A method, device and system for constructing a customer resource library and a storage medium

Abstract

The application discloses a kind of construction method, device, system and storage medium of customer resource library.The method comprises the following steps: receiving the first feedback form sent by first user client;Wherein, first feedback form contains first user profile and first feedback questionnaire;Receive the second feedback form sent by the second user client matched with the first user client;Wherein, second feedback form contains second user profile and second feedback questionnaire;According to first feedback questionnaire and second feedback questionnaire, determine the consumption opinion difference result, and according to the consumption opinion difference result, determine the profile quality attribute value;First user profile, second user profile and profile quality attribute value are stored in the customer resource library corresponding to target advertisement object, and the embodiment enables the advertisement platform to have the ability of profile quality dimension labeling classification to user profile.

Description

Technical Field

[0001] This invention relates to the field of Internet technology, and in particular to a method, apparatus, system and storage medium for constructing a customer resource database. Background Technology

[0002] Lead advertising is a form of advertising that helps marketing categories such as home furnishing, automobiles, and healthcare, which have the characteristics of online customer acquisition and offline sales conversion, acquire customer resources. Unlike common advertising types, lead advertising obtains user information by providing consumers with lead forms, so that merchants can contact high-intent consumers and increase sales volume.

[0003] In the process of realizing this invention, at least the following technical problems were found in the prior art:

[0004] For high-value items or services, merchants usually incur higher marketing costs. Therefore, merchants have high requirements for the quality of the user data they acquire. However, traditional advertising platforms do not have the ability to label and classify the user data acquired through lead generation advertising based on data quality dimensions. Summary of the Invention

[0005] This invention provides a method, apparatus, system, and storage medium for constructing a customer resource database, addressing the problem that traditional advertising platforms lack the ability to label and classify user data based on data quality dimensions. It provides data support for advertising platforms to classify user data based on data quality dimensions, thereby improving the matching degree between user data and merchant needs.

[0006] According to an embodiment of the present invention, a method for constructing a customer resource database is provided, the method comprising:

[0007] Receive a first feedback form sent by a first user client; wherein the first feedback form contains first user information and a first feedback questionnaire, and the first feedback questionnaire represents the first user's consumption opinion on the target advertising object;

[0008] Receive a second feedback form sent by a second user client that matches the first user client; wherein the second feedback form contains second user information and a second feedback questionnaire, and the second feedback questionnaire represents the second user's consumption opinion on the target advertising object;

[0009] Based on the first and second feedback questionnaires, the results of the differences in consumer opinions are determined, and based on the results of the differences in consumer opinions, the data quality attribute values ​​are determined;

[0010] The first user data, the second user data, and the data quality attribute values ​​are stored in the customer resource library corresponding to the target advertising object.

[0011] According to another embodiment of the present invention, a customer resource database construction apparatus is provided, the apparatus comprising:

[0012] The first feedback form receiving module is used to receive a first feedback form sent by a first user client; wherein, the first feedback form includes first user information and a first feedback questionnaire, and the first feedback questionnaire represents the first user's consumption opinion on the target advertising object;

[0013] The second feedback form receiving module is used to receive a second feedback form sent by a second user client that matches the first user client; wherein, the second feedback form contains second user information and a second feedback questionnaire, and the second feedback questionnaire represents the second user's consumption opinion on the target advertising object;

[0014] The data quality attribute value determination module is used to determine the consumer opinion difference results based on the first feedback questionnaire and the second feedback questionnaire, and to determine the data quality attribute value based on the consumer opinion difference results.

[0015] The user data storage module is used to store the first user data, the second user data, and the data quality attribute values ​​into the customer resource library corresponding to the target advertising object.

[0016] According to another embodiment of the present invention, a customer resource database construction system is provided, the construction system comprising: an advertising platform, a matching first user client, and a second user client;

[0017] The first user client is used to send a first feedback form to the advertising platform; wherein the first feedback form includes first user information and a first feedback questionnaire, and the first feedback questionnaire represents the first user's consumption opinion on the target advertising object;

[0018] The second user client is used to send the second feedback form to the advertising platform; wherein the second feedback form contains second user information and a second feedback questionnaire, and the second feedback questionnaire represents the second user's consumption opinion on the target advertising object;

[0019] The advertising platform includes: at least one processor, and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to execute the customer resource database construction method according to any embodiment of the present invention.

[0020] According to another embodiment of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the client resource library construction method according to any embodiment of the present invention.

[0021] The technical solution of this invention collects a first feedback form sent by a first user client and a second feedback form sent by a second user client matched with the first user client. Based on the first feedback questionnaire in the first feedback form and the second feedback questionnaire in the second feedback form, the difference in consumer opinions is determined. The first user data in the first feedback form, the second user data in the second feedback form, and the data quality attribute values ​​are stored in the customer resource library corresponding to the target advertising object. This embodiment achieves the purpose of labeling the quality attributes of the collected user data from the dimension of the difference in consumer opinions of multiple users regarding the target advertising object. It solves the problem that traditional advertising platforms do not have the ability to label and classify user data according to the data quality dimension, improves the matching degree between user data and merchant needs, and provides data support for merchants to formulate marketing strategies based on user data.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 A flowchart illustrating a method for constructing a customer resource database according to an embodiment of the present invention;

[0025] Figure 2 A flowchart illustrating another method for constructing a customer resource library according to an embodiment of the present invention;

[0026] Figure 3 A flowchart illustrating another method for constructing a customer resource library according to an embodiment of the present invention;

[0027] Figure 4 This is a schematic diagram of a customer resource database construction device provided in one embodiment of the present invention;

[0028] Figure 5This is a schematic diagram of the structure of a customer resource database construction system provided in one embodiment of the present invention;

[0029] Figure 6 A timing diagram of a customer resource database construction system provided in one embodiment of the present invention;

[0030] Figure 7 This is a schematic diagram of the structure of an advertising platform provided in one embodiment of the present invention. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first," "second," "reference," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] Figure 1 This is a flowchart illustrating a method for constructing a customer resource database according to an embodiment of the present invention. This embodiment is applicable to situations where a customer resource database is constructed using lead generation advertising. The method can be executed by a customer resource database construction device, which can be implemented in hardware and / or software and can be configured within an advertising platform. Figure 1 As shown, the method includes:

[0034] S110, Receive the first feedback form sent by the first user client.

[0035] In this embodiment, the first feedback form includes first user information and a first feedback questionnaire. Specifically, the first user information includes user information filled in by the first user using the first user client on the user information form, and the first feedback questionnaire includes questionnaire information filled in by the first user on the first survey questionnaire. The first feedback questionnaire represents the first user's consumption opinion regarding the target advertising object.

[0036] Specifically, a user profile form is a front-end page used to promote a target audience and attract consumers to fill in their user information. For example, a user profile form can be generated by the merchant using MDF (Model-Driven Framework). The form includes, but is not limited to, elements such as a landing page URL, background image, and input fields. The input fields can be of various types, including input, selection, and dropdown. There are no restrictions on the generation method or content of the user profile form; specific settings can be customized according to actual needs.

[0037] Specifically, the first questionnaire is a survey used to investigate users' consumption opinions regarding a target advertising object. In one specific embodiment, the first questionnaire includes at least one business question and / or consensus question corresponding to the target advertising object. The business question is used to characterize issues related to the business of the target advertising object, such as "Do you have requirements for the interior space of your car?", and the consensus question is used to characterize issues that play a decisive role in consumption opinions, such as "In which of the following budget ranges do you have a budget for vehicle purchases?".

[0038] S120: Receive the second feedback form sent by the second user client that matches the first user client.

[0039] In one specific embodiment, if the first user and the second user are related by blood, then the client application used by the first user matches the client application used by the second user. For example, the kinship relationship can further include spousal relationship, parent-child relationship, and child-child relationship, etc.

[0040] In another specific embodiment, if the first user and the second user have a consumption binding relationship on their payment platforms, then the first user client used by the first user is matched with the second user client used by the second user.

[0041] It should be noted that the embodiments of the present invention are only illustrated by taking the second user client as an example. In other embodiments, a third user client or a fourth user client that matches the first user client may also be included. The number of user clients that match the first user client is not limited here.

[0042] In this embodiment, the second feedback form includes second user information and a second feedback questionnaire. Specifically, the second user information includes user information filled in by the second user using the second user client on the user information form, and the second feedback questionnaire includes questionnaire information filled in by the second user on the second survey questionnaire. The second feedback questionnaire represents the second user's consumption opinion regarding the target advertising object.

[0043] Specifically, the first and second questionnaires can be the same or different. For example, the first and second questionnaires can be created and sent by the merchant.

[0044] In one specific embodiment, the first questionnaire and the second questionnaire are the same. The method further includes: sending a user profile form and the first questionnaire to a first user client, so that the first user client responds to the detection of a form sharing instruction, obtains the sharing link in the form sharing instruction, and sends the user profile form and the first questionnaire to a second user client corresponding to the sharing link.

[0045] In another specific embodiment, the first questionnaire and the second questionnaire are different. The method further includes: sending a user profile form, the first questionnaire, and the second questionnaire to a first user client so that the first user client can output and display the user profile form and the first questionnaire; and in response to detecting a form sharing instruction, obtaining the sharing link in the form sharing instruction, and sending the user profile form and the second questionnaire to a second user client corresponding to the sharing link.

[0046] Based on the above embodiments, for example, the target advertising objects include, but are not limited to, stores, items, services and activities. The target advertising objects are not limited here, and can be customized according to actual needs.

[0047] In one specific embodiment, the target advertising object is an advertising object with high-value attributes. For example, the advertising object can be a car, and the high-value attribute can be a single purchase of more than 100,000 yuan or 200,000 yuan. The definition of high-value attributes is not limited here, and can be customized according to actual needs.

[0048] Because high-value ad targets typically require consensus among multiple users to make a purchase decision, this consensus leads to higher conversion rates. Targeting high-value ad targets also allows for a narrower reach of surveys, thereby improving the efficiency of user data collection.

[0049] S130. Based on the first and second feedback questionnaires, determine the results of the differences in consumer opinions, and based on the results of the differences in consumer opinions, determine the data quality attribute values.

[0050] Specifically, the consumer opinion difference result is used to characterize the differences in consumption opinions between the first user and the second user regarding the target advertising object. For example, the result type of the consumer opinion difference result can be a multi-category difference result or a binary difference result. The multi-category difference result can be a smooth difference score, such as 1-1000 points, or a stepped difference score, such as 1-5 points. The binary difference result indicates whether the consumer opinions are different or the consumer opinions are the same, such as 0 points or 1 point. The result type of the consumer opinion difference result is not limited here; it can be customized according to actual needs.

[0051] In one specific embodiment, determining the difference in consumer opinions based on the first and second feedback questionnaires includes: using a preset evaluation algorithm to determine the difference in consumer opinions based on the first and second feedback questionnaires. Exemplarily, the preset evaluation algorithm includes, but is not limited to, at least one of mathematical statistical algorithms, similarity algorithms, clustering analysis algorithms, and visualization analysis algorithms. The preset evaluation algorithm is not limited here and can be customized according to actual needs.

[0052] In another specific embodiment, determining the consumer opinion difference results based on the first feedback questionnaire and the second feedback questionnaire includes: performing questionnaire preprocessing on the first feedback questionnaire and the second feedback questionnaire respectively to obtain first preprocessed data and second preprocessed data; inputting the first preprocessed data and the second preprocessed data into a pre-trained target classification model respectively to obtain the output consumer opinion difference results.

[0053] For example, questionnaire preprocessing includes, but is not limited to, data cleaning and feature extraction. Taking the first feedback questionnaire as an example, feature extraction can be the extraction of feedback data related to key issues such as personal consumption preferences, product function requirements, and consumption budget from the first feedback questionnaire.

[0054] For example, the model architecture of the object classification model includes, but is not limited to, support vector machines, CNN (Convolutional Neural Networks), FCN (Fully Convolutional Networks), Residual Networks (ResNet), DNN (Deep Neural Networks), RNN (Recurrent Neural Networks), or Transformer networks, etc. The model architecture of the object classification model is not limited here, and can be customized according to actual needs.

[0055] Based on the above embodiments, specifically, the method further includes: inputting the training dataset into the untrained initial classification model to obtain the output prediction opinion difference results; calculating the loss function based on the prediction opinion difference results and the standard opinion difference results; adjusting the model parameters of the initial classification model according to the loss function until the loss function converges; and determining the target classification model based on the initial classification model.

[0056] Specifically, the training dataset contains at least one training data pair, and each training data pair contains questionnaire feedback data corresponding to two matched user clients.

[0057] For example, the loss function types include, but are not limited to, squared loss function, logarithmic loss function, exponential loss function, mean squared error loss function, logistic regression loss function, Huber loss function, cross-entropy loss function, or Kullback-Leibler divergence loss function, etc. The type of loss function is not limited here; it can be customized according to actual needs.

[0058] In one specific embodiment, determining the target classification model based on the initial classification model includes: using the initial classification model as the target classification model.

[0059] Based on the above embodiments, specifically, the method further includes: during the training process of the initial classification model, using a cross-validation algorithm to verify the model performance of the initial classification model during the training process, and / or using a regularization algorithm to adjust the model parameters of the initial classification model according to the loss function.

[0060] The advantage of setting up a cross-validation algorithm is that it can improve the generalization ability of the target classification model, while the advantage of using a regularization algorithm is that it can prevent the target classification model from overfitting.

[0061] In another specific embodiment, determining the target classification model based on the initial classification model includes: determining the model performance parameters corresponding to the initial classification model based on the validation dataset and the initial classification model; if the model performance parameters meet the preset performance conditions, using the initial classification model as the target classification model; if the model performance parameters do not meet the preset performance conditions, adjusting the hyperparameters of the initial classification model to obtain an updated initial classification model, and repeatedly executing the step of inputting the training dataset into the untrained initial classification model to obtain the output prediction opinion difference results.

[0062] Specifically, the validation dataset contains at least one validation data pair, and each validation data pair contains questionnaire feedback data corresponding to two matching user clients.

[0063] For example, model performance parameters include, but are not limited to, accuracy and F1 score, and the hyperparameters to be tuned include, but are not limited to, regularization parameters and learning rate, and the hyperparameter tuning algorithms include, but are not limited to, grid search algorithms and random search algorithms.

[0064] The advantage of this setup is that it can improve the performance of the target classification model, thereby increasing the accuracy of the consumer opinion difference results.

[0065] Specifically, the results of differences in consumer opinions are negatively correlated with the data quality attribute values. That is, the larger the difference score represented by the results of differences in consumer opinions, the smaller the data quality attribute value, and vice versa.

[0066] In one specific embodiment, determining the data quality attribute value based on the consumer opinion difference results includes: taking the difference between the maximum consumer difference score and the consumer difference score corresponding to the consumer opinion difference results as the data quality attribute value.

[0067] For example, when the difference score range of the consumer opinion difference results is [0 1000], the maximum consumer difference score is 1000; when the difference score range is [0 5], the maximum consumer difference score is 5; and when the difference score range is [0 1], the maximum consumer difference score is 1. For instance, assuming the maximum consumer difference score is 1000 and the corresponding consumer difference score is 400, the data quality attribute value is 600.

[0068] In another specific embodiment, determining the data quality attribute value based on the consumer opinion difference results includes: obtaining the target user consumption profile corresponding to the target user client; and determining the data quality attribute value based on the consumer opinion difference results and the target user consumption profile.

[0069] In this embodiment, the target user client includes a first user client and / or a second user client, and the target user consumption profile includes at least one of resource demand level, offline store visit probability, and form sharing probability.

[0070] In one embodiment, when the target user client includes a first user client and a second user client, the target consumption profile can be a statistical value between the first user consumption profile corresponding to the first user client and the second user consumption profile corresponding to the second user client. For example, the resource demand level in the target consumption profile can be the maximum or average of the resource demand levels in the first user consumption profile and the second user consumption profile, and the form sharing probability in the target consumption profile can be the maximum or average of the form sharing probability in the first user consumption profile and the second user consumption profile.

[0071] Specifically, the form sharing probability is used to characterize the probability of sharing a lead form between two matching user clients.

[0072] In one specific embodiment, determining data quality attribute values ​​based on the results of differences in consumer opinions and the target user's consumption profile includes: using a preset analysis algorithm to determine data quality attribute values ​​based on the results of differences in consumer opinions and the target user's consumption profile. For example, the preset analysis algorithm includes, but is not limited to, at least one of subtraction, averaging, weighted averaging, clustering, hypothesis testing, and machine learning algorithms. The preset analysis algorithm is not limited here and can be customized according to actual needs.

[0073] S140. Store the first user data, the second user data, and the data quality attribute values ​​into the customer resource database corresponding to the target advertising object.

[0074] For example, the database type of the customer resource database can be Oracle database, MySQL database, ACCESS database, and SQL (Structured Query Language) database, etc. There is no limitation on the database type of the customer resource database here, and the specific settings can be customized according to actual needs.

[0075] The technical solution of this embodiment collects a first feedback form sent by a first user client and a second feedback form sent by a second user client matched with the first user client. Based on the first feedback questionnaire in the first feedback form and the second feedback questionnaire in the second feedback form, the difference in consumer opinions is determined. The first user data in the first feedback form, the second user data in the second feedback form, and the data quality attribute values ​​are stored in the customer resource library corresponding to the target advertising object. This embodiment achieves the purpose of labeling the quality attributes of the collected user data from the dimension of the difference in consumer opinions of multiple users regarding the target advertising object. It solves the problem that traditional advertising platforms do not have the ability to label and classify user data according to the data quality dimension, improves the matching degree between user data and merchant needs, and also provides data support for merchants to formulate marketing strategies based on user data.

[0076] Figure 2 This is a flowchart illustrating another method for constructing a customer resource database according to an embodiment of the present invention. This embodiment further refines the method for constructing the customer resource database described in the above embodiment. For example... Figure 2 As shown, the method includes:

[0077] S210. Obtain the original lead form that matches the target advertising audience.

[0078] In this embodiment, the original lead form includes a user profile form, a first questionnaire, and a second questionnaire.

[0079] In one specific embodiment, obtaining an original lead form matching the target advertising object includes: receiving an original lead form matching the target advertising object sent by the merchant. For example, the first questionnaire and the second questionnaire may be the same or different.

[0080] In another specific embodiment, obtaining the original lead form matching the target advertising object includes: when the first questionnaire and the second questionnaire are the same, obtaining question category data corresponding to the target advertising object; wherein the question category data includes business question categories and / or consensus question categories; determining at least one target question based on at least one question category in the question category data; generating a target questionnaire based on each target question; wherein the target questionnaire is the first questionnaire or the second questionnaire.

[0081] Specifically, the business question category is used to characterize question categories related to the target advertising object's business. For example, the business question category includes at least one question category such as functional requirement category and geographical location category. For instance, the target question corresponding to the geographical location category could be "Do you accept vehicles and stores located in other cities?". In one specific embodiment, at least one question category in the business question category can be sent by the merchant. The question category sent by the merchant can characterize the target advertising object's special interest category, thereby improving the personalization level of the questionnaire.

[0082] Specifically, consensus question categories are used to characterize question categories that play a decisive role in consumer opinions. For example, consensus question categories include at least one question category such as budget category and personal preference category. For example, the target question corresponding to the personal preference category can be "Do you accept foreign-made vehicles?".

[0083] In another specific embodiment, obtaining the original lead form matching the target advertising object includes: when the first questionnaire and the second questionnaire are different, obtaining question category data corresponding to the target advertising object; wherein the question category data includes business question categories and / or consensus question categories; determining at least one matching question pair based on at least one question category in the question category data; wherein the matching question pair includes a first question and a second question; generating a first questionnaire based on at least one first question, and generating a second questionnaire based on at least one second question.

[0084] In this embodiment, the first question and the second question correspond to the same question object but different question description text. For example, the first question in the matching question pair is "What are your preferences for vehicle brands?", and the second question can be "Which of the following vehicle brands do you prefer?". In this example, the question object of both questions is vehicle brand, but the question description text is different.

[0085] In one specific embodiment, a first question in any question setting position of the first questionnaire and a second question in the same question setting position of the second questionnaire are not considered a matching question pair. For example, the question setting position can be used to characterize the display order of questions or the position of the questionnaire text. For instance, the first question displayed in the first questionnaire might be "What are your preferences for vehicle brands?", while the first question displayed in the second questionnaire might be "What are your preferences for vehicle comfort?". In this example, the question subjects and question description texts of the two questions are different.

[0086] Based on the above embodiments, for example, the target question or matching question pair can be generated by filtering from a question library that matches the question category, or it can be automatically generated by an artificial intelligence model. There is no limitation on the generation method of the target question or matching question pair here, and the specific settings can be customized according to actual needs.

[0087] By setting up different questionnaires, the possibility of the first user and the second user exchanging answers while filling out the first and second questionnaires respectively is reduced, thereby improving the accuracy of subsequent consumer opinion differences.

[0088] Based on the above embodiments, specifically, obtaining the original lead form matching the target advertising object further includes: in response to receiving the user information form corresponding to the target advertising object sent by the merchant, storing the user information form, the first questionnaire and the second questionnaire matching the target advertising object as the corresponding original lead form.

[0089] S220. Send the user information form and the first survey questionnaire as the first lead form to the first user client.

[0090] For example, the first user client may output and display the received first questionnaire, and after the first questionnaire is completed, output and display the user information form; or, the first user client may output and display the received user information form, and after the user information form is completed, output and display the first questionnaire.

[0091] S230. Send the user information form and the second questionnaire as a second lead form to the second user client.

[0092] In one specific embodiment, sending the user profile form and the second questionnaire as a second lead form to the second user client includes: using the user client used by the second user who has a kinship relationship and / or consumption binding relationship with the first user as the second user client, and sending the user profile form and the second questionnaire as a second lead form to the second user client.

[0093] In another specific embodiment, sending the user profile form and the second questionnaire as a second lead form to the second user client includes: in response to detecting a sharing request sent by the first user client, obtaining the sharing link in the sharing request; and sending the user profile form and the second questionnaire as a second lead form to the second user client corresponding to the sharing link.

[0094] For example, the first user client displays a sharing control in the display interface. In response to detecting the sharing instruction of the sharing control, the first user client generates a sharing request according to the sharing link in the sharing instruction and sends the sharing request to the advertising platform.

[0095] For example, the second user client may output and display the received second questionnaire, and output and display the user information form after the second questionnaire is completed; or, the second user client may output and display the received user information form, and output and display the second questionnaire after the user information form is completed.

[0096] S240, Receive the first feedback form sent by the first user client.

[0097] S250, Receive a second feedback form sent by a second user client that matches the first user client.

[0098] S260. Based on the first and second feedback questionnaires, determine the results of the differences in consumer opinions.

[0099] S270. Store the first user data, the second user data, and the data quality attribute values ​​into the customer resource database corresponding to the target advertising object.

[0100] S240-S270 in this embodiment are the same as those in the above embodiment. Figure 1 The S110-S140 shown are the same or similar, and will not be described again in this embodiment.

[0101] The technical solution of this embodiment obtains an original lead form that matches the target advertising object. The original lead form includes a user profile form, a first questionnaire, and a second questionnaire. The user profile form and the first questionnaire are sent as the first lead form to the first user client, and the user profile form and the second questionnaire are sent as the second lead form to the second user client. This solves the problem of pushing lead forms containing questionnaires. Furthermore, by setting two different questionnaires, the accuracy of the results of differences in consumer opinions is improved, thereby further improving the matching degree between user data and merchant needs.

[0102] Figure 3 This is a flowchart illustrating another method for constructing a customer resource database according to an embodiment of the present invention. This embodiment further refines the method for constructing a customer resource database as described in the above embodiment. Figure 3 As shown, the method includes:

[0103] S310. Obtain the original lead form that matches the target advertising audience.

[0104] S310 in this embodiment is the same as that in the above embodiment. Figure 2 The S210 shown is the same or similar, and will not be described again in this embodiment.

[0105] S320. Obtain the preset user profile corresponding to at least one reference user client.

[0106] For example, the preset user profile includes, but is not limited to, family situation, target consumption probability for the target advertising audience, interests, resource needs, family identity, and social identity.

[0107] In one specific embodiment, the preset user profile includes a target consumption probability for the target advertising object. Specifically, the target consumption probability is used to characterize the willingness of the reference user using the reference user's client to consume the target advertising object.

[0108] Based on the above embodiments, specifically, obtaining a preset user profile corresponding to at least one reference user client includes: obtaining reference user data corresponding to each reference user client; wherein, the reference user data includes user feature data and / or user behavior data corresponding to the target advertising object; inputting each reference user data into a pre-trained target user profile model to obtain the output target consumption probability of at least one reference user client for the target advertising object.

[0109] Specifically, user characteristic data is used to characterize feature data related to user identity attributes. For example, user characteristic data includes, but is not limited to, age, gender, place of residence, and occupation. Specifically, user behavior data is used to characterize the behavior data of a reference user on social media. For example, user behavior data includes, but is not limited to, search data, like data, browsing data, sharing data, and comment data targeting the advertising object. Search data may include search keywords and search frequency, while like data may include like frequency and functional attributes of liked videos or articles related to the target advertising object.

[0110] For example, the model type of the target user profile model includes, but is not limited to, support vector machine, CNN network, FCN network, residual network, DNN network, RNN network or Transformer network, etc. The model architecture of the target classification model is not limited here, and can be customized according to actual needs.

[0111] For example, the method further includes: inputting the training user data corresponding to the training user client into the untrained initial user profile model to obtain the output predicted consumption probability of the training user for the target advertising object; and adjusting the model parameters of the initial user profile model according to the standard consumption probability and predicted consumption probability of the training user for the target advertising object to obtain the trained target user profile model.

[0112] Based on the above embodiments, specifically, the method further includes: in response to detecting updated user data corresponding to the reference user client, inputting the updated user data into the target user profile model to obtain the output updated consumption probability of the reference user client for the target advertising object.

[0113] Based on the above embodiments, specifically, before inputting each reference user data into the pre-trained target user profile model to obtain the target consumption probability of at least one reference user client for the target advertising object, the method further includes: performing data preprocessing on at least one reference user data.

[0114] For example, data preprocessing includes, but is not limited to, removing duplicate data, handling missing values, data standardization, and feature encoding. Feature encoding can be the conversion of text content in the reference user data into a numerical representation. The data preprocessing described here is not limited; specific settings can be customized according to actual needs.

[0115] The advantage of this setup is that it improves the availability and consistency of reference user data.

[0116] S330. At least one reference user client whose preset user profile meets the preset profile conditions shall be designated as the first user client.

[0117] In this embodiment, when the preset user profile contains the target consumption probability, the preset profile condition contains the target consumption probability exceeding the preset probability threshold.

[0118] For example, the preset probability threshold can be 80% or 60%. There is no limitation on the preset probability threshold here. It can be customized according to actual needs.

[0119] S340. Send the user information form and the first survey questionnaire as the first lead form to the first user client.

[0120] S350. Send the user information form and the second questionnaire as a second lead form to the second user client.

[0121] S340-S350 in this embodiment are the same as those in the above embodiment. Figure 2The S220-S230 shown are the same or similar, and will not be described again in this embodiment.

[0122] S360 receives the first feedback form sent by the first user client.

[0123] S370, Receive a second feedback form sent by a second user client that matches the first user client.

[0124] S380. Based on the first and second feedback questionnaires, determine the results of the differences in consumer opinions.

[0125] S390. Store the first user data, the second user data, and the data quality attribute values ​​into the customer resource database corresponding to the target advertising object.

[0126] In this embodiment, S360-S390 correspond to or are similar to S110-S140 in the above embodiment, and will not be described again in this embodiment.

[0127] The technical solution of this embodiment obtains a preset user profile corresponding to at least one reference user client, and uses at least one reference user client whose preset user profile meets the preset profile conditions as the first user client. The preset user profile includes the target consumption probability for the target advertising object, and the preset profile conditions include the target consumption probability exceeding a preset probability threshold. This solves the problem of wasted push resources due to the excessive scope of user data collection and improves the efficiency of user data collection.

[0128] It should be noted that the collection, use, storage, sharing and transfer of user personal information involved in the technical solution of the present invention all comply with the provisions of relevant laws and regulations, and require notification to users and obtaining their consent or authorization. When applicable, user personal information is subjected to de-identification and / or anonymization and / or encryption technical processing.

[0129] The following are embodiments of the customer resource database construction apparatus provided in this invention. This apparatus and the customer resource database construction method described above belong to the same inventive concept. For details not described in detail in the embodiments of the customer resource database construction apparatus, please refer to the content of the customer resource database construction method in the above embodiments.

[0130] Figure 4 This is a schematic diagram of a customer resource database construction apparatus provided in one embodiment of the present invention. Figure 4 As shown, the device includes: a first feedback form receiving module 410, a second feedback form receiving module 420, a data quality attribute value determination module 430, and a user data storage module 440.

[0131] The first feedback form receiving module 410 is used to receive a first feedback form sent by a first user client; wherein the first feedback form contains first user information and a first feedback questionnaire, and the first feedback questionnaire represents the first user's consumption opinion on the target advertising object;

[0132] The second feedback form receiving module 420 is used to receive a second feedback form sent by a second user client that matches the first user client; wherein, the second feedback form contains second user information and a second feedback questionnaire, and the second feedback questionnaire represents the second user's consumption opinion on the target advertising object;

[0133] The data quality attribute value determination module 430 is used to determine the consumer opinion difference results based on the first feedback questionnaire and the second feedback questionnaire, and to determine the data quality attribute values ​​based on the consumer opinion difference results.

[0134] The user data storage module 440 is used to store the first user data, the second user data, and the data quality attribute values ​​into the customer resource library corresponding to the target advertising object.

[0135] The technical solution of this embodiment collects a first feedback form sent by a first user client and a second feedback form sent by a second user client matched with the first user client. Based on the first feedback questionnaire in the first feedback form and the second feedback questionnaire in the second feedback form, the difference in consumer opinions is determined. The first user data in the first feedback form, the second user data in the second feedback form, and the data quality attribute values ​​are stored in the customer resource library corresponding to the target advertising object. This embodiment achieves the purpose of labeling the quality attributes of the collected user data from the dimension of the difference in consumer opinions of multiple users regarding the target advertising object. It solves the problem that traditional advertising platforms do not have the ability to label and classify user data according to the data quality dimension, improves the matching degree between user data and merchant needs, and also provides data support for merchants to formulate marketing strategies based on user data.

[0136] In one specific embodiment, the data quality attribute value determination module 430 includes:

[0137] The consumer opinion difference result output unit is used to preprocess the first feedback questionnaire and the second feedback questionnaire respectively to obtain the first preprocessed data and the second preprocessed data.

[0138] The first and second preprocessed data are respectively input into the pre-trained target classification model to obtain the output results of consumer opinion differences.

[0139] In one specific embodiment, the data quality attribute value determination module 430 includes:

[0140] The data quality attribute value determination unit is used to obtain the target user consumption profile corresponding to the target user client.

[0141] Based on the results of differences in consumer opinions and the consumer profile of the target users, determine the data quality attribute values;

[0142] The target user client includes a first user client and / or a second user client, and the target user consumption profile includes at least one of the following: resource demand level, probability of offline in-store visit, and probability of form sharing.

[0143] In one specific embodiment, the method further includes:

[0144] The original lead form acquisition module is used to acquire original lead forms that match the target advertising audience; the original lead form includes a user profile form, a first questionnaire, and a second questionnaire.

[0145] The first questionnaire sending module is used to send the user information form and the first questionnaire as the first clue form to the first user client.

[0146] The second questionnaire sending module is used to send the user information form and the second questionnaire as a second lead form to the second user client.

[0147] In one specific embodiment, the original clue form acquisition module is specifically used for:

[0148] Obtain the issue category data corresponding to the target advertising object; wherein, the issue category data includes business issue categories and / or consensus issue categories;

[0149] Based on at least one question category in the question category data, determine at least one matching question pair; wherein the matching question pair contains a first question and a second question;

[0150] A first questionnaire is generated based on at least one first question, and a second questionnaire is generated based on at least one second question.

[0151] The first and second questions correspond to the same problem objects, but their problem description texts are different.

[0152] In one specific embodiment, a first question in a first questionnaire at any question setting location and a second question in a second questionnaire at the same question setting location are not considered a matching question pair.

[0153] In one specific embodiment, the second questionnaire sending module is specifically used for:

[0154] In response to detecting a sharing request sent by the first user client, obtain the sharing link in the sharing request;

[0155] The user profile form and the second survey questionnaire are sent as the second lead form to the second user client corresponding to the sharing link.

[0156] In one specific embodiment, the device further includes:

[0157] The first user client determination module is used to obtain at least one preset user profile corresponding to a reference user client before sending the user information form and the first questionnaire as the first clue form to the first user client.

[0158] Each of the following is designated as the first user client: At least one reference user client whose preset user profile meets the preset profile conditions.

[0159] Among them, the preset user profile includes the target consumption probability for the target advertising object, and the preset profile condition includes the target consumption probability exceeding the preset probability threshold.

[0160] In one specific embodiment, the first user client determining module is specifically used for:

[0161] Obtain the reference user data corresponding to each reference user client; wherein, the reference user data includes user characteristic data and / or user behavior data corresponding to the target advertising object;

[0162] Each reference user data is input into a pre-trained target user profile model to obtain the target consumption probability of at least one reference user client for the target advertising object.

[0163] The customer resource database construction apparatus provided in this embodiment of the invention can execute the customer resource database construction method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0164] Figure 5 This is a schematic diagram of the structure of a customer resource database construction system provided in one embodiment of the present invention, as shown below. Figure 5 As shown, the customer resource database construction system 500 includes an advertising platform 510, a matching first user client 520, and a second user client 530. The first user client 520 and the second user client 530 are communicatively connected to the advertising platform 510.

[0165] The first user client 520 is used to send the first feedback form to the advertising platform 510. The first feedback form contains the first user information and the first feedback questionnaire, which represents the first user's consumption opinion on the target advertising object.

[0166] In one specific embodiment, the first user client 520 is further configured to: output and display the user information form and the first questionnaire sent by the advertising platform 510.

[0167] In one specific embodiment, a communication connection is established between the first user client 520 and the second user client 530. Accordingly, the first user client 520 is further configured to: in response to detecting a sharing instruction from the sharing control, send the received user profile form and second questionnaire sent by the advertising platform 510 to the second user client 530.

[0168] In one specific embodiment, the first user client 520 is further configured to: in response to detecting a sharing instruction from a sharing control, generate a sharing request based on the sharing link in the sharing instruction, and send the sharing request to the advertising platform 510.

[0169] The second user client 530 is used to send the second feedback form to the advertising platform 510; wherein, the second feedback form contains the second user information and the second feedback questionnaire, and the second feedback questionnaire represents the second user's consumption opinion on the target advertising object.

[0170] In one specific embodiment, the second user client 530 is further configured to: output and display the user information form and the second questionnaire sent by the advertising platform 510.

[0171] Based on the above embodiments, specifically, the customer resource database construction system 500 also includes a merchant side, used to send user information forms to the advertising platform 510.

[0172] In one specific embodiment, the merchant's side is also used to send the first questionnaire and the second questionnaire to the advertising platform 510, or to send the business question category to the advertising platform 510.

[0173] Figure 6 This is a sequence diagram of a customer resource database construction system provided in one embodiment of the present invention. Specifically, the merchant sends a user profile form and a business question category to the advertising platform. The advertising platform generates a matching questionnaire based on the business question category and / or consensus question category. The matching questionnaire includes a first questionnaire and a second questionnaire. The user profile form and the matching questionnaire together constitute the original lead form.

[0174] The advertising platform sends the user profile form and the first survey questionnaire as the first lead form to the first user client. In response to receiving the sharing request from the first user client, it obtains the sharing link in the sharing request and sends the user profile form and the second survey questionnaire as the second lead form to the second user client corresponding to the sharing link. The advertising platform receives the first feedback form sent by the first user client and the second feedback form sent by the second user client. Based on the first feedback questionnaire and the second feedback questionnaire, it determines the consumer opinion difference result and, based on the consumer opinion difference result, determines the data quality attribute value. The first user data, the second user data, and the data quality attribute value are stored in the customer resource database corresponding to the target advertising object.

[0175] Figure 7 This is a schematic diagram of an advertising platform provided according to one embodiment of the present invention. The advertising platform 510 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), 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 invention described and / or claimed herein.

[0176] like Figure 7 As shown, the advertising platform 510 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor 11. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from the storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0177] Multiple components in the advertising platform 510 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, optical disk, etc.; and a communication unit 19, such as a network card, modem, wireless transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information or data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0178] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 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 processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the client resource library construction method provided in the above embodiments.

[0179] In some embodiments, the customer resource library construction method provided in the above embodiments can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the advertising platform 510 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the customer resource library construction method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to execute the customer resource library construction method by any other suitable means (e.g., by means of firmware).

[0180] Various embodiments of the systems and techniques described above herein can be implemented in the following systems or combinations thereof: digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), systems on chips (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.

[0181] Computer programs used to implement the method for constructing a customer resource library according to the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0182] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage 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. Alternatively, a computer-readable storage medium can be a machine-readable storage medium. Examples of machine-readable storage media include, based on an electrical connection of at least one wire, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0183] To provide interaction with a user, the systems and techniques described herein can be implemented on a terminal device having: a display device for displaying information to the user (e.g., a cathode-ray tube (CRT) or liquid crystal display (LCD) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the terminal device. Other types of devices can also 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).

[0184] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations 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 (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0185] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system. It addresses the shortcomings of traditional physical hosts and Virtual Private Server (VPS) services, such as high management difficulty and weak business scalability.

[0186] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0187] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. 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 invention should be included within the scope of protection of this invention.

Claims

1. A method for constructing a customer resource database, characterized in that, include: Receive a first feedback form sent by a first user client; wherein the first feedback form contains first user information and a first feedback questionnaire, and the first feedback questionnaire represents the first user's consumption opinion on the target advertising object; Receive a second feedback form sent by a second user client that matches the first user client; wherein the second feedback form contains second user information and a second feedback questionnaire, and the second feedback questionnaire represents the second user's consumption opinion on the target advertising object; Based on the first feedback questionnaire and the second feedback questionnaire, the results of the differences in consumer opinions are determined, and based on the results of the differences in consumer opinions, the data quality attribute values ​​are determined; The first user data, the second user data, and the data quality attribute values ​​are stored in the customer resource library corresponding to the target advertising object.

2. The method according to claim 1, characterized in that, The step of determining the difference in consumer opinions based on the first feedback questionnaire and the second feedback questionnaire includes: The first feedback questionnaire and the second feedback questionnaire are preprocessed to obtain first preprocessed data and second preprocessed data. The first preprocessed data and the second preprocessed data are respectively input into the pre-trained target classification model to obtain the output consumer opinion difference results.

3. The method according to claim 1, characterized in that, The step of determining data quality attribute values ​​based on the results of the differences in consumer opinions includes: Obtain the target user's consumption profile corresponding to the target user's client; Based on the results of the differences in consumer opinions and the target user's consumption profile, determine the data quality attribute values; The target user client includes the first user client and / or the second user client, and the target user consumption profile includes at least one of resource demand level, offline store visit probability and form sharing probability.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: Obtain the original lead form that matches the target advertising object; wherein the original lead form includes a user profile form, a first questionnaire, and a second questionnaire; The user profile form and the first questionnaire are sent as the first clue form to the first user client. The user profile form and the second questionnaire are sent as a second lead form to the second user client.

5. The method according to claim 4, characterized in that, The process of obtaining the original lead form that matches the target advertising object includes: Obtain the issue category data corresponding to the target advertising object; wherein, the issue category data includes business issue categories and / or consensus issue categories; Based on at least one question category in the question category data, at least one matching question pair is determined; wherein the matching question pair includes a first question and a second question; A first questionnaire is generated based on at least one first question, and a second questionnaire is generated based on at least one second question. The first question and the second question correspond to the same question object, but the question description text is different.

6. The method according to claim 5, characterized in that, The first question in any question setting position of the first questionnaire and the second question in the same question setting position of the second questionnaire do not belong to a matching question pair.

7. The method according to claim 4, characterized in that, Sending the user profile form and the second survey questionnaire as a second lead form to the second user client includes: In response to detecting a sharing request sent by the first user client, the sharing link in the sharing request is obtained; The user profile form and the second questionnaire are sent as a second lead form to the second user client corresponding to the sharing link.

8. The method according to claim 4, characterized in that, Before sending the user profile form and the first survey questionnaire as a first lead form to the first user client, the method further includes: Obtain at least one preset user profile corresponding to each reference user client; Each of the following is designated as the first user client: At least one reference user client whose preset user profile meets the preset profile conditions. The preset user profile includes a target consumption probability for the target advertising object, and the preset profile condition includes the target consumption probability exceeding a preset probability threshold.

9. The method according to claim 8, characterized in that, The step of obtaining the preset user profiles corresponding to at least one reference user client includes: Obtain reference user data corresponding to each of the reference user clients; wherein, the reference user data includes user feature data and / or user behavior data corresponding to the target advertising object; Each of the reference user data is input into a pre-trained target user profile model to obtain the target consumption probability of at least one reference user client for the target advertising object.

10. An apparatus for constructing a customer resource database, characterized in that, include: The first feedback form receiving module is used to receive a first feedback form sent by a first user client; wherein, the first feedback form includes first user information and a first feedback questionnaire, and the first feedback questionnaire represents the first user's consumption opinion on the target advertising object; The second feedback form receiving module is used to receive a second feedback form sent by a second user client that matches the first user client; wherein, the second feedback form contains second user information and a second feedback questionnaire, and the second feedback questionnaire represents the second user's consumption opinion on the target advertising object; The data quality attribute value determination module is used to determine the consumer opinion difference results based on the first feedback questionnaire and the second feedback questionnaire, and to determine the data quality attribute value based on the consumer opinion difference results. The user data storage module is used to store the first user data, the second user data, and the data quality attribute values ​​into the customer resource library corresponding to the target advertising object.

11. A system for constructing a customer resource database, characterized in that, The system includes: an advertising platform, a matching first user client, and a second user client; The first user client is used to send a first feedback form to the advertising platform; wherein the first feedback form includes first user information and a first feedback questionnaire, and the first feedback questionnaire represents the first user's consumption opinion on the target advertising object; The second user client is used to send the second feedback form to the advertising platform; wherein the second feedback form contains second user information and a second feedback questionnaire, and the second feedback questionnaire represents the second user's consumption opinion on the target advertising object; The advertising platform includes: at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method for constructing a customer resource database according to any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for constructing a client resource library as described in any one of claims 1-9.

Images