User portrait construction method and device, storage medium and electronic equipment
By obtaining user association data of the target user and performing feature extraction and clustering operations, the user portrait construction process is simplified, the manual processing time is reduced, and efficiency is improved.
Patent Information
- Application Number
- CN202410040095.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-01-10
- Publication Date
- 2025-07-11
AI Technical Summary
In the prior art, it takes a long time to build user portraits and is complex to operate.
By obtaining the user association data of the target user, performing feature extraction operations, calculating the correlation degree to determine the feature keywords, performing clustering and interest value calculations, and building a user portrait.
Simplify the process, reduce the time-consuming process of manual processing, and improve the efficiency of user portrait construction.
Smart Images
Figure CN120298012A_ABST
Abstract
Description
Technical Field
[0001] The technical solution of the present disclosure relates to the field of computer technologies, and particularly relates to a method and apparatus for constructing a user profile, a storage medium, and an electronic device. Background Art
[0002] A user profile refers to a way of depicting and summarizing the characteristics, interests, etc. of a specific user. The purpose of constructing a user profile is to better understand and gain insights into users, so as to provide more personalized and accurate products or services.
[0003] In related technical solutions, machine learning is mostly used to construct a user profile of a user. However, the model used in this method needs to be obtained through learning and training on a large amount of data, which is complex in operation and time-consuming. Summary of the Invention
[0004] In view of this, embodiments of the present disclosure provide a method and apparatus for constructing a user profile, a storage medium, and an electronic device.
[0005] According to a first aspect of the present disclosure, a method for constructing a user profile is proposed. The method includes:
[0006] Obtain user association data of a target user;
[0007] Perform a feature extraction operation on the user association data to obtain at least one feature keyword corresponding to the target user;
[0008] Construct a user profile of the target user based on the at least one feature keyword.
[0009] Combined with any implementation manner provided by the present disclosure, the performing a feature extraction operation on the user association data to obtain at least one feature keyword corresponding to the target user includes:
[0010] For each target word in the user association data, calculate the relevance between the target word and the user association data;
[0011] Determine the target word corresponding to the relevance greater than a preset threshold as the feature keyword.
[0012] Combined with any implementation manner provided by the present disclosure, the relevance between the target word and the user association data is positively correlated with the number of times the target word appears in the user association data.
[0013] Combined with any implementation manner provided by the present disclosure, the constructing a user profile of the target user based on the at least one feature keyword includes:
[0014] Perform a clustering operation on the feature keywords that meet the preset similarity conditions among the at least one feature keyword to obtain at least one clustering cluster;
[0015] Calculate the interest values of the target user for the at least one clustering cluster respectively;
[0016] Determine the clustering cluster corresponding to the interest value that meets the preset interest value condition as the target clustering cluster;
[0017] Construct a user portrait of the target user based on the feature keywords included in the target clustering cluster.
[0018] Combined with any one of the embodiments provided in the present disclosure, the calculating the interest values of the target user for the at least one clustering cluster respectively includes:
[0019] For the target clustering cluster, use the ratio of the number of feature keywords belonging to the target clustering cluster among the feature keywords extracted from the user association data of the target user to the number of feature keywords extracted from the user association data of the target user as the interest value of the target user for the target clustering cluster.
[0020] Combined with any one of the embodiments provided in the present disclosure, the method further includes:
[0021] Based on the customer mining rules preset by the target user, determine the potential transaction customers corresponding to the user portrait of the target user.
[0022] According to the second aspect of the present disclosure, a user portrait construction device is proposed. The device includes:
[0023] An acquisition module, configured to acquire user association data of a target user;
[0024] A feature extraction module, configured to perform a feature extraction operation on the user association data to obtain at least one feature keyword corresponding to the target user;
[0025] A construction module, configured to construct a user portrait of the target user based on the at least one feature keyword.
[0026] According to the third aspect of the present disclosure, a computer-readable storage medium is provided. The machine-readable storage medium stores machine-readable instructions, and when the machine-readable instructions are called and executed by a processor, the processor is caused to implement the user portrait construction method of any embodiment of the present disclosure.
[0027] According to the fourth aspect of the present disclosure, an electronic device is provided, including
[0028] A processor;
[0029] A memory for storing processor-executable instructions;
[0030] Wherein, the processor is configured to execute the user profile construction method of any embodiment of the present disclosure.
[0031] The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects:
[0032] In the user profile construction method, device, storage medium, and electronic device provided by the embodiments of the present disclosure, after obtaining the user association data of the target user, a feature extraction operation may be performed on the user association data to obtain at least one feature keyword corresponding to the target user. Then, based on the at least one feature keyword, a user profile of the target user may be constructed. Compared with the related technical solutions that use machine learning to construct a user profile, the process is greatly simplified and the time-consuming of manual processing is reduced.
[0033] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present disclosure and used together with the specification to explain the principles of the present disclosure.
[0035] Figure 1 is a flowchart of a user profile construction method shown according to an exemplary embodiment of the present disclosure;
[0036] Figure 2 is a flowchart of another user profile construction method shown according to an exemplary embodiment of the present disclosure;
[0037] Figure 3 is a diagram of a hierarchical clustering result shown according to an exemplary embodiment of the present disclosure;
[0038] Figure 4 is a flowchart of another user profile construction method shown according to an exemplary embodiment of the present disclosure;
[0039] Figure 5 is a schematic structural diagram of a user profile construction device shown according to an exemplary embodiment of the present disclosure;
[0040] Figure 6 is a schematic structural diagram of an electronic device shown according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0041] Exemplary embodiments will be described in detail herein, and examples thereof are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are merely examples of apparatuses and methods consistent with some aspects of the present disclosure as detailed in the appended claims.
[0042] The terms used in this disclosure are for the purpose of describing particular embodiments only and are not intended to limit the present disclosure. The singular forms "a", "the", and "said" used in this disclosure and the appended claims are also intended to include the plural forms unless the context clearly dictates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
[0043] It should be understood that although the terms first, second, third, etc. may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present disclosure, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".
[0044] A user profile refers to a way of depicting and summarizing the characteristics, interests, etc. of a specific user. The purpose of constructing a user profile is to better understand and gain insights into users, so as to provide more personalized and accurate products or services.
[0045] In related technical solutions, machine learning is mostly used to construct user profiles. When using this method, a large amount of training data of user profiles of already labeled users is required to train the model so that it can output the user profile of the target user according to the input data related to the target user.
[0046] Since the model used in the above method needs to be obtained by learning and training a large amount of data, it takes a long time.
[0047] In view of this, an embodiment of the present disclosure provides a method for constructing a user profile. The method for constructing a user profile provided by the embodiment of the present disclosure will be described in detail below with reference to the accompanying drawings.
[0048] Figure 1 is a flowchart of a method for constructing a user profile according to an exemplary embodiment of the present disclosure. As Figure 1 shown, the method of this exemplary embodiment may include the following steps:
[0049] In step 101, obtain the user-related data of the target user.
[0050] Among them, the target user can be an individual or an enterprise, which is specifically determined based on the actual situation, and the present disclosure does not limit this.
[0051] When the target user is an individual, through the user portrait construction method of this example, a user portrait for the individual can be constructed, so as to provide more personalized and accurate products or services for this user. When the target user is an enterprise, through the user portrait construction method of this example, a user portrait for the enterprise can be constructed, so as to mine potential customers interested in the enterprise's products for this enterprise.
[0052] The user-related data is data related to the target user. When the target user is an individual, the user-related data of this target user may include the article content viewed by this user within a preset time period, the theme content included in the websites browsed, etc. When the target user is an enterprise, the user-related data of this target user may include the product introductions of the products produced by the enterprise within a preset time period, the brief introduction of the enterprise, relevant reports released for this enterprise, etc.
[0053] In this example, the user-related data of the above-mentioned target user can be obtained through multiple channels. For example, the user-related data of the target user can be obtained through channels such as Google Search, LinkedIn, and customs data. Or, the data related to the target user uploaded and received can be used as the user-related data of the above-mentioned target user. The present disclosure does not limit the manner of obtaining the user-related data of the target user.
[0054] Optionally, after obtaining the user-related data of the target user, the user-related data can be subjected to data cleaning to ensure the quality, consistency, and availability of the user-related data, and improve the accuracy and credibility of the user-related data.
[0055] During the data cleaning process, it may include but is not limited to the following operations: removing duplicate data, handling missing values, correcting incorrect data, adjusting formats, and standardizing data, etc.
[0056] In step 102, perform a feature extraction operation on the user-related data to obtain at least one feature keyword corresponding to the target user.
[0057] After obtaining the user-related data of an individual or an enterprise, a feature extraction operation can be performed on this user-related data, so as to obtain at least one feature keyword corresponding to this individual or enterprise.
[0058] In an optional example, the user - associated data of the target user can be feature - extracted by the following method:
[0059] For each target word in the user - associated data, calculate the relevance between the target word and the user - associated data. Then, determine the target words corresponding to the relevance greater than the preset threshold as the feature keywords.
[0060] Specifically, the method of this example can calculate the relevance between the target word and the user - associated data using the following formula (1):
[0061]
[0062] where i represents the target word, n i represents the number of times the target word i appears in the user - associated data, M represents the number of texts obtained by splitting the user - associated data into multiple texts, sum represents the total number of words in the user - associated data, and p j represents the relevance between the target word and the user - associated data.
[0063] When actually calculating the relevance between the target word and the user - associated data, the values of the parameters n i 、M、sum in formula (1) are all known, and substituting them into the above formula can calculate the relevance between the target word and the user - associated data.
[0064] For example, the obtained user - associated data may include:
[0065] As I walked through the orchard,I couldn't help but notice thevibrant red apples hanging from the branches.The crisp scent of apples filledthe air,and I eagerly plucked a juicy Apple,savoring the sweet and refreshingtaste。
[0066] After the text paragraph is split, we get:
[0067] M1: As I walked through the orchard
[0068] M2: I couldn't help but notice the vibrant red apples hanging from thebranches
[0069] M3: The crisp scent of apples filled the air
[0070] M4: and I eagerly plucked a juicy Apple
[0071] M5: savoring the sweet and refreshing taste
[0072] When calculating the relevance between the target word "apples" and the above-mentioned user-related data, it can be obtained that: n i = 3, M = 5, sum = 56. Substituting the above parameters into the foregoing formula (1), the relevance between the target word "apples" and the above-mentioned user-related data can be calculated to be 0.55.
[0073] Similarly, the relevance between each target word in the user-related data and the user-related data can be calculated. Then, the target words corresponding to the relevance greater than a preset threshold, such as greater than 0.52, are determined as the foregoing characteristic keywords. Alternatively, the target words corresponding to the highest relevance, or the target words corresponding to the top x relevances after sorting the relevances from high to low, can also be determined as the foregoing characteristic keywords.
[0074] It should be noted that the foregoing takes calculating the relevance between the target word and the user-related data using formula (1) and then determining the characteristic keywords based on the calculated relevance as an example for introduction. In practical applications, other feature extraction methods can also be used to extract features from the obtained user-related data, and then the corresponding characteristic keywords can be obtained. The present disclosure does not limit the feature extraction method.
[0075] In an optional example, the relevance between the target word and the user-related data is positively correlated with the number of times the target word appears in the user-related data.
[0076] That is to say, when the number of times the target word appears in the user-related data is more, the relevance between the target word and the user-related data is higher. When the number of times the target word appears in the user-related data is less, the relevance between the target word and the user-related data is lower.
[0077] In step 103, based on the at least one characteristic keyword, a user portrait of the target user is constructed.
[0078] Exemplarily, the foregoing characteristic keywords can be used as labels of the target user, and a user portrait of the target user can be constructed.
[0079] In the user profile construction method provided by the embodiments of the present disclosure, after obtaining the user association data of the target user, feature extraction operations may be performed on the user association data to obtain at least one feature keyword corresponding to the target user. Then, based on the at least one feature keyword, a user profile of the target user may be constructed. Compared with the related technical solutions that use machine learning to construct user profiles, the process is greatly simplified and the time-consuming for manual processing is reduced.
[0080] In an alternative example, as Figure 2 shown, step 103 above may specifically include:
[0081] In step 201, clustering operations are performed on the feature keywords that meet the preset similarity condition among the at least one feature keyword to obtain at least one clustering cluster.
[0082] After obtaining the at least one feature keyword, hierarchical clustering may be performed on the at least one feature keyword based on the hierarchical clustering algorithm.
[0083] Exemplarily, as Figure 3 shown, it is a hierarchical clustering result graph obtained based on the hierarchical clustering algorithm. Among them, the left side of the image is the aforementioned at least one feature keyword, and the horizontal axis above the image represents the similarity.
[0084] For example, when selecting a similarity of 0.4 as the splitting point, 24 clustering clusters can be obtained. When selecting a similarity of 0.1 as the splitting point, 12 clustering clusters can be obtained. In practical applications, relevant staff may select an appropriate similarity based on the actual situation.
[0085] For ease of understanding, the introduction is made with a similarity of 0.4 as the splitting point.
[0086] As Figure 3 , at this time, the feature keyword 1 Fed keeps interest rates steady and the feature keyword 2 Fedkeeps interest rates steady are the feature keywords that meet the aforementioned preset similarity condition, and clustering operations may be performed on the above two feature keywords to obtain the clustering cluster 1. Similarly, the feature keyword 3 Fed holds interestrates steady and the feature keyword 4 Fed to keep interest rates steady are the feature keywords that meet the aforementioned preset similarity condition, and clustering operations may be performed on the above two feature keywords to obtain the clustering cluster 2. The clustering operations performed on other feature keywords that meet the preset similarity condition are similar to the foregoing and will not be elaborated here.
[0087] In step 202, the interest values of the target user for the at least one clustering cluster are calculated respectively.
[0088] After performing a clustering operation on the feature keywords that meet the preset similarity condition among the at least one feature keyword to obtain at least one clustering cluster, the interest values of the target user for the at least one clustering cluster can be calculated respectively.
[0089] Taking the calculation of the interest value of the target user for the target clustering cluster as an example:
[0090] For the target clustering cluster, the ratio of the number of feature keywords belonging to the target clustering cluster among the feature keywords extracted from the user association data of the target user to the number of feature keywords extracted from the user association data of the target user can be used as the interest value of the target user for the target clustering cluster.
[0091] Exemplarily, the above relationship can be expressed by the following formula (2):
[0092]
[0093] In step 203, the clustering cluster corresponding to the interest value that meets the preset interest value condition is determined as the target clustering cluster.
[0094] After calculating the interest values of the target user for the at least one clustering cluster respectively, the clustering cluster corresponding to the interest value that meets the preset interest value condition can be further determined as the target clustering cluster.
[0095] Among them, the preset interest value condition can be: after arranging the calculated interest values in descending order, they are in the top preset positions, for example, in the top 3 positions or the top 1 position.
[0096] Taking the preset interest value condition as the interest value that is in the top 1 position after arranging the calculated interest values in descending order as an example. In this example, the clustering cluster corresponding to the highest calculated interest value can be determined as the target clustering cluster.
[0097] In step 204, based on the feature keywords included in the target clustering cluster, a user portrait of the target user is constructed.
[0098] After determining the target clustering cluster, a user portrait of the target user can be constructed based on the feature keywords included in the target clustering cluster.
[0099] As shown in Table 1 below, it is an example of user portraits for multiple users constructed based on the foregoing user portrait construction method:
[0100] Table 1
[0101] User ID Feature keywords 001 Technology enthusiasts, Artificial Intelligence 002 Food lovers, Cooking 003 Health pursuers, Sports 004 Travel lovers, Travel 005 Literature pursuers, Reading
[0102] Further, based on the foregoing characteristic keywords, the main fields and industries related to each user can be further analyzed to obtain user portraits of multiple users as shown in Table 2 below:
[0103] Table 2
[0104]
[0105] In the user portrait construction method provided by the embodiments of the present disclosure, after obtaining at least one characteristic keyword, hierarchical clustering can be performed on the at least one characteristic keyword based on the hierarchical clustering algorithm to obtain at least one clustering cluster. Then, the interest values of the target user for the at least one clustering cluster are calculated respectively, and the clustering cluster corresponding to the interest value that meets the preset interest value condition is determined as the target clustering cluster. Finally, based on the characteristic keywords included in the target clustering cluster, the user portrait of the target user is constructed. Compared with the related technical solutions that use machine learning to construct user portraits, the process is greatly simplified and the time-consuming of manual processing is reduced.
[0106] After constructing a user portrait for an individual based on the foregoing user portrait construction method, more personalized and accurate products or services can be provided for the user based on this user portrait. After constructing a user portrait for an enterprise based on the foregoing user portrait construction method, potential customers interested in the products of the enterprise can be mined for the enterprise based on this user portrait.
[0107] Taking the construction of a user portrait for an enterprise as an example, in this example, as Figure 4 shown, on the basis of the user portrait construction method shown in Figure 1 the user portrait construction method may further include:
[0108] In step 401, based on the customer mining rules preset by the target user, the intended transaction customers corresponding to the user portrait of the target user are determined.
[0109] Among them, the preset customer mining rules may be as shown in Table 3 below:
[0110] Table 3
[0111] User ID Lead mining Convert lead pool EDM inquiry Convert customers 001 500 per day Convert immediately Full - volume email inquiry Reply email conversion 002 100 per day Convert when conditions are met Full - volume email inquiry Correspondence email conversion 003 1000 per day Convert immediately Full - volume email inquiry Open email conversion 004 800 per day Convert and label Full - volume email inquiry Correspondence email conversion 005 1000 per day Convert when conditions are met Labeled email inquiry Correspondence email conversion
[0112] After constructing the user portrait of the target user based on the foregoing user portrait construction method, the intended transaction customers of the target user can be determined based on the customer mining rules preset by the target user.
[0113] Taking the target user as User 001 as an example, based on the aforementioned customer mining rules, 500 customer leads related to technology enthusiasts and artificial intelligence can be mined for this user every day. After mining the customer leads, the customer leads are converted into a conversion lead pool. Then, when certain time conditions are met, EDM (Email Direct Marketing) emails are sent to the customers in the conversion lead pool. After receiving the reply emails from the customers based on the EDM emails, it is determined that these customers are the intended transaction customers corresponding to the user portrait of the target user.
[0114] For example, if User 001 is an enterprise selling robots, and the aforementioned mined customer leads are the customer leads of customers who love technology and artificial intelligence. At this time, the method of this example can also send EDM emails to these customers, and after detecting that the customers reply to the EDM emails, it is determined that these customers are the intended transaction customers corresponding to the user portrait of the target user, that is, these customers are customers who are likely to be willing to buy robots.
[0115] Furthermore, the customer leads of the intended transaction customers can be sent to User 001 so that User 001 can perform subsequent operations based on these customer leads, such as contacting the customer by phone, providing a more detailed product introduction to the customer, further promoting sales, etc.
[0116] In the user portrait construction method provided by the embodiments of the present disclosure, after constructing the user portrait for the target user, the intended transaction customers corresponding to the user portrait of the target user can also be determined based on the customer mining rules preset by the target user. Thus, effective business opportunities can be refined for the target user, achieving the effect of automatically determining the intended transaction customers for the target user and automatically determining the customers who can conduct transactions for the target user.
[0117] For the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present disclosure is not limited by the described action sequence, because according to the present disclosure, some steps can be performed in other sequences or simultaneously.
[0118] Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to the present disclosure.
[0119] Corresponding to the foregoing method embodiments for realizing application functions, the present disclosure also provides embodiments of an apparatus for realizing application functions and a corresponding terminal.
[0120] Figure 5 It is a schematic structural diagram of a user portrait construction apparatus shown by the present disclosure according to an exemplary embodiment, as Figure 5As shown, the user profile construction device may include:
[0121] An acquisition module 51, configured to acquire user association data of a target user.
[0122] A feature extraction module 52, configured to perform a feature extraction operation on the user association data to obtain at least one feature keyword corresponding to the target user.
[0123] A construction module 53, configured to construct a user profile of the target user based on the at least one feature keyword.
[0124] Optionally, when the feature extraction module 52 is configured to perform a feature extraction operation on the user association data to obtain at least one feature keyword corresponding to the target user, it includes:
[0125] For each target word in the user association data, calculate the relevance between the target word and the user association data.
[0126] Determine the target words corresponding to the relevance greater than a preset threshold as the feature keywords.
[0127] Optionally, the relevance between the target word and the user association data is positively correlated with the number of times the target word appears in the user association data.
[0128] Optionally, when the construction module 53 is configured to construct a user profile of the target user based on the at least one feature keyword, it includes:
[0129] Perform a clustering operation on the feature keywords that meet the preset similarity condition among the at least one feature keyword to obtain at least one clustering cluster.
[0130] Calculate the interest values of the target user for the at least one clustering cluster respectively.
[0131] Determine the clustering cluster corresponding to the interest value that meets the preset interest value condition as the target clustering cluster.
[0132] Construct a user profile of the target user based on the feature keywords included in the target clustering cluster.
[0133] Optionally, when the construction module 53 is configured to calculate the interest values of the target user for the at least one clustering cluster respectively, it includes:
[0134] For the target clustering cluster, use the ratio of the number of feature keywords belonging to the target clustering cluster among the feature keywords extracted from the user association data of the target user to the number of feature keywords extracted from the user association data of the target user as the interest value of the target user for the target clustering cluster.
[0135] Optionally, based on the Figure 5 shown modules, the user profile construction device may further include:
[0136] A customer determination module, configured to determine potential transaction customers corresponding to the user profile of the target user based on the customer mining rules preset by the target user.
[0137] For the apparatus embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial descriptions of the method embodiments. The apparatus embodiments described above are only illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present disclosure solution. Those of ordinary skill in the art can understand and implement it without creative efforts.
[0138] Figure 6 is a schematic structural diagram of an electronic device 600 shown according to an exemplary embodiment.
[0139] Referring to Figure 6 , the electronic device 600 may include one or more of the following components: a processing component 602, a memory 604, a power component 606, a multimedia component 608, an audio component 610, an input / output (I / O) interface 612, a sensor component 614, and a communication component 616.
[0140] The processing component 602 generally controls the overall operation of the electronic device 600, such as operations associated with display, telephone call, data communication, camera operation, and recording operation. The processing component 602 may include one or more processors 620 to execute instructions to complete all or part of the steps of the above method. In addition, the processing component 602 may include one or more modules to facilitate the interaction between the processing component 602 and other components. For example, the processing component 602 may include a multimedia module to facilitate the interaction between the multimedia component 608 and the processing component 602.
[0141] The memory 604 is configured to store various types of data to support the operation of the device 600. Examples of such data include instructions for any application or method operating on the electronic device 600, contact data, phone book data, messages, pictures, videos, and the like. The memory 604 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disk.
[0142] The power supply component 606 provides power to various components of the electronic device 600. The power supply component 606 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 600.
[0143] The multimedia component 608 includes a screen that provides an output interface between the above-mentioned electronic device 600 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The above-mentioned touch sensors can not only sense the boundaries of touch or swipe actions, but also detect the duration and pressure associated with the above-mentioned touch or swipe operations. In some embodiments, the multimedia component 608 includes a front camera and / or a rear camera. When the electronic device 600 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each of the front camera and the rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.
[0144] The audio component 610 is configured to output and / or input audio signals. For example, the audio component 610 includes a microphone (MIC) that is configured to receive external audio signals when the electronic device 600 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals can be further stored in the memory 604 or transmitted via the communication component 616. In some embodiments, the audio component 610 further includes a speaker for outputting audio signals.
[0145] The I / O interface 612 provides an interface between the processing component 602 and a peripheral interface module, and the above-mentioned peripheral interface module can be a keyboard, a click wheel, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.
[0146] The sensor assembly 614 includes one or more sensors for providing status assessment of various aspects for the electronic device 600. For example, the sensor assembly 614 can detect the on / off state of the electronic device 600, the relative positioning of components, such as the display and keypad of the electronic device 600 as described above. The sensor assembly 614 can also detect a change in the position of the electronic device 600 or a component of the electronic device 600, the presence or absence of user contact with the electronic device 600, the orientation or acceleration / deceleration of the electronic device 600, and the temperature change of the electronic device 600. The sensor assembly 614 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 614 can also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 614 can also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
[0147] The communication component 616 is configured to facilitate communication between the electronic device 600 and other devices in a wired or wireless manner. The electronic device 600 can access a wireless network based on communication standards, such as WiFi, 4G or 5G, 4G LTE, 5G NR, or a combination thereof. In an exemplary embodiment, the communication component 616 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 616 further includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
[0148] In an exemplary embodiment, the electronic device 600 can be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the above method.
[0149] In an exemplary embodiment, a non-transitory computer-readable storage medium is also provided, such as a memory 604 including instructions, which when executed by a processor 620 of the electronic device 600, enables the electronic device 600 to perform the following user profile building method:
[0150] Obtain user-associated data of a target user.
[0151] Perform a feature extraction operation on the user-associated data to obtain at least one feature keyword corresponding to the target user.
[0152] Construct a user profile of the target user based on the at least one feature keyword.
[0153] The non-transitory computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.
[0154] Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not disclosed herein. The specification and examples are only to be considered as exemplary, and the true scope and spirit of the present disclosure are pointed out by the following claims.
[0155] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.
Claims
1. A method for constructing a user profile, characterized in that, The method includes: Obtaining user - associated data of a target user; Performing a feature extraction operation on the user - associated data to obtain at least one feature keyword corresponding to the target user; Constructing a user profile of the target user based on the at least one feature keyword.
2. The method according to claim 1, characterized in that, The performing a feature extraction operation on the user - associated data to obtain at least one feature keyword corresponding to the target user includes: For each target word in the user - associated data, calculating the relevance of the target word to the user - associated data; Determining the target word corresponding to the relevance greater than a preset threshold as the feature keyword.
3. The method according to claim 2, wherein, The relevance of the target word to the user - associated data is positively correlated with the number of times the target word appears in the user - associated data.
4. The method according to claim 1, wherein The constructing a user profile of the target user based on the at least one feature keyword includes: Performing a clustering operation on the feature keywords that meet a preset similarity condition among the at least one feature keyword to obtain at least one clustering cluster; Calculating the interest value of the target user for the at least one clustering cluster respectively; Determining the clustering cluster corresponding to the interest value that meets a preset interest - value condition as the target clustering cluster; Constructing a user profile of the target user based on the feature keywords included in the target clustering cluster.
5. The method according to claim 4, characterized in that, The calculating the interest value of the target user for the at least one clustering cluster respectively includes: For a target clustering cluster, taking the ratio of the number of feature keywords belonging to the target clustering cluster among the feature keywords extracted from the user - associated data of the target user to the number of feature keywords extracted from the user - associated data of the target user as the interest value of the target user for the target clustering cluster.
6. The method according to claim 1, wherein The method further includes: Based on the customer - mining rules preset by the target user, determining the intended transaction customers corresponding to the user profile of the target user.
7. A user portrait construction device, characterized in that, The device includes: An obtaining module, configured to obtain user - associated data of a target user; A feature extraction module, configured to perform a feature extraction operation on the user - associated data to obtain at least one feature keyword corresponding to the target user; A constructing module, configured to construct a user profile of the target user based on the at least one feature keyword.
8. The device according to claim 7, characterized in that, When the feature extraction module is used to perform a feature extraction operation on the user - associated data to obtain at least one feature keyword corresponding to the target user, it includes: For each target word in the user - associated data, calculating the relevance of the target word to the user - associated data; Determining the target word corresponding to the relevance greater than a preset threshold as the feature keyword.
9. A computer - readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the steps of the method according to any one of claims 1 - 6.
10. An electronic device, including: A processor; A memory for storing instructions executable by the processor; Wherein, the processor is configured to execute the steps of the method according to any one of claims 1 - 6.