House resource flow regulation and control method and device

Abstract

The invention provides a housing resource flow regulation and control method and device, and the method comprises the steps: predicting the corresponding real-time housing resource connection amount of a target housing resource in a first time period according to the corresponding real-time housing resource connection amount of a target city in the first time period and the proportion of the plurality of cascaded housing resource connection amounts associated with the target housing resource in a second time period, the second time period is before the first time period and has the same duration as the first time period; according to the real-time housing resource connection amount of the target housing resource and the housing resource privilege lifting parameter of the target housing resource, determining the target housing resource connection amount, the housing resource privilege lifting parameter being determined based on the housing resource value-added service, the housing resource verification information and the housing resource privilege falling information of the target housing resource; and in response to the fact that the real house resource connection quantity corresponding to a certain statistical moment of the target house resource in the first time period is greater than the target house resource connection quantity at the moment, performing flow regulation and control on the target house resource in the first time period so as to reduce the exposure quantity of the target house resource. According to the invention, house resource flow regulation and control can be performed in a targeted manner, and the house resource flow can be accurately controlled.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method and apparatus for regulating housing supply flow. Background Technology

[0002] In traditional property listing traffic management strategies, landlords / sellers increase customer acquisition through methods such as purchasing commercial products to boost listing exposure, verifying listing authenticity according to platform verification rules, and using low-price lead generation. When purchasing commercial products, landlords / sellers experience a significant increase in listing exposure, thus gaining more user traffic. Verifying listing authenticity according to platform rules involves methods such as on-site verification, property certificate verification, and video authentication to ensure the listing's authenticity, thereby boosting traffic ranking and increasing customer acquisition. Using low-price lead generation involves landlords / sellers posting low-priced listings to increase customer acquisition.

[0003] Since property prices fluctuate dynamically, the platform can only determine whether a property listed by a landlord or seller is a suspected low-priced property. Removing such listings could easily lead to a large number of complaints. Therefore, the measures that the platform can take regarding low-priced properties are limited.

[0004] Under the current property listing traffic management strategy, most users are attracted by low-priced properties, while verified, genuine properties and those selling commercial properties attract very few customers. This will severely damage the platform's ecosystem in the long run. Furthermore, after users are attracted by low-priced properties, the transaction rate is often not optimistic, resulting in a poor user experience and a high risk of user churn. Summary of the Invention

[0005] In view of the above problems, this application provides a method and apparatus for controlling housing supply flow to overcome or at least partially solve the above problems.

[0006] In a first aspect, embodiments of this application provide a method for regulating housing supply flow, including:

[0007] Based on the real-time housing connection volume of the target city in the first time period and the proportion of multiple cascaded housing connection volumes associated with the target housing in the second time period, the real-time housing connection volume of the target housing in the first time period is predicted. The second time period is located before the first time period and has the same duration as the first time period.

[0008] The number of connections to the target property is determined based on the real-time connection volume of the target property and the property ranking enhancement parameters corresponding to the target property. The property ranking enhancement parameters are determined based on the property value-added services, property verification information and property ranking reduction information corresponding to the target property.

[0009] In response to the fact that the number of actual listing connections for the target property at a certain statistical moment in the first time period is greater than the number of target property connections at that moment, traffic control is applied to the target property in the first time period to reduce the exposure of the target property.

[0010] Secondly, embodiments of this application provide a housing flow control device, comprising:

[0011] The prediction module is used to predict the real-time connection volume of the target property in the first time period based on the real-time property connection volume of the target city in the first time period and the proportion of the connection volume of multiple cascaded properties associated with the target property in the second time period. The second time period is located before the first time period and has the same duration as the first time period.

[0012] The first determining module is used to determine the target property connection volume based on the real-time property connection volume corresponding to the target property and the property ranking parameter corresponding to the target property. The property ranking parameter is determined based on the property value-added services, property verification information and property ranking demotion information corresponding to the target property.

[0013] The first control module is used to control the traffic of the target property during the first period when the number of actual property connections at a certain statistical moment in the first period is greater than the number of target property connections at that moment, so as to reduce the exposure of the target property.

[0014] Thirdly, embodiments of this application provide an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps of the housing traffic control method described in the first aspect above.

[0015] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the housing traffic control method described in the first aspect above.

[0016] The technical solution of this application embodiment involves a server predicting the number of property connections based on the real-time property connection volume of the target city at the first statistical time and the proportion of cascaded property connections associated with the target property in the second statistical time. The server predicts the real-time property connection volume of the target property at the first statistical time, determines the target property connection volume based on the real-time property connection volume and the property weighting parameters corresponding to the target property, and compares the actual property connection volume of the target property in the first statistical time with the target property connection volume. If the actual property connection volume of the target property is greater than the target property connection volume at a certain statistical time, traffic control is applied to the target property in the first statistical time to reduce its exposure. This targeted traffic control precisely manages property traffic, ensuring that properties purchasing value-added services are not affected, while allowing high-quality, genuine properties to receive weighted traffic. This effectively curbs the use of fake property listings to drive traffic, ensuring a positive cycle for the entire platform ecosystem and guaranteeing user experience while reducing user churn. Attached Figure Description

[0017] Figure 1 A schematic diagram illustrating the housing traffic control method provided in the embodiments of this application;

[0018] Figure 2 This diagram illustrates a specific example of how the real-time housing connection volume is predicted based on the city's real-time housing connection volume and the proportion of multiple cascaded housing connection volumes, as provided in this application embodiment.

[0019] Figure 3 This is a flowchart illustrating the overall implementation of the housing supply flow control method provided in this application embodiment;

[0020] Figure 4 This is a schematic diagram of the housing traffic control device provided in the embodiments of this application;

[0021] Figure 5 This is a schematic diagram of the electronic device structure provided in the embodiments of this application. Detailed Implementation

[0022] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Multiple embodiments in this application may include two or more.

[0024] In the various embodiments of this application, it should be understood that the sequence number of each process described below does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0025] This application provides a method for regulating housing supply flow, such as... Figure 1 As shown, the method includes the following steps:

[0026] Step 101: Based on the real-time housing connection volume of the target city in the first time period and the proportion of multiple cascaded housing connection volumes associated with the target housing in the second time period, predict the real-time housing connection volume of the target housing in the first time period. The second time period is before the first time period and has the same duration as the first time period.

[0027] In this embodiment, the server counts the real-time listing connections for the target city at each statistical time point in the first time period, and pre-obtains the proportion of cascading listing connections associated with the target listing in the second time period. Then, based on the real-time listing connections for the target city at each statistical time point in the first time period and the proportion of cascading listing connections associated with the target listing, the server predicts the real-time listing connections for the target listing at each statistical time point in the first time period. In this embodiment, the first time period includes multiple statistical time points. The server can count the real-time listing connections for the target city at preset time intervals, such as 1 minute, 5 minutes, and 10 minutes, and can perform the real-time listing connection count based on randomly set statistical time points. Furthermore, the real-time listing connection count increases synchronously with time, and the real-time listing connection count at a later statistical time point is greater than or equal to the real-time listing connection count at a previous statistical time point. For each statistical time point, the corresponding real-time listing connection count is the total listing connection count from the initial time point of the first time period to the current time point.

[0028] The second time period precedes the first time period and has the same duration. To ensure the provision of the latest property connection volume ratio, the second time period is preferably continuous with the first time period. The duration of the first and second time periods is a pre-set unit duration, such as 24 hours. When the first and second time periods are continuous, the real-time property connection volume related to the target property for the following day is predicted based on the previous day's cascading property connection volume ratio associated with the target property and the real-time property connection volume of the target city as statistically analyzed for the following day.

[0029] In this embodiment, the number of property listing connections refers to the number of valid connections made by users using at least one target application (a platform supporting property rental and sales functions) with property agents / landlords through the target application, as counted by the server. Valid connections include chat connections within the target application and call connections established based on the target application. The target application is either a dedicated application supporting property rental and sales functions or a comprehensive application supporting multiple business functions (including property rental and sales functions). The server, as the backend platform for at least one target application, is used to count the number of property listing connections, such as counting the number of property listing connections for the entire city or for a specific region; it is also used to count other property-related information.

[0030] The rental and sales mentioned in this application embodiment can be understood as renting and / or selling, or renting / selling. The following example illustrates the server's statistics on parameters related to housing listings.

[0031] As shown in Table 1, for a given city, the server performs statistical analysis on the following metrics across all business districts within that city: total number of listings (i.e., the total number of listings in the city), number of commercial listings (the number of listings for which landlords and landlords purchase value-added services; value-added services can be understood as services enjoyed by landlords and landlords who purchase value-added service packages or obtain membership privileges on the platform to gain more exposure for their listings), number of listings with enhanced privileges (the number of listings corresponding to genuine and high-quality listings as determined by the platform's rules), number of fake listings, average exposure (the average number of times a listing is displayed to users on the listing page, determined based on the ratio of total listing views to total number of listings), average VPPV (the average number of times users click to enter the listing details page from the application's listing page), average price (such as average rental price or average selling price), total listing connections (the total number of valid connections within a certain period), and average listing connections (the ratio of total listing connections to total number of users within a certain period). Based on this data analysis, the distribution of listings and user traffic across various business districts in the entire city can be clearly seen, thus providing a basis for overall traffic control in the city.

[0032]

[0033] Table 1

[0034] As shown in Table 2, the server performs statistical analysis on the total number of listings, commercial listings, elevated listings, fake listings, average exposure, average VPPV, average price, total listing connections, and average listing connections of all brokerage companies (the companies that own the applications that support property rental and sales business functions) within a certain business district at a certain time period. This provides a clear understanding of the distribution of listings and user traffic across various companies in the entire business district, thereby providing a basis for overall traffic control in the business district.

[0035]

[0036] Table 2

[0037] As shown in Table 3, the server performs statistical analysis on a brokerage company at the brokerage company level for a certain period of time, including the total number of whole rentals and shared rentals, the number of commercial rentals, the number of listings with elevated privileges, the number of fake listings, the rental type, the average room rate, the average exposure, the average VPPV, the total number of listing connections, and the average number of listing connections. This provides a clear understanding of the distribution of user traffic across different types of rentals for the entire company, thus providing a basis for the company's overall traffic control.

[0038]

[0039] Table 3

[0040] Based on the contents of Tables 1, 2 and 3 above, it can be seen that by extracting valuable content for traffic control from massive housing data, and by statistically collecting and analyzing the extracted indicator data, refined traffic operation can be achieved.

[0041] In this embodiment, the percentage of multiple cascaded property connections associated with the target property during the second time period is determined based on the total property connections related to the target property, and these multiple property connection percentages have a cascaded relationship. This cascaded relationship is formed by the total property connections in a hierarchical manner. For example, the total property connections of a city, the total property connections of a certain area within the city (such as Dongcheng District), and the total property connections of a certain community within that area form a hierarchical relationship. Therefore, the percentage of multiple cascaded property connections is determined based on the total property connections forming this hierarchical relationship. As an example, based on Table 1, the total property connections of the target city and the total property connections of business district A are determined for a certain time period. Based on Table 2, the total property connections belonging to brokerage company A within business district A for a certain time period are determined. Therefore, the total property connections of the city, the total property connections of business district A, and the total property connections of brokerage company A have a hierarchical relationship, and the percentage of property connections is calculated based on each total property connection.

[0042] Since the proportion of multiple cascaded property connections is determined based on the total property connections related to the target property, after obtaining the real-time property connection volume of the target city at the first statistical time and the proportion of multiple cascaded property connections, the real-time property connection volume of the target property at the first statistical time can be predicted based on the obtained information.

[0043] Step 102: Determine the target property connection volume based on the real-time property connection volume and the property ranking parameters corresponding to the target property. The property ranking parameters are determined based on the property value-added services, property verification information and property ranking demotion information corresponding to the target property.

[0044] The server needs to determine the property boosting parameters corresponding to the target property based on the property value-added services, property verification information, and property de-weighting information corresponding to the target property. Then, based on the predicted real-time property connection volume of the target property at the statistical time and the property boosting parameters corresponding to the target property, the server determines the target property connection volume at the statistical time.

[0045] Value-added services corresponding to a target property refer to the value-added services purchased by the target landlord or tenant for that property. By purchasing these value-added services, the target property's exposure on the platform can be increased. For example, the target landlord or tenant may purchase value-added services such as property placement at the top of the list or product refresh. The purchased property placement service ensures that the target property is displayed at the top of the platform, while the purchased product refresh service ensures that the target property remains visible even after the property list is refreshed, thereby increasing the property's exposure.

[0046] The verification information for the target property is determined based on on-site verification, property certificate authentication, video authentication, and other information. This verification information is used to characterize the authenticity of the target property. The demotion information for the target property includes false information such as false prices, false listing status (e.g., the property is already rented, but the application still shows it as vacant), and false property location.

[0047] The predicted real-time connection volume of the target property at the statistical time can be understood as the predicted normal connection volume at the statistical time. After predicting the normal connection volume of the target property, the normal connection volume and the property weighting parameter corresponding to the target property are integrated to determine the target property connection volume. Based on the normal connection volume, the weighting situation corresponding to the target property is considered to determine the target property connection volume as the benchmark.

[0048] Step 103: In response to the fact that the number of actual listing connections for the target listing at a certain statistical moment in the first time period is greater than the number of target listing connections at that moment, traffic control is implemented for the target listing in the first time period to reduce the exposure of the target listing.

[0049] In the first period, the server monitors the actual number of connections to the target property in real time at each statistical moment. If the actual number of connections to the target property at a certain statistical moment in the first period is greater than the target property connection at that moment, it is determined that the actual number of connections to the target property has exceeded the target property connection set by prediction and property weighting parameters. Then, traffic control is implemented for the target property in the first period to reduce the exposure of the target property and achieve targeted property traffic control.

[0050] Specifically, when regulating the traffic of target properties during the first time period, the traffic regulation is carried out within a predetermined time period (e.g., within 2 hours) to reduce the exposure of target properties. After the regulation is completed, steps 101 to 103 are executed again to identify whether the regulation conditions are met based on the comparison between the actual property connection volume and the target property connection volume at the statistical time, and then the property traffic is regulated accordingly.

[0051] In the above implementation scheme of this application, the server predicts the number of property connections based on the real-time property connection volume of the target city at the first statistical time and the proportion of the connection volume of multiple cascaded property connections associated with the target property in the second statistical time. It predicts the real-time property connection volume of the target property at the first statistical time, determines the target property connection volume based on the real-time property connection volume and the property weighting parameters corresponding to the target property, and compares the actual property connection volume of the target property in the first statistical time with the target property connection volume. If the actual property connection volume of the target property is greater than the target property connection volume at a certain statistical time, traffic control is applied to the target property in the first statistical time to reduce its exposure. This achieves targeted property traffic control and precise control of property traffic. While ensuring that properties purchasing value-added services are not affected, it allows high-quality, genuine properties to receive weighted traffic, effectively curbing the use of fake property listings to drive traffic, ensuring a positive cycle for the entire platform ecosystem, guaranteeing user experience, and reducing user churn.

[0052] The following describes the process of predicting the real-time listing connectivity for the target property in the first time period. Before predicting the real-time listing connectivity, the method also includes:

[0053] The system acquires the total number of property listings connected to the target city, the total number of property listings connected to the target region, the total number of property listings connected to the target store on the target platform in the target region, the total number of property listings connected to the target landlord / seller, and the total number of property listings connected to the target property in the second time period. The target region belongs to the target city, the target store includes the property listings in the target region that belong to the target platform, and the property listings published by the target landlord / seller in the target store include the target property. The target city, target region, target store, target landlord / seller, and target property form a target set that includes multiple cascading objects arranged in sequence.

[0054] Based on the total number of property connections corresponding to adjacent subsequent cascaded objects and preceding cascaded objects in the target set during the second time period, calculate the proportion of property connections associated with multiple cascaded objects in the target property during the second time period.

[0055] The server counts the total number of property listings connected to the target city, the total number of property listings connected to the target region, the total number of property listings connected to the target platform's target stores in the target region, the total number of property listings connected to the target sellers' listings at the target stores, and the total number of property listings connected to the target properties in the second time period. The target region is one of multiple regions included in the target city, such as a business district or one of the multiple regions divided within the city; the target platform is a platform that supports property rental and sales functions; the target store is a store on the target platform corresponding to the target region; the target property is a property listed by the target seller at the target store, and the property listed by the target seller may also include other properties. In this embodiment, the total number of property listings connected to the target seller is the total number of property listings connected to all properties listed by the target seller at the target store. The target city, target region, target store, target landlord / tenant, and target property form a series of cascading objects. The cascading objects are located in the target set. That is, the target city is the first-level object of the target region, the target region is the first-level object of the target store, the target store is the first-level object of the target landlord / tenant, and the target landlord / tenant is the first-level object of the target property.

[0056] As an example, servers connected to multiple platforms can count the total number of listings connected to properties in city M on a given day; the total number of listings connected to business district A in city M on a given day; the total number of listings connected to store B on platform B in business district A on a given day; the total number of listings posted by seller C on store B on a given day; and the total number of listings connected to property D belonging to seller C on store B (property D is a listing posted by seller C on store B). City M, business district A, store B, seller C, and property D form multiple cascading objects arranged in sequence.

[0057] After obtaining the total number of property connections for the target city, target region, target store, target landlord / tenant, and target property in the second time period through data statistics, the property connection percentage is calculated for adjacent cascaded objects in the target set. Since the target city, target region, target store, and target landlord / tenant in the target set are all indirectly or directly related to the target property, the property connection percentage is determined based on the total number of property connections corresponding to the adjacent subsequent cascaded objects and the preceding cascaded objects, respectively. Therefore, the calculated property connection percentages for multiple cascades are all associated with the target property.

[0058] When calculating the proportion of property connections of multiple cascaded properties associated with the target property in the second time period, the following steps are taken: for any two adjacent cascaded objects in the target set, the proportion of property connections is calculated based on the ratio of the total property connections of the later cascaded object in the second time period to the total property connections of the earlier cascaded object in the second time period, so as to determine the proportion of property connections of multiple cascaded properties associated with the target property in the second time period.

[0059] For cascading objects forming a cascading relationship in the target set, for any group of cascading objects (including two adjacent cascading objects), the proportion of property connections is calculated based on the ratio of the total property connections of the subsequent cascading object in the second time period to the total property connections of the preceding cascading object in the second time period. The target set includes multiple groups of cascading objects, each group including one preceding cascading object and one subsequent cascading object, and these two cascading objects are adjacent in the target set. By calculating the proportion of property connections for each group of cascading objects, the proportion of property connections for multiple cascading objects associated with the target property can be determined. The proportion of property connections for multiple cascading objects is adapted to the multiple groups of cascading objects included in the target set. In this embodiment, cascading refers to the hierarchical connection relationship between multiple objects.

[0060] As an example, after the server obtains the total number of property listings connected in city M, the total number of property listings connected in business district A, the total number of property listings connected at store B in business district A, the total number of property listings connected at store B by seller C, and the total number of property listings connected (listed by seller C at store B) for the second time period through data statistics, it determines the property listing connection ratio of 1 for a cascaded object consisting of city M and business district A, based on the ratio of the total number of property listings connected in business district A to the total number of property listings connected in city M; for business district A... For a cascading object consisting of store B and property B, the property connection percentage 2 is determined based on the ratio of the total number of property connections corresponding to store B to the total number of property connections corresponding to business district A. For a cascading object consisting of store B and property C, the property connection percentage 3 is determined based on the ratio of the total number of property connections corresponding to property C to the total number of property connections corresponding to store B. For a cascading object consisting of property C and property D, the property connection percentage 4 is determined based on the ratio of the total number of property connections corresponding to property D to the total number of property connections corresponding to property C. The four property connection percentages determined above are cascading and all associated with property D. Thus, the multiple cascading property connection percentages associated with property D include property connection percentage 1, property connection percentage 2, property connection percentage 3, and property connection percentage 4.

[0061] After obtaining the percentage of cascading property connections associated with the target property, when predicting the real-time property connections for the target property in the first time period, based on the real-time property connections for the target city in the first time period and the percentage of cascading property connections associated with the target property in the second time period, the following steps are taken:

[0062] The target result is obtained by progressively multiplying the real-time housing connection volume of the target city at the statistical time corresponding to the first time period with the proportion of housing connection volume of multiple cascades; the target result is determined as the predicted real-time housing connection volume of the target housing at the statistical time; wherein, the first time period includes multiple statistical times, and the order of the proportion of housing connection volume of multiple cascades is matched with the order of the cascaded objects in the target set.

[0063] After determining the real-time housing connection volume of the target city at the first statistical time based on real-time data statistics, and obtaining the proportion of housing connection volume of multiple cascaded properties associated with the target property in the second time period, the real-time housing connection volume of the target city at the first statistical time period is progressively multiplied by the proportion of housing connection volume of multiple cascaded properties to obtain the target result. The target result is the predicted real-time housing connection volume of the target property at the first statistical time period. The order of the proportion of housing connection volume of multiple cascaded properties matches the order of the cascaded objects in the target set; that is, the order of the proportion of housing connection volume of multiple cascaded properties matches the order of the multiple sets of cascaded objects.

[0064] For example, such as Figure 2 As shown, for city M, the total number of property listings connected in the second time period is m, and the proportion of property listings connected in business district A in the second time period is a% (the ratio of the total number of property listings connected in business district A in the second time period to the total number of property listings connected in city M in the second time period, m, is a%). Figure 2 In this scenario, City M, Business District A, Platform B's Store B in Business District A, Rental / Sales Agent C, and Property D constitute multiple cascading entities. Rental / Sales Agent C posts a property on Store B, and Property D is one of multiple properties posted by Rental / Sales Agent C on Store B. Platform B's Store B in Business District accounts for b% of the property connections in the second time period (the ratio of Platform B's Store B's total property connections in Business District A in the second time period to the total property connections in Business District A in the second time period is b%), Rental / Sales Agent C accounts for c% of the property connections in the second time period (the ratio of Rental / Sales Agent C's total property connections on Store B in the second time period to the total property connections on Store B in the second time period is c%), and Property D accounts for d% of the property connections in the second time period (the ratio of Property D's total property connections in the second time period to the total property connections on Store C's Store B in the second time period is d%). After obtaining the real-time housing connection volume n of the target city at the first statistical time based on real-time statistics, the real-time housing connection volume n is predicted based on the progressive multiplication of the real-time housing connection volume n with the proportion of housing connection volume of multiple cascaded properties at the first statistical time. Specifically, the predicted real-time housing connection volume p = n * a% * b% * c% * d.

[0065] The above implementation scheme of this application obtains the total number of property connections corresponding to the target city, target region, target store, target landlord / seller, and target property in the second time period. After calculating the proportion of multiple cascading property connections associated with the target property based on the total number of property connections, the real-time property connection volume of the target city at the statistical time of the first time period is progressively multiplied by the proportion of multiple cascading property connections to predict the real-time property connection volume corresponding to the target property at the statistical time of the first time period. The prediction of real-time property connection volume can be achieved from the dimensions of city -> region -> store -> landlord / seller -> property.

[0066] In an optional embodiment of this application, the method further includes:

[0067] The first boosting parameter is determined based on the value-added service category of the target property; the second boosting parameter is determined based on the property verification information of the target property; the demotion parameter is determined based on the property demotion information of the target property, including false property information; the property boosting parameter for the target property is determined based on the first boosting parameter, the second boosting parameter, and the demotion parameter; wherein the first boosting parameter and the second boosting parameter are positively correlated with the property boosting parameter, and the demotion parameter is negatively correlated with the property boosting parameter.

[0068] Before determining the target property's connection volume based on the predicted real-time connection volume at the first time period, it is also necessary to determine the property's weighting parameters. These weighting parameters are determined based on the first weighting parameter of the associated property's value-added services, the second weighting parameter of the associated property's verification information, and the third weighting parameter of the associated property's deweighting information.

[0069] The first boosting parameter is determined based on the value-added service category of the target property. For example, if the validity period of the property's featured listing service is one month, the first boosting parameter is 0.2; or if the validity period of the product refresh service and the featured listing service is two months, the first boosting parameter is 0.6. The second boosting parameter is determined based on the property verification information. For example, if the target property has undergone on-site verification, the second boosting parameter is 0.1; or if the target property has undergone on-site verification, video verification, and property certificate verification, the second boosting parameter is 0.3. The demotion parameter is determined based on the property's demotion information, which includes false information such as false prices, false locations, and false listing status.

[0070] After determining the first and second boosting parameters that are positively correlated with the property listing boosting parameter, and the debuffing parameter that is negatively correlated with the property listing boosting parameter, the property listing boosting parameter is calculated based on the following formula when determining the property listing boosting parameter based on the first boosting parameter, the second boosting parameter, and the debuffing parameter:

[0071] q=(1+E)*(1+F)*(1-G)

[0072] Where q is the property listing priority parameter, E is the first priority parameter, F is the second priority parameter, and G is the priority demotion parameter.

[0073] After determining the first weighting parameter, the second weighting parameter, and the weighting reduction parameter, the first parameter is determined based on the sum of the first weighting parameter and 1, the second parameter is determined based on the sum of the second weighting parameter and 1, the third parameter is determined based on the difference between 1 and the weighting reduction parameter, and the housing weighting parameter is determined based on the product of the first parameter, the second parameter, and the third parameter. The final housing weighting parameter is determined by fusing two types of parameters that are positively correlated with the housing weighting parameter and those that are negatively correlated with the housing weighting parameter.

[0074] After predicting the real-time connection volume of the target property and determining the property weighting parameters, when determining the target property connection volume based on the real-time connection volume and the property weighting parameters, the target property connection volume corresponding to the statistical time of the first time period is determined by multiplying the real-time connection volume of the target property at the statistical time of the first time period with the property weighting parameters.

[0075] Given the predicted real-time connection volume of the target property at the first statistical time, and the determination of the property weighting parameters based on the weighting and deweighting of the target property, the predicted real-time connection volume is integrated with the property weighting parameters to estimate the target property connection volume at the first statistical time. This achieves the goal of determining the target property connection volume based on the prediction of the real-time connection volume, considering the property weighting parameters, and multiplying the predicted real-time connection volume with the property weighting parameters.

[0076] The following example illustrates the process of determining the target property listing connection volume. In city M, the property listing connection volume at the first statistical moment of the first time period is 1000. The pre-determined proportion of property listing connections in business district A is 10%. Platform B's store in business district A accounts for 20% of the total property listing connections in business district A. Platform C's rental and sales platform accounts for 50% of the total property listing connections compared to its store. Property D's property listing connection volume compared to Platform C's rental and sales platform accounts for 30%. Therefore, the predicted real-time property listing connection volume for property D at the first statistical moment of the first time period is: 1000 * 10% * 20% * 50% * 30%, which is 3. If property D has purchased product refresh value-added services, property listing top placement value-added services, or other value-added services, its weight should be increased by 80%. If property D has also undergone on-site verification, property certificate authentication, etc., its weight should be increased by 30%. If property D does not have any false property listing information, no weight reduction parameter needs to be considered. In this case, the weighting parameter for property D is (1+80%)*(1+30%) = 2.34. When the predicted real-time connection volume of property D at the first statistical time is 3, the target connection volume is determined based on the product of the predicted real-time connection volume and the weighting parameter of property D, 2.34.

[0077] The above-described implementation scheme of this application determines the target property's weighting parameters, and determines the target property's connection volume based on the weighting parameters and the predicted real-time property connection volume. It can estimate the target property's connection volume as a benchmark by considering the property weighting parameters based on the prediction of the property connection volume.

[0078] The following describes the scheme for controlling the traffic to a property listing. When the server determines that the actual number of connections to a target property listing at a certain statistical moment in the first time period is greater than the number of connections to the target property listing at that moment, it will control the traffic to the target property listing for a preset duration within the first time period. This process includes the following steps:

[0079] In response to a statistical moment when the number of actual listing connections for a target property exceeds the number of listing connections for that property, the display of the target property on the property recommendation page will be canceled and / or the proactive recommendation of the target property to the user will be canceled within a preset time period.

[0080] In the first time period, the server employs a real-time statistical strategy to track the actual connection volume of the target property. If, at a certain statistical moment, the actual connection volume of the target property exceeds the predicted connection volume for that moment, traffic control is implemented for the target property within a preset duration (e.g., 2 hours) to reduce its exposure. During the traffic control phase, the prediction of real-time connection volume and the tracking of actual connection volume can be temporarily suspended, resuming only after the control period ends. Alternatively, the tracking of actual connection volume can continue during the control phase to compare it with the target property's connection volume, stopping control when certain conditions are met.

[0081] Specifically, when controlling traffic to target properties, measures include removing the display of target properties on the property recommendation page and / or canceling proactive recommendations of target properties to users. This reduces the exposure of target properties, allowing for targeted traffic control and precise management. Removing the display of target properties on the property recommendation page prevents users from learning about them while browsing the page, thus reducing their exposure. Canceling proactive recommendations reduces the frequency of recommendations, further decreasing the exposure of target properties.

[0082] In the case of traffic control for the target property, if a property search request is received, the system determines the list of matching property search results based on the property search request. In response to the property search results list including the target property, the system controls the target property to be placed at the end of the property search results list.

[0083] By selectively controlling the traffic to target properties to reduce their exposure, in response to a property search request, the system determines a list of property search results that match the request. If the target property is included in the search results list, it controls the target property to be placed at the end of the search results list. This ensures that users' property search needs are met while preventing the precisely searched target property from being displayed at the top of the search results list.

[0084] In the implementation process described above, the server counts the actual number of connections to the target property during the first time period. If the actual number of connections to the target property at a certain statistical moment is greater than the estimated number of connections, the server reduces the exposure of the target property by canceling its display on the property recommendation page and / or canceling the proactive recommendation of the target property to users. This allows for precise control of property traffic. When regulating the traffic to the target property, if the target property is determined based on the property search request, controlling its placement at the end of the property search results list can ensure that the properties that meet the user's needs are pushed to the server while preventing the target property from being displayed in a prominent position.

[0085] In an optional embodiment of this application, the method further includes: responding to the newly published first listing being an approximate listing of the target listing, determining the real-time listing connection volume corresponding to the predicted target listing in the first time period as the real-time predicted listing connection volume corresponding to the first listing in the first time period; determining the target predicted listing connection volume corresponding to the first listing based on the real-time predicted listing connection volume and the listing weighting parameter corresponding to the first listing; and performing traffic control on the first listing in the first time period based on the target predicted listing connection volume and the actual listing connection volume corresponding to the first listing.

[0086] For newly released first listings (such as listings newly added in the first time period or listings added before the first time period with a short online time), similar listings are identified. Similar listings include, for example, listings in the same community with the same room type, or listings with the same floor plan. Since the newly released first listing and the target listing are similar, the real-time listing connection volume corresponding to the target listing at the statistical time of the first time period is determined as the real-time predicted listing connection volume corresponding to the first listing at the statistical time of the first time period. This achieves the determination of the real-time predicted listing connection volume related to the first listing based on the prediction of similar listings. Furthermore, for the first listing, its corresponding listing weighting parameters are determined. These parameters are based on the listing's value-added services, verification information, and deweighting information. The process of determining the listing weighting parameters for the first listing is similar to that for the target listing, and will not be elaborated here.

[0087] The target predicted number of listing connections for the first listing is determined by multiplying the real-time predicted listing connection volume at a specific statistical moment within the first time period by the listing weighting parameter. Based on the target predicted listing connection volume at each statistical moment, traffic control is applied to the first listing within the first time period. The target predicted listing connection volume is determined by considering the listing weighting effect based on the real-time predicted listing connection volume. By comparing the target predicted listing connection volume with the actual listing connection volume corresponding to the first listing, it is determined whether traffic control is necessary. For example, if the actual listing connection volume corresponding to the first listing at a certain statistical moment exceeds the target predicted listing connection volume at that moment, the exposure of the first listing is reduced, achieving targeted traffic control.

[0088] The above implementation process, in response to the fact that the newly released first listing and the target listing are similar listings, uses the real-time listing connection volume of the target listing at the statistical time as the real-time predicted listing connection volume of the first listing at the statistical time. Then, considering the listing weighting parameters, the target predicted listing connection volume is determined. The target predicted listing connection volume is used as a benchmark and compared with the actual listing connection volume at the corresponding time to regulate the traffic of the first listing in the first time period. This can realize the traffic regulation of newly released listings based on the predicted listing connection volume of similar listings, ensuring reasonable and accurate listing traffic regulation.

[0089] The following describes a scheme for controlling the flow of target properties through a comprehensive implementation process, such as... Figure 3 As shown:

[0090] Step 301: Obtain the total number of property listings connected in the target city during the second time period, the total number of property listings connected in the target region, the total number of property listings connected in the target region by the target platform, the total number of property listings connected in the target rental and sales parties, and the total number of property listings connected in the target property.

[0091] Step 302: Determine the proportion of multiple cascaded property connections based on the total number of property connections obtained.

[0092] Step 303: Multiply the real-time housing connection volume of the target city at the first time period statistical time by the proportion of housing connection volume of multiple cascaded properties to predict the real-time housing connection volume of the target property at the first time period statistical time.

[0093] Step 304: Determine the parameters for improving the ranking of the target property based on the property value-added services, property verification information, and property ranking downgrade information corresponding to the target property.

[0094] Step 305: Determine the target property connection volume by multiplying the real-time property connection volume corresponding to the target property by the property weighting parameter.

[0095] Step 306: In response to the determination at a certain statistical moment in the first time period that the actual number of connections to the target property is greater than the number of connections to the target property at that moment, cancel the display of the target property on the property recommendation page and / or cancel the proactive recommendation of the target property to the user within a preset time period.

[0096] The above implementation process predicts the real-time connection volume of the target property based on the proportion of multiple cascaded property connections and the real-time property connection volume of the target city. Based on the predicted property connection situation and property weighting parameters, the final property connection volume is estimated. Property flow is adjusted according to the comparison between the estimated final property connection volume and the actual property connection volume, which can carry out targeted, reasonable and precise property flow control.

[0097] The above is the overall real-time solution for the housing traffic control method provided in this application embodiment. The server predicts the housing connection volume based on the real-time housing connection volume of the target city at the statistical time of the first time period and the proportion of the connection volume of multiple cascaded housings associated with the target housing in the second time period. It predicts the real-time housing connection volume of the target housing at the statistical time of the first time period, determines the target housing connection volume based on the real-time housing connection volume and the housing weighting parameters of the target housing, and compares the real housing connection volume of the target housing in the real-time statistics of the first time period with the target housing connection volume. In response to the real housing connection volume of the target housing at a certain statistical time being greater than the target housing connection volume at that time, traffic control is performed on the target housing in the first time period to reduce the exposure of the target housing, thereby achieving targeted housing traffic control and precise control of housing traffic. Under the premise of ensuring that housing purchase value-added services are not affected, high-quality and genuine housing obtains weighted traffic, effectively curbs the behavior of fake housing driving traffic, ensures the positive cycle of the entire platform ecosystem, and can guarantee user experience and reduce user churn.

[0098] When a target property is determined based on a property search request, controlling the target property's placement at the end of the property search results list can ensure that properties that meet user needs are pushed to the user while preventing the target property from being displayed in a prominent position. By adjusting the traffic of newly released properties based on the predicted connection volume of similar properties, reasonable and accurate property traffic control can be achieved.

[0099] This application provides a housing flow control device, such as... Figure 4 As shown, it includes:

[0100] The prediction module 401 is used to predict the real-time housing connection volume of the target housing in the first time period based on the real-time housing connection volume of the target city in the first time period and the proportion of multiple cascaded housing connection volumes associated with the target housing in the second time period. The second time period is located before the first time period and has the same duration as the first time period.

[0101] The first determining module 402 is used to determine the target property connection volume based on the real-time property connection volume corresponding to the target property and the property ranking parameter corresponding to the target property. The property ranking parameter is determined based on the property value-added service, property verification information and property ranking demotion information corresponding to the target property.

[0102] The first control module 403 is used to control the traffic of the target property during the first period in response to the fact that the actual property connection volume at a certain statistical moment in the first period is greater than the target property connection volume at that moment. This is done to reduce the exposure of the target property.

[0103] Optionally, the device further includes:

[0104] The acquisition module is used to acquire the total number of housing connections corresponding to the target city, the total number of housing connections corresponding to the target region, the total number of housing connections corresponding to the target store of the target platform in the target region, the total number of housing connections corresponding to the target landlord / seller, and the total number of housing connections corresponding to the target housing during the second time period. The target region belongs to the target city, the target store includes housing in the target region belonging to the target platform, and the housing posted by the target landlord / seller in the target store includes the target housing. The target city, the target region, the target store, the target landlord / seller, and the target housing form a target set including multiple cascading objects arranged in sequence.

[0105] The calculation module is used to calculate the proportion of the number of cascaded properties associated with the target property in the second time period based on the total number of property connections of adjacent downstream cascaded objects and upstream cascaded objects in the target set in the second time period.

[0106] Optionally, the computing module is further configured to:

[0107] For any two adjacent cascaded objects in the target set, the proportion of property connection volume is calculated based on the ratio of the total property connection volume of the subsequent cascaded object in the second time period to the total property connection volume of the preceding cascaded object in the second time period, so as to determine the proportion of property connection volume of the target property associated with multiple cascades in the second time period.

[0108] Optionally, the prediction module includes:

[0109] The processing submodule is used to progressively multiply the real-time housing connection volume corresponding to the statistical time of the target city in the first time period with the proportion of housing connection volume of multiple cascaded units to obtain the target result;

[0110] The determination submodule is used to determine the target result as the predicted real-time number of housing connections for the target housing at the statistical time.

[0111] The first time period includes multiple statistical moments, and the order of the percentage of cascaded property connections matches the order of cascaded objects in the target set.

[0112] Optionally, the device further includes:

[0113] The second determining module is used to determine the first weighting parameter based on the value-added service category to which the value-added service of the target property belongs;

[0114] The third determining module is used to determine the second weighting parameter based on the property verification information corresponding to the target property.

[0115] The fourth determining module is used to determine the demotion parameters based on the demotion information of the target property, wherein the demotion information includes false information about the property.

[0116] The fifth determining module is used to determine the property escalation parameters corresponding to the target property based on the first escalation parameter, the second escalation parameter, and the de-escalation parameter;

[0117] The first and second weighting parameters are positively correlated with the property weighting parameters, while the weighting parameter is negatively correlated with the property weighting parameters.

[0118] Optionally, the fifth determining module is further configured to:

[0119] The property listing's weighting parameters are calculated based on the following formula:

[0120] q=(1+E)*(1+F)*(1-G)

[0121] Wherein, q is the property listing priority parameter, E is the first priority parameter, F is the second priority parameter, and G is the priority demotion parameter.

[0122] Optionally, the first determining module is further configured to:

[0123] The target property connection volume at the statistical time of the first time period is determined by multiplying the real-time property connection volume at the statistical time of the first time period with the property weighting parameter.

[0124] Optionally, the first control module includes:

[0125] The Cancel submodule is used to respond to a situation where, at a certain statistical moment, the actual number of connections to the target property is greater than the number of connections to the target property at that moment, and within a preset time period, cancel the display of the target property on the property recommendation page and / or cancel the proactive recommendation of the target property to the user.

[0126] Optionally, the device further includes:

[0127] The sixth determining module is used to determine a list of matching property search results based on a property search request if a property search request is received when the first regulating module regulates the flow of the target property.

[0128] A control module is configured to, in response to the fact that the property search results list includes the target property, control the target property to be placed at the end of the property search results list.

[0129] Optionally, the device further includes:

[0130] The seventh determination module is used to determine the real-time listing connection volume corresponding to the target listing in the first time period as the real-time predicted listing connection volume corresponding to the first listing in the first time period in response to the newly released first listing being an approximate listing of the target listing.

[0131] The eighth determining module is used to determine the target predicted number of housing connections corresponding to the first housing based on the real-time predicted housing connection volume and the housing weighting parameter corresponding to the first housing.

[0132] The second control module is used to control the flow of the first property based on the target predicted property connection volume and the actual property connection volume corresponding to the first property during the first time period.

[0133] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0134] This application also provides an electronic device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the various processes of the above-described housing flow control method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0135] For example, Figure 5 A schematic diagram of the physical structure of an electronic device is shown. (For example...) Figure 5 As shown, the electronic device may include a processor 510, a communications interface 520, a memory 530, and a communication bus 540. The processor 510, communications interface 520, and memory 530 communicate with each other via the communication bus 540. The processor 510 can call logical instructions stored in the memory 530. The processor 510 is used to execute various processes of the housing traffic control method according to the embodiments of this application, which will not be described in detail here.

[0136] Furthermore, the logical instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0137] This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described housing traffic control method embodiments and achieves the same technical effects. To avoid repetition, it will not be described again here. The computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0138] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0139] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0140] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

[0141] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0142] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0143] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0144] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0145] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0146] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0147] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for regulating housing supply flow, characterized in that, include: Based on the real-time housing connection volume of the target city in the first time period and the proportion of multiple cascaded housing connection volumes associated with the target housing in the second time period, the real-time housing connection volume of the target housing in the first time period is predicted. The second time period is located before the first time period and has the same duration as the first time period. The number of connections to the target property is determined based on the real-time connection volume of the target property and the property ranking enhancement parameters corresponding to the target property. The property ranking enhancement parameters are determined based on the property value-added services, property verification information and property ranking reduction information corresponding to the target property. In response to the fact that the number of actual listing connections for the target property at a certain statistical moment in the first time period is greater than the number of target property connections at that moment, traffic control is applied to the target property in the first time period to reduce the exposure of the target property.

2. The method according to claim 1, characterized in that, The method further includes: The system acquires the total number of property listings connected to the target city, the total number of property listings connected to the target region, the total number of property listings connected to the target store on the target platform in the target region, the total number of property listings connected to the target landlord / seller, and the total number of property listings connected to the target property during the second time period. The target region belongs to the target city, the target store includes properties in the target region belonging to the target platform, and the properties posted by the target landlord / seller in the target store include the target property. The target city, the target region, the target store, the target landlord / seller, and the target property form a target set consisting of multiple cascading objects arranged in sequence. Based on the total number of property connections corresponding to adjacent subsequent cascaded objects and preceding cascaded objects in the target set during the second time period, the proportion of property connections associated with the target property in multiple cascaded sets during the second time period is calculated.

3. The method according to claim 2, characterized in that, The step of calculating the proportion of property connections of the target property associated with multiple cascades in the second time period based on the total property connections of adjacent subsequent cascade objects and preceding cascade objects in the target set in the second time period includes: For any two adjacent cascaded objects in the target set, the proportion of property connection volume is calculated based on the ratio of the total property connection volume of the subsequent cascaded object in the second time period to the total property connection volume of the preceding cascaded object in the second time period, so as to determine the proportion of property connection volume of the target property associated with multiple cascades in the second time period.

4. The method according to claim 2, characterized in that, The step of predicting the real-time connection volume of the target property in the first time period based on the real-time property connection volume of the target city in the first time period and the proportion of the connection volume of multiple cascaded properties associated with the target property in the second time period includes: The target result is obtained by progressively multiplying the real-time housing connection volume of the target city at the statistical time of the first time period with the proportion of housing connection volume of the multiple cascaded properties. The target result is determined as the predicted real-time number of property connections for the target property at the statistical time. The first time period includes multiple statistical moments, and the order of the percentage of cascaded property connections matches the order of the cascaded objects in the target set.

5. The method according to claim 1, characterized in that, The method further includes: The first priority parameter is determined based on the value-added service category to which the value-added service of the target property belongs; The second weighting parameter is determined based on the property verification information corresponding to the target property. The demotion parameters are determined based on the demotion information of the target property, including false information about the property. Based on the first boosting parameter, the second boosting parameter, and the debuffing parameter, determine the boosting parameter for the target property. The first and second weighting parameters are positively correlated with the property weighting parameters, while the weighting parameter is negatively correlated with the property weighting parameters.

6. The method according to claim 5, characterized in that, The step of determining the property ranking parameters corresponding to the target property based on the first ranking parameter, the second ranking parameter, and the ranking demotion parameter includes: The property listing's weighting parameters are calculated based on the following formula: q=(1+E)*(1+F)*(1-G) Wherein, q is the property listing priority parameter, E is the first priority parameter, F is the second priority parameter, and G is the priority demotion parameter.

7. The method according to claim 1, 5, or 6, characterized in that, The step of determining the target property connection volume based on the real-time property connection volume and the property weighting parameters corresponding to the target property includes: The target property connection volume at the statistical time of the first time period is determined by multiplying the real-time property connection volume at the statistical time of the first time period with the property weighting parameter.

8. The method according to claim 1, characterized in that, In the case of traffic control for the target properties, the following are also included: If a property search request is received, determine a list of matching property search results based on the property search request; In response to the fact that the property search results list includes the target property, the target property is controlled to be placed at the end of the property search results list.

9. The method according to claim 1, characterized in that, The method further includes: In response to the newly released first listing being a listing similar to the target listing, the predicted real-time listing connection volume of the target listing in the first time period is determined as the real-time predicted listing connection volume of the first listing in the first time period. Based on the real-time predicted housing connection volume and the housing weighting parameters corresponding to the first housing, the target predicted housing connection volume corresponding to the first housing is determined. Based on the target predicted number of property connections and the actual number of property connections corresponding to the first property, traffic control is applied to the first property during the first time period.

10. A housing flow control device, characterized in that, include: The prediction module is used to predict the real-time connection volume of the target property in the first time period based on the real-time property connection volume of the target city in the first time period and the proportion of the connection volume of multiple cascaded properties associated with the target property in the second time period. The second time period is located before the first time period and has the same duration as the first time period. The first determining module is used to determine the target property connection volume based on the real-time property connection volume corresponding to the target property and the property ranking parameter corresponding to the target property. The property ranking parameter is determined based on the property value-added services, property verification information and property ranking demotion information corresponding to the target property. The first control module is used to control the traffic of the target property during the first period when the number of actual property connections at a certain statistical moment in the first period is greater than the number of target property connections at that moment, so as to reduce the exposure of the target property.

Images