Target user group positioning method and device, electronic equipment and storage medium
By acquiring and aligning target customer group data and auxiliary customer group data, rule clusters are generated to identify target user groups. This solves the problem of low accuracy in user value hierarchy segmentation on internet platforms when there is a lack of tags and historical data, and achieves efficient and accurate user value hierarchy segmentation.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING BAIDU NETCOM SCI & TECH CO LTD
- Filing Date
- 2023-03-31
- Publication Date
- 2026-07-14
AI Technical Summary
The lack of tags and historical data to identify user value levels in existing technologies leads to low accuracy in user value level classification by internet platforms, making it impossible to conduct effective precision marketing.
By acquiring target customer group data and auxiliary customer group data from the target storage, feature alignment is performed to generate target rule clusters. These rule clusters are then used to determine the target user group, thereby improving the accuracy of user value hierarchy segmentation.
It enables efficient and accurate identification of target user groups in cold start samples, improves the accuracy of user value hierarchy segmentation, and solves the problem of low accuracy caused by manually generated customer groups based on business expert rules.
Smart Images
Figure CN116342164B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of computer technology, further to the field of big data, and in particular to a method, apparatus, electronic device, and storage medium for locating a target user group. Background Technology
[0002] With the development of internet technology, intelligent internet marketing and communication are receiving increasing attention and in-depth application from enterprises. When conducting precise marketing to users, internet platforms first need to segment users into value tiers, such as high-value, medium-value, and low-value customer groups, and then recommend different products to different customer groups. However, when internet platforms lack both tags to identify user value tiers and historical marketing data to generate these tags, a cold start problem arises due to a lack of target samples. Related technologies typically rely on business expert rules to manually generate customer groups, but this approach suffers from low accuracy in segmenting users into value tiers due to significant differences between expert rules. Summary of the Invention
[0003] This disclosure provides a method, apparatus, electronic device, and storage medium for locating a target user group, in order to at least solve the technical problem of low accuracy in classifying users by value hierarchy due to the use of business expert rules to manually generate customer groups.
[0004] According to one aspect of this disclosure, a method for locating a target user group is provided, comprising: obtaining target customer group data and auxiliary customer group data from a target storage device, wherein the target customer group data is customer group data to be classified into value categories, and the auxiliary customer group data is used to determine at least one target feature value corresponding to a first label, the first label being used to identify the value category of the target customer group data; performing feature alignment on the target customer group data and the auxiliary customer group data to obtain a target feature list, wherein the target feature list is used to record the same features in the target customer group data and the auxiliary customer group data; invoking a target processor to generate a target rule cluster in the auxiliary customer group data based on the target feature list, wherein the target rule cluster includes at least one target feature value; and using the target rule cluster to determine the target user group in the target customer group data.
[0005] According to another aspect of this disclosure, a device for locating a target user group is provided, comprising: an acquisition module, configured to acquire target customer group data and auxiliary customer group data from a target memory, wherein the target customer group data is customer group data to be classified into value categories, and the auxiliary customer group data is used to determine at least one target feature value corresponding to a first label, the first label being used to identify the value category of the target customer group data; an alignment module, configured to perform feature alignment on the target customer group data and the auxiliary customer group data to obtain a target feature list, wherein the target feature list is used to record the same features in the target customer group data and the auxiliary customer group data; a generation module, configured to call a target processor to generate a target rule cluster in the auxiliary customer group data based on the target feature list, wherein the target rule cluster includes at least one target feature value; and a determination module, configured to determine the target user group in the target customer group data using the target rule cluster.
[0006] According to another aspect of this 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, the instructions being executed by the at least one processor to enable the at least one processor to perform the target user group positioning method proposed in this disclosure.
[0007] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause a computer to execute the target user group positioning method proposed in this disclosure.
[0008] According to another aspect of this disclosure, a computer program product is provided, including a computer program that is executed by a processor to locate a target user group as proposed in this disclosure.
[0009] In this disclosure, target customer group data and auxiliary customer group data in the target scenario are obtained from the target memory. Then, the target customer group data and auxiliary customer group data are feature aligned to obtain a target feature list. Subsequently, the target processor is called to generate target rule clusters in the auxiliary customer group data based on the target feature list. Finally, the target user group in the target customer group data is determined using the target rule clusters. This achieves the goal of efficiently and accurately determining the target user group in the cold start sample, and improves the accuracy of value hierarchy segmentation of users. This solves the technical problem of low accuracy in value hierarchy segmentation of users caused by manually generating customer groups using business expert rules in related technologies.
[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description
[0011] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:
[0012] Figure 1 This is a flowchart of a method for locating a target user group according to an embodiment of the present disclosure;
[0013] Figure 2 This is a flowchart of another method for locating a target user group according to an embodiment of the present disclosure;
[0014] Figure 3 This is a structural block diagram of a positioning device for a target user group according to an embodiment of the present disclosure;
[0015] Figure 4 This is a hardware structure block diagram of a computer terminal (or mobile device) for implementing a positioning method for a target user group according to an embodiment of the present disclosure. Detailed Implementation
[0016] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.
[0017] Figure 1 This is a flowchart of a method for locating a target user group according to an embodiment of this disclosure, such as... Figure 1 As shown, the method may include the following steps:
[0018] Step S11: Obtain target customer group data and auxiliary customer group data from the target memory. The target customer group data is customer group data to be classified into value categories. The auxiliary customer group data is used to determine at least one target feature value corresponding to the first label. The first label is used to identify the value category of the target customer group data.
[0019] The aforementioned target scenario can be an intelligent marketing scenario. It should be noted that the embodiments disclosed herein can be applied to any scenario involving intelligent marketing in the fields of health, science, society, language and art, but are not limited to.
[0020] The target storage device described above includes electrical connections based on one or more wires, a portable computer disk, a hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical fiber, portable compact disk read-only memory, optical storage device, magnetic storage device, or any suitable combination of the foregoing, and is not limited thereto in this disclosure. The target storage device can store customer data deployed on a local or cloud-based server as a source of customer data acquisition in this disclosure.
[0021] For example, the target user group positioning method in this embodiment can be applied to marketing recommendation scenarios to address the cold start problem caused by the lack of historical marketing data. The following example illustrates this cold start problem: An internet platform needs to conduct targeted marketing to users, dividing them into three different customer groups: high-value, medium-value, and low-value, and recommending different products to each group. However, this internet platform lacks tags to identify user value levels and also lacks historical data to generate these value level identifiers. This is the meaning of a cold start, and the cold start process requires processing data to create cold start samples.
[0022] The aforementioned target customer data represents part or all of the customer data in the cold start sample. The cold start sample lacks any primary tags for intelligent marketing. Primary tags are used to categorize the target customer data by value, resulting in different value categories such as high-value, medium-value, and low-value customers. Taking intelligent marketing scenarios on internet platforms as an example, the target customer data includes some or all users of the internet platform and multiple characteristics corresponding to each user. For instance, when the internet platform is a bank platform, the target customer data could be the customer data corresponding to all users using Bank A's application (APP) client. The target customer data for each user could include basic characteristics such as the user's age, education level, and industry.
[0023] The aforementioned auxiliary customer group data refers to customer group data with the same application scenario as the target customer group data. This auxiliary customer group data is used to determine at least one target feature value corresponding to the first label. For example, when the application scenario of the target customer group data is a financial marketing scenario, the auxiliary customer group data is also customer group data with some marketing labels within the same financial marketing scenario. Specifically, when the first label is used to identify high-value customers in the target customer group data, the auxiliary customer group data can be used to determine the values of characteristics such as age, education, and industry corresponding to the high-value customer group. For example, when the internet platform is a banking platform, the target customer group data can be the customer group data corresponding to all users using Bank A's APP client. The target customer group data for each user can include basic characteristics such as the user's age, education, and industry. The auxiliary customer group data can be the customer group data corresponding to all users using Bank B's APP client. The auxiliary customer group data for each user can include characteristics such as the user's income, age, education, industry, installed APP list, and interest tags.
[0024] Step S12: Align the target customer group data and the auxiliary customer group data with features to obtain a target feature list, wherein the target feature list is used to record the same features in the target customer group data and the auxiliary customer group data;
[0025] Continuing with the example of target customer data (customer data corresponding to users of Bank A's APP) and auxiliary customer data (customer data corresponding to users of Bank B's APP), the target customer data also includes features such as users' age, education, and industry, while the auxiliary customer data also includes features such as users' income, age, education, industry, list of installed APPs, and interest tags. After aligning the features of the target customer data and the auxiliary customer data, the resulting target feature list includes features such as age, education, and industry.
[0026] Step S13: Invoke the target processor to generate target rule clusters in the auxiliary customer group data based on the target feature list, wherein the target rule clusters include at least one target feature value;
[0027] The aforementioned target processor includes, but is not limited to, processing devices such as microprocessors or programmable logic devices. The number of target processors may be one or more, and this disclosure does not limit this.
[0028] It should be noted that the aforementioned one or more target processors and / or other data processing circuits may also be referred to as "data processing circuits" in this disclosure. The data processing circuit can be embodied, in whole or in part, as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuit can be a single, independent processing module, or integrated, in whole or in part, into any other element in a computer terminal. As involved in the embodiments of this disclosure, the data processing circuit serves as a processor control, for example, the selection of a variable resistor termination path connected to an interface.
[0029] Step S14: Use the target rule cluster to determine the target user group in the target customer group data.
[0030] Specifically, the aforementioned target customer group can be a high-value customer group.
[0031] According to steps S11 to S14 of this disclosure, target customer group data and auxiliary customer group data in the target scenario are obtained from the target memory. Then, the target customer group data and auxiliary customer group data are aligned to obtain a target feature list. Subsequently, the target processor is called to generate target rule clusters in the auxiliary customer group data based on the target feature list. Finally, the target user group in the target customer group data is determined using the target rule clusters. This achieves the goal of efficiently and accurately determining the target user group in the cold start sample, and improves the accuracy of value hierarchy classification of users. This solves the technical problem in related technologies where the accuracy of value hierarchy classification of users is low due to the manual generation of customer groups using business expert rules.
[0032] The method for locating the target user group in the above embodiments will be further described below.
[0033] As an optional implementation, in step S13, invoking the target processor to generate a target rule cluster in the auxiliary customer group data based on the target feature list includes:
[0034] Step S131: Determine a second label associated with the first label, wherein the second label is used to identify the value category of the auxiliary customer group data;
[0035] Step S132: Using the second label as the target, pre-train the initial rule model using the target feature list to obtain the target rule model;
[0036] Step S133: Analyze the target rule model to obtain the target rule cluster.
[0037] Specifically, the second label mentioned above is a label that is highly correlated with the first label. Continuing with the example of target customer data (customer data corresponding to users of Bank A's APP) and auxiliary customer data (customer data corresponding to users of Bank B's APP), when the first label is used to indicate that the target customer data falls under the value category of high-value customers, high-value customers are correlated with income levels. Therefore, the second label can be used to identify high-income customers in the auxiliary customer data. By statistically analyzing the income distribution of the auxiliary customer data samples, the top 5% of the income distribution are taken as high-income customers, corresponding to high-value customers, while the remaining 95% of the samples are ordinary customers.
[0038] Furthermore, targeting the second label, the initial rule model is pre-trained using a list of target features to obtain the target rule model. The initial rule model can be, but is not limited to, a random forest model, an optimized distributed gradient boosting library model (XGBoost), or a distributed gradient boosting framework model based on decision tree algorithms (Light Gradient Boosting Machine, LightGBM). Specifically, the random forest model randomly samples from the original dataset to form n different sample datasets, then builds n different decision tree models based on these datasets, and finally obtains the final classification result based on the voting results of these decision tree models; XGBoost is a gradient boosting tree system that can efficiently, flexibly, and conveniently process data, is compatible with small to medium-sized datasets, enables parallel data processing, and runs cross-validation after each iteration; LightGBM is a distributed high-performance framework that uses decision trees to handle ranking, classification, and regression tasks. Parsing the pre-trained target rule model yields the target rule cluster.
[0039] Based on the above optional implementation methods, by determining the second label associated with the first label, and then using the second label as the target, the initial rule model is pre-trained using the target feature list to obtain the target rule model. Finally, the target rule model is parsed, thereby enabling the rapid acquisition of the target rule cluster to accurately locate high-value customer groups in cold start samples.
[0040] As an optional implementation, in step S131, determining the second tag associated with the first tag includes:
[0041] Step S1311: Obtain multiple third tags associated with the first tag from the target associated data;
[0042] Step S1312: Calculate the target parameters between the multiple third tags and the first tag, where the target parameters are used to represent the degree of correlation between the multiple third tags and the first tag;
[0043] Step S1313: Select a second label from multiple third labels based on the target parameters.
[0044] The aforementioned target-related data can be third-party data in intelligent marketing scenarios. From this third-party data, a second tag associated with the first tag can be determined. Specifically, multiple third tags that appear simultaneously with the first tag in the third-party data are queried, and the target parameters between each third tag and the first tag are calculated. These target parameters can be, but are not limited to, Pearson correlation coefficient, cosine similarity, and Kullback-Leibler (KL) divergence. The Pearson coefficient measures the linear correlation between the third tag and the first tag, and its value ranges between -1 and 1. Cosine similarity, also known as cosine similarity, assesses the similarity between two vectors by calculating the cosine of the angle between them. Cosine similarity is typically used in positive space, so its value ranges between -1 and 1. KL divergence, also known as relative entropy, is equivalent to the difference in information entropy between two probability distributions in information theory. Furthermore, based on the target parameters, the third tag with the highest correlation to the first tag is determined, and this third tag is designated as the second tag.
[0045] Based on the above optional implementation methods, by obtaining multiple third labels associated with the first label from the target association data, and then calculating the target parameters between the multiple third labels and the first label, a second label can be selected from the multiple third labels based on the target parameters, thereby quickly determining the pre-training target of the initial rule model.
[0046] As an optional implementation, the target rule model is a tree structure model, which includes at least one root node and at least one leaf node. In step S133, the target rule model is parsed to obtain the target rule cluster, which includes:
[0047] Step S1331: Traverse the path from the root node to the leaf node to obtain multiple candidate rules;
[0048] Step S1332: Calculate the evidence weights corresponding to multiple candidate rules;
[0049] Step S1333: In response to the fact that the evidence weight of the candidate rule is greater than the preset value, the candidate rule is determined as the target rule;
[0050] Step S1334: Generate a target rule cluster using the target rules.
[0051] Specifically, the target rule model is a tree structure model. Analyzing this model yields the paths from the root node to the leaf nodes in each tree, with each path corresponding to a candidate rule. The Weight of Evidence (WOE) for each candidate rule is calculated; a higher WOE value indicates a more important and crucial candidate rule. Further, candidate rules with a WOE greater than 0 are selected as target rules, i.e., rules for generating high-value customer groups. All target rules are then used to form the final target rule cluster.
[0052] Based on the above optional implementation method, multiple candidate rules are obtained by traversing the path from the root node to the leaf node, and then the evidence weights corresponding to the multiple candidate rules are calculated. Subsequently, in response to the evidence weight of the candidate rule being greater than a preset value, the candidate rule is determined as the target rule. Finally, the target rule is used to quickly generate a target rule cluster to accurately locate high-value customer groups in the cold start sample.
[0053] As an optional implementation, in step S12, feature alignment is performed on the target customer group data and the auxiliary customer group data to obtain a target feature list including:
[0054] Step S121: Filter the auxiliary customer group data using preset rules to obtain the filtering results;
[0055] Step S122: Based on the target customer group data and the screening results, perform feature alignment to obtain a target feature list.
[0056] Specifically, based on human experience, customer data with the same characteristics as the target customer data can be filtered from the auxiliary customer data to serve as the filtering results. Continuing with the example of target customer data being customer data corresponding to users of Bank A's APP and auxiliary customer data being customer data corresponding to users of Bank B's APP, the target customer data also includes features such as age, education, and industry, while the auxiliary customer data includes features such as income, age, education, industry, installed APP list, and interest tags. From the installed APP list in the auxiliary customer data, the filtering results for users installing Bank A's APP are obtained, and the remaining samples are discarded. After feature alignment based on the target customer data and the filtering results, the resulting target feature list contains the same features as both the target customer data and the auxiliary customer data: age, education, and industry.
[0057] Based on the above optional implementation methods, by using preset rules to filter auxiliary customer group data to obtain filtering results, and then performing feature alignment based on target customer group data and filtering results, a target feature list can be quickly obtained, thereby efficiently pre-training the tree structure model.
[0058] As an optional implementation, in step S14, determining the target user group in the target customer group data using the target rule cluster includes: performing feature matching between at least one target feature value in the target rule cluster and the target customer group data to determine the target user group.
[0059] Continuing with the example of app users from Bank A as the target customer group and app users from Bank B as the secondary customer group, each target rule in the target rule cluster contains at least one target feature value, such as target rule 1: Education: Master's degree or above; Age: 30-38; Industry: Finance. By matching the target feature value in target rule 1 with the target customer group data, high-value customers within the target customer group data can be identified.
[0060] Figure 2 This is a flowchart of another target user group positioning method according to an embodiment of the present disclosure, such as... Figure 2 As shown, the method may include the following steps:
[0061] Step S201: Obtain target customer group data and auxiliary customer group data from the target memory. The target customer group data is customer group data to be classified into value categories. The auxiliary customer group data is used to determine at least one target feature value corresponding to the first label. The first label is used to identify the value category of the target customer group data.
[0062] Step S202: Filter the auxiliary customer group data using preset rules to obtain the filtering results;
[0063] Step S203: Based on the target customer group data and the screening results, perform feature alignment to obtain a target feature list;
[0064] Step S204: Obtain multiple third tags associated with the first tag from the target association data;
[0065] Step S205: Calculate the target parameters between the multiple third tags and the first tag, where the target parameters are used to represent the degree of correlation between the multiple third tags and the first tag;
[0066] Step S206: Select a second label from multiple third labels based on the target parameters;
[0067] Step S207: Using the second label as the target, pre-train the initial rule model using the target feature list to obtain the target rule model;
[0068] Step S208: Traverse the path from the root node to the leaf node to obtain multiple candidate rules;
[0069] Step S209: Calculate the evidence weights corresponding to multiple candidate rules;
[0070] Step S210: In response to the fact that the evidence weight of the candidate rule is greater than the preset value, the candidate rule is determined as the target rule;
[0071] Step S211: Generate a target rule cluster using the target rules;
[0072] Step S212: Based on at least one target feature value in the target rule cluster, perform feature matching with the target customer group data to determine the target user group.
[0073] Specifically, the following example illustrates the target user group positioning method implemented in this disclosure, using target customer group data as sample A and auxiliary customer group data as sample B. Sample A is a cold start sample, meaning it has no tags for marketing, while sample B has some tags that can be used to indirectly generate marketing customer group tags. This embodiment of the disclosure can generate marketing rules from sample B, which can then be transferred to sample A, thereby assisting sample A in generating marketing customer group tags. The specific implementation process is as follows:
[0074] First, samples similar to sample A are selected from sample B based on rules. Then, the selected samples are aligned with the features of sample A. This yields the common features between sample A and sample B, which is the target feature list. The target feature list includes K features: X1, X2, ..., XK.
[0075] Then, target variable mapping is performed. Specifically, assume that the first label used to divide the customer groups in sample A is L, and the first label L has N values, namely L1, L2, ..., LN. Sample B does not have a first label L, but has a second label M that is strongly correlated with L. Therefore, the second label M can be used to replace the first label L for pre-training of the tree structure model.
[0076] To further achieve automatic rule generation, specifically, on sample B, with the second label M as the target, features X1, X2, ..., XK are taken, and a tree structure model is used for pre-training to obtain the target rule model. The target rule model is then parsed to generate the target rule cluster.
[0077] Finally, rule shifting is performed. Specifically, feature matching is performed between sample A and at least one target feature value in the target rule cluster to determine the high-value customer group.
[0078] Based on the above steps S201 to S212, by acquiring target customer group data and auxiliary customer group data in the target scenario, and then performing feature alignment on the target customer group data and auxiliary customer group data to obtain a target feature list, target rule clusters are then generated in the auxiliary customer group data based on the target feature list. Finally, the target user group in the target customer group data is determined using the target rule clusters. This achieves the goal of efficiently and accurately determining the target user group in the cold start sample, and improves the accuracy of value hierarchy segmentation of users. This solves the technical problem in related technologies where the accuracy of value hierarchy segmentation of users is low due to the manual generation of customer groups using business expert rules.
[0079] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.
[0080] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this disclosure.
[0081] This disclosure also provides a positioning device for a target user group, which is used to implement the above embodiments and preferred embodiments, and will not be repeated hereafter. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0082] Figure 3 This is a structural block diagram of a positioning device for a target user group according to an embodiment of the present disclosure, such as... Figure 3 As shown, a positioning device 300 for a target user group includes:
[0083] The acquisition module 301 is used to acquire target customer group data and auxiliary customer group data in the target scene from the target storage. The target customer group data is customer group data to be classified into value categories. The auxiliary customer group data is used to determine at least one target feature value corresponding to the first label. The first label is used to identify the value category of the target customer group data.
[0084] Alignment module 302 is used to perform feature alignment on target customer group data and auxiliary customer group data to obtain a target feature list, wherein the target feature list is used to record the same features in the target customer group data and auxiliary customer group data;
[0085] The generation module 303 is used to call the target processor to generate a target rule cluster in the auxiliary customer group data based on the target feature list, wherein the target rule cluster includes at least one target feature value;
[0086] The determination module 304 is used to determine the target user group in the target customer group data using the target rule cluster.
[0087] Optionally, the generation module 303 is further configured to: determine a second label associated with the first label, wherein the second label is used to identify the value category of the auxiliary customer group data; pre-train the initial rule model using the second label as the target and the target feature list to obtain the target rule model; and parse the target rule model to obtain the target rule cluster.
[0088] Optionally, the generation module 303 is further configured to: obtain multiple third tags associated with the first tag from the target association data; calculate target parameters between the multiple third tags and the first tag, wherein the target parameters are used to represent the degree of correlation between the multiple third tags and the first tag; and select a second tag from the multiple third tags based on the target parameters.
[0089] Optionally, the target rule model is a tree structure model, which includes at least one root node and at least one leaf node. The generation module 303 is further configured to: traverse the path from the root node to the leaf node to obtain multiple candidate rules; calculate the evidence weights corresponding to the multiple candidate rules; determine the candidate rule as the target rule in response to the evidence weight of the candidate rule being greater than a preset value; and generate a target rule cluster using the target rule.
[0090] Optionally, the alignment module 302 is also used to: filter the auxiliary customer group data using preset rules to obtain the filtering results; and perform feature alignment based on the target customer group data and the filtering results to obtain a target feature list.
[0091] Optionally, the determining module 304 is further configured to: perform feature matching between at least one target feature value in the target rule cluster and the target customer group data to determine the target user group.
[0092] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.
[0093] According to embodiments of this disclosure, this disclosure also provides an electronic device including a memory and at least one processor, the memory storing computer instructions, the processor being configured to execute the computer instructions to perform the steps in the above method embodiments.
[0094] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.
[0095] Optionally, in this disclosure, the processor described above can be configured to perform the following steps via a computer program:
[0096] S1, retrieve target customer group data and auxiliary customer group data from the target memory in the target scenario, wherein the target customer group data is customer group data to be classified into value categories, and the auxiliary customer group data is used to determine at least one target feature value corresponding to the first label, and the first label is used to identify the value category of the target customer group data;
[0097] S2, perform feature alignment on the target customer group data and the auxiliary customer group data to obtain a target feature list, wherein the target feature list is used to record the same features in the target customer group data and the auxiliary customer group data;
[0098] S3, Invoke the target processor to generate target rule clusters in the auxiliary customer group data based on the target feature list, wherein the target rule clusters include at least one target feature value;
[0099] S4 uses target rule clusters to determine the target user group in the target customer group data.
[0100] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.
[0101] Figure 4 This is a hardware structure block diagram of a computer terminal (or mobile device) for implementing a positioning method for a target user group according to an embodiment of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.
[0102] like Figure 4As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 402 or a computer program loaded from storage unit 408 into random access memory (RAM) 403. RAM 403 may also store various programs and data required for the operation of device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. Input / output (I / O) interface 405 is also connected to bus 404.
[0103] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0104] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as the method for locating a target user group. For example, in some embodiments, the method for locating a target user group can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program can be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the method for locating a target user group described above can be performed. Alternatively, in other embodiments, the computing unit 401 can be configured to perform the method for locating a target user group by any other suitable means (e.g., by means of firmware).
[0105] Various embodiments 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-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0106] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, 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 sound input, voice input, or tactile input).
[0107] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.
[0108] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.
[0109] According to embodiments of this disclosure, this disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are configured to execute the steps in the above method embodiments at runtime.
[0110] Optionally, in this embodiment, the aforementioned non-transitory computer-readable storage medium may be configured to store a computer program for performing the following steps:
[0111] S1, retrieve target customer group data and auxiliary customer group data from the target memory in the target scenario, wherein the target customer group data is customer group data to be classified into value categories, and the auxiliary customer group data is used to determine at least one target feature value corresponding to the first label, and the first label is used to identify the value category of the target customer group data;
[0112] S2, perform feature alignment on the target customer group data and the auxiliary customer group data to obtain a target feature list, wherein the target feature list is used to record the same features in the target customer group data and the auxiliary customer group data;
[0113] S3, Invoke the target processor to generate target rule clusters in the auxiliary customer group data based on the target feature list, wherein the target rule clusters include at least one target feature value;
[0114] S4 uses target rule clusters to determine the target user group in the target customer group data.
[0115] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0116] According to embodiments of this disclosure, a computer program product is also provided. Program code for implementing embodiments of the methods of this disclosure can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on a machine, partially on a machine, partially on a remote machine as a standalone software package, or entirely on a remote machine or server.
[0117] 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 executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.
[0118] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.
Claims
1. A method for locating a target user group, comprising: Retrieve target customer group data and auxiliary customer group data from the target memory in the target scenario. The target customer group data is customer group data to be classified into value categories. The auxiliary customer group data is used to determine at least one target feature value corresponding to a first label. The first label is used to identify the value category of the target customer group data. The target customer group data and the auxiliary customer group data are aligned to obtain a target feature list, wherein the target feature list is used to record the same features in the target customer group data and the auxiliary customer group data; The target processor generates a target rule cluster in the auxiliary customer group data based on the target feature list, wherein the target rule cluster includes the at least one target feature value; The target user group in the target customer group data is determined using the target rule cluster; The step of calling the target processor to generate a target rule cluster in the auxiliary customer group data based on the target feature list includes: determining a second label associated with the first label, wherein the second label is used to identify the value category of the auxiliary customer group data; using the second label as the target, pre-training an initial rule model using the target feature list to obtain a target rule model; and parsing the target rule model to obtain the target rule cluster.
2. The method for locating a target user group according to claim 1, wherein, Determining the second tag associated with the first tag includes: Obtain multiple third tags associated with the first tag from the target association data; Calculate the target parameters between the plurality of third tags and the first tag, wherein the target parameters are used to represent the degree of correlation between the plurality of third tags and the first tag; The second tag is selected from the plurality of third tags based on the target parameters.
3. The method for locating a target user group according to claim 1, wherein, The target rule model is a tree structure model, which includes at least one root node and at least one leaf node. Parsing the target rule model yields the target rule cluster, which includes: Traverse the path from the root node to the leaf node to obtain multiple candidate rules; Calculate the evidence weights corresponding to the multiple candidate rules; If the evidence weight of the candidate rule is greater than a preset value, the candidate rule is determined as the target rule. The target rule cluster is generated using the target rule.
4. The method for locating a target user group according to claim 1, wherein, The target customer group data and the auxiliary customer group data are aligned to obtain a target feature list, which includes: The auxiliary customer group data is filtered using preset rules to obtain the filtering results; Based on the target customer group data and the screening results, feature alignment is performed to obtain the target feature list.
5. The method for locating a target user group according to claim 1, wherein, Determining the target user group in the target customer group data using the target rule cluster includes: The target user group is determined by performing feature matching between at least one target feature value in the target rule cluster and the target customer group data.
6. A positioning device for a target user group, comprising: The acquisition module is used to acquire target customer group data and auxiliary customer group data in the target scene from the target storage, wherein the target customer group data is customer group data to be classified into value categories, and the auxiliary customer group data is used to determine at least one target feature value corresponding to a first label, and the first label is used to identify the value category of the target customer group data; An alignment module is used to perform feature alignment on the target customer group data and the auxiliary customer group data to obtain a target feature list, wherein the target feature list is used to record the same features in the target customer group data and the auxiliary customer data; A generation module is used to call a target processor to generate a target rule cluster in the auxiliary customer group data based on the target feature list, wherein the target rule cluster includes the at least one target feature value; The determination module is used to determine the target user group in the target customer group data using the target rule cluster; The generation module is further configured to determine a second label associated with the first label, wherein the second label is used to identify the value category of the auxiliary customer group data; using the second label as the target, the initial rule model is pre-trained using the target feature list to obtain a target rule model; and the target rule model is parsed to obtain the target rule cluster.
7. The positioning device for a target user group according to claim 6, wherein, The generation module is also used for: Obtain multiple third tags associated with the first tag from the target association data; Calculate the target parameters between the plurality of third tags and the first tag, wherein the target parameters are used to represent the degree of correlation between the plurality of third tags and the first tag; The second tag is selected from the plurality of third tags based on the target parameters.
8. The positioning device for a target user group according to claim 6, wherein, The target rule model is a tree structure model, which includes at least one root node and at least one leaf node. The generation module is further used for: Traverse the path from the root node to the leaf node to obtain multiple candidate rules; Calculate the evidence weights corresponding to the multiple candidate rules; If the evidence weight of the candidate rule is greater than a preset value, the candidate rule is determined as the target rule. The target rule cluster is generated using the target rule.
9. The positioning device for a target user group according to claim 6, wherein, The alignment module is also used for: The auxiliary customer group data is filtered using preset rules to obtain the filtering results; Based on the target customer group data and the screening results, feature alignment is performed to obtain the target feature list.
10. The positioning device for a target user group according to claim 6, wherein, The determining module is also used for: The target user group is determined by performing feature matching between at least one target feature value in the target rule cluster and the target customer group data.
11. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.
12. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-5.
13. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-5.