Hair room effect improving method and device

Abstract

The invention provides a house issuing effect improving method and device. The method comprises the following steps: acquiring house resource putting data of each broker account in a broker account set in a target time period; based on a large model, analyzing housing resource release data, and determining a target broker account of which the release effect does not meet a first condition and a target housing resource of which the release effect does not meet a second condition; for each target broker account, based on a large model, analyzing housing resource putting data of the target broker account, and obtaining a first factor and / or a second factor associated with the target broker account, the first factor being a factor affecting the putting effect of the target broker account, and the second factor being a factor affecting the putting effect of the target broker account; the second factor is a factor influencing the putting effect of the target housing resource belonging to the target broker account; and according to the first factor and / or the second factor associated with the target broker account, generating a guidance suggestion for guiding improvement of the delivery effect. Effective room issuing guidance can be performed by analyzing factors influencing the delivery effect, and the customer obtaining effect of brokers is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computers, and in particular to a house listing effect improving method and device. BACKGROUND

[0002] Currently, when house listing agents publish house sources on a platform, they rely on their own experience and market perception to do so, which can easily lead to large differences in customer acquisition effects of different house listing agents, thereby making house listing agents with low customer acquisition quantities have poor customer acquisition experiences and easily losing customers.

[0003] Sales personnel who provide publishing seats for house listing agents on the platform lack guidance tools for guiding house listing agents to publish houses, which prevents the sales personnel from comprehensively assessing the correctness of the work of house listing agents.

[0004] As can be seen, in the prior art, when house listing agents publish houses on a platform, there are problems of poor customer acquisition effects of house listing agents due to lack of effective guidance, and problems of lack of house publishing guidance tools for sales personnel, which cannot objectively guide house listing agents to effectively publish houses. SUMMARY

[0005] In view of the above problems, the embodiments of the present application provide a house listing effect improving method and device which overcome the above problems or at least partially solve the above problems.

[0006] In a first aspect, the embodiments of the present application provide a house listing effect improving method, comprising:

[0007] Obtaining house source publishing data respectively corresponding to each agent account in a set of agent accounts in a target period;

[0008] Based on a large model, analyzing the obtained house source publishing data, determining a target agent account whose publishing effect does not satisfy a first condition, and determining a target house source whose publishing effect does not satisfy a second condition;

[0009] For each target agent account, based on a large model, analyzing house source publishing data corresponding to the target agent account, obtaining a first factor and / or a second factor associated with the target agent account, the first factor being a factor affecting the publishing effect of the target agent account, and the second factor being a factor affecting the publishing effect of a target house source attributed to the target agent account;

[0010] According to the first factor and / or the second factor associated with the target agent account, generating a guidance suggestion for guiding the target agent account to improve the publishing effect.

[0011] In a second aspect, the embodiments of the present application provide a house listing effect improving device, comprising:

[0012] The first obtaining module is configured to obtain house source posting data corresponding to each broker account in the set of broker accounts respectively in a target period;

[0013] The determining module is configured to determine a target broker account whose posting effect does not satisfy a first condition based on the large model analyzing the obtained house source posting data, and determine a target house source whose posting effect does not satisfy a second condition;

[0014] The analyzing module is configured to, for each target broker account, obtain a first factor and / or a second factor associated with the target broker account based on the large model analyzing house source posting data corresponding to the target broker account, the first factor being a factor affecting the posting effect of the target broker account, and the second factor being a factor affecting the posting effect of a target house source attributed to the target broker account;

[0015] The first generating module is configured to generate a guidance suggestion for guiding the target broker account to improve the posting effect according to the first factor and / or the second factor associated with the target broker account.

[0016] In a third aspect, an electronic device is provided, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor, and the computer program, when executed by the processor, implements the steps of the house posting effect improvement method according to the first aspect.

[0017] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program, when executed by a processor, implements the steps of the house posting effect improvement method according to the first aspect.

[0018] The technical scheme of the embodiment of the application, after obtaining the house source putting data corresponding to each broker account in the target period in the broker account set, identifies the target broker account with poor house source putting effect and the target house source with poor house source putting effect based on the obtained house source putting data; for each target broker account, analyzes the first factor affecting the putting effect of the target broker account, and / or analyzes the second factor affecting the putting effect of the target house source belonging to the target broker account, and generates guidance suggestions for guiding the target broker account to improve the putting effect according to the first factor and / or the second factor associated with the target broker account. The target broker with poor customer acquisition effect and the target house source belonging to the target broker can be marked, the target broker is guided based on the analyzed factors affecting the house source putting effect, the target broker can effectively put the house based on the guidance, the browsing volume of the customer to the published house source is improved, and the customer acquisition effect of the target broker is improved. While increasing the stickiness of the broker and the platform, the customer conversion and order transaction are further promoted. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 An example of a house putting effect improvement method provided by the embodiment of the application is shown.

[0020] Figure 2 An example of a calculation rule for calculating in the port dimension is shown.

[0021] Figure 3 An example of determining a score based on the ranking is shown.

[0022] Figure 4 An example of a calculation rule for calculating in the house source dimension is shown.

[0023] Figure 5 An example of a port effect display diagram provided by the embodiment of the application is shown.

[0024] Figure 6 An example of a house putting effect improvement device provided by the embodiment of the application is shown.

[0025] Figure 7 An example of an electronic device structure provided by the embodiment of the application is shown. DETAILED DESCRIPTION

[0026] The technical scheme of the embodiment of the application will be described in detail below with reference to the drawings in the embodiment of the application. Obviously, the described embodiments are part of the embodiments of the application, not all embodiments. Based on the embodiments in the application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the application.

[0027] It should be understood that every reference made throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. Therefore, appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily referring to the same embodiment. Furthermore, the particular features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous embodiments of the application can include, two or more, combinations of features, structures, or characteristics.

[0028] In various embodiments of the application, it should be understood that the magnitude of the serial number of the following processes does not mean the order of execution, the execution order of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the application.

[0029] To solve the problem of lack of effective guidance for house brokers when publishing houses on the platform, resulting in poor customer acquisition effect, and the problem that sales personnel cannot objectively guide house brokers to effectively publish houses, the embodiments of the application provide a house publishing effect improvement method. The house publishing effect improvement method includes the following steps: identifying target brokers and target houses with poor customer acquisition effect by counting house customer acquisition conditions; marking target brokers and target houses; analyzing factors affecting the publishing effect of target brokers and factors affecting the publishing effect of target houses attributed to target brokers; and guiding target brokers to effectively publish houses based on the analyzed factors affecting the publishing effect, thereby improving the house publishing effect and increasing the stickiness of brokers to the platform.

[0030] The house publishing effect improvement method provided by the embodiments of the application, as shown in Figure 1 includes the following steps:

[0031] Step 101: Obtain house publishing data corresponding to each broker account in a set of broker accounts in a target period.

[0032] The platform counts house publishing data corresponding to each broker account in a target period in the stored historical data for a set of broker accounts including multiple broker accounts, to obtain the house publishing conditions of each broker account. The broker account in the embodiments of the application corresponds to a house broker publishing houses on the platform. The house broker purchases one or more ports based on the guidance of sales personnel to publish houses on the platform. The number of houses allowed to be published by each port is limited, for example, one port allows to publish 20 houses. The length of the target period is a preset length, for example, one month, 15 days, 7 days, etc. The length of the target period can also be adjusted based on actual needs.

[0033] The house source putting data corresponding to the target period of the broker account includes at least the following information: house source publishing situation, port purchase situation, interaction with house finding users, click situation of the published house source, cost of purchasing value-added products, value-added house source situation put, and house source feature situation, etc.; the value-added product refers to a series of paid products launched by the platform to improve the exposure of the house source, attract potential customers, and protect the safety of the transaction; the value-added house source refers to the house source that obtains higher exposure rate, better display effect, and more security measures by purchasing value-added products provided by the platform; the house source feature situation includes, for example, house source quality (related to information completeness, uploaded picture and video quality, high-quality house source label, etc.), authenticity of the put house source, distribution of the put house source, house source covering building situation, building attribute of the house source covering building, etc.

[0034] Step 102, based on the large model analysis of the obtained house source putting data, determine the target broker account whose putting effect does not meet the first condition, and determine the target house source whose putting effect does not meet the second condition.

[0035] After obtaining the house source putting data corresponding to each broker account in the broker account set respectively, the obtained house source putting data is analyzed by using a large model, and the broker account whose putting effect does not meet the first condition is identified from the multiple broker accounts, which is used as the target broker account that needs to be focused on; and the house source whose putting effect does not meet the second condition is identified from the put house sources, which is used as the target house source, and the target house source is the house source that needs to be focused on.

[0036] Among them, the target broker account is the account corresponding to the house source broker whose house source putting effect is poor in the target period, and the target broker account is screened out based on intuitive data, so that the broker whose customer acquisition situation is poor can be marked as a key; the target house source is the house source whose putting effect is poor in the target period, and the target house source is screened out, so that the house source whose customer acquisition situation is poor can be marked as a key.

[0037] Step 103, for each target broker account, based on the large model analysis of the house source putting data corresponding to the target broker account, obtain the first factor and / or the second factor associated with the target broker account, the first factor is the factor affecting the putting effect of the target broker account, and the second factor is the factor affecting the putting effect of the target house source belonging to the target broker account.

[0038] After the target broker account is identified, for each target broker account, the large model is used to analyze the house source posting data corresponding to the target broker account to obtain a first factor affecting the posting effect of the target broker account in the target period, so as to analyze the factors affecting the house source posting effect in the broker dimension. Based on the house source posting data corresponding to the target broker account, the large model can also be used to analyze a second factor affecting the posting effect of the target house source belonging to the target broker account in the target period, so as to analyze the factors affecting the house source posting effect in the house source dimension. The first factor affecting the posting effect of the target broker account can also be analyzed based on the large model, and the second factor affecting the posting effect of the target house source belonging to the target broker account can also be analyzed based on the large model, so as to analyze the factors affecting the house source posting effect in the broker dimension and the house source dimension.

[0039] It should be noted that the analyzed factors affecting the posting effect at least include reverse factors, which can be understood as factors leading to poor posting effect; positive factors can also be included in addition to the reverse factors, which can be understood as factors improving the posting effect.

[0040] Step 104, generating guidance suggestions for improving the posting effect of the target broker account according to the first factor and / or the second factor associated with the target broker account.

[0041] After the first factor and / or the second factor associated with the target broker account are obtained for the target broker account, guidance suggestions for the target broker account are generated based on the first factor and / or the second factor associated with the target broker account and affecting the house source posting effect, which are used to guide the target broker corresponding to the target broker account to improve the house source posting effect. The generated guidance suggestions at least include improvement suggestions on how to improve the house source posting effect, which are generated based on reverse factors leading to poor posting effect; the guidance suggestions can also include positive suggestions generated based on positive factors improving the posting effect, which are used to guide the target broker to maintain the original positive behavior that can improve the posting effect, or to guide the target broker to increase the input intensity of the positive behavior.

[0042] The above embodiments of the present application, after obtaining the house source putting data corresponding to each broker account in the broker account set in the target period respectively, identify the target broker account with poor house source putting effect and the target house source with poor house source putting effect; for each target broker account, analyze the first factor affecting the putting effect of the target broker account, and / or analyze the second factor affecting the putting effect of the target house source belonging to the target broker account, and generate guidance suggestions for guiding the target broker account to improve the putting effect according to the first factor and / or the second factor associated with the target broker account. The target broker with poor customer acquisition effect and the target house source belonging to the target broker can be marked, the target broker is guided based on the analyzed factors affecting the house source putting effect, the target broker effectively publishes the house source based on the guidance, the customer's browsing volume of the published house source is improved, and the customer acquisition effect of the target broker is improved. At the same time, the stickiness of the broker and the platform is increased, and customer conversion and order transaction are further promoted.

[0043] The process of determining the target broker account is introduced as follows. When the house source putting data is analyzed based on the large model, the target broker account with putting effect not satisfying the first condition is determined, and the target house source with putting effect not satisfying the second condition is determined, including:

[0044] For each broker account, the average effective connection amount and the average house source detail page browsing amount corresponding to the port of the current broker account in a unit time are analyzed based on the large model, the first putting effect score of the current broker account is calculated, and whether the putting effect satisfies the first condition is determined based on the first putting effect score to identify the target broker account;

[0045] For each house source put, the average effective connection amount and the average detail page browsing amount corresponding to the house source in a unit time are analyzed based on the large model, the second putting effect score of the current house source is calculated, and whether the putting effect satisfies the second condition is determined based on the second putting effect score to identify the target house source;

[0046] Among them, the average effective connection amount and the average house source detail page browsing amount corresponding to the current broker account, and the average effective connection amount and the average detail page browsing amount corresponding to the current house source are determined based on the house source putting data corresponding to the target period and the number of unit time included in the target period.

[0047] When identifying a target agent account within a set of agent accounts, the process first involves analyzing the listings posted by the agent account within the target time period for each account. This analysis yields the average number of effective connections per port within a given time period, and the average number of property detail page views per port within the same time period. The unit of time is a pre-defined duration, such as one day. The average number of effective connections per port is determined by the ratio of the total effective connections to the target time period to the number of time units within that period. Similarly, the average number of property detail page views per port is determined by the ratio of the total number of property detail page views to the number of time units within that period. The total number of property detail page views per port within the target time period is determined by the number of times the listings posted by the agent account are accessed. Finally, the total number of effective connections per port within the target time period is determined by the interaction between the agent account and users searching for properties during that period.

[0048] After obtaining the average effective connections and average property details page views per unit time for the current agent account within the target time period, the first campaign performance score for the current agent account is calculated based on these two parameters. Based on the calculated first campaign performance score, it is determined whether the campaign performance of the agent account meets the first condition, thereby identifying whether the current agent account belongs to the target agent account.

[0049] It is important to note that if an agent purchases multiple ports, the total number of valid connections for each port during the target time period needs to be aggregated to determine the total number of valid connections for the agent's account during the target time period. Similarly, the total number of views on the property details page for each port during the target time period needs to be aggregated to determine the total number of views on the property details page for the agent's account during the target time period.

[0050] When selecting target properties from the numerous listings, the process first involves obtaining the total number of valid connections and the total number of page views for each property during the target time period. The total number of valid connections for a property during the target time period is determined based on the interaction between the agent associated with the property and users searching for the property during that time period. The total number of page views for a property during the target time period is determined based on the number of clicks to access the property's details page during that time period.

[0051] Having obtained the total number of valid connections and the total number of page views for the current property within the target time period, the average number of valid connections for the current property within each unit of time is determined based on the ratio of the total number of valid connections to the number of unit durations included in the target time period. Similarly, the average number of page views for the current property within each unit of time is determined based on the ratio of the total number of page views to the number of unit durations included in the target time period. Then, based on these average valid connections and average page views, a second performance score for the current property is calculated. This second performance score is then used to determine whether the property's performance meets the second condition, thus identifying whether the current property is a target property.

[0052] In the above implementation process, when screening target agent accounts, a first campaign performance score is calculated based on the average effective connections and average property details page views for the corresponding port of the agent account. The performance of the agent account's property campaign is measured based on the calculated first campaign performance score to identify target agent accounts with poor campaign performance. When screening target properties, a second campaign performance score is calculated based on the average effective connections and average property details page views for the corresponding property. The performance of the property campaign is measured based on the calculated second campaign performance score to identify target properties with poor campaign performance.

[0053] The following describes how to calculate the first campaign performance score and the process of identifying target agent accounts based on the first campaign performance score. When analyzing the average effective connections and average property detail page views per unit time for the current agent account using a large model, calculating the first campaign performance score for the current agent account, and determining whether the campaign performance meets the first condition based on the first campaign performance score, the process includes:

[0054] Based on the large model analysis, the ratios of the average effective connection volume of the current broker account to the average effective connection volume of the first port, the average effective connection volume of the second port, and the average effective connection volume of the third port are used to determine the three first scores;

[0055] Based on the large model analysis, the average number of views on the property details page corresponding to the current agent account is compared with the average number of views on the property details page of the first port, the average number of views on the property details page of the second port, and the average number of views on the property details page of the third port to determine the three second scores;

[0056] The first delivery effectiveness score is determined by calculating the sum of the three first scores and the three second scores based on the large model.

[0057] In response to the large model identifying that the first performance score of the current agent account is ranked as low among the multiple first performance scores corresponding to the agent account set, it is determined that the performance of the current agent account does not meet the first condition.

[0058] Among them, the average effective connection volume of the first port, the average effective connection volume of the second port, and the average effective connection volume of the third port are the average effective connection volume of the ports corresponding to the first set, the second set, and the third set within a unit time period, respectively; and the average number of views on the property details page of the first port, the average number of views on the property details page of the second port, and the average number of views on the property details page of the third port are the average number of views on the property details page of the ports corresponding to the first set, the second set, and the third set within a unit time period, respectively.

[0059] The first set is a set of agent accounts that includes all agent accounts in the current city. The second set includes agent accounts that belong to the first region. The third set includes agent accounts that belong to the target store. The target store is the store to which the agent corresponding to the current agent account belongs, and the first region is the region to which the target store belongs in the current city.

[0060] In this embodiment, before calculating the first performance score of the current broker account, it is necessary to determine the average effective connection volume of the first port, the average effective connection volume of the second port, and the average effective connection volume of the third port. The average effective connection volume of the first port is the average effective connection volume of the port corresponding to the first set within a unit of time. The first set is the aforementioned set of broker accounts, including all broker accounts belonging to the platform and located in the current city. When calculating the average effective connection volume of the first port, the total effective connection volume of each broker account in the first set is counted for the target time period. The sum of the total effective connection volume of each broker account is obtained to obtain the total effective connection volume of the port corresponding to the first set. Then, the ratio of the total effective connection volume of the port corresponding to the first set to the number of broker accounts included in the first set and the number of unit time periods included in the target time period is calculated to determine the average effective connection volume of the first port.

[0061] The average effective connection volume of the third port is the average effective connection volume of the port corresponding to the third set within a unit of time. The third set includes the agent accounts corresponding to the agents belonging to the target store under the platform, and the target store is the store to which the agent corresponding to the current agent account belongs. The average effective connection volume of the second port is the average effective connection volume of the port corresponding to the second set within a unit of time. The second set includes the agent accounts corresponding to the agents belonging to the first region under the platform, and the first region is the region to which the target store belongs in the current city. The process of calculating the average effective connection volume of the third port and the average effective connection volume of the second port is similar to the process of calculating the average effective connection volume of the first port, and will not be described further here.

[0062] After determining the average effective connection volume of the first port, the average effective connection volume of the second port, and the average effective connection volume of the third port, the calculation rules for calculating based on the average effective connection volume of the ports corresponding to the current broker account and the above three averages are as follows: Figure 2 As shown:

[0063] At the level of effective port connections, the average effective port connection for the current broker account is compared with the average of multiple broker accounts in the first set, the average of multiple broker accounts in the second set, and the average of multiple broker accounts in the third set, to calculate the ratio of the average effective port connection for the current broker account to the average effective port connection for the first, second, and third ports, respectively.

[0064] Specifically, when determining the three first scores based on ratios, the process is as follows: The first, second, and third parameters are determined based on the ratios of the average effective connections per port to the average effective connections per first port, second port, and third port, respectively. The three first scores are then determined based on the ranking of the first parameter corresponding to the current broker account among the multiple first parameters corresponding to the first set, the ranking of the second parameter corresponding to the current broker account among the multiple second parameters corresponding to the second set, and the ranking of the third parameter corresponding to the current broker account among the multiple third parameters corresponding to the third set. It should be noted that the number of multiple first parameters corresponding to the first set is the total number of broker accounts included in the first set. Each broker account corresponds to one first parameter, and the first parameter corresponding to a broker account is determined based on the ratio of the broker account's average effective connections per port to the average effective connections per first port. The second and third parameters are determined similarly to the first parameters.

[0065] After determining the first parameter based on the ratio of the average effective connection volume of the port corresponding to the current broker account to the average effective connection volume of the first port, the sorting of the first parameter corresponding to the current broker account among the multiple first parameters corresponding to the first set is obtained, and the corresponding first score is determined based on the sorting of the first parameter corresponding to the current broker account. For example, ... Figure 3 As shown, the specific score is determined based on the ranking rank. A score of 1 corresponds to the top 10%, 0.9 to the top 20%, 0.8 to the top 30%, and so on. The first matching score is determined based on the ranking rank of the first parameter corresponding to the current broker account within all first parameters in the first set. Similarly, after determining the second and third parameters corresponding to the current broker account, the first matching score is determined based on the ranking rank of the second parameter within all second parameters in the second set, and the first matching score is determined based on the ranking rank of the third parameter within all third parameters in the third set. Thus, three first scores associated with the current broker account can be determined at the level of effective port connections.

[0066] Before calculating the first performance score for the current agent account, it is necessary to determine the average page views for property details pages on the first, second, and third platforms. The average page views for the first platform are the average page views for the first set of properties within a given time period; the average page views for the second platform are the average page views for the second set of properties within a given time period; and the average page views for the third platform are the average page views for the third set of properties within a given time period. The method for calculating the average page views for each set is similar to the process for calculating the average number of effective connections for each set, and will not be further elaborated here.

[0067] After determining the average page views for property detail pages on the first, second, and third portals, the calculation rules for comparing the average page views for property detail pages on the portals corresponding to the current agent's account with the above three averages are also detailed below. Figure 2 As shown:

[0068] Regarding the number of page views for property details pages on different platforms, the average page views for the current agent's account are compared with the average page views for multiple agent accounts in the first set, the average page views for the current agent's account are compared with the average page views for multiple agent accounts in the second set, and the average page views for the current agent's account are compared with the average page views for multiple agent accounts in the third set. This allows us to calculate the ratio of the average page views for the current agent's account on different platforms to the average page views for the first, second, and third platforms, respectively. This yields the fourth, fifth, and sixth parameters.

[0069] Then, the ranking of the fourth parameter corresponding to the current agent account among the multiple fourth parameters corresponding to the first set is obtained, and the corresponding second score is determined based on the ranking of the fourth parameter corresponding to the current agent account. The ranking of the fifth parameter corresponding to the current agent account among the multiple fifth parameters corresponding to the second set is obtained, and the corresponding second score is determined based on the ranking of the fifth parameter corresponding to the current agent account. The ranking of the sixth parameter corresponding to the current agent account among the multiple sixth parameters corresponding to the third set is obtained, and the corresponding second score is determined based on the ranking of the sixth parameter corresponding to the current agent account. Thus, three second scores can be determined at the level of port listing detail page views. The number of multiple fourth parameters corresponding to the first set is the total number of agent accounts included in the first set. Each agent account corresponds to one fourth parameter, and the fourth parameter corresponding to an agent account is determined based on the ratio of the agent account's average port listing detail page views to the average port listing detail page views. The fifth and sixth parameters are handled similarly to the fourth parameters.

[0070] After determining three first scores based on the number of effective connections at the port and three second scores based on the number of views on the property details page at the port, the first campaign performance score for the current agent account is determined by summing the three first and three second scores. Then, based on the first campaign performance score for the current agent account, its ranking is determined among multiple first campaign performance scores for the agent account set. If the ranking is low, the agent account's campaign performance does not meet the first condition, and the agent associated with the current account is a target agent requiring attention and support. For example, if the agent account's first campaign performance score determines that it ranks in the top 30% of the agent account set, the agent is considered high-level, indicating strong competitiveness; if it ranks in the middle 40%, the agent is considered mid-level; and if it ranks in the bottom 30%, the agent is considered low-level and requires close monitoring.

[0071] In the above implementation process, after determining three first scores at the level of effective port connections and three second scores at the level of port property details page views, the first delivery effect score of the agent account is determined based on the score accumulation. Based on the determined first delivery effect score, the ranking level of the current agent account in the agent account set is identified to determine whether the current agent belongs to the target agent to be followed.

[0072] The following describes the process of identifying target properties. Based on a large model analysis of the average effective connections and average detail page views of the current property within a unit of time, a second performance score for the current property is calculated. Based on this second performance score, it is determined whether the performance meets the second condition. This includes:

[0073] Based on the large model analysis, the ratios of the average effective connections of the current property to the average effective connections of the first, second, and third properties are used to determine the three third scores.

[0074] Based on the large model analysis, the ratio of the average number of page views of the current property's detail page to the average number of page views of the first, second, and third property detail pages is used to determine three fourth scores;

[0075] The second delivery effectiveness score is determined by calculating the sum of the three third scores and the three fourth scores based on the large model.

[0076] In response to the large model identifying that the second delivery effect score of the current property is ranked as low among the multiple second delivery effect scores in the fourth set, it is determined that the delivery effect of the current property does not meet the second condition.

[0077] Among them, the average effective connection volume of the first, second, and third listings are the average effective connection volume of the fourth, fifth, and sixth sets of listings within a unit of time, respectively; and the average page views of the first, second, and third listings are the average page views of the fourth, fifth, and sixth sets of listings within a unit of time, respectively.

[0078] The fourth set includes all available properties in the current city during the target time period; the fifth set includes all available properties in the second region during the target time period; and the sixth set includes all available properties in the target business district during the target time period. The target business district is the business district to which the current property belongs, and the second region is the area in the current city to which the target business district belongs.

[0079] In this embodiment, before calculating the second placement effect score of the current property, it is necessary to determine the average effective connection volume of the first property, the average effective connection volume of the second property, and the average effective connection volume of the third property, as well as the average number of page views of the first property details page, the average number of page views of the second property details page, and the average number of page views of the third property details page.

[0080] The average number of valid connections for the first set of properties is the average number of valid connections for the fourth set of properties within a unit of time. The fourth set of properties includes all properties belonging to the platform and deployed in the current city during the target time period. When calculating the average number of valid connections for the first set of properties, the total number of valid connections for each property in the fourth set during the target time period is calculated. The sum of the total number of valid connections for each property is then obtained to determine the total number of valid connections for the fourth set. Finally, the ratios of the total number of valid connections for the fourth set to the number of properties included in the fourth set and the number of unit time periods included in the target time period are calculated to determine the average number of valid connections for the first set of properties.

[0081] The average number of valid connections for the third property is the average number of valid connections for the sixth set within a unit of time. The sixth set is a property set that includes all properties listed in the target business district on the platform during the target time period. The target business district is the business district to which the current property belongs. The average number of valid connections for the second property is the average number of valid connections for the fifth set within a unit of time. The fifth set is a property set that includes all properties listed in the second region on the platform during the target time period. The second region is the region to which the target business district belongs in the current city. The current city, the second region, and the target business district form progressively smaller regional ranges. In this embodiment, the brokers and properties all belong to the current platform.

[0082] After determining the average effective connections for the first, second, and third listings, the calculation rules for the average effective connections for the current listing, based on the average effective connections of the listings corresponding to that listing and the above three averages, are as follows: Figure 4 As shown:

[0083] In terms of effective connections to properties, the current property is compared with properties in the fourth set, the current property is compared with properties in the fifth set, and the current property is compared with properties in the sixth set to calculate the ratio of the average effective connections of the current property to the average effective connections of the first, second, and third properties, respectively.

[0084] After determining the three ratios based on the above calculations, the three third scores are determined based on the three ratios. The process of determining the three third scores is similar to the process of determining the three first scores, and will not be described further here.

[0085] The average page views for the first property listing's detail page are the average page views for the fourth set of property listings within the same time period. The average page views for the second property listing's detail page are the average page views for the fifth set of property listings within the same time period. The average page views for the third property listing's detail page are the average page views for the sixth set of property listings within the same time period. The calculation rules for calculating based on the average page views for the current property listing's detail page and the above three averages are also detailed in [link to calculation]. Figure 4 As shown:

[0086] In terms of property detail page views, the current property is compared with properties in the fourth set, the fifth set, and the sixth set to calculate the ratio of the average number of property detail page views for the current property to the average number of property detail page views for the first, second, and third sets, respectively.

[0087] After determining the three ratios based on the above calculations, the three fourth scores are determined based on the three ratios. The process of determining the three fourth scores is similar to the process of determining the three second scores, and will not be described further here.

[0088] After determining the three third scores and three fourth scores, the three third scores and three fourth scores are summed to determine the second placement effect score of the housing. Based on the second placement effect score corresponding to the current housing, the ranking level of the second placement effect score of the current housing is determined among the multiple second placement effect scores corresponding to the fourth set. In response to the ranking level being low, it is determined that the placement effect of the current housing does not meet the second condition and the current housing is a housing that needs attention and support.

[0089] In the above implementation process, after determining three third scores at the level of effective connection volume and three fourth scores at the level of property details page views, the second delivery effect score of the property is determined based on the score accumulation. Based on the determined second delivery effect score, the current property's ranking level is identified to determine whether the current property belongs to the target property to be followed.

[0090] In one embodiment of this application, when analyzing the property listing data corresponding to a target broker account based on a large model to obtain a first factor and / or a second factor associated with the target broker account, the method includes:

[0091] Based on the large model, the data on property listings corresponding to the target agent account is processed to analyze the value-added investment, service level, and property characteristics of the target agent account during the target period in order to obtain the primary factor;

[0092] and / or

[0093] Based on the large model, the data on property listings corresponding to the target agent's account is processed to analyze the authenticity of the property listings, the distribution of the property listings, and the matching of the property listings with the search needs of the target agent's account, in order to obtain the second factor.

[0094] When analyzing the primary factor influencing the effectiveness of ad placements for target agent accounts, a large model is used to process the property listing data corresponding to the target agent account. The model analyzes the value-added investment, service level, and property characteristics of the target agent account during the target period to obtain an agent profile representing the target agent's ad placement characteristics from the property listing data. Then, the agent profile is used to identify the primary factor influencing the agent's property listing effectiveness from the dimensions of value-added investment, service level, and property characteristics of the property.

[0095] When identifying the primary factor influencing the effectiveness of property listings across three dimensions—value-added investment, service level, and property characteristics—the following factors are included:

[0096] Based on the large model, the data on the listings of the target broker account is processed. The average value-added spending of the target broker account per unit time period is analyzed, and the proportion of value-added listings of the target broker account in the target time period is analyzed, so as to identify the impact of the value-added investment of the target broker account on the listing effect.

[0097] Based on the large model, the data on property listings corresponding to the target agent accounts is processed, and the chat response rate, call connection rate and agent rating of the target agent accounts during the target time period are analyzed to identify the impact of the service level of the target agent accounts on the listing effect.

[0098] Based on the large model, the data on housing listings corresponding to the target agent account is processed. The analysis includes the richness of housing coverage, the property attributes of the covered properties, the matching degree between the housing listings and the housing search demand in the area, the proportion of real listings, and the port full-load rate within a unit of time, in order to identify the impact of housing characteristics on the listing effect.

[0099] Based on the impact of identified value-added investments, service levels, and property characteristics on ad performance, identify the primary factor influencing the ad performance of the target agent's account.

[0100] When identifying the primary factor influencing listing effectiveness based on a large model at the level of value-added investment, the average value-added spending of the target agent account per unit time period and the percentage of value-added listings for the target agent account during the target time period are calculated. The calculated average value-added spending and the calculated percentage of value-added listings are then compared with a benchmark value-added spending figure to analyze whether the target agent account's value-added investment is higher than the average level. If at least one of the average value-added spending or the percentage of value-added listings is higher than the average level, it indicates that the target agent account's value-added investment can promote listings and is a positive factor in improving listing effectiveness.

[0101] The benchmark value-added cost is determined based on the value-added costs of all broker accounts in the first set during the target period. For example, the total value-added cost is determined by summing the value-added costs of each target broker account during the target period. The benchmark value-added cost is then determined based on the ratio of the total value-added cost to the number of broker accounts and the number of unit hours included in the target period. Similarly, the benchmark percentage is determined based on the percentage of value-added properties listed by all broker accounts in the first set during the target period. For example, the cumulative percentage of value-added properties listed by each target broker account during the target period is determined. The benchmark percentage is then determined based on the ratio of the cumulative percentage of value-added properties to the number of broker accounts.

[0102] When identifying the primary factor influencing the effectiveness of property listings based on a large-scale model at the service level dimension, the system calculates the target agent's WeChat response rate and phone connection rate during the target time period, and obtains the agent's rating for that period. It then identifies whether the WeChat response rate, phone connection rate, and agent rating are higher than the baseline response rate, call connection rate, and agent rating, respectively, to analyze whether the target agent's service level exceeds the baseline. The baseline response rate, baseline connection rate, and baseline rating are determined based on the WeChat response rate, phone connection rate, and agent rating of all agent accounts in the first set during the target time period.

[0103] When the WeChat reply rate is higher than the benchmark level, it indicates that the WeChat reply performance of the target agent account can promote the property listing, which is a positive factor in improving the effectiveness of property listing. When the phone connection rate is higher than the benchmark level, it indicates that the phone connection performance of the target agent account can promote the property listing, which is a positive factor in improving the effectiveness of property listing. When the agent rating is higher than the benchmark level, it indicates that the overall performance of the target agent corresponding to the target agent account can promote the property listing, which is a positive factor in improving the effectiveness of property listing.

[0104] When identifying the primary factor influencing the effectiveness of property listings based on a large model in terms of property characteristics, we statistically analyze the richness of property coverage, the property attributes of the covered properties, and the percentage of real listings for the target agent account within the target time period. We also analyze the matching degree between the listed properties and the housing demand in the area where the properties are located, and the port full-load rate within a unit time period. Based on the above content, we can measure whether the property characteristics of the listed properties can promote the property promotion.

[0105] Specifically, after statistically analyzing the richness of property coverage corresponding to the listings posted by the target agent accounts within the target time period, the system checks whether the richness of property coverage is higher than the corresponding benchmark level. After statistically analyzing the property attributes covered by the posted listings, the system checks whether the proportion of "blue ocean" properties (properties with supply less than demand) is higher than the corresponding benchmark level. After statistically analyzing the proportion of actual listings, the system checks whether the proportion of actual listings is higher than the corresponding benchmark level. After analyzing the matching degree between the posted listings and the housing demand in the area where the listings are located, the system checks whether the matching degree is greater than a threshold or higher than the corresponding benchmark level. After identifying the port saturation rate (the ratio of property promotion volume to the total number of properties allowed to be posted on the port within a unit of time), the system checks whether the port saturation rate is greater than or equal to 1. Since some properties may be promoted directly without using the port, a port saturation rate greater than 1 is allowed. The multiple benchmark levels mentioned above can be determined by averaging the data of all agent accounts in the first set.

[0106] For any given agent account, there are usually multiple listings, not limited to the same area. When analyzing the matching degree between the listed properties and the housing demand in the area where the properties are located, for each listing area, the matching degree between the property characteristics of the listed properties in that area and the area and price requirements of the housing seekers in that area can be calculated. The percentage of properties with a matching degree greater than a preset threshold is obtained, and the matching degree between the promoted properties and the actual needs of housing seekers is measured based on the percentage of properties that meet the requirements. Then, the matching degree of each listing area is combined. For example, the average percentage of properties that meet the requirements across multiple listing areas can be calculated to obtain the matching degree between the agent's listed properties and the housing demand. The actual needs of housing seekers (e.g., area and price requirements) are determined based on the housing seeker's profile. The process of calculating the matching degree between the listed properties and the housing seeker's needs can be seen as the process of matching the property characteristics in the agent's profile with the property demand characteristics in the housing seeker's profile.

[0107] Specifically, if the richness of property coverage exceeds the corresponding benchmark level, it indicates that the property coverage of the listings posted by the target agent account can promote property promotion, which is a positive factor in improving the effectiveness of property placement. If the proportion of the posted properties belonging to "blue ocean" properties exceeds the corresponding benchmark level, it indicates that the property ownership of the properties posted by the target agent account can promote property promotion, which is a positive factor in improving the effectiveness of property placement. If the proportion of genuine properties posted exceeds the corresponding benchmark level, it indicates that the proportion of genuine properties posted by the target agent account is relatively high, which can promote property promotion, which is a positive factor in improving the effectiveness of property placement. If the matching degree between the posted properties and the needs of users seeking housing is greater than the threshold or exceeds the corresponding benchmark level, it indicates that most of the properties posted by the target agent account can meet the actual needs of users seeking housing in terms of area and / or price, which can promote property promotion, which is a positive factor in improving the effectiveness of property placement. If the port saturation rate within a unit of time is greater than or equal to 1, it indicates that the number of properties posted by the target agent account meets the requirements, which can promote property promotion, which is a positive factor in improving the effectiveness of property placement.

[0108] After analyzing the factors affecting the effectiveness of property listings in terms of value-added investment, service level, and property characteristics, we can identify the positive and negative factors affecting the effectiveness of listings. By summarizing the identified factors, we can obtain the primary factor affecting the effectiveness of property listings for the target agent's account.

[0109] When analyzing the second factor influencing the effectiveness of listings for target properties belonging to target agent accounts, a large-scale model is used to process the listing data corresponding to the target agent accounts, analyzing the factors affecting the effectiveness of the listings from multiple dimensions. Specifically: identifying the authenticity of target properties belonging to target agent accounts; if the listed target properties are genuine, it can promote the listings; identifying the property development to which the target properties belong; if the target properties are located in less competitive developments, it can promote the listings; identifying the match between the target properties and the needs of homebuyers; if the characteristics of the target properties, such as the property size, lighting, and price, match the actual needs of homebuyers in the area where the property is located, it can promote the listings.

[0110] After analyzing the factors affecting the effectiveness of property listings, such as the authenticity of the listings, the distribution of listings, and the matching of listings with the needs of homebuyers, we can identify the positive and negative factors affecting the effectiveness of the listings. By summarizing the identified factors, we can obtain the second factor affecting the effectiveness of the listings for the target properties.

[0111] In the above implementation process, based on the agent profile, the positive and negative factors affecting the listing effect of the target agent are analyzed, and the first factor affecting the listing effect of the target agent is obtained by summarizing. At the property level, the positive and negative factors affecting the listing effect of the target property are analyzed, and the second factor affecting the listing effect of the target property is obtained by summarizing.

[0112] In an optional embodiment of this application, when generating guidance suggestions to improve the advertising performance of the target broker account based on a first factor and / or a second factor associated with the target broker account, the following are included:

[0113] Based on the first factor affecting the ad performance of the target agent account, and / or the second factor affecting the ad performance of the target listings attributable to the target agent account, identify the positive factors that improve ad performance and the negative factors that reduce ad performance.

[0114] Positive suggestions are generated based on housing allocation data associated with positive factors, and improvement suggestions are generated based on housing allocation data associated with negative factors.

[0115] Having identified the primary factor influencing the advertising performance of target agent accounts at the agent level and the secondary factor influencing the advertising performance of target properties at the property level, the system identifies positive factors that improve advertising performance and negative factors that reduce it, based on the primary factor influencing the advertising performance of target agent accounts; and / or, based on the secondary factor influencing the advertising performance of target properties belonging to target agent accounts, it identifies positive factors that improve advertising performance and negative factors that reduce it. Then, based on the property advertising situation associated with the positive factors, the system generates positive suggestions for target agent accounts, such as maintaining or increasing the proportion of genuine listings, maintaining or increasing call connection rates, and maintaining or improving property quality; and generates improvement suggestions based on the property advertising situation associated with the negative factors, such as increasing the investment cost of value-added products, increasing the WeChat response rate, and increasing the proportion of properties matching the search needs.

[0116] By generating positive suggestions for target agent accounts, target agents can be encouraged to continue campaign behaviors that promote campaign effectiveness or increase support. By generating improvement suggestions for target agent accounts, target agents can improve behaviors that do not promote campaign effectiveness, thereby further promoting property listings through improvement suggestions.

[0117] In an optional embodiment of this application, the method further includes:

[0118] Obtain customer acquisition analysis details for the target agent account during the target time period. The customer acquisition analysis details should include at least the target agent account's customer acquisition level, customer acquisition ranking, effective connection volume of the portal, page views of the property details page of the portal, and value-added investment costs.

[0119] Based on the customer acquisition analysis details, the first and / or second factors affecting the campaign performance analyzed, and the generated guidance suggestions for improving the campaign performance of the target agent account, a portal performance display chart is generated.

[0120] By analyzing the listing data of target agent accounts during the target time period, we can obtain detailed customer acquisition analysis for those accounts. This analysis includes at least: the target agent account's customer acquisition level, customer acquisition ranking, effective connections from various portals, page views of property details pages from those portals, and value-added investment costs. Customer acquisition level represents the target agent account's competitiveness level, indicating its performance among numerous agents on the platform. Customer acquisition ranking indicates the order of customer acquisition among all agent accounts on the platform. Effective connections from various portals reflect the number of effective connections the target agent account has established with users searching for properties over a period of time. Page views of property details pages from various portals reflect the number of clicks on property details pages for listings placed by the target agent account over a period of time. Value-added investment costs reflect the value-added investment made by the target agent account in purchasing value-added products over a period of time.

[0121] Customer acquisition analysis details may also include: the number of effective connections to the target agent's account, the number of views on the property details page, and the cost of value-added services compared with the benchmark level of the same company, compared with the benchmark level of the whole city, and compared with the previous period (such as the previous week or the previous month).

[0122] After obtaining customer acquisition analysis details, based on these details, the primary and / or secondary factors influencing campaign performance, and guidance suggestions (including positive and improvement suggestions) to help target agent accounts improve campaign performance, a portal performance chart is generated. This chart is then displayed in the CMS (Content Management System) backend for sales personnel to use. Sales personnel can clearly understand the customer acquisition situation of their assigned agents, the factors affecting campaign performance, and the guidance suggestions based on the portal performance chart. This allows them to provide targeted guidance to agents on effective listing and service improvement, thereby increasing the number of customers acquired by each agent.

[0123] like Figure 5As shown, the portal performance display presented to sales personnel includes three sections: portal performance analysis, guidance and suggestions, and factors affecting campaign performance. Based on the portal performance analysis, sales personnel can understand the following: the ranking of agent accounts, the effective connection status of listings within a period (e.g., 7 days), the page views of listing details pages (click-through rates), and comparisons of agents with company benchmarks and city benchmarks. Based on the factors affecting campaign performance, sales personnel can identify agent shortcomings and behaviors worth maintaining, and provide targeted guidance to agents based on the guidance and suggestions to increase customer acquisition. In addition to specific suggestions, the guidance and suggestions section also includes a portal to a property diagnostic report, through which agents can view diagnostic reports corresponding to their property campaign performance.

[0124] During the above implementation process, by generating a port effect display diagram and presenting it to the sales staff, the sales staff can provide targeted guidance to the agents to improve the listing of properties, thereby improving the listing effect and increasing the number of customers acquired.

[0125] In the method for improving the listing effect provided in this application embodiment, a profile analysis is performed on the house search behavior and the listing behavior. By comparing the missing factors of the placement, the key factors affecting the placement effect are determined. Based on the analyzed factors, targeted and refined suggestions are given to guide the agents in which aspects they should invest, thereby improving the listing effect.

[0126] Furthermore, after highlighting agents with poor customer acquisition performance through intuitive data, continuous data monitoring and behavior improvement plans are implemented to perceive changes in agent customer acquisition data, identify the benefits of improvement plans for agents, and thus continuously optimize improvement methods.

[0127] This application provides a device for improving hair growth effect, such as... Figure 6 As shown, it includes:

[0128] The first acquisition module 601 is used to acquire the housing listing data corresponding to each broker account in the broker account set during the target time period.

[0129] The determination module 602 is used to determine the target broker accounts whose placement effect does not meet the first condition and the target properties whose placement effect does not meet the second condition based on the property placement data obtained from the analysis of the large model.

[0130] Analysis module 603 is used to analyze the property listing data corresponding to each target agent account based on a large model, and obtain a first factor and / or a second factor associated with the target agent account. The first factor is a factor that affects the listing effect of the target agent account, and the second factor is a factor that affects the listing effect of the target properties belonging to the target agent account.

[0131] The first generation module 604 is used to generate guidance suggestions for improving the advertising performance of the target broker account based on the first factor and / or the second factor associated with the target broker account.

[0132] Optionally, the determining module includes:

[0133] The first processing submodule is used to analyze the average effective connection volume and average property details page views of the current agent account within a unit of time based on the large model for each agent account, calculate the first advertising performance score of the current agent account, and determine whether the advertising performance meets the first condition based on the first advertising performance score, so as to identify the target agent account.

[0134] The second processing submodule is used to analyze the average number of effective connections and the average number of page views of the current property within a unit of time for each property that has been advertised, based on the large model, calculate the second advertising performance score of the current property, and determine whether the advertising performance meets the second condition based on the second advertising performance score, so as to identify the target property.

[0135] The average number of valid connections and average number of page views for the property details page corresponding to the current agent account, as well as the average number of valid connections and average number of page views for the property details page corresponding to the current property, are determined based on the property listing data for the target time period and the number of unit durations included in the target time period.

[0136] Optionally, the first processing submodule includes:

[0137] The first determining unit is used to analyze the ratio of the average effective connection volume of the port corresponding to the current broker account to the average effective connection volume of the first port, the average effective connection volume of the second port, and the average effective connection volume of the third port based on the large model, and to determine three first scores;

[0138] The second determining unit is used to analyze the ratio of the average number of views of the property details page corresponding to the current agent account to the average number of views of the property details page of the first port, the average number of views of the property details page of the second port, and the average number of views of the property details page of the third port based on the large model, and to determine three second scores;

[0139] The third determining unit is used to calculate the sum of the three first scores and the three second scores based on the large model, and to determine the first delivery effect score;

[0140] The fourth determining unit is used to determine that the current agent account's delivery performance does not meet the first condition in response to the large model identifying that the first delivery performance score of the current agent account is ranked as low among the multiple first delivery performance scores corresponding to the agent account set.

[0141] Wherein, the average effective connection volume of the first port, the average effective connection volume of the second port, and the average effective connection volume of the third port are respectively the average effective connection volume of the ports corresponding to the first set, the second set, and the third set within a unit time period; and the average number of views on the property details page of the first port, the average number of views on the property details page of the second port, and the average number of views on the property details page of the third port are respectively the average number of views on the property details page of the ports corresponding to the first set, the second set, and the third set within a unit time period.

[0142] The first set is a set of agent accounts that includes all agent accounts corresponding to agents in the current city. The second set includes agent accounts corresponding to agents belonging to the first region. The third set includes agent accounts corresponding to agents belonging to the target store. The target store is the store to which the agent corresponding to the current agent account belongs, and the first region is the region to which the target store belongs in the current city.

[0143] Optionally, the first determining unit includes:

[0144] The first calculation and determination subunit is used to calculate the ratio of the average effective connection volume of the port corresponding to the current broker account to the average effective connection volume of the first port, the average effective connection volume of the second port, and the average effective connection volume of the third port based on the large model, and to determine the first parameter, the second parameter, and the third parameter.

[0145] The second calculation and determination subunit is used to analyze the ranking of the first parameter corresponding to the current broker account in the first set of multiple first parameters, the ranking of the second parameter corresponding to the current broker account in the second set of multiple second parameters, and the ranking of the third parameter corresponding to the current broker account in the third set of multiple third parameters based on the large model, and determine three first scores.

[0146] Optionally, the second processing submodule includes:

[0147] The fifth determination unit is used to analyze the ratio of the average effective connection volume of the current property to the average effective connection volume of the first property, the average effective connection volume of the second property, and the average effective connection volume of the third property based on the large model analysis, and to determine the three third scores;

[0148] The sixth determination unit is used to analyze the ratio of the average number of views on the current property's details page to the average number of views on the first, second, and third property details pages, respectively, based on the large model, and to determine the three fourth scores;

[0149] The seventh determining unit is used to calculate the sum of the three third scores and the three fourth scores based on the large model, and to determine the second delivery effect score;

[0150] The eighth determining unit is used to determine that the current property's delivery performance does not meet the second condition in response to the large model identifying that the ranking level of the current property's second delivery performance score among the multiple second delivery performance scores corresponding to the fourth set is low.

[0151] Wherein, the average effective connection volume of the first property, the average effective connection volume of the second property, and the average effective connection volume of the third property are respectively the average effective connection volume of the fourth set, the fifth set, and the sixth set within a unit time period; and the average page views of the first property details page, the average page views of the second property details page, and the average page views of the third property details page are respectively the average page views of the fourth set, the fifth set, and the sixth set within a unit time period.

[0152] The fourth set includes all available properties in the current city during the target time period; the fifth set includes all available properties in the second region during the target time period; and the sixth set includes all available properties in the target business district during the target time period. The target business district is the business district to which the current property belongs, and the second region is the region in the current city to which the target business district belongs.

[0153] Optionally, the analysis module includes:

[0154] The first analysis and acquisition submodule is used to process the property listing data corresponding to the target broker account based on the large model, and analyze the value-added investment, service level and property characteristics of the target broker account during the target period to obtain the first factor;

[0155] and / or

[0156] The second analysis and acquisition submodule is used to process the housing listing data corresponding to the target broker account based on the large model, analyze the authenticity of the target housing listings belonging to the target broker account, the distribution of housing listings, and the matching of housing listings with housing search needs, so as to obtain the second factor.

[0157] Optionally, the first analysis and acquisition submodule includes:

[0158] The first analysis and identification unit is used to process the listing data corresponding to the target broker account based on a large model, analyze the average value-added spending of the target broker account within a unit of time during the target period, and analyze the proportion of value-added listings of the target broker account during the target period, so as to identify the impact of the value-added investment of the target broker account on the listing effect.

[0159] The second analysis and identification unit is used to process the listing data corresponding to the target agent account based on the large model, and analyze the micro-chat response rate, call connection rate and agent rating of the target agent account during the target time period, so as to identify the impact of the service level of the target agent account on the listing effect.

[0160] The third analysis and identification unit is used to process the housing listing data corresponding to the target broker account based on the large model, and analyze the richness of the property coverage, the property attributes of the covered properties, the matching degree between the properties and the housing search demand in the area, the proportion of real properties, and the port full rate within a unit of time, so as to identify the impact of the property characteristics of the listed properties on the listing effect.

[0161] The acquisition unit is used to acquire the first factor affecting the advertising effect of the target broker account based on the impact of the identified value-added investment, service level, and property characteristics on the advertising effect.

[0162] Optionally, the first generation module is further configured to:

[0163] Based on a first factor affecting the advertising performance of the target broker account, and / or a second factor affecting the advertising performance of the target listings belonging to the target broker account, positive factors that improve advertising performance and negative factors that reduce advertising performance are identified.

[0164] Positive suggestions are generated based on the housing supply situation associated with the positive factors, and improvement suggestions are generated based on the housing supply situation associated with the negative factors.

[0165] Optionally, the device further includes:

[0166] The second acquisition module is used to acquire customer acquisition analysis details of the target broker account during the target time period. The customer acquisition analysis details include at least the customer acquisition level, customer acquisition ranking, effective connection volume of the port, port property details page views, and value-added investment costs of the target broker account.

[0167] The second generation module is used to generate a port effect display diagram based on the customer acquisition analysis details, the first and / or second factors that affect the advertising effect, and the generated guidance suggestions for improving the advertising effect of the target agent account.

[0168] 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.

[0169] 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 method for improving the effect of hair growth and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0170] For example, Figure 7 A schematic diagram of the physical structure of an electronic device is shown. (For example...) Figure 7 As shown, the electronic device may include a processor 710, a communications interface 720, a memory 730, and a communication bus 740. The processor 710, communications interface 720, and memory 730 communicate with each other via the communication bus 740. The processor 710 can call logical instructions from the memory 730. The processor 710 is used to execute various processes of the room-effect improvement method of this application embodiment, which will not be described in detail here.

[0171] Furthermore, the logical instructions in the aforementioned memory 730 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.

[0172] 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 method embodiments for improving room-feeling effects 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.

[0173] 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.

[0174] 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.

[0175] 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.

Claims

1. A method for improving the effectiveness of room opening, characterized in that, include: Retrieve the property listing data for each agent account in the agent account set during the target time period; Based on the housing listing data obtained from the large model analysis, target agent accounts whose listing performance does not meet the first condition are identified, and target housing listings whose listing performance does not meet the second condition are identified. For each target broker account, the property listing data corresponding to the target broker account is analyzed based on a large model to obtain a first factor and / or a second factor associated with the target broker account. The first factor is a factor that affects the listing effect of the target broker account, and the second factor is a factor that affects the listing effect of the target properties belonging to the target broker account. Based on the first and / or second factors associated with the target broker account, generate guidance suggestions to help the target broker account improve its advertising performance.

2. The method according to claim 1, characterized in that, The property listing data obtained based on the large model analysis is used to identify target agent accounts whose listing performance does not meet the first condition, and to identify target properties whose listing performance does not meet the second condition, including: For each agent account, based on the large model analysis, the average effective connection volume and average property details page views of the current agent account within a unit of time are calculated to determine the first advertising performance score of the current agent account. Based on the first advertising performance score, it is determined whether the advertising performance meets the first condition in order to identify the target agent account. For each property listing, the average number of valid connections and the average number of page views of the property details page are analyzed based on the big model within a unit of time. The second listing performance score of the current property is calculated, and the second listing performance score is used to determine whether the listing performance meets the second condition in order to identify the target property. The average number of valid connections and average number of page views for the property details page corresponding to the current agent account, as well as the average number of valid connections and average number of page views for the property details page corresponding to the current property, are determined based on the property listing data for the target time period and the number of unit durations included in the target time period.

3. The method according to claim 2, characterized in that, The process involves analyzing the average effective connections and average property detail page views per unit time for the current agent account based on a large model, calculating the first campaign performance score for the current agent account, and determining whether the campaign performance meets the first condition based on the first campaign performance score, including: Based on the large model analysis, the ratios of the average effective connection volume of the current broker account to the average effective connection volume of the first port, the average effective connection volume of the second port, and the average effective connection volume of the third port are used to determine the three first scores; Based on the large model analysis, the average number of views on the property details page corresponding to the current agent account is compared with the average number of views on the property details page of the first port, the average number of views on the property details page of the second port, and the average number of views on the property details page of the third port to determine the three second scores; The first delivery effectiveness score is determined by calculating the sum of the three first scores and the three second scores based on the large model. In response to the large model identifying that the first delivery performance score of the current broker account is ranked as low among the multiple first delivery performance scores corresponding to the broker account set, it is determined that the delivery performance of the current broker account does not meet the first condition. Wherein, the average effective connection volume of the first port, the average effective connection volume of the second port, and the average effective connection volume of the third port are respectively the average effective connection volume of the ports corresponding to the first set, the second set, and the third set within a unit time period; and the average number of views on the property details page of the first port, the average number of views on the property details page of the second port, and the average number of views on the property details page of the third port are respectively the average number of views on the property details page of the ports corresponding to the first set, the second set, and the third set within a unit time period. The first set is a set of agent accounts that includes all agent accounts corresponding to agents in the current city. The second set includes agent accounts corresponding to agents belonging to the first region. The third set includes agent accounts corresponding to agents belonging to the target store. The target store is the store to which the agent corresponding to the current agent account belongs, and the first region is the region to which the target store belongs in the current city.

4. The method according to claim 3, characterized in that, The method, based on large-scale model analysis, determines three first scores by comparing the average effective connection volume of the current broker account with the average effective connection volume of the first port, the average effective connection volume of the second port, and the average effective connection volume of the third port. Based on the large model, the ratios of the average effective connection volume of the port corresponding to the current broker account to the average effective connection volume of the first port, the average effective connection volume of the second port, and the average effective connection volume of the third port are calculated to determine the first parameter, the second parameter, and the third parameter. Based on the large model analysis, the ranking of the first parameter corresponding to the current broker account among the multiple first parameters corresponding to the first set, the ranking of the second parameter corresponding to the current broker account among the multiple second parameters corresponding to the second set, and the ranking of the third parameter corresponding to the current broker account among the multiple third parameters corresponding to the third set are used to determine three first scores.

5. The method according to claim 2, characterized in that, The process involves analyzing the average number of valid connections and average number of detail page views for the current property within a unit of time based on a large model, calculating a second performance score for the current property, and determining whether the performance meets the second condition based on the second performance score, including: Based on the large model analysis, the ratios of the average effective connections of the current property to the average effective connections of the first, second, and third properties are used to determine the three third scores. Based on the large model analysis, the ratio of the average number of page views of the current property's detail page to the average number of page views of the first, second, and third property detail pages is used to determine three fourth scores; The second delivery effect score is determined by calculating the sum of the three third scores and the three fourth scores based on the large model. In response to the large model identifying that the ranking of the second delivery effect score of the current property is low among the multiple second delivery effect scores corresponding to the fourth set, it is determined that the delivery effect of the current property does not meet the second condition. Wherein, the average effective connection volume of the first property, the average effective connection volume of the second property, and the average effective connection volume of the third property are respectively the average effective connection volume of the fourth set, the fifth set, and the sixth set within a unit time period; and the average page views of the first property details page, the average page views of the second property details page, and the average page views of the third property details page are respectively the average page views of the fourth set, the fifth set, and the sixth set within a unit time period. The fourth set includes all available properties in the current city during the target time period; the fifth set includes all available properties in the second region during the target time period; and the sixth set includes all available properties in the target business district during the target time period. The target business district is the business district to which the current property belongs, and the second region is the region in the current city to which the target business district belongs.

6. The method according to claim 1, characterized in that, The step of analyzing the property listing data corresponding to the target agent's account based on a large model to obtain the first factor and / or second factor associated with the target agent's account includes: Based on the large model, the property listing data corresponding to the target broker account is processed, and the value-added investment, service level, and property characteristics of the target broker account during the target period are analyzed to obtain the first factor; and / or Based on the large model, the property listing data corresponding to the target agent account is processed, and the authenticity, distribution, and matching of the properties with the search needs of the target agent account are analyzed to obtain the second factor.

7. The method according to claim 6, characterized in that, The process of processing the property listing data corresponding to the target agent account based on a large model, analyzing the value-added investment, service level, and property characteristics of the target agent account during the target period, to obtain the first factor includes: Based on the large model, the data on the listings corresponding to the target broker account is processed. The average value-added spending of the target broker account within a unit of time during the target period is analyzed, and the proportion of value-added listings of the target broker account during the target period is analyzed, so as to identify the impact of the value-added investment of the target broker account on the listing effect. Based on the large model, the property listing data corresponding to the target agent account is processed, and the micro-chat response rate, call connection rate and agent rating of the target agent account during the target time period are analyzed to identify the impact of the service level of the target agent account on the listing effect. Based on the large model, the data on the listings of the target agent account is processed. The richness of the property coverage, the property attributes of the covered properties, the matching degree between the listings and the housing demand in the area, the proportion of real listings, and the port full rate within a unit time period are analyzed to identify the impact of the listing characteristics on the listing effect. Based on the impact of identified value-added investments, service levels, and property characteristics on the advertising effectiveness, the first factor affecting the advertising effectiveness of the target broker account is obtained.

8. The method according to claim 1, 6, or 7, characterized in that, The step of generating guidance suggestions to improve the advertising performance of the target broker account based on the first factor and / or the second factor associated with the target broker account includes: Based on a first factor affecting the advertising performance of the target broker account, and / or a second factor affecting the advertising performance of the target listings belonging to the target broker account, positive factors that improve advertising performance and negative factors that reduce advertising performance are identified. Positive suggestions are generated based on the housing supply situation associated with the positive factors, and improvement suggestions are generated based on the housing supply situation associated with the negative factors.

9. The method according to claim 1, characterized in that, The method further includes: Obtain customer acquisition analysis details for the target broker account during the target time period. The customer acquisition analysis details include at least the target broker account's customer acquisition level, customer acquisition ranking, effective connection volume of the port, port property details page views, and value-added investment costs. Based on the customer acquisition analysis details, the first and / or second factors affecting the campaign performance analyzed, and the generated guidance suggestions for improving the campaign performance of the target agent account, a port performance display chart is generated.

10. A device for enhancing the effect of hair coloring, characterized in that, include: The first acquisition module is used to acquire the property listing data corresponding to each broker account in the broker account set during the target time period. The determination module is used to identify target agent accounts whose placement performance does not meet the first condition and target properties whose placement performance does not meet the second condition, based on the property placement data obtained from the analysis of the large model. The analysis module is used to analyze the property listing data corresponding to each target agent account based on a large model, and to obtain a first factor and / or a second factor associated with the target agent account. The first factor is a factor that affects the listing effect of the target agent account, and the second factor is a factor that affects the listing effect of the target properties belonging to the target agent account. The first generation module is used to generate guidance suggestions for improving the advertising performance of the target broker account based on a first factor and / or a second factor associated with the target broker account.

Images