A NPL Information Push Method and Device Based on Multiple Platforms

Abstract

The present invention relates to the technical field of data information processing, solves the problem that there are significant defects in the information symmetry and transaction efficiency of the existing non-performing asset marketing solutions, and provides a method and device for pushing non-performing asset information based on multiple platforms. The method includes obtaining the promotion information of each non-performing asset, pushing the promotion information to each designated platform through a preset standardized interface, and calculating the asset heat value of each non-performing asset according to the behavior data of the users in each of the designated platforms; pushing the promotion information of the non-performing assets of interest on the self-owned channel platform according to the asset heat value and / or the behavior data; in response to a non-performing asset meeting a preset withdrawal condition, withdrawing the promotion information of the corresponding non-performing asset on all the designated platforms through the preset standardized interface. The present invention improves the marketing efficiency of non-performing assets and also ensures the accuracy and relevance of information.

Description

Technical Field

[0001] The present invention relates to the field of data information processing, and in particular, to a method and device for pushing non-performing asset information based on multiple platforms. Background Art

[0002] Non-performing assets generally refer to asset losses caused by borrowers' defaults or inability to fulfill contracts. Such assets mainly include non-performing loans, overdue accounts receivable, assets of bankrupt enterprises, etc. Due to the value loss of non-performing assets, dealing with and disposing of non-performing assets has become an important task for financial institutions and investors. Effectively pushing and disposing of non-performing assets can not only reduce financial risks but also help achieve the value recovery and maximization of assets.

[0003] Currently, the external marketing of assets in the non-performing asset industry mainly relies on offline negotiation methods. Specifically, the transferor needs to communicate and negotiate face-to-face with potential investors to reach a transaction. Although this method can promote the conclusion of transactions to a certain extent, there are also obvious deficiencies. The existing offline negotiation methods lack an efficient and stable matchmaking mechanism, resulting in information asymmetry between non-performing asset transferors and investors. The transferor cannot quickly find suitable investors, and investors are also difficult to obtain accurate information about specific assets. Investors often have difficulty obtaining accurate and reliable non-performing asset information, which affects the accuracy of their investment decisions. This lack of information has led to value mismatches in the market, and many potential high-quality non-performing assets cannot be reasonably valued and processed. Due to poor information flow and deficiencies in the matchmaking mechanism, the transaction process of many non-performing assets is cumbersome and time-consuming, restricting the rapid marketing and circulation of non-performing assets. This low efficiency not only affects the market activity but also fails to promptly realize the interests of investors and transferors.

[0004] In summary, the existing non-performing asset marketing solutions have significant defects in information symmetry and transaction efficiency. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a method and device for pushing non-performing asset information based on multiple platforms to solve the problem that the existing non-performing asset marketing solutions have significant defects in information symmetry and transaction efficiency.

[0006] In a first aspect, embodiments of the present invention provide a method for pushing non-performing asset information based on multiple platforms, the method including:

[0007] Obtaining the promotion information of each non-performing asset and pushing the promotion information to each designated platform through a preset standardized interface, where the designated platforms are divided into self-owned channel platforms and external promotion platforms;

[0008] Obtaining first behavior data of users in each of the designated platforms in response to the recommendation information, and calculating the asset heat value of each of the non-performing assets;

[0009] Pushing recommendation information of interested non-performing assets on the own channel platform according to the asset heat value and / or the second behavior data of the own channel platform;

[0010] In response to a non-performing asset satisfying a preset withdrawal condition, the recommendation information of the corresponding non-performing asset on all the designated platforms is withdrawn through the preset standardized interface.

[0011] Preferably, the obtaining of the first behavior data of the users in each of the designated platforms with respect to the recommendation information and calculating the asset heat value of each of the non-performing assets includes:

[0012] At every preset time period, the first behavior data of users on each of the designated platforms for the recommendation information is obtained through the preset standardized interface, wherein the self-owned channel platform includes an internal promotion platform and a service provider platform, the first behavior data on the external promotion platform and the internal promotion platform include the number of onlookers of the auction of each non-performing asset, and the first behavior data on the service provider platform includes the number of service provider solutions for each non-performing asset;

[0013] According to the number of auction spectators of all the non-performing assets, the total number of auction spectators on the external promotion platform and the internal promotion platform is obtained;

[0014] According to the number of service provider solutions for all the non-performing assets, the total number of solutions on the service provider platform is obtained;

[0015] Determine the behavioral data weight of each of the designated platforms according to the total number of auction spectators and the total number of plans;

[0016] A weighted calculation is performed based on the first behavior data of each designated platform and the corresponding behavior data weight to obtain the asset heat value of each non-performing asset.

[0017] Preferably, the pushing of recommendation information of the interested non-performing assets on the own channel platform according to the asset heat value and / or the second behavior data of the own channel platform includes:

[0018] Determine whether the user has logged into the own channel platform;

[0019] If logged in, determining the user's interested non-performing assets according to the login information, the second behavior data and the asset heat value;

[0020] If the user is not logged in, the user's interested non-performing assets are determined according to the asset heat value;

[0021] Push the promotion information of non-performing assets of interest to the self-owned channel platform through the preset standardized interface.

[0022] Preferably, the promotion information includes the type of non-performing assets. If logged in, determine the non-performing assets of interest to the user according to the login information, the behavior data, and the asset heat value, including:

[0023] Obtain the personal behavior data of each user under the self-owned channel platform according to the login information of the user and the second behavior data, where the personal behavior data includes the first click quantity of the user on each non-performing asset and the second click quantity of the user on each type of non-performing asset;

[0024] Obtain the interest degree value of the user for all non-performing assets according to the first click quantity, the second click quantity, and the asset heat value;

[0025] Determine the non-performing assets of interest to the user according to the interest degree value of each non-performing asset.

[0026] Preferably, the step of obtaining the interest degree value of the user for all non-performing assets according to the first click quantity, the second click quantity, and the asset heat value includes:

[0027] Obtain the initial weight values of the first click quantity, the second click quantity, and the asset heat value respectively;

[0028] Adjust each of the initial weight values according to a pre-constructed neural network model and the behavior data to obtain target weight values;

[0029] Perform weighted operations according to the first click quantity, the second click quantity, the asset heat value, and the corresponding target weight values to obtain the initial interest degree value of each non-performing asset;

[0030] Perform normalization processing on the initial interest degree value to obtain the interest degree value of the user for all non-performing assets.

[0031] Preferably, the step of, in response to a non-performing asset meeting the preset withdrawal condition, withdrawing the promotion information of the corresponding non-performing asset on all the specified platforms through the preset standardized interface includes:

[0032] Obtain the asset status information of each non-performing asset through the specified standard interface, where the asset status information includes: asset status change information and asset term information;

[0033] Judge whether the corresponding non-performing asset meets the preset withdrawal condition according to the asset status change information and the asset term information;

[0034] When a non-performing asset meets the preset withdrawal conditions and / or receives a manual withdrawal instruction, a withdrawal instruction is sent to each of the specified platforms through the preset standard interface to withdraw the promotion information of the corresponding non-performing asset.

[0035] Preferably, obtaining the promotion information of each non-performing asset and pushing the promotion information to each specified platform through a preset standard interface includes:

[0036] Obtaining the initial multi-dimensional information of each non-performing asset according to a preset data source;

[0037] Preprocessing the initial multi-dimensional information of each non-performing asset to obtain target multi-dimensional information, where the preprocessing includes: data cleaning, data standardization, and data verification;

[0038] Generating multi-dimensional labels for each non-performing asset according to the target multi-dimensional information and a preset rule engine, where the multi-dimensional labels include a disposal status label, an asset type label, a disposal difficulty label, and a historical auction label;

[0039] Generating promotion information corresponding to each specified platform according to the multi-dimensional labels and the user portraits of each specified platform, denoted as platform promotion information, where the user portraits are generated based on the first behavioral data;

[0040] Pushing each of the platform promotion information to the corresponding specified platform through the preset standard interface.

[0041] Preferably, the generating multi-dimensional labels for each non-performing asset according to the target multi-dimensional information and a preset rule engine includes:

[0042] Initializing the preset rule engine according to preset non-performing asset business classification standard information to obtain a target rule engine;

[0043] Inputting the target multi-dimensional information into the target rule engine to obtain the initial multi-dimensional labels of each non-performing asset;

[0044] Statistically analyzing the historical data of each non-performing asset according to the initial multi-dimensional labels of each non-performing asset to obtain representative indicators of each initial multi-dimensional label, where the representative indicators at least include a mean value and a variance;

[0045] Screening the corresponding initial multi-dimensional labels according to the representative indicators of each initial multi-dimensional label and the corresponding representative indicator thresholds to obtain intermediate multi-dimensional labels;

[0046] Input the target multi-dimensional information and the corresponding intermediate multi-dimensional labels into a pre-constructed Bayesian network to obtain the joint probability between each of the intermediate multi-dimensional labels and the corresponding target multi-dimensional information;

[0047] Based on the joint probability, determine whether there is a conflict between the intermediate multi-dimensional label and the corresponding target multi-dimensional information;

[0048] If there is a conflict, adjust the target rule engine according to the intermediate multi-dimensional label with the conflict, and return to the step of inputting the target multi-dimensional information into the target rule engine to obtain the initial multi-dimensional labels of each non-performing asset;

[0049] If there is no conflict, use the initial multi-dimensional label of the non-performing asset as its final multi-dimensional label.

[0050] Preferably, after the method responds to a non-performing asset meeting the preset withdrawal condition and withdraws the promotion information of the corresponding non-performing asset on all the specified platforms through the preset standard interface, it further includes:

[0051] According to the asset term information, obtain the non-performing assets withdrawn after exceeding the preset sale term, denoted as overdue withdrawal assets;

[0052] According to the asset status information, obtain the set of sold non-performing assets;

[0053] According to the multi-dimensional label, obtain the non-performing assets matching the overdue withdrawal assets in the set of sold non-performing assets, denoted as target sold assets;

[0054] Obtain the promotion information of each of the target sold assets on the specified platform where it is sold, denoted as sold promotion information;

[0055] Obtain the display parameters of the sold promotion information, where the display parameters include the display frequency, display time period, and promotion content of the promotion information;

[0056] Perform data aggregation processing on the display parameters to generate aggregated display parameters;

[0057] Perform correlation analysis on the multi-dimensional labels of the overdue withdrawal assets and the multi-dimensional labels of the unsold non-performing assets to determine the similarity between each of the overdue withdrawal assets and the unsold non-performing assets;

[0058] Classify the unsold non-performing assets according to the similarity to obtain multiple asset classification groups;

[0059] Match the aggregated display parameters with each asset classification group to obtain the optimized promotion information for each asset classification group;

[0060] The optimized recommendation information is updated to each designated platform through the preset standardized interface to adjust the recommendation information of the currently unsold non-performing assets.

[0061] In a second aspect, an embodiment of the present invention provides an information push device, comprising: at least one processor, at least one memory, and computer program instructions stored in the memory, and when the computer program instructions are executed by the processor, the method of the first aspect in the above-mentioned embodiment is implemented.

[0062] In summary, the beneficial effects of the present invention are as follows:

[0063] The embodiment of the present invention provides a method and device for pushing information of non-performing assets based on multiple platforms. The method obtains the promotion information of each non-performing asset and pushes the promotion information to each designated platform through a preset standardized interface. The designated platform includes a self-owned channel platform and an external promotion platform. The standardized interface is used to ensure the rapid, accurate and consistent transmission of the non-performing asset promotion information, reduce human errors and delays in information transmission, and improve the efficiency of information release. In addition, covering multiple platforms broadens the exposure rate of assets and increases the interaction opportunities between the transferor and potential investors. By analyzing user behavior data, the market demand and investor interest of non-performing assets can be monitored and evaluated in real time to form a dynamic asset heat value. This mechanism helps the transferor to understand which assets are of concern in a timely manner, thereby optimizing marketing strategies and resource allocation. Pushing according to the asset heat value and user behavior data effectively improves the relevance and matching of information, making the promotion information more targeted. This not only improves the user's response rate to the promotion information, but also enhances the investor's sense of participation and satisfaction. By setting withdrawal conditions and performing real-time monitoring, the timeliness and accuracy of non-performing asset information are ensured. This flexible management approach can reduce the interference of outdated information to investors, thereby maintaining the credibility and effectiveness of platform information.

[0064] In summary, the method of the present invention not only improves the marketing efficiency of non-performing assets, but also ensures the accuracy and relevance of information, thereby better promoting the circulation and trading of non-performing assets and providing a more stable and efficient channel for the connection between transferors and investors. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the drawings required for use in the embodiment of the present invention will be briefly introduced below. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work, and these are all within the protection scope of the present invention.

[0066] Figure 1It is a schematic flowchart of a method for pushing non-performing asset information based on multiple platforms according to an embodiment of the present invention.

[0067] Figure 2 It is another schematic flowchart of a method for pushing non-performing asset information based on multiple platforms according to an embodiment of the present invention.

[0068] Figure 3 It is another schematic flowchart of a method for pushing non-performing asset information based on multiple platforms according to an embodiment of the present invention.

[0069] Figure 4 It is another schematic flowchart of a method for pushing non-performing asset information based on multiple platforms according to an embodiment of the present invention

[0070] Figure 5 It is another schematic flowchart of a method for pushing non-performing asset information based on multiple platforms according to an embodiment of the present invention

[0071] Figure 6 It is a schematic structural diagram of an information push device according to an embodiment of the present invention. Detailed implementation manners

[0072] Next, the features and exemplary embodiments of various aspects of the present invention will be described in detail. In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only configured to explain the present invention and are not configured to limit the present invention. For those skilled in the art, the present invention can be implemented without some of these specific details. The following description of the embodiments is only intended to provide a better understanding of the present invention by showing examples of the present invention.

[0073] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, elements defined by the statement "including..." do not exclude the existence of additional identical elements in the process, method, article or device including the said elements.

[0074] It should be noted that all actions of obtaining signals, information, or data in the present invention are carried out on the premise of complying with the corresponding data protection regulations and policies of the location and with the authorization given by the owner of the corresponding device.

[0075] Embodiment 1

[0076] Please refer to Figure 1 , the embodiment of the present invention provides a method for pushing non-performing asset information based on multiple platforms, and the method includes:

[0077] S1. Obtain the promotion information of each non-performing asset, and push the promotion information to each specified platform through a preset standardized interface, where the specified platforms are divided into self-owned channel platforms and external promotion platforms;

[0078] Specifically, the promotion information refers to a detailed description of the non-performing asset, including information such as asset type, value, disposal method, market conditions, etc., so that potential investors can understand the basic situation of the asset. The preset standardized interface is a set of pre-set rules and protocols to ensure the efficient and seamless transmission of information between different systems.

[0079] The purpose of this step is to increase the exposure of the asset and attract the attention of potential investors by obtaining the promotion information of the non-performing asset and transmitting it to multiple platforms through a standardized interface. By spreading information through multiple channels, the market liquidity of the asset is enhanced. Through data collection tools, relevant information of non-performing assets is collected, including basic asset situation, historical performance, market valuation, etc. Using the preset standardized interface, the collected promotion information is formatted to ensure the consistency and readability of the information. The formatted promotion information is pushed to multiple specified platforms, divided into self-owned channel platforms and external promotion platforms. The external promotion platform mainly refers to a third-party auction platform for publishing the investment promotion information of non-performing assets externally to attract potential buyers to bid and watch; the self-owned channel platform is an internal or cooperative channel for precise pushing and internal asset management.

[0080] In a specific embodiment, the preset standardized interface is a RESTful interface, which is a Web service interface based on the REST (Representational State Transfer) architectural style and is widely used in modern Web applications and services. Its design principles aim to simplify and improve the scalability, maintainability and performance of Web services. In the non-performing asset recommendation system, the use of the RESTful interface can bring the following advantages: the recommendation information of non-performing assets can be efficiently transmitted between various designated platforms through the RESTful interface to ensure the real-time and accuracy of the data; resources such as the status, labels and recommendation information of non-performing assets can be flexibly managed and updated through the RESTful interface to support dynamically changing business needs. The RESTful interface can be seamlessly integrated with various client applications and external platforms, such as Web applications, mobile applications, etc., to facilitate the recommendation and trading of non-performing assets.

[0081] S2. Calculating the asset heat value of each of the non-performing assets according to the first behavior data of the users in each of the designated platforms in response to the recommendation information;

[0082] Specifically, the first behavioral data refers to the activity records on various platforms, including browsing history, click-through rate, number of favorites, comments, transaction behavior, etc. The asset heat value reflects the degree of user attention and interest in a certain non-performing asset in a specific period of time, and is an important indicator for evaluating asset market demand. By analyzing user behavioral data, the asset heat value is obtained in order to understand the market's interest in each non-performing asset in real time and help the transferor develop a more effective marketing strategy. Collect user behavior data on a designated platform, analyze the data regularly or in real time, and calculate the heat value of each non-performing asset. A weighted algorithm can be used to assign different weights to different behavioral data.

[0083] By calculating the asset heat value, the transferor can timely grasp the market demand dynamics and optimize the promotion strategy. For assets with higher heat, the promotion efforts can be increased. Conversely, the asset disposal method or pricing strategy can be adjusted to improve resource utilization efficiency.

[0084] S3. Pushing recommendation information of the non-performing assets of interest on the own channel platform according to the asset heat value and / or the second behavior data of the own channel platform;

[0085] Specifically, the first-line data is the overall behavior data of users on all platforms, while the second-line data is the behavior data sourced from the proprietary channel platform. The non-performing assets of interest refer to the non-performing assets that meet the user's preferences obtained based on the user's behavior data and the asset heat value. Based on the second-line data of the proprietary channel platform, the user's preferences are analyzed, combined with the asset heat value, and the promotion information that matches the user's interests is promptly pushed to the proprietary channel platform to improve the relevance of the information and the user's participation. Through precise push, the user experience is enhanced, and the user's attention and response rate to the promotion information are increased. This not only effectively facilitates transactions but also improves the user's trust and satisfaction with the platform, increasing customer stickiness.

[0086] S4. In response to a non-performing asset satisfying a preset withdrawal condition, withdraw the promotion information of the corresponding non-performing asset on all the specified platforms through the preset standardized interface.

[0087] Specifically, the preset withdrawal condition refers to a specific condition set in advance to trigger the withdrawal of promotion information, such as the asset has been traded, the asset status has changed, etc. It refers to an instruction to stop promoting a non-performing asset sent to each specified platform according to the withdrawal condition. By promptly withdrawing the no-longer-applicable promotion information, it is possible to prevent users from obtaining outdated or misleading information, enhancing the information transparency and reliability of the platform. This flexible management method will help maintain customer trust and improve the asset circulation efficiency.

[0088] Preferably, obtaining the first-line behavior data of users in each of the specified platforms for the promotion information and calculating the asset heat value of each non-performing asset includes:

[0089] S21. Every preset time period, obtain the first-line behavior data of users in each of the specified platforms for the promotion information through the preset standardized interface. Among them, the proprietary channel platform includes an internal promotion platform and a service provider platform. The first-line behavior data under the external promotion platform and the internal promotion platform includes the number of people viewing the auction of each non-performing asset, and the first-line behavior data under the service provider platform includes the number of service provider solutions for each non-performing asset;

[0090] Specifically, the preset time period is a fixed time interval set by the system, such as daily or weekly, which is used to regularly obtain the behavioral data of the platform to ensure the timeliness and update of the data. The purpose of this step is to regularly collect the behavioral data of each platform through the preset standardized interface. In this step, the number of onlookers during the auction provided by the external promotion platform and the internal promotion platform, while the number of solution submissions provided by the service provider platform. The number of solution submissions by the service provider portal refers to the number of solutions for specific non-performing assets submitted through the service provider portal system, which is one of the self-owned channel platforms. When a service provider views a certain non-performing asset in the portal system, they may submit corresponding asset disposal solutions or investment plans based on the characteristics and requirements of the asset. For example: how to package the asset, the investment promotion strategy, the buyer matching suggestions, the debt disposal plan, etc. These solutions represent the attention and handling intention of the service provider towards the non-performing asset. The number of solution submissions reflects the degree of interest and active participation of the service provider in the non-performing asset. If an asset can attract multiple service providers to submit disposal solutions, it usually indicates that the asset has high attractiveness and value in the market. Different from ordinary onlooker or click behaviors, submitting a solution is a more in-depth and active behavioral data, meaning that the service provider has a higher degree of participation in the asset and may consider further negotiating cooperation or disposal operations.

[0091] S22. Obtain the total number of auction onlookers of the external promotion platform and the internal promotion platform according to the auction onlookers of all the non-performing assets;

[0092] Specifically, the purpose of this step is to integrate the onlooker data of multiple promotion platforms to provide a comprehensive user interest indicator for heat calculation. Add up the onlooker numbers pulled from each platform, and calculate the total onlooker numbers of the external promotion platform and the internal promotion platform respectively. By integrating the onlooker data, it can more comprehensively reflect the market attention of non-performing assets and provide support for the accurate calculation of asset heat.

[0093] S23. Obtain the total number of solutions of the service provider platform according to the number of service provider solutions of all the non-performing assets;

[0094] Specifically, this step is used to measure the degree of interest of the service provider platform in non-performing assets and the number of solution plans they provide for asset disposal, adding an important dimension to the heat value calculation.

[0095] S24. Determine the behavioral data weights of each of the specified platforms according to the total number of auction onlookers and the total number of solutions;

[0096] S25. Perform a weighted operation according to the first behavioral data of each of the specified platforms and the corresponding behavioral data weights to obtain the asset heat value of each non-performing asset.

[0097] Specifically, in order to determine the weights of different platform data in asset popularity to reflect the influence of each platform in asset marketing, in one embodiment, the external promotion platform includes external platform 1 and external platform 2, and the proprietary channel platform includes the service provider platform and the internal platform 3, then weight 1: weight 2: weight 3: weight 4 = total number of onlookers on external platform 1: total number of onlookers on external platform 2: total number of service provider solutions: total number of onlookers on internal platform 3; after the above data are proportionally converted and normalized, the behavioral data weights of each of the designated platforms can be obtained;

[0098] Subsequently, the data and weights of different platforms will be weighted and calculated to obtain the final asset heat value, which will provide a reference for the subsequent asset promotion and package collection strategy. The asset heat of a non-performing asset = the number of onlookers on external platform 1 * weight 1 + the number of onlookers on external platform 2 * weight 2 + the number of service provider solutions * weight 3 + the number of onlookers on internal platform 3 * weight 4;

[0099] Through weighted calculation, the asset heat value can fully reflect the comprehensive attention paid by multiple platforms to non-performing assets. User behaviors on different platforms are reasonably integrated, making the calculation results more in line with the actual market situation. Through the calculation of heat value, the market's interest level in non-performing assets can be quantified, providing accurate data support for asset promotion and guiding enterprises to formulate more effective marketing strategies and package acquisition decisions.

[0100] Preferably, the pushing of recommendation information of the interested non-performing assets on the own channel platform according to the asset heat value and / or the behavior data includes:

[0101] S31, determining whether the user has logged in to the proprietary channel platform;

[0102] Specifically, the purpose of determining whether a user is logged in is to distinguish between personalized and general push strategies. The behavior data of logged-in users is more complete, and more accurate recommendation information can be provided; the data of logged-in users is limited, so push needs to be based on more extensive heat analysis. In other words, distinguishing between logged-in and logged-out states enables the system to adopt different push strategies based on the integrity of the user's data, thereby improving the accuracy of push information and user experience.

[0103] S32: If logged in, determine the user's interested non-performing assets according to the login information, the second behavior data and the asset heat value;

[0104] Specifically, the login information includes but is not limited to the user's account data, such as name, role, historical browsing or investment records. The personalized behavior data of logged-in users is more abundant. By integrating the user's historical behavior and asset heat value, non-performing assets that the user is interested in can be accurately identified. The system extracts the user's second behavior data from the database based on the user's login information, such as the assets recently viewed or the types of assets collected. These behavior data are matched with the asset heat value to calculate the attractiveness of each non-performing asset to the user, and assets with high heat and meeting the user's preferences are preferentially recommended. Thereby improving the accuracy of the pushed content, making it easier for users to find assets they are interested in, and increasing the transaction conversion rate and user satisfaction.

[0105] Preferably, the promotion information includes the type of non-performing assets. If logged in, determining the non-performing assets of interest to the user according to the login information, the second behavior data, and the asset heat value includes:

[0106] S321. According to the user's login information and the second behavior data, obtain the personal behavior data of each user under the self-owned channel platform, where the personal behavior data includes the first click count of the user for each non-performing asset and the second click count of the user for each non-performing asset type;

[0107] Specifically, the system extracts the user's historical behavior records from the second behavior data according to the user's login information on the self-owned channel platform, denoted as personal behavior data. The first click count and the second click count are extracted from the user's behavior data and classified into different assets and asset types. The first click count refers to the number of clicks of the user on a specific non-performing asset, which is used to reflect the intensity of the user's interest in a single asset. The second click count refers to the number of clicks of the user on a specific type of non-performing asset (such as residential, commercial real estate, etc.), which reflects the user's overall preference for this type of asset.

[0108] S322. According to the first click count, the second click count, and the asset heat value, obtain the degree of interest value of the user in each non-performing asset;

[0109] Specifically, the number of clicks of the user on an asset, the number of clicks of this type of asset, and the heat value of the asset are calculated through weighted calculation to obtain the degree of interest value of the user in this asset, that is, the interest score for this asset.

[0110] Preferably, the obtaining the degree of interest value of the user in each non-performing asset according to the first click count, the second click count, and the asset heat value includes:

[0111] S3221. Obtain the initial weight values of the first click count, the second click count, and the asset heat value respectively;

[0112] Specifically, the initial weight is used to characterize the influence degree of different data types. For example, whether the click count can reflect user interest better than the market heat. The system assigns initial weight values to the first click count, the second click count, and the asset heat value respectively through preset rules or historical data statistics.

[0113] S3222. Adjust each of the initial weight values according to the pre-constructed neural network model and the behavior data to obtain the target weight values;

[0114] Specifically, the neural network model is an algorithm based on deep learning, used to analyze complex data and adaptively adjust model parameters, including multi-layer perceptron (MLP), convolutional neural network (CNN), or recurrent neural network (RNN), etc., which can be selected according to the data type and scenario. In this scenario, since the weighted problem of user behavior data needs to be processed, a fully connected feedforward neural network is preferred. The fully connected feedforward neural network (FNN) is a neural network model widely applicable to structured data, especially suitable for weighted calculation, feature mapping, and processing of complex relationships between data. User behavior data usually contains multi-dimensional information, such as click count, asset heat, preference type, etc. There may be non-linear relationships between these features, and these relationships may not be captured by simple linear methods.

[0115] The system inputs the user's behavior data (click count and asset heat) into the neural network model for training. The model adjusts the initial weights according to the correlation between the data to generate more accurate target weights. Thus, it realizes dynamic optimization of weights, improves the calculation accuracy of the interest degree value, and further enhances the recommendation effect.

[0116] S3223. Perform weighted operations according to the first click count, the second click count, the asset heat value, and the corresponding target weight values to obtain the initial interest degree value of each non-performing asset;

[0117] Specifically, through weighted calculation, the influences of different data sources are combined to obtain the preliminary interest degree value. The following formula is used for calculation:

[0118] Interest degree value = First click count × Weight 1 + Second click count × Weight 2 + Asset heat value × Weight 3

[0119] Through the above weighted calculation, different types of data are effectively integrated to ensure that the calculation result of the interest degree value truly reflects the user's interest.

[0120] S3224. Normalize the initial degree of interest value to obtain the degree of interest value of the user in each non-performing asset.

[0121] Specifically, by normalizing to eliminate the dimensional differences in the degree of interest values between different assets, the results become more comparable. After normalization, the degree of interest values between different assets can be directly compared, which helps to screen out the assets that the user is most interested in.

[0122] S323. Determine the non-performing assets of interest to the user based on the degree of interest value.

[0123] Specifically, based on the degree of interest value, the system can screen out the assets that meet the user's interests and generate personalized recommendations. The system sorts the normalized degree of interest values of all assets and selects several assets with the highest scores as the non-performing assets of interest to the user, thereby providing precise asset recommendations and improving user satisfaction and the platform's transaction conversion rate.

[0124] S33. If not logged in, determine the non-performing assets of interest to the user based on the asset heat value;

[0125] Specifically, the behavior data of unlogged users is insufficient. Therefore, it is necessary to push based on the overall market data (such as the asset heat value) to ensure that the recommended assets are attractive to most users. The system generates push content based on the high-heat asset list of the current platform. If the number of onlookers of a certain asset is high both on the external and internal platforms, the system defaults that asset to be the asset that users are interested in on the market and pushes it to unlogged users. The push content can adopt default filtering, such as "Recommended Hot Assets" or "Recently High-Concern Assets", to attract users to further browse. Even if the user is not logged in, the platform can push high-value assets through market heat data to ensure a certain push effect and improve the asset exposure rate and access volume.

[0126] S34. Push the promotion information of the non-performing assets of interest to the self-owned channel platform through the preset standard interface.

[0127] Finally, the system generates push content based on the matched asset information of interest and formats it into a push template supported by the platform. Through the preset interface, the push information is automatically sent to the front end of the self-owned channel platform.

[0128] Preferably, the step of withdrawing the promotion information of the corresponding non-performing asset on all the specified platforms through the preset standard interface in response to a non-performing asset meeting the preset withdrawal condition includes:

[0129] S41. Obtain the asset status information of each non-performing asset through the specified standard interface, where the asset status change information and the asset term information;

[0130] Specifically, the asset status change information is the status change information of non-performing assets during their life cycle, such as the asset changing from "for sale" to "sold"; the asset term information is the effective promotion period of non-performing assets, such as the auction deadline, sales validity period, etc.

[0131] The system makes data requests to each designated platform through a preset standardized interface to obtain the real-time status information and term information of non-performing assets, ensuring that the system can timely obtain asset status changes, avoid the continued display of expired or sold assets on the platform, and improve the accuracy and timeliness of information management.

[0132] S42. Determine whether the corresponding non-performing assets meet the preset withdrawal conditions according to the asset status change information and the asset term information;

[0133] Specifically, according to the status changes and term information of the assets, automatically determine which assets are no longer suitable for display, thereby triggering the withdrawal of the promotion information. The preset withdrawal conditions and the predefined conditions for triggering withdrawal include, but are not limited to, the asset being sold, the term expiring, or no longer being promoted. If any condition is met, mark the asset as needing to be withdrawn to avoid the continued display of invalid or incorrect asset information on the platform to improve the user experience and the management efficiency of the platform.

[0134] S43. When a non-performing asset meets the preset withdrawal conditions and / or receives a manual withdrawal instruction, send a withdrawal instruction to each of the designated platforms through the preset standard interface to withdraw the promotion information of the corresponding non-performing asset.

[0135] Specifically, this step aims to execute the withdrawal task according to the preset conditions and at the same time support the administrator to manually trigger the withdrawal when necessary to ensure the accuracy and flexibility of the information. When the system detects that a certain asset meets the preset withdrawal conditions or receives a manual withdrawal instruction, the system sends a withdrawal instruction to each platform through the standardized interface.

[0136] Preferably, obtaining the promotion information of each non-performing asset and pushing the promotion information to each designated platform through a preset standardized interface includes:

[0137] S11. Obtain the initial multi-dimensional information of each non-performing asset according to a preset data source;

[0138] Specifically, the preset data source refers to multiple sources that the system has accessed for obtaining non-performing asset information, such as financial institutions, asset management companies, third-party data service providers, etc. The initial multi-dimensional information is the original data about non-performing assets, including but not limited to the basic information of the assets such as the asset name, amount, historical auction records, and status information such as whether it has been disposed of in multiple dimensions.

[0139] Specifically, comprehensive initial multi-dimensional information is collected from various data sources to ensure that the system has a detailed enough understanding of non-performing assets, laying a foundation for subsequent analysis and processing.

[0140] S12. Preprocess the initial multi-dimensional information to obtain target multi-dimensional information, where the preprocessing includes: data cleaning, data standardization, and data verification;

[0141] Specifically, the purpose of this step is to improve data quality through preprocessing and ensure the accuracy of data in subsequent analysis, generating labels, and promoting information. First, invalid or duplicate data is removed through data cleaning, and errors in the data are corrected, such as filling in null values, unifying date formats, and converting currency units. Subsequently, data fields from different sources are standardized to ensure the consistency of the data structure. Finally, some incomplete information is supplemented using preset rules or external databases, and the multi-source information is verified for consistency to ensure the accuracy of the information. After preprocessing, the obtained target multi-dimensional information should have a standardized format and be available for generating promotion information in the next step.

[0142] S13. Generate multi-dimensional labels for each non-performing asset according to the target multi-dimensional information and a preset rule engine, where the multi-dimensional labels include a disposal status label, an asset type label, a disposal difficulty label, and a historical auction label;

[0143] Specifically, a rule engine is a system that analyzes and classifies data based on predefined rules, such as generating a "high-value" or "low-value" label according to the size of the asset amount. A system that analyzes and classifies data based on predefined rules, the system analyzes the target multi-dimensional information according to the rule engine and generates multiple labels. The multi-dimensional labels provide a basis for asset classification and recommendation, improving the matching degree and accuracy of promotion information.

[0144] S14. Generate promotion information corresponding to each specified platform according to the multi-dimensional labels and the user portraits of each specified platform, denoted as platform promotion information, where the user portraits are generated based on the first behavior data;

[0145] Specifically, promotion information that meets the needs of the user portrait is generated according to the characteristics and behavior data of platform users, improving the asset exposure rate and conversion rate. The system combines the multi-dimensional labels of the asset and the user behavior data of the platform (such as browsing records, interest preferences) to generate promotion information suitable for the platform. For example, if a platform user has a high interest in industrial real estate, the system will give priority to pushing relevant asset information, thus generating personalized promotion information for different platforms and improving the promotion effect and user participation.

[0146] Preferably, based on the multi-dimensional tags and the behavioral data of each of the specified platforms, generate promotion information corresponding to each of the specified platforms, denoted as platform promotion information, including:

[0147] S141. According to the first behavioral data of each of the specified platforms, extract the basic user characteristics and user preference characteristics of each of the specified platforms. Among them, the basic user characteristics include user age, user gender, and the device used by the user, and the platform user preference characteristics include investment preference, asset category preference, purchasing power, and activity level;

[0148] Specifically, the basic user characteristics refer to static information such as age, gender, and device type that reflect the user's identity or usage habits. The user preference characteristics are dynamic characteristics based on the user's behavioral data, reflecting their investment habits and purchasing tendencies. By deeply analyzing the behavioral data of each of the specified platforms, the extracted basic user characteristics and user preference characteristics will provide basic data support for subsequent asset promotion. This process of feature extraction can not only help the system better understand user needs but also enhance the personalization and accuracy of the promotion information, thereby effectively promoting the rapid marketing and circulation of non-performing assets.

[0149] S142. According to the basic user characteristics and the user preference characteristics, construct a user portrait for each of the specified platforms;

[0150] Specifically, a user portrait is a comprehensive description of a user formed through data analysis and modeling techniques based on the user's basic characteristics and preference characteristics. It can help enterprises better understand user needs, thereby achieving precise marketing in the promotion of non-performing assets.

[0151] For each user, based on their basic characteristics and preference characteristics, generate a user portrait containing various dimensions. For example, but not limited to, the user portrait may contain the following fields:

[0152] Basic characteristics: user ID, age, gender, device type used.

[0153] Preference characteristics: investment preference (such as high risk or low risk), asset category preference (such as non-performing assets, real estate), purchasing power level (such as high, medium, low), activity level (such as high, normal, low).

[0154] By constructing a user portrait based on the basic user characteristics and user preference characteristics, a deep understanding of user behavior can be achieved, thereby improving the pertinence and effectiveness of non-performing asset promotion. The user portrait can not only help the platform achieve personalized recommendations in the promotion information but also provide an important decision-making basis for the optimization of the overall market strategy.

[0155] S143. Match the multi-dimensional tags of the user profile with the non-performing assets to obtain the target non-performing assets for each of the specified platforms;

[0156] Specifically, in this step, the goal is to determine the target non-performing assets on each specified platform by matching the user profile with the multi-dimensional tags of the non-performing assets. This process involves accurately identifying the user's needs and effectively docking them with the characteristics of the non-performing assets in order to push the asset information that best matches the user's preferences;

[0157] The matching process can be achieved by pre-establishing matching criteria, such as the user's investment preferences must be consistent with the asset type of the non-performing assets; the user's purchasing power should match the valuation of the non-performing assets; the user's activity level is associated with the disposal status of the assets; etc. It can also be realized through algorithms for automatic matching of the user profile and the non-performing asset tags. First, filter out the corresponding types of non-performing assets according to the user's asset category preferences. For example, if user A prefers real estate, only consider all real estate-related assets. Score each potential target asset, and the scoring basis includes: the matching degree of investment preferences, the relative matching degree of purchasing power and asset valuation, and the compatibility of disposal difficulty with the user's investment ability. Calculate the comprehensive score of each asset, and sort them according to the score, and select several assets with the highest score as the target non-performing assets.

[0158] S144. Generate initial promotion information based on the target multi-dimensional information and multi-dimensional tags of the target non-performing assets;

[0159] In this step, the goal is to generate initial promotion information using the multi-dimensional information and tags of the determined target non-performing assets for subsequent display and promotion on the specified platforms. First, it is necessary to clarify the relevant information and tags of the target non-performing assets, including asset type, disposal status, valuation information, and historical data, etc. In addition, multi-dimensional tags also need to be extracted, such as disposal status tags, asset type tags, disposal difficulty tags, and historical auction tags.

[0160] The process of generating the initial promotion information begins with extracting these key information. By selecting the data that is most important to potential investors, such as asset type, valuation, and disposal status, a clear and concise promotion content is constructed. For example, it can be mentioned that this is a real estate asset to be disposed of, with a valuation of 500,000 yuan and 3 historical auction times. This information will be used to attract the attention of investors.

[0161] The generated promotion information also needs to be formatted to ensure that it can be correctly displayed on various platforms. According to the requirements of different platforms, apply suitable promotion information templates for formatting. This may include setting the title, adding asset photos, the layout of the main information, and the display of contact information and inquiry channels.

[0162] S145. Determine the display form of the promotion information for each of the specified platforms according to the basic user characteristics;

[0163] Specifically, it is necessary to collect and analyze the basic characteristics of users on each specified platform, including age, gender, and the devices used, etc. These characteristics provide an important basis for the display form of the promotion information. For example, young users may be more inclined to a simple and fashionable display style, while older users may prefer a traditional and easy-to-understand layout. The devices used by users, such as mobile phones, tablets, and computers, also affect the display form of the promotion information. On mobile devices, the display should be simple and clear, easy to slide and click; while on desktop devices, more information and a more complex layout can be provided.

[0164] S146. Generate the platform promotion information corresponding to each of the specified platforms according to the initial promotion information and the corresponding display form of the promotion information.

[0165] Specifically, organize the initial promotion information according to the display form corresponding to the user characteristics, and push the generated promotion information to each specified platform through a preset standardized interface. The generated promotion information can be subjected to A / B testing on a small scale to evaluate the impact of different display forms on user engagement. According to user feedback and behavioral data, continuously optimize the content and display method of the promotion information to ensure maximizing user attention and improving the conversion rate.

[0166] S15. Push each of the platform promotion information to the corresponding specified platform through the preset standardized interface.

[0167] Specifically, finally, the system sends the generated promotion information to each specified platform through the standardized interface. This process includes steps such as data packaging, sending instructions, and successful confirmation to ensure that the information reaches the platform accurately and without error.

[0168] Preferably, generating the multi-dimensional labels for each of the non-performing assets according to the target multi-dimensional information and the preset rule engine includes:

[0169] S131. Initialize the preset rule engine according to the preset non-performing asset business classification standard information to obtain the target rule engine;

[0170] Specifically, the preset non-performing asset business classification standard information refers to the standard information predefined for describing the characteristics and classification of non-performing assets, such as asset types such as residential real estate, commercial real estate, disposal methods such as auctions, transfers, etc. The system reads the preset classification standards and business rules, imports them into the rule engine, and the initialization process includes loading the data model, rule configuration, and fine-tuning according to different industry practices and platform requirements. The initialized rule engine is more accurate and meets the business needs.

[0171] S132. Input the target multi-dimensional information into the target rule engine to obtain the initial multi-dimensional labels of each non-performing asset;

[0172] Specifically, the system automatically transmits the pre-processed target multi-dimensional information to the rule engine, and the rule engine generates initial multi-dimensional labels according to the input information according to the preset logic. The labels include the basic characteristics and classification information of the assets. Through this step, the system can preliminarily screen and classify the assets, improving the accuracy and matching degree of asset promotion.

[0173] S133. Conduct statistical analysis on the historical data of each non-performing asset according to the initial multi-dimensional labels to obtain the representative indicators of each initial multi-dimensional label, where the representative indicators at least include the mean and variance;

[0174] Specifically, the system conducts statistical descriptive analysis on the historical data of non-performing assets (such as transaction records, market performance, user interaction data, etc.), including calculating representative indicators such as the mean and variance of each label. These indicators are used to evaluate the representativeness and stability of the labels, so as to determine which labels can fully reflect the characteristics of non-performing assets.

[0175] S134. Screen the corresponding initial multi-dimensional labels according to the representative indicators of each initial multi-dimensional label and the corresponding representative indicator thresholds to obtain intermediate multi-dimensional labels;

[0176] Specifically, the system screens the initial multi-dimensional labels according to the representative indicators and the preset thresholds. Only those labels that meet the threshold requirements can be retained to obtain intermediate multi-dimensional labels. This screening process ensures that the generated labels have high representativeness and accuracy, and eliminates noise and unreliable labels.

[0177] S135. Input the target multi-dimensional information and the corresponding intermediate multi-dimensional labels into a pre-constructed Bayesian network to obtain the joint probability between each intermediate multi-dimensional label and the corresponding target multi-dimensional information;

[0178] Specifically, a Bayesian network is a graph model based on probability theory, where its nodes represent variables and the edges represent the dependencies between variables. In this scenario, the node variables include target multi-dimensional information and initial multi-dimensional labels. During the model training phase, the system constructs a Bayesian network based on historical data, sets the dependencies between variables and the conditional probability table. The system converts the target multi-dimensional information and the initial multi-dimensional labels into structured data that conforms to the input format of the Bayesian network, and inputs this data as observed variables into the corresponding nodes of the Bayesian network. The Bayesian network calculates the joint probability between the target multi-dimensional information and the initial multi-dimensional labels through the conditional probability chain rule. The joint probability represents the probability that two or more events occur simultaneously. In this step, it is used to measure the degree of mutual matching between the label and the multi-dimensional information, and the Bayesian network is used to determine whether there are contradictions or deviations between the multi-dimensional label and the asset information. The system inputs the target multi-dimensional information and the initial label as inputs and passes them to the Bayesian network for calculation. The Bayesian network analyzes the mutual dependencies of each piece of information and label and outputs their joint probability to ensure the matching between the label and the asset information, providing a basis for correcting potential wrong labels.

[0179] S136. Judge whether there is a conflict between the intermediate multi-dimensional label and the corresponding target multi-dimensional information according to the joint probability.

[0180] Specifically, a conflict means that the generated initial multi-dimensional label has a weak or contradictory association with the target multi-dimensional information. The system will set a conflict threshold for the joint probability according to historical data, and judge and detect the logical inconsistency between the label and the information through the conflict threshold to avoid wrong labels affecting subsequent analysis and promotion.

[0181] S137. If there is a conflict, adjust the target rule engine according to the initial multi-dimensional label with the conflict, and return to the step of inputting the target multi-dimensional information into the target rule engine to obtain the initial multi-dimensional labels of each non-performing asset.

[0182] Specifically, when there is a conflict, the system will adjust the conditional probability table or logical rules in the rule engine for the conflicting label, update the parameters of the rule engine through a feedback mechanism to make it more in line with the actual situation and reduce the generation of wrong labels. If a certain label conflicts repeatedly, the system can trigger a manual review to modify the model parameters. After adjustment, the system will return to step S132, input the target multi-dimensional information into the rule engine again to generate new initial multi-dimensional labels, ensure a more accurate association between the label and the asset information, and improve the intelligence and adaptability of the system.

[0183] S138. If there is no conflict, use the initial multi-dimensional label of the non-performing asset as its final multi-dimensional label.

[0184] Specifically, if the joint probability of all tags and asset information is higher than the preset threshold, it is determined that there is no conflict between the tag and the information. The system confirms that the currently generated intermediate multidimensional tags can truly reflect the characteristics of the assets, and directly stores the non-conflicting tags as the final multidimensional tags for subsequent analysis and recommendation. The final multidimensional tags ensure the accuracy of asset recommendation information, allowing investors to obtain real and reliable asset characteristics.

[0185] Through the above steps, the system can effectively generate platform promotion information corresponding to each designated platform, ensuring that the information is not only attractive but also meets the needs and expectations of users, thereby improving the display effect of non-performing assets and market circulation efficiency.

[0186] In one embodiment, in response to a non-performing asset satisfying a preset withdrawal condition, the recommendation information of the corresponding non-performing asset on all the designated platforms is withdrawn through the preset standardized interface, and the method further includes:

[0187] S05. According to the asset term information, obtain the non-performing assets that are withdrawn after the preset selling term, and record them as overdue withdrawn assets;

[0188] Specifically, the purpose of this step is to screen out non-performing assets that have been promoted on the platform for a period of time but have not been successfully sold. Identifying these assets helps to further analyze the shortcomings in their promotion process, thereby optimizing the promotion strategy. The system first queries the asset term information of each non-performing asset, and determines whether it exceeds the preset effective sales period by comparing the current time with the sales period. For those assets that have exceeded the period but have not been sold, they will be withdrawn from the promotion and recorded as "overdue withdrawn assets", effectively screening out assets that have not been sold within the scheduled time, facilitating subsequent cause analysis and promotion optimization, thereby improving the success rate of asset promotion.

[0189] S06. Acquire a set of sold non-performing assets according to the asset status information;

[0190] The purpose of this step is to identify those non-performing assets that have been successfully sold, collect their promotion data, and provide reference samples for subsequent promotion optimization. The system reads the asset status information of the non-performing assets and filters out the assets marked as sold. This process is usually implemented through database query to ensure that the latest sales status data is obtained.

[0191] S07. According to the multi-dimensional tags, obtain the non-performing assets matching the overdue withdrawn assets from the set of sold non-performing assets, and record them as target sold assets;

[0192] First, the system searches for the most similar assets in the set of sold non-performing assets based on the multi-dimensional tags of each overdue withdrawn asset. This matching process can use similarity calculation algorithms such as cosine similarity or Euclidean distance to ensure that the sold assets found are as close as possible to the withdrawn assets in terms of attributes. By matching the sold assets with similar tags, successful cases can be provided for the promotion strategy of overdue withdrawn assets, helping to improve the promotion effect.

[0193] S08. Obtain the promotion information of each of the target sold assets on the specified platform where they were sold, denoted as sold promotion information.

[0194] In the promotion records of the specified platform, the system extracts the relevant promotion information of the target sold assets. These promotion information is usually stored in the platform's database and may involve query operations on fields such as promotion frequency, time period, and promotion content. By analyzing the promotion information of successfully sold assets, effective means and methods in the promotion process can be summarized, providing data support for the optimization of the promotion of similar assets.

[0195] S09. Obtain the display parameters of the sold promotion information, where the display parameters include the display frequency, display time period, and promotion content of the promotion information.

[0196] The system extracts various display parameters from the sold promotion information, including the display frequency (the number of times the promotion information is displayed on the platform), the display time period (the display arrangement of the promotion information during a day or a specific time period), and the promotion content (the description method and graphic information of the promotion). This step requires parsing and extracting the detailed fields in the promotion information. Extracting these display parameters can provide rich information for subsequent data aggregation and analysis, thereby optimizing future promotion strategies and increasing the promotion effect of non-performing assets.

[0197] S010. Perform data aggregation processing on the display parameters to generate aggregated display parameters.

[0198] Data aggregation processing refers to combining, classifying, and statistically analyzing the display parameters from multiple data sources to generate a representative result. The aggregated display parameters are comprehensive parameters obtained after processing multiple display parameters, reflecting the best display strategy.

[0199] The system performs statistical analysis on display parameters such as display frequency, display time period, and promotion content, calculates indicators such as average display frequency and most frequently used time period to generate aggregated display parameters. This aggregation can use simple average calculation or weighted calculation to ensure the extraction of effective display patterns. Through data aggregation, it can be summarized which display methods are the most effective, so as to optimize in future promotion strategies and improve the promotion effect of assets.

[0200] S011. Perform correlation analysis on the multi-dimensional labels of the overdue-withdrawn assets and the multi-dimensional labels of the unsold non-performing assets to determine the similarity between each overdue-withdrawn asset and the unsold non-performing assets;

[0201] Specifically, by calculating the similarity, identify the feature similarities between the overdue-withdrawn assets and the unsold assets to provide support for subsequent promotion optimization. Use machine learning or statistical analysis tools to compare the multi-dimensional labels of the overdue-withdrawn assets and the unsold assets and calculate their similarities. The similarity calculation can adopt various methods, such as Euclidean distance, Manhattan distance, or cosine similarity, etc. Determining the similarity can help apply specific promotion strategies to more similar assets, thereby improving the success rate of promotion.

[0202] S012. Classify the unsold non-performing assets according to the similarity to obtain multiple asset classification groups;

[0203] Specifically, the asset classification groups divide the unsold non-performing assets into different groups according to the similarity, and the assets within each group have similar characteristics. The system divides the unsold assets into multiple classification groups according to the similarity calculated previously. The classification method can be based on clustering algorithms, such as K-means clustering or hierarchical clustering, to ensure that the asset characteristics in each classification group are as similar as possible. Classification can help the system adopt different promotion methods for different types of assets, thereby achieving refined operation and improving the success rate of promotion.

[0204] S013. Match the aggregated display parameters with each asset classification group to obtain the optimized promotion information for each asset classification group;

[0205] Specifically, the system matches the characteristics of each asset classification group with the aggregated display parameters to generate optimized promotion information suitable for each group of assets. These promotion information will include the suitable display frequency, time period, and promotion content, etc., so as to ensure that these assets can be promoted more effectively. Through personalized optimized promotion information, the exposure effect and conversion rate of the assets can be significantly improved, which helps to sell the assets as soon as possible.

[0206] S014. Update the optimized promotion information to each designated platform through the preset standardized interface to adjust the promotion information of the currently unsold non-performing assets.

[0207] Specifically, the system updates the generated optimized promotion information to each designated platform through the preset standardized interface. These updates usually include replacing the old promotion content, adjusting the display time and frequency, etc. Through the interface for data interaction, ensure that the promotion information can be synchronized in a timely manner.

[0208] Example 2

[0209] In the solution of Embodiment 1, the asset heat value is obtained only by weighted calculation of the number of onlookers in the auction in the behavior data. This solution can reflect the heat of non-performing assets to a certain extent, but there are problems of single data source and relatively simplified weight setting. In order to improve the calculation accuracy of the asset heat value, Embodiment 2 is improved on the basis of Embodiment 1.

[0210] In this embodiment, the obtaining of the first behavior data of the users in each of the specified platforms for the promotion information and the calculation of the asset heat value of each of the non-performing assets include:

[0211] S1-21. Every preset time period, obtain the first behavior data of the users in each of the specified platforms for the promotion information through the preset standard interface; wherein, the self-owned channel platforms include the internal promotion platform and the service provider platform, the first behavior data under the external promotion platform and the internal promotion platform includes positive behavior data and negative behavior data, and the first behavior data under the service provider platform includes the number of service provider solutions for each non-performing asset;

[0212] Specifically, the implementation process of this embodiment is similar to step S21 in Embodiment 1. The difference is that in this embodiment, the first behavior data under the external promotion platform and the internal promotion platform includes positive behavior data and negative behavior data, wherein the positive behavior data includes:

[0213] Click behavior: Record the number of times the user clicks to view the promotion information, reflecting the user's direct interest in a specific asset; Browsing duration: Calculate the time the user stays on the promotion information page, indicating the user's in-depth attention; Sharing / forwarding behavior: Calculate the number of times the user shares or forwards the promotion information, reflecting the social dissemination potential of the asset; Favorite behavior: Count the number of assets favorited by the user, indicating the user's investment willingness in the asset; Conversion behavior: Such as behaviors such as signing up for an auction or submitting a purchase intention, used to measure the user's actual purchase interest;

[0214] The negative behavior data includes but is not limited to: Bounce behavior, that is, the user exits or jumps to other pages in a short time, usually indicating that the promotion information fails to attract the user's interest. Blocking operation: The user blocks a specific promotion information or non-performing asset category, indicating that the user does not want to see similar content again, as well as unfollowing, etc.;

[0215] Positive behavior reflects the user's positive interest in non-performing assets, while negative behavior can show the user's tendency of rejection and disinterest. Combining these two types of data can better identify which assets can attract users and which assets are unpopular, so as to avoid promoting assets that users are obviously not interested in.

[0216] S1-22. Remove the abnormal behavior data from the data in the first row to obtain the target behavior data;

[0217] Specifically, in this step, the behavior data collected from different platforms is initially screened to eliminate noise data. For example, data with too short browsing duration (such as less than 3 seconds) may be accidental clicks and can be excluded from the heat calculation. Abnormal behaviors are eliminated by setting rules (such as repeatedly clicking a large number of asset information within a short period). The elimination of abnormal behaviors can be based on the Z-Score method to filter the data that deviates from the mean by more than the set threshold, reducing the noise affecting the results, thereby obtaining the target behavior data;

[0218] S1-23. Perform cluster analysis on the target behavior data of the external promotion platform and the internal promotion platform to obtain the cluster analysis result;

[0219] In this step, the K-means algorithm is used to perform cluster analysis on the target behavior data of the external promotion platform and the internal promotion platform. The main goal is to divide users into different groups according to their behavior characteristics. First, multiple dimensions that can reflect users' behavior characteristics are selected from the target behavior data as clustering features, including but not limited to the total number of clicks on specific non-performing assets by users, which reflects users' attention to assets. The stay time of users on the promotion information page usually indicates the depth of users' interest in the content; the number of shares or favorites: the sharing or favorite behavior of users on the promotion information indicates the degree of affirmation of the asset by users; the number of negative behaviors: such as the number of operations such as quickly jumping out, canceling, or blocking, indicating users' negative tendencies. Standardize the above features to adjust data with different dimensions to the same scale to prevent certain data from having too much influence on the clustering result. In the K-means clustering process, the Euclidean Distance is used to calculate the similarity between users in each behavior feature. By comparing the differences in features such as the number of clicks and stay time, the similarity of users' behaviors is measured. Through multiple experiments and using methods such as the elbow method or silhouette coefficient, the appropriate value of K is selected to ensure that users are reasonably divided into multiple groups. Generally, the value of K can be between 3 and 5, such as being divided into "high interaction group", "low interaction group", "high potential investment group", etc. After determining the value of K, the K-means algorithm is applied to cluster the users' behavior data. During the operation of the algorithm, each user will be classified into the group that is most similar to their behavior characteristics.

[0220] S1-24. According to the cluster analysis result, divide the users of the external promotion platform and the internal promotion platform to obtain several user groups and the corresponding user behavior characteristic labels;

[0221] Specifically, according to the previous K-means clustering analysis results, users are assigned to different groups. Each group represents a group of users with highly similar behavior data. Corresponding behavioral feature tags are assigned to each user group to identify the main behavioral features and preferences of the group. The feature tags include not only positive behavioral data (such as click-through rate, dwell time, number of shares, etc.), but also negative behavioral data (such as quick bounce, cancellation operation, etc.). Based on the feature tags, the behavioral preferences of each group can be further analyzed. For example, some user groups may tend to click on non-performing assets with lower prices, or show significant interest in a certain type of specific asset (such as real estate), and this information can be recorded as a behavioral preference tag.

[0222] S1-25. Perform a weighted operation based on the user behavior feature tags and the target behavior data to obtain the asset heat value of each non-performing asset;

[0223] Specifically, corresponding weighting coefficients are set according to the differences in each user behavior feature tag. These weights can be based on the judgment of the actual interest and investment potential of non-performing assets. Usually, the weights of positive behaviors (such as click-through rate, dwell time) are greater than those of negative behaviors (such as bounce rate), and the weights of high-interaction users are greater than those of low-interaction users. For example, the weight of the high-interaction group can be set between 1.2 and 1.5 to highlight the contribution of their behavior to the asset heat. The weight of the low-interaction group can be set between 0.5 and 0.8 to reduce the impact of this group on the heat. For negative behavior tags (such as quick bounce), negative weights can be set to reduce the contribution of users who are not interested in non-performing assets. Multiply the standardized behavior data by the weighting coefficient to reflect the contributions of different behaviors and groups to the asset heat.

[0224] Specifically, the behavior patterns of different groups may be different, so the above weights can be adjusted according to the clustering analysis results. For example, if a certain group shows a high level of activity, frequently clicks and stays for a long time, the weights of their positive behaviors can be appropriately increased to highlight their degree of interest. Specifically, the following rules can be followed: increase the positive behavior weights for the high-active group, and enhance and adjust the negative behavior weights for the low-active group to capture the rejection tendency.

[0225] After adding negative behaviors, this solution can more accurately identify users' interests and rejection tendencies. Based on the combined weight calculation of positive and negative behaviors, combined with judgment and clustering analysis, users who are not interested can be effectively screened out, reduce ineffective push, and ensure that the recommended content better meets the actual needs of users.

[0226] By way of example and not limitation, for users with a relatively high negative tendency, appropriately reduce the push frequency to avoid user boredom. For users with a relatively high frequency of blocking or jumping out, try to push different types of non-performing assets to avoid monotonous recommended content. For users with an obvious positive tendency and few negative behaviors, further refine the push content to make the promotion information more in line with their demand preferences.

[0227] Embodiment 3

[0228] In addition, in combination with Figure 1 The multi-platform-based non-performing asset information push method described in the embodiments of the present invention can be implemented by an information push device. Figure 6 FIG. shows a schematic hardware structure diagram of the information push device provided by the embodiments of the present invention.

[0229] The information push device may include a processor and a memory storing computer program instructions.

[0230] Specifically, the above-mentioned processor may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0231] The memory may include a mass storage for data or instructions. By way of example and not limitation, the memory may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disc, a magneto-optical disc, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. In a suitable case, the memory may include a removable or non-removable (or fixed) medium. In a suitable case, the memory may be internal or external to the data processing device. In a specific embodiment, the memory is a non-volatile solid state memory. In a specific embodiment, the memory includes a read only memory (ROM). In a suitable case, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0232] The processor reads and executes the computer program instructions stored in the memory to implement any one of the multi-platform-based non-performing asset information push methods in the above embodiments.

[0233] In one example, the information push device may further include a communication interface and a bus. Among them, as Figure 6As shown, a processor 401, a memory 402, and a communication interface 403 are connected via a bus 410 to complete communication with each other.

[0234] The communication interface is mainly used to implement communication between each module, device, unit, and / or equipment in the embodiments of the present invention.

[0235] The bus includes hardware, software, or both, and couples the components of the information push device to each other. By way of example and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, the bus may include one or more buses. Although the embodiments of the present invention describe and illustrate specific buses, the present invention contemplates any suitable bus or interconnect.

[0236] Embodiment 4

[0237] In addition, in combination with the non-performing asset information push method based on multiple platforms in the above embodiments, the embodiments of the present invention can be implemented by providing a computer-readable storage medium. Computer program instructions are stored on the computer-readable storage medium; when the computer program instructions are executed by a processor, any one of the non-performing asset information push methods based on multiple platforms in the above embodiments is implemented.

[0238] In summary, the bad asset information push method, device, and storage medium based on multiple platforms provided by the embodiments of the present invention obtain the promotion information of each bad asset and push the promotion information to each designated platform through a preset standardized interface. Among them, the designated platforms include the self-owned channel platform and the external promotion platform. By using the standardized interface, it ensures the fast, accurate, and consistent transmission of bad asset promotion information, reduces human errors and delays in information transmission, and improves the efficiency of information release. In addition, covering multiple platforms broadens the exposure rate of assets and increases the interaction opportunities between the transferor and potential investors. By analyzing user behavior data, it is possible to monitor and evaluate the market demand and investor interest in bad assets in real time, and form a dynamic asset heat value. This mechanism helps the transferor to timely understand which assets are being concerned, so as to optimize marketing strategies and resource allocation. Pushing based on the asset heat value and user behavior data effectively improves the relevance and matching degree of information, making the promotion information more targeted. This not only improves the response rate of users to the promotion information, but also enhances the sense of participation and satisfaction of investors. By setting withdrawal conditions and monitoring in real time, it ensures the timeliness and accuracy of bad asset information. This flexible management method can reduce the interference of outdated information to investors, thus maintaining the credibility and effectiveness of platform information.

[0239] It should be clear that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, the detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order between steps after understanding the spirit of the present invention.

[0240] The functional blocks shown in the above structural block diagrams can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a functional card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted through a data signal carried in a carrier wave on a transmission medium or a communication link. A "machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical discs, hard disks, fiber optic media, radio frequency (RF) links, and so on. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0241] It should also be noted that in the exemplary embodiments mentioned in the present invention, some methods or systems are described based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps can be executed in the order mentioned in the embodiments, or different from the order in the embodiments, or several steps can be executed simultaneously.

[0242] As described above, the above is only the specific implementation manner of the present invention. Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described systems, modules, and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein. It should be understood that the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention.

Claims

1. A method for pushing non-performing asset information based on multiple platforms, characterized in that, The method includes: Obtaining the promotion information of each non-performing asset and pushing the promotion information to each designated platform through a preset standardized interface, where the designated platforms are divided into self-owned channel platforms and external promotion platforms; Obtaining the first behavior data of users in each of the designated platforms for the promotion information, and calculating the asset heat value of each non-performing asset, including: At every preset time period, obtaining the first behavior data of users in each of the designated platforms for the promotion information through the preset standardized interface, where the self-owned channel platforms include internal promotion platforms and service provider platforms, and the first behavior data under the external promotion platforms and the internal promotion platforms includes the number of auction viewers for each non-performing asset, and the first behavior data under the service provider platforms includes the number of service provider solutions for each non-performing asset; Obtaining the total number of auction viewers of the external promotion platforms and the internal promotion platforms according to the number of auction viewers of all the non-performing assets; Obtaining the total number of solutions of the service provider platforms according to the number of service provider solutions of all the non-performing assets; Determining the behavior data weights of each of the designated platforms according to the total number of auction viewers and the total number of solutions; Performing a weighted operation according to the first behavior data of each of the designated platforms and the corresponding behavior data weights to obtain the asset heat value of each non-performing asset; Pushing the promotion information of the non-performing assets of interest to the self-owned channel platforms according to the asset heat value and / or the second behavior data of the self-owned channel platforms, where the second behavior data is extracted from the database based on the login information of users on the self-owned channel platforms and includes the assets historically viewed by users and the types of assets collected; In response to a non-performing asset meeting the preset withdrawal condition, withdrawing the promotion information of the corresponding non-performing asset on all the designated platforms through the preset standardized interface.

2. The bad asset information push method based on multiple platforms according to claim 1, wherein The pushing the promotion information of the non-performing assets of interest to the self-owned channel platforms according to the asset heat value and / or the second behavior data of the self-owned channel platforms includes: Judging whether the user logs in to the self-owned channel platform; If logged in, determining the non-performing assets of interest to the user according to the login information, the second behavior data, and the asset heat value; If not logged in, determining the non-performing assets of interest to the user according to the asset heat value; Pushing the promotion information of the non-performing assets of interest to the self-owned channel platforms through the preset standardized interface.

3. The non-performing asset information push method based on multiple platforms according to claim 2, wherein The promotion information includes the type of non-performing assets. The determining the non-performing assets of interest to the user if logged in according to the login information, the behavior data, and the asset heat value includes: Obtaining the personal behavior data of each user on the self-owned channel platform according to the login information of the user and the second behavior data, where the personal behavior data includes the first click quantity of the user for each non-performing asset and the second click quantity of the user for each type of non-performing asset; Obtaining the interest degree value of the user for all non-performing assets according to the first click quantity, the second click quantity, and the asset heat value; Determine the non-performing assets of interest to the user according to the interest degree value of each non-performing asset.

4. The method for pushing non-performing asset information based on multiple platforms according to claim 3, characterized in that, The obtaining of the interest degree value of the user for all non-performing assets according to the first click quantity, the second click quantity, and the asset heat value includes: Obtain the initial weight values of the first click quantity, the second click quantity, and the asset heat value respectively; Adjust each of the initial weight values according to a pre-constructed neural network model and the behavior data to obtain target weight values; Perform a weighted operation according to the first click quantity, the second click quantity, the asset heat value, and the corresponding target weight values to obtain the initial interest degree value of each non-performing asset; Perform a normalization process on the initial interest degree value to obtain the interest degree value of the user for all non-performing assets.

5. The bad asset information push method based on multiple platforms according to any one of claims 1-4, characterized in that, The responding to a non-performing asset meeting a preset withdrawal condition and withdrawing the promotion information of the corresponding non-performing asset on all the specified platforms through the preset standard interface includes: Obtain the asset status information of each non-performing asset through the preset standard interface, where the asset status information includes: asset status change information and asset term information; Judge whether the corresponding non-performing asset meets the preset withdrawal condition according to the asset status change information and the asset term information; When a non-performing asset meets the preset withdrawal condition and / or receives a manual withdrawal instruction, send a withdrawal instruction to each of the specified platforms through the preset standard interface to withdraw the promotion information of the corresponding non-performing asset.

6. The method for pushing non-performing asset information based on multiple platforms according to claim 5, wherein Obtain the promotion information of each non-performing asset and push the promotion information to each specified platform through the preset standard interface, including: Obtain the initial multi-dimensional information of each non-performing asset according to a preset data source; Perform preprocessing on the initial multi-dimensional information of each non-performing asset to obtain target multi-dimensional information, where the preprocessing includes: data cleaning, data standardization, and data verification; Generate multi-dimensional labels for each non-performing asset according to the target multi-dimensional information and a preset rule engine, where the multi-dimensional labels include a disposal status label, an asset type label, a disposal difficulty label, and a historical auction label; Generate promotion information corresponding to each specified platform, denoted as platform promotion information, according to the multi-dimensional labels and the user portraits of each specified platform, where the user portraits are generated based on the first behavior data; Push each of the platform promotion information to the corresponding specified platform through the preset standard interface.

7. The method for pushing non-performing asset information based on multiple platforms according to claim 6, characterized in that The generating of multi-dimensional labels for each non-performing asset according to the target multi-dimensional information and a preset rule engine includes: Initialize the preset rule engine according to the preset non-performing asset business classification standard information to obtain a target rule engine; Input the target multi-dimensional information into the target rule engine to obtain the initial multi-dimensional labels of each non-performing asset; Perform statistical analysis on the historical data of each non-performing asset according to the initial multi-dimensional labels of each non-performing asset to obtain the representative indicators of each initial multi-dimensional label, where the representative indicators at least include the mean and the variance; Screen the corresponding initial multi-dimensional labels according to the representative indicators of each initial multi-dimensional label and the corresponding representative indicator thresholds to obtain intermediate multi-dimensional labels; Input the target multi-dimensional information and the corresponding intermediate multi-dimensional labels into a pre-constructed Bayesian network to obtain the joint probabilities between each of the intermediate multi-dimensional labels and the corresponding target multi-dimensional information; Judge whether there is a conflict between the intermediate multi-dimensional label and the corresponding target multi-dimensional information according to the joint probability; If there is a conflict, adjust the target rule engine according to the intermediate multi-dimensional label with the conflict, and return to the step of inputting the target multi-dimensional information into the target rule engine to obtain the initial multi-dimensional labels of each non-performing asset; If there is no conflict, use the initial multi-dimensional label of the non-performing asset as its final multi-dimensional label.

8. The non-performing asset information pushing method based on multiple platforms according to claim 7, characterized in that After the method responds to a non-performing asset satisfying a preset withdrawal condition and withdraws the promotion information of the corresponding non-performing asset on all the specified platforms through the preset standard interface, it further includes: According to the asset term information, obtain the non-performing assets withdrawn after exceeding the preset sale term, and record them as overdue withdrawal assets; According to the asset status information, obtain the set of sold non-performing assets; According to the multi-dimensional label, obtain the non-performing assets matching the overdue withdrawal assets in the set of sold non-performing assets, and record them as target sold assets; Obtain the promotion information of each of the target sold assets on the specified platform where it is sold, and record it as sold promotion information; Obtain the display parameters of the sold promotion information, where the display parameters include the display frequency, display time period, and promotion content of the promotion information; Perform data aggregation processing on the display parameters to generate aggregated display parameters; Perform correlation analysis on the multi-dimensional labels of the overdue withdrawal assets and the multi-dimensional labels of the unsold non-performing assets to determine the similarity between each of the overdue withdrawal assets and the unsold non-performing assets; Classify the unsold non-performing assets according to the similarity to obtain multiple asset classification groups; Match the aggregated display parameters with each asset classification group to obtain the optimized promotion information for each asset classification group; Update the optimized promotion information to each specified platform through the preset standard interface to adjust the promotion information of the currently unsold non-performing assets.

9. An information push device, characterized in that, Includes: At least one processor, at least one memory, and computer program instructions stored in the memory, which implement the method for pushing non-performing asset information based on multiple platforms as described in any one of claims 1-8 when the computer program instructions are executed by the processor.

Images