree.

According to one aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to perform a data processing method.

According to one aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute a data processing method.

According to one aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements a data processing method when executed by a processor.

According to one or more embodiments of the present disclosure, the target user is determined by supervised training, and the mining scope and mining accuracy of the target user are expanded. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easy to understand through the following description.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings exemplarily illustrate the embodiments and constitute a part of the specification, and together with the text description of the specification, are used to explain the exemplary implementation of the embodiments. The embodiments shown are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar but not necessarily identical elements.

FIG1 shows a flow chart of a data processing method according to an exemplary embodiment of the present disclosure;

FIG2 shows a schematic diagram of generating a recall rule according to an exemplary embodiment of the present disclosure;

FIG3 is a schematic diagram showing a workflow of a sorting model according to an exemplary embodiment of the present disclosure;

FIG4 shows a schematic diagram of generating a recall rule based on a decision tree according to an exemplary embodiment of the present disclosure;

FIG5 shows a structural block diagram of a data processing device according to an exemplary embodiment of the present disclosure; and

FIG. 6 shows a block diagram of an exemplary electronic device that can be used to implement an embodiment of the present disclosure.

DETAILED DESCRIPTION

The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, timing relationship, or importance relationship of these elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, based on the description of the context, they may also refer to different instances.

The terms used in the description of various examples in this disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. In addition, the term "and/or" used in this disclosure covers any one of the listed items and all possible combinations.

In related technologies, target users are usually mined and determined based on business rules, which may be, for example, age, gender, region, education or income. The formulation of such business rules requires the accumulation of a large amount of business field experience and a thorough analysis of relevant field knowledge. This method requires high experience in relevant fields and is difficult to implement. In addition, the rules obtained through exhaustive analysis may still be imperfect, have a limited coverage, and have a low accuracy rate.

To solve one or more of the above problems, the present disclosure generates recall rules for recalling users through supervised training based on a binary classification algorithm, which effectively expands the recall rules and realizes the recall of users in a wider range.

It should be noted that in the technical solution of this disclosure, the acquisition, storage and application of user personal information (such as historical behavior information and geographic location information) involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good customs. In addition, user personal information has been desensitized (i.e., anonymized) during the acquisition, storage and application process.

The data processing method of the present disclosure will be further described below in conjunction with the accompanying drawings.

FIG. 1 shows a flow chart of a data processing method according to an exemplary embodiment of the present disclosure.

As shown in FIG1 , the method includes: step S101 , obtaining sample user data; step S102 , performing supervised training on the sample user data based on a binary classification algorithm and generating a decision tree; step S103 , generating recall rules related to user attributes based on one or more nodes in the decision tree.

According to some embodiments, the binary classification algorithm may be one or more of binary classification algorithms including but not limited to logistic regression (LG), gradient boosting decision tree (GBDT) and eXtreme Gradient Boosting (XGBoost), or any combination of several of these algorithms. The present disclosure does not limit the type of the binary classification algorithm.

For ease of description and understanding, the following content will take the binary classification algorithm as the XGBoost algorithm as an example to specifically describe the technical solution of the present disclosure. It should be noted that the technical solution of the present disclosure is not limited to the binary classification algorithm based on XGBoost, but is also applicable to other binary classification algorithms.

According to some embodiments, the sample users can be determined based on the definition of the target users. For example, the target users can be potential users of a certain type of product or service. In this case, the sample users can be users who have purchased the product or service and users who have not purchased the product or service, serving as positive samples and negative samples for supervised training, respectively. All instances corresponding to the user attributes of the sample users can be used as feature inputs in supervised training. For example, the user attributes can be the user's search terms. Accordingly, the word set obtained by performing word segmentation processing on the sample user's search history can be used as feature input in supervised training. It can be understood that the nodes in the decision tree finally generated by the supervised training can be all or part of the words in the above word set.

According to some embodiments, step S103 further includes: performing weighted calculation on one or more nodes in the decision tree to generate the recall rule related to the user attribute. This process is equivalent to screening out features that are more relevant to the target behavior of the target user (for example, the behavior of purchasing a product or service) in all nodes of the decision tree according to preset calculation rules, and using the screened features as recall rules to improve the accuracy of mining the target user. The specific method of weighted calculation of the nodes will be described in detail in subsequent embodiments.

According to some embodiments, weighted calculation is performed on one or more nodes in the decision tree to generate the recall rule related to the user attributes, including: generating a feature value list based on the corresponding feature values of one or more nodes in the decision tree, wherein the feature value is the product of the number of times the corresponding node is used for splitting and the gain of the node when split, and the feature value list contains the one or more nodes in the decision tree and their corresponding feature values; and sorting the feature value list and generating the recall rule related to the user attributes.

It can be understood that the feature value of a node is equal to the number of times the node is used for splitting multiplied by the gain during splitting. The larger the feature value, the higher the correlation between the feature and the target behavior of the target user. Therefore, feature value calculation provides a way to filter features. Generate a feature value list for all nodes in the decision tree, and sort the feature values of all nodes according to the calculation results obtained by the above formula to filter out features with high feature values as the recall rules for recalling users.

According to some embodiments, the data processing method further includes: after the recall rules are generated by the above steps, users can be matched in the data source according to the recall rules, wherein the users obtained by matching are recallable users.

According to some embodiments, the user attribute may correspond to a search term from the user, and accordingly, the data source may be a search log of all users. It is understandable that the user's search term may reflect the user's intention to a certain extent. For example, when a user searches for a product, it can be inferred that the user may have the intention to purchase the product. Therefore, the accuracy of users recalled based on the search term is relatively high.

In one example, the method may include: using users who have purchased a product and users who have not purchased the product as positive and negative samples, respectively, performing word segmentation on the search history of the sample users and obtaining a set of search terms, performing multiple rounds of XGBoost training on the positive and negative samples and the set of search terms as features and obtaining a decision tree; performing weighted calculations and sorting on all nodes in the decision tree to obtain a list of feature values, and the search terms corresponding to the nodes with higher weights can be used as the final recall rules for recalling users; matching the search terms obtained in the supervised training in the search logs of all users, and the users corresponding to the results matched in the search logs are the recallable users. In the process of matching the search terms in the search logs, the time range of the data source can be set as needed, for example, the data source can be the search logs of all users within one year.

It should be noted that in the embodiments of the present disclosure, the user's search log is obtained, stored and used based on the user's authorization and consent. In addition, the search log is desensitized (i.e., anonymized) during the process of being obtained, stored and used.

According to some embodiments, the above search terms may be expanded using a word vector algorithm to further expand the recall rules.

According to some other embodiments, the user attribute may also correspond to an application (APP) installed by the user, and accordingly, the data source is an application installation log. Similar to the search term, the APP installed by the user may also be used as a user attribute to determine the target user, further expanding the scope of user recall based on the search term.

FIG2 shows a schematic diagram of generating recall rules according to an exemplary embodiment of the present disclosure. As shown in FIG2, the process of generating recall rules using the APPs installed by the user is similar to the workflow of the above-mentioned application search terms, and will not be repeated here. Furthermore, after obtaining a list of APPs with high feature values, the positive sample rate of each APP can be calculated, and the positive sample rate can be sorted to further obtain a high-intention APP cluster as a recall rule.

According to some embodiments, user attributes may also correspond to the user's post bar visit history, the user's geographic location information, etc., to recall users from different data sources and expand the user's recall scope. The specific instance of the user attribute and its corresponding data source can also be determined according to the definition of the target user, and can also be set according to the specific application scenario. It is understandable that for different user attributes, the process for generating recall rules is similar to the process of generating recall rules by applying search terms as described above, and the present disclosure will not go into details here.

It should be noted that in the embodiments of the present disclosure, similar to the user's search log, the user's post bar visit history and other historical behavior information and geographic location information are all acquired, stored and used based on the user's authorization and consent. In addition, the above information has been desensitized (i.e., anonymized) during the acquisition, storage and use process.

In one example, the recallable users obtained by the method may be a collection of users recalled from the above-mentioned various data sources using different recall rules.

According to some embodiments, the data processing method further includes: inputting the user features of the recallable user into a preset sorting model; and determining whether the recallable user is a target user based on the output result of the sorting model. The preset sorting model can be a model obtained by supervised training based on a binary classification algorithm. The sorting model further screens the recallable users and improves the accuracy of mining the target users.

FIG3 shows a schematic diagram of the workflow of the sorting model according to an exemplary embodiment of the present disclosure. As shown in FIG3 , the workflow of the sorting model can be divided into two parts: 301, training of the sorting model; 302, the sorting model scores and ranks users. In 301, users who have purchased a product and users who have not purchased the product can be used as positive and negative samples, respectively. The positive and negative samples, the features of the sample users (for example, user portraits, online behaviors and derived features, etc.) and the product features of the product are used as inputs for supervised training based on a binary classification algorithm to obtain the sorting model. In 302, the user features of the above-mentioned recallable users are input into the sorting model. The trained sorting model will score and rank the recallable users and output a score ranking, which represents the probability that the corresponding recallable user will purchase the product.

According to some embodiments, the data processing method may further include: setting push rules based on the score ranking output by the above-mentioned ranking model and pushing relevant products or services to the corresponding target users accordingly. For example, the accuracy and recall rate of each threshold score can be checked, and when the accuracy and recall rate meet the preset standards, the relevant products or services are pushed to all recallable users within the threshold. Specific push rules and standards can be set according to specific application scenarios, and this disclosure does not limit this.

FIG4 shows a schematic diagram of generating a recall rule based on a decision tree according to an exemplary embodiment of the present disclosure. It should be noted that, for the purpose of explaining the scheme of the present disclosure only, the present embodiment adopts an application scenario of recommending potential insurance users. It can be understood by those skilled in the art that the scheme of the present disclosure is not limited to the application scenario of the present embodiment; on the contrary, based on the teaching of the present disclosure, other application scenarios are also conceivable. In the present embodiment, the target user is a high-risk credit user, and the user attribute is a search term from the user. By training the sample user data with XGBoost, a decision tree as shown in FIG4 can be obtained, wherein each node on the tree is a search term from the user. After multiple rounds of XGBoost training, multiple decision trees as shown in FIG4 can be obtained. Here, FIG4 is taken as an example to describe the process of generating a recall rule based on a decision tree. Each node in the decision tree corresponds to a search term from the user, and at the same time, each node in the decision tree corresponds to a gain. According to the characteristic value calculation formula introduced in the present disclosure, that is, the product of the number of times a certain search term appears in all decision tree nodes and the gain corresponding to the node, the characteristic value of each node in the decision tree can be calculated. The larger the eigenvalue, the higher the correlation between the search term corresponding to the node and the behavior of the high-risk credit user. The search term corresponding to the high-eigenvalue node is the recall rule. Generating recall rules and recalling users in this way has the advantages of wide recall range and high accuracy.

According to another aspect of the present disclosure, a data processing device is provided for executing any of the above methods. As shown in FIG5 , the data processing device 500 includes: an acquisition module 501 configured to acquire sample user data; a training module 502 configured to perform supervised training on the sample user data based on a binary classification algorithm and generate a decision tree; and a recall rule generation module 503 configured to generate a recall rule related to user attributes based on one or more nodes in the decision tree.

The operations of the units 501 - 503 of the data processing device 500 are similar to the operations of the aforementioned steps S101 - S103 , and are not described in detail herein.

According to some embodiments, the recall rule generation module 503 is further configured to: perform weighted calculation on one or more nodes in the decision tree to generate the recall rule related to the user attribute. This process is equivalent to screening out features that are more relevant to the target behavior of the target user (for example, the behavior of purchasing a product or service) through a calculation unit. The specific method of weighted calculation of the nodes will be described in detail in subsequent embodiments.

According to some embodiments, the recall rule generation module 503 includes: a list generation unit, configured to generate a feature value list based on the corresponding feature values of one or more nodes in the decision tree, wherein the feature value is the product of the number of times the corresponding node is used for splitting and the gain of the node when splitting, and the feature value list contains the one or more nodes in the decision tree and their corresponding feature values; and a sorting unit, which sorts the feature value list and generates the recall rule related to the user attributes.

It can be understood that the feature value of a node is equal to the number of times the node is used for splitting multiplied by the gain during splitting, and the larger the feature value, the higher the relevance of the feature to the target behavior of the target user. The list generation unit generates a feature value list based on all nodes in the decision tree, and the sorting unit sorts the feature values of all nodes according to the calculation results obtained by the above formula to screen out features with larger weights as recall rules for recalling users.

According to some embodiments, the data processing device further includes: a matching module configured to match users in the data source according to the recall rule, wherein the users obtained by matching are recallable users.

According to some embodiments, the user attribute may correspond to a search term from the user, and accordingly, the data source may be a search log of all users. It is understandable that the user's search term may reflect the user's intention to a certain extent. For example, when a user searches for a product, it can be inferred that the user may have the intention to purchase the product.

According to some embodiments, the above search terms may be expanded using a word vector algorithm to further expand the recall rules.

According to some other embodiments, the user attribute may also correspond to an application (APP) installed by the user, and accordingly, the data source is an application installation log. Similar to the search term, the APP installed by the user may also be used as a user attribute to determine the target user.

It should be noted that in the embodiments of the present disclosure, the user's historical behavior information is acquired, stored, and used based on the user's authorization and consent. In addition, the above information is desensitized (i.e., anonymized) during the acquisition, storage, and use process.

In one example, the recallable users obtained by the matching module may be a collection of users recalled from different data sources by applying different recall rules.

According to some embodiments, the data processing device further includes: an input module configured to input the user features of the recallable user into a preset ranking model; and a determination module configured to determine whether the recallable user is a target user based on an output result of the ranking model. The preset ranking model may be a model obtained through supervised training based on a binary classification algorithm.

According to some embodiments, the data processing device may further include: a push module, configured to set push rules based on the output score ranking of the above-mentioned ranking model and push relevant products or services to the corresponding target users accordingly. For example, the accuracy and recall rate of each threshold score can be checked, and when the accuracy and recall rate meet the preset standards, the relevant products or services are pushed to all recallable users within the threshold. Specific push rules and standards can be set according to specific application scenarios, and this disclosure does not limit this.

According to another aspect of the present disclosure, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned data processing method.

According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is also provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned data processing method.

According to another aspect of the present disclosure, a computer program product is further provided, including a computer program, wherein the computer program implements the above data processing method when executed by a processor.

With reference to Figure 6, a block diagram of an electronic device 600 that can be used as a server of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely examples, and are not intended to limit the implementation of the present disclosure described and/or required herein.

As shown in Figure 6, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to the bus 604.

Multiple components in the device 600 are connected to the I/O interface 605, including: an input unit 606, an output unit 607, a storage unit 608, and a communication unit 609. The input unit 606 can be any type of device that can input information to the device 600. The input unit 606 can receive input digital or character information and generate key signal input related to user settings and/or function control of the electronic device, and can include but is not limited to a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and/or a remote controller. The output unit 607 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video/audio output terminal, a vibrator, and/or a printer. The storage unit 608 can include but is not limited to a disk, an optical disk. The communication unit 609 allows the device 600 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver, and/or a chipset, such as a Bluetooth™ device, a 1302.11 device, a WiFi device, a WiMax device, a cellular communication device, and/or the like.

The computing unit 601 may be a variety of general and/or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as data processing methods. For example, in some embodiments, the data processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed on the device 600 via ROM 602 and/or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the data processing method in any other appropriate manner (e.g., by means of firmware).

Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and/or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions/operations specified in the flow chart and/or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but only by the claims after authorization and their equivalent scope. Various elements in the embodiments or examples can be omitted or replaced by their equivalent elements. In addition, each step can be performed in an order different from that described in the present disclosure. Further, the various elements in the embodiments or examples can be combined in various ways. It is important that with the evolution of technology, many elements described herein can be replaced by equivalent elements that appear after the present disclosure.

Claims (13)

1. A data processing method, comprising:

acquiring sample user data;

performing supervised training on the sample user data based on a classification algorithm and generating a decision tree; and

Generating recall rules related to user attributes based on a plurality of nodes in the decision tree, comprising:

Weighting a plurality of nodes in the decision tree to generate the recall rule related to a user attribute, comprising:

Generating a characteristic value list based on corresponding characteristic values of a plurality of nodes in the decision tree, wherein the characteristic values are products of the times of splitting of the corresponding nodes and gains when the nodes split, and the characteristic value list comprises the plurality of nodes and the corresponding characteristic values of the nodes in the decision tree; and

Ranking the list of feature values and generating the recall rule related to the user attribute includes:

Sorting the characteristic value list to obtain a high characteristic value list through screening;

Calculating a positive sample rate corresponding to each node in the high eigenvalue list; and

Generating the recall rule related to the user attribute based on a positive sample rate corresponding to each node,

Wherein the user attributes correspond to terms from the user and/or the user attributes correspond to applications installed by the user.

2. The method of claim 1, further comprising:

and matching the users in the data source according to the recall rule, wherein the matched users are recall users.

3. The method of claim 2, wherein the data source is a search log of a full number of users when the user attribute corresponds to a term from a user.

4. The method of claim 2, wherein the data source is an application installation log when the user attribute corresponds to an application installed by a user.

5. The method of any of claims 2 to 4, further comprising:

inputting the user characteristics of the recallable user into a preset sequencing model; and

And determining whether the recallable user is a target user according to an output result of the sequencing model.

6. A data processing apparatus comprising:

An acquisition module configured to acquire sample user data;

a training module configured to supervise training the sample user data based on a classification algorithm and generate a decision tree; and

A recall rule generation module configured to generate recall rules related to user attributes based on a plurality of nodes in the decision tree, wherein the recall rule generation module is further configured to weight the plurality of nodes in the decision tree to generate the recall rules related to user attributes, wherein the recall rule generation module comprises:

A list generation unit configured to generate a feature value list based on respective feature values of a plurality of nodes in the decision tree, wherein a feature value is a product of the number of times a respective node is split and a gain at which the node is split, the feature value list containing the plurality of nodes in the decision tree and their corresponding feature values; and

A ranking unit configured to rank the feature value list and generate the recall rule related to the user attribute, wherein the ranking unit is further configured to:

Sorting the characteristic value list to obtain a high characteristic value list through screening;

Calculating a positive sample rate corresponding to each node in the high eigenvalue list; and

Generating the recall rule related to the user attribute based on a positive sample rate corresponding to each node,

Wherein the user attributes correspond to terms from the user and/or the user attributes correspond to applications installed by the user.

7. The apparatus of claim 6, further comprising,

And the matching module is configured to match users in the data source according to the recall rule, wherein the matched users are recall users.

8. The apparatus of claim 7, wherein the data source is a search log of a full number of users when the user attribute corresponds to a term from a user.

9. The apparatus of claim 7, wherein the data source is an application installation log when the user attribute corresponds to an application installed by a user.

10. The apparatus of any of claims 7 to 9, further comprising:

The input module is configured to input the user characteristics of the recallable user into a preset ordering model; and

And the determining module is configured to determine whether the recall user is a target user according to the output result of the sequencing model.

11. An electronic device, comprising:

At least one processor; and

A memory communicatively coupled to the at least one processor; wherein the method comprises the steps of

The memory stores instructions executable by the at least one processor, which when executed by the at least one processor, enable the at least one processor to perform the method of any one of claims 1 to 5.

12. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1 to 5.

13. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the method of any one of claims 1 to 5.