House source screening method, system and device based on semantic analysis and storage medium
By constructing a property decision tree and performing semantic analysis, the system simulates the customer's property selection process, solving the problem of matching properties with customer needs. This enables efficient and accurate property recommendations and marketing strategy adjustments, thereby increasing market transaction rates.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN HAIZHICHUANG TECH CO LTD
- Filing Date
- 2022-12-30
- Publication Date
- 2026-05-15
AI Technical Summary
Before a property goes on sale, it is difficult to accurately determine customer demand and whether the property meets customer budgets and intentions, leading to difficulties in market judgment, especially when facing a large number of customers and properties, making it impossible to predict the sales situation.
By constructing a property decision tree and obtaining customer voice data based on semantic analysis to form a digital twin, the process of simulating the customer's property selection is simulated. Combining price and degree of intent, multiple simulated openings are conducted to analyze the commonalities and differences in the results, and marketing strategies are adjusted to promote sales.
It improves the efficiency and accuracy of property recommendations, solves the problem of matching properties with customer needs in the market, accurately identifies customers who make purchases, and improves the conversion rate and the accuracy of sales analysis.
Smart Images
Figure CN116012070B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of computer technology, and in particular to a method, system, device, and storage medium for screening housing listings based on semantic analysis. Background Technology
[0002] With the advancement of computer technology and the development of the information age, more and more offline activities can be completed online through computer software or online processing. However, when transitioning from offline to online operations, many human factors often make it difficult to make accurate judgments or predictions, resulting in significant challenges in online operations.
[0003] Especially during the process of managing the sales of new properties, before the market opens, we conduct location analysis on potential customers to determine if the available properties meet their needs; we survey customers' budgets to determine if the prices are acceptable; and we analyze and assess customers' intentions to determine if their willingness to buy is high enough. Each of these issues can be tracked and resolved through software or offline records.
[0004] However, if the above-mentioned issues are combined, it becomes difficult to make a judgment. At the same time, manual recording and analysis of housing information, customer intentions, and customer budgets involve too many subjective and human factors. Not to mention, when faced with a large number of customers, a large number of housing information, and multiple price versions, it is impossible to make a judgment or predict the sales situation. Summary of the Invention
[0005] In view of this, embodiments of this application provide a method, system, device and storage medium for screening housing resources based on semantic analysis. Based on semantic analysis of customers to form a digital twin of the customer, and combined with the configuration parameters of the opening, the system can accurately judge or predict the customer's intended housing needs for sale.
[0006] To achieve the above objectives, the present invention provides the following technical solution:
[0007] In a first aspect, the present invention provides a property listing screening method based on semantic analysis, comprising the following steps:
[0008] Based on a real estate database and configuration parameters, a housing decision tree containing housing information is constructed.
[0009] Acquire voice data input from the client regarding the target property, and based on semantic analysis, obtain simulated placement data of the customer's intention from the voice data to form a digital twin of the customer;
[0010] Each customer's digital twin is set up as a placement order as a house selection attempt. After multiple simulated openings, houses are selected in order, and the final decision on whether the customer makes a purchase is made based on price, availability, and level of interest.
[0011] By comparing the commonalities and differences in the results of each simulated launch, we can analyze the sales performance on the actual launch and make targeted adjustments to our marketing strategies to help boost sales on the real launch.
[0012] Secondly, the present invention also provides a housing information screening system based on semantic analysis, comprising:
[0013] The parameter configuration module, based on a real estate database and configuration parameters, constructs a housing decision tree containing housing information;
[0014] The semantic analysis module is used to acquire voice data input by the client regarding the target property, and based on semantic analysis, to obtain simulated location data of the client's intention in the voice data and form a digital twin of the client.
[0015] The simulated placement module is used to set up a placement order for each customer's digital twin as a house selection attempt. After multiple simulated openings, the customers select houses in order, taking into account price, availability, and level of interest, and finally determine whether the customer makes a purchase.
[0016] The predictive analysis module is used to compare the commonalities and differences in the results of each simulated launch, analyze the sales performance on the actual launch, and obtain targeted marketing strategy adjustments to help boost sales on the actual launch.
[0017] Thirdly, the present invention provides a computer device, including a memory, a processor, and a computer program running on the processor, wherein the processor executes the program to implement the steps of the above-mentioned semantic analysis-based housing screening method.
[0018] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described semantic analysis-based housing screening method.
[0019] The technical solution provided by this invention may include the following beneficial effects:
[0020] This application provides a semantic analysis-based method, system, device, and storage medium for property selection. It constructs a property decision tree containing property information; acquires voice data input from clients regarding target properties; uses semantic analysis to obtain simulated placement data of client intentions from the voice data and forms a digital twin of the client; sets each client's digital twin as a placement order as a property selection attempt; after multiple simulated sales launches, properties are selected sequentially, considering price, availability, and degree of intention, ultimately determining whether a transaction is completed; compares the commonalities and differences in the results of each simulated launch, analyzes the sales performance, and obtains targeted marketing strategy adjustments to help promote sales during the actual launch. It facilitates semantic analysis based on customer voice information to obtain recommended properties, improving the efficiency of finding suitable properties and saving time, thus achieving efficient and accurate property recommendations. It addresses the current industry problem of whether estimated properties meet customer needs by analyzing customer intentions and property placement. It also solves the current industry problem of accurately identifying potential customers and determining whether estimated property prices are acceptable in the front-line market by using quartile price statistical analysis to assist in reasonable valuation. Furthermore, it addresses the current industry problem of low conversion rates in accurately identifying potential customers in the front-line market by predicting and analyzing customer placement, accurately analyzing customer sales performance, and precisely identifying high-intent customers.
[0021] These or other aspects of this application will become more apparent from the following description of embodiments. It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the application. Attached Figure Description
[0022] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. In the drawings:
[0023] Figure 1 A flowchart illustrating a semantic analysis-based property selection method provided in this application embodiment;
[0024] Figure 2 A flowchart illustrating the formation of a digital twin in a semantic analysis-based housing resource screening method provided in this application embodiment;
[0025] Figure 3 A structural block diagram of a housing information screening system based on semantic analysis provided in this application embodiment;
[0026] Figure 4 This is a hardware architecture diagram of a computer device in some embodiments of the present invention;
[0027] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0028] The present application will now be further described in conjunction with the accompanying drawings and specific embodiments. It should be noted that, without conflict, the various embodiments or technical features described below can be arbitrarily combined to form new embodiments.
[0029] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.
[0030] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0031] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present application, not the entire structure.
[0032] In related technologies, before a property launch, it's common practice to analyze customer preferences to determine if available properties meet demand; assess customer budgets to determine price acceptance; and analyze customer intentions to determine their purchasing intent. Each of these issues can be tracked and resolved through software or offline records. However, combining several of these issues becomes difficult. Furthermore, manual recording and analysis of property listings, customer intentions, and budgets introduces too many subjective and human factors. This is especially problematic when dealing with large numbers of customers, numerous properties, and multiple pricing options, making it impossible to make informed judgments or predict sales performance.
[0033] In view of this, this application provides a method, system, device and storage medium for screening housing resources based on semantic analysis. Based on semantic analysis of customers to form a digital twin of the customer, and combined with the configuration parameters of the opening, it accurately judges or predicts the customer's intended demand for housing resources for sale.
[0034] In some embodiments of this application, see Figure 1 As shown, this embodiment of the invention provides a property listing screening method based on semantic analysis, including steps S10-S40:
[0035] Step S10: Based on a real estate database and configuration parameters, construct a housing decision tree containing housing information;
[0036] Step S20: Obtain the voice data of the customer regarding the target property input by the client, obtain the simulated placement data of the customer's intention in the voice data based on semantic analysis, and form a digital twin of the customer;
[0037] Step S30: Set each customer's digital twin as a placement order as a house selection attempt. After multiple simulated openings, select houses in order, and combine price, housing availability, and degree of interest to finally determine whether the customer has made a purchase.
[0038] Step S40: Compare the commonalities and differences between the results of each simulated opening, analyze the sales performance of the opening, and make targeted adjustments to the marketing strategy to help promote sales in the actual opening.
[0039] In this embodiment, the housing decision tree includes housing information such as housing batches, buildings to be launched, units, and rooms.
[0040] In some embodiments, see Figure 2 As shown, the process of obtaining simulated location data of customer intent from the voice data based on semantic analysis and forming a digital twin of the customer includes the following steps S101-S103:
[0041] Step S201: Obtain the voice data of the customer regarding the target property input by the client, and convert the voice data into corresponding text data;
[0042] Step S202: Input the text data into the semantic analysis model for analysis to obtain the corresponding semantic analysis data;
[0043] Step S203: Compare the semantic analysis data with the preset housing conditions to obtain customer simulated location data, forming a digital twin of the customer.
[0044] In this embodiment, the housing resource constraints include the batch, building, unit, room, and price information of the property. The semantic analysis data includes the customer's preferred building, unit, room, and intended unit price. The customer is simulated and assigned a location based on the semantic analysis data compared with the preset housing resource constraints, thus forming a digital twin of the customer.
[0045] In this embodiment, the semantic analysis model uses a preset analysis strategy to analyze the text data. The preset analysis strategy includes preset nouns and preset verbs, which are used to divide the input text data according to parts of speech and punctuation marks to obtain semantic analysis data.
[0046] For example, "room" can be used as a preset noun and "search" as a preset verb. If the text data includes both the preset noun and the preset verb, the text data can be segmented according to part of speech and punctuation marks to obtain the corresponding semantic analysis data. For instance, if the text data is "Search for whether room 602, Unit 2, Building 1, in the first batch of February 2021 has been occupied", then the text can be segmented according to part of speech and whether it contains punctuation marks. The resulting semantic analysis data would be: verb - "search"; noun - "first batch of February 2021", "Unit 2, Building 1", "room 602"; punctuation - ","; noun - "occupied"; adjective - "whether".
[0047] In some embodiments, each customer's digital twin is set as a placement order as a room selection attempt, and multiple simulated openings are conducted, including a first round of simulation, a second round of simulation, and an intention simulation; wherein, the first round of simulation is an intelligent simulated opening without actual prices or intention judgment; the second round of simulation is an intelligent simulated opening with actual prices but without intention judgment; and the intention simulation is an intelligent simulated opening with actual room prices and intention judgment.
[0048] In this embodiment, the first round of simulation includes: analyzing first-intent customers based on rooms, and controlling the sale of the rooms at the highest first-intent price; the rooms are sold and the customers whose rooms are sold are marked as having completed the transaction.
[0049] The remaining properties are put on sale at the highest second-highest intended price. Customers who pay the second-highest intended price are marked as successful. This process is repeated 5 times. The number of remaining properties is checked, and the remaining properties are determined as those that cannot be sold in this simulation.
[0050] In this embodiment, the two-round simulation includes: based on a room, if the highest first intended price of the room is higher than the actual price, then the room is put on sale and the customer marks the transaction as completed; for the remaining rooms, if the highest second intended price of the room is higher than the actual price, then the room is put on sale and the customer marks the transaction as completed; this is repeated for 5 rounds, and the number of remaining rooms is checked. The remaining rooms are determined to be rooms that cannot be sold in this simulation.
[0051] In this embodiment, the intention simulation includes: processing with a probability method plus a random function, with a probability of 90% or more, calculated at 90%, calculating with a specified probability, and the probability of any position between [0,1] being equal, obtaining a value of 1 or 0 according to the specified probability function; using the system to generate a random number between 0 and 1, if the random number is less than the specified probability, outputting 0, if the random number is greater than the specified probability, outputting 1, and predicting the transaction based on the probability.
[0052] When predicting a transaction based on probability, a random function is generated using the current probability as a parameter. The function has only two results: 1 and 0. 1 represents a transaction, and 0 represents no transaction. The higher the intention level, the greater the probability of a transaction.
[0053] Through multiple simulations, comparing the commonalities and differences in each result, analyzing the sales performance at the opening, and making targeted adjustments to the marketing strategy, we can ultimately help boost sales at the actual opening.
[0054] The first prediction result shows the number of rounds in which the house was selected. 1 represents the first round, 2 represents the second round, and so on, up to the fifth round. This means that the house was not selected in the previous rounds and was finally purchased in the fifth round.
[0055] It should be understood that although the above description follows a certain order, these steps are not necessarily executed in that order. Unless otherwise expressly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, some steps in this embodiment may include multiple steps or multiple stages, which are not necessarily completed at the same time, but may be executed at different times. The execution order of these steps or stages is not necessarily sequential, but may be performed alternately or in turn with other steps or at least a portion of the steps or stages in other steps.
[0056] This invention presents a semantic analysis-based property selection method. It constructs a property decision tree containing property information; acquires voice data input from clients regarding target properties; and uses semantic analysis to obtain simulated placement data of client intentions from the voice data, forming a digital twin of the client. Each client's digital twin is designated as a placement list as a property selection attempt. After multiple simulated sales launches, properties are selected sequentially, considering price, availability, and level of intention, ultimately determining whether a transaction is completed. By comparing the commonalities and differences in the results of each simulated launch, the method analyzes the sales performance and adjusts marketing strategies accordingly to help promote sales on the actual launch. This method facilitates semantic analysis based on client voice information to obtain recommended properties, improving the efficiency of finding suitable properties, saving time, and achieving efficient and accurate property recommendations.
[0057] In some embodiments of this application, see Figure 3 As shown, the property listing screening system based on semantic analysis includes:
[0058] The parameter configuration module 100 constructs a housing decision tree containing housing information based on a real estate database and configuration parameters. When configuring parameters, the parameter configuration module 100 includes housing information such as batch, building, unit, and room to be launched.
[0059] The semantic analysis module 200 is used to acquire voice data input by the client regarding the target property, and based on semantic analysis, obtain simulated placement data of the client's intention from the voice data to form a digital twin of the client. Specifically, when forming the digital twin of the client, the semantic analysis module 200 first acquires the voice data input by the client regarding the target property, converts the voice data into corresponding text data, inputs the text data into the semantic analysis model for analysis, obtains corresponding semantic analysis data, and finally compares the semantic analysis data with preset property constraints to obtain simulated placement data of the client, thus forming the digital twin of the client.
[0060] The housing resource restrictions include the batch, building, unit, room, and price information of the property. The semantic analysis data includes the customer's preferred building, unit, room, and intended unit price. The customer is simulated and assigned a location based on the semantic analysis data and the preset housing resource restrictions, thus forming a digital twin of the customer.
[0061] The simulated listing module 300 is used to set up a listing order for each customer's digital twin as a room selection attempt. After multiple simulated openings, rooms are selected sequentially, and the final decision on whether the customer completes the transaction is made based on price, availability, and level of interest. Specifically, the simulated listing module 300 performs a first-round simulation, a second-round simulation, and an intention simulation in sequence. The first-round simulation is an intelligent simulated opening without actual price or intention judgment; the second-round simulation is an intelligent simulated opening with actual price but without intention judgment; and the intention simulation is an intelligent simulated opening with actual room price and intention judgment.
[0062] The predictive analysis module 400 compares the commonalities and differences between the results of each simulated launch, analyzes the sales performance on the actual launch, and provides targeted adjustments to marketing strategies to help boost sales during the real launch. Through multiple simulations, the module compares the commonalities and differences between the results of each launch, analyzes the sales performance on the actual launch, and provides targeted adjustments to marketing strategies to ultimately help boost sales during the real launch.
[0063] It should be noted that the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may, for example, be executed synchronously or asynchronously in multiple modules.
[0064] It should be noted that although several modules or units of the device for performing actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.
[0065] This embodiment also provides a computer device, such as... Figure 4 As shown, the computer device includes multiple computer devices 1000. In this embodiment, the components of the semantic analysis-based housing screening system can be distributed across different computer devices 1000. Each computer device 1000 can be a smartphone, tablet, laptop, desktop computer, rack server, blade server, tower server, or cabinet server (including standalone servers or server clusters composed of multiple servers), etc. The computer device 1000 in this embodiment includes, but is not limited to, a memory 1001 and a processor 1002 that can communicate with each other via a system bus. It should be noted that... Figure 4 Only a computer device 1000 with component memory 1001 and processor 1002 is shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.
[0066] In this embodiment, the memory 1001 (i.e., the readable storage medium) includes flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 1001 may be an internal storage unit of the computer device 1000, such as the hard disk or memory of the computer device 1000. In other embodiments, the memory 1001 may also be an external storage device of the computer device 1000, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the computer device 1000. Of course, the memory 1001 may also include both the internal storage unit and the external storage device of the computer device 1000. In this embodiment, the memory 1001 is typically used to store the operating system and various application software installed on the computer device, such as the semantic analysis-based housing screening system of this embodiment. In addition, the memory 1001 can also be used to temporarily store various types of data that have been output or will be output.
[0067] In some embodiments, processor 1002 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. Processor 1002 is typically used to control the overall operation of computer device 1000. In this embodiment, processor 1002 is used to run program code stored in memory 1001 or process data. When processors 1002 of multiple computer devices 1000 in this embodiment jointly execute a computer program, they implement the semantic analysis-based housing screening method of this embodiment. The method includes:
[0068] Based on a real estate database and configuration parameters, a housing decision tree containing housing information is constructed.
[0069] Acquire voice data input from the client regarding the target property, and based on semantic analysis, obtain simulated placement data of the customer's intention from the voice data to form a digital twin of the customer;
[0070] Each customer's digital twin is set up as a placement order as a house selection attempt. After multiple simulated openings, houses are selected in order, and the final decision on whether the customer makes a purchase is made based on price, availability, and level of interest.
[0071] By comparing the commonalities and differences in the results of each simulated launch, we can analyze the sales performance on the actual launch and make targeted adjustments to our marketing strategies to help boost sales on the real launch.
[0072] The process of obtaining simulated location data of customer intent from the voice data based on semantic analysis and forming a digital twin of the customer includes the following steps:
[0073] Obtain the voice data of the customer regarding the target property input by the client, and convert the voice data into corresponding text data;
[0074] The text data is input into a semantic analysis model for analysis to obtain the corresponding semantic analysis data.
[0075] By comparing the semantic analysis data with preset housing restrictions, simulated customer placement data is obtained, forming a digital twin of the customer.
[0076] In this embodiment, each customer's digital twin is set as a placement order as a room selection attempt. After multiple simulated openings, including a first round of simulation, a second round of simulation, and an intention simulation, the first round of simulation is an intelligent simulated opening without actual prices or intention judgment; the second round of simulation is an intelligent simulated opening with actual prices but without intention judgment; and the intention simulation is an intelligent simulated opening with actual room prices and intention judgment.
[0077] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-compatible storage medium, and when executed, it can include the processes of the embodiments of the methods described above.
[0078] Embodiments of this application also provide a computer-readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, server, App application store, etc., which stores a computer program. When the program is executed by a processor, it implements the corresponding function. In this embodiment, the computer-readable storage medium stores the semantic analysis-based housing screening system 10 of the embodiment. When executed by a processor, it implements the semantic analysis-based housing screening method of the embodiment, which includes:
[0079] Based on a real estate database and configuration parameters, a housing decision tree containing housing information is constructed.
[0080] Acquire voice data input from the client regarding the target property, and based on semantic analysis, obtain simulated placement data of the customer's intention from the voice data to form a digital twin of the customer;
[0081] Each customer's digital twin is set up as a placement order as a house selection attempt. After multiple simulated openings, houses are selected in order, and the final decision on whether the customer makes a purchase is made based on price, availability, and level of interest.
[0082] By comparing the commonalities and differences in the results of each simulated launch, we can analyze the sales performance on the actual launch and make targeted adjustments to our marketing strategies to help boost sales on the real launch.
[0083] The process of obtaining simulated location data of customer intent from the voice data based on semantic analysis and forming a digital twin of the customer includes the following steps:
[0084] Obtain the voice data of the customer regarding the target property input by the client, and convert the voice data into corresponding text data;
[0085] The text data is input into a semantic analysis model for analysis to obtain the corresponding semantic analysis data.
[0086] By comparing the semantic analysis data with preset housing restrictions, simulated customer placement data is obtained, forming a digital twin of the customer.
[0087] In this embodiment, each customer's digital twin is set as a placement order as a room selection attempt. After multiple simulated openings, including a first round of simulation, a second round of simulation, and an intention simulation, the first round of simulation is an intelligent simulated opening without actual prices or intention judgment; the second round of simulation is an intelligent simulated opening with actual prices but without intention judgment; and the intention simulation is an intelligent simulated opening with actual room prices and intention judgment.
[0088] 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.
[0089] Storage medium – any type of memory device or storage device. The term “storage medium” is intended to include: mounting media, such as CD-ROM, floppy disk, or magnetic tape systems; computer system memory or random access memory, such as DRAM, DDRRAM, SRAM, EDORAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. Storage medium may also include other types of memory or combinations thereof. Furthermore, storage medium may reside in a first computer system in which the program is executed, or it may reside in a different second computer system connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term “storage medium” can include two or more storage media that may reside in different locations (e.g., in different computer systems connected via a network). Storage medium may store program instructions (e.g., specifically implemented as a computer program) executable by one or more processors.
[0090] Of course, the computer-executable instructions provided in the embodiments of this application are not limited to the semantic analysis-based property screening operation described above, but can also perform related operations in the semantic analysis-based property screening method provided in any embodiment of this application.
[0091] This invention provides a semantic analysis-based property screening method, system, device, and storage medium that addresses the current industry problem of whether estimated properties meet customer needs by analyzing customer intentions and property placement. It also solves the problem of accurately locating potential buyers and determining the acceptable price of estimated properties in the current market by using quartile price statistical analysis to assist in reasonable valuation. Furthermore, it addresses the low conversion rate in accurately locating potential customers in the current market by predicting and analyzing customer placement, accurately analyzing customer sales performance, and precisely identifying high-intent customers.
[0092] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.
Claims
1. A method for screening housing listings based on semantic analysis, characterized in that, Includes the following steps: Based on a real estate database and configuration parameters, a housing decision tree containing housing information is constructed. Acquire voice data input from the client regarding the target property, and based on semantic analysis, obtain simulated placement data of the customer's intention in the voice data to form a digital twin of the customer; Each customer's digital twin is set up as a placement order as a house selection attempt. After multiple simulated openings, houses are selected in order, and the final decision on whether the customer makes a purchase is made based on price, availability, and level of interest. By comparing the commonalities and differences in the results of each simulated opening, we can analyze the sales performance on the actual opening and make targeted adjustments to our marketing strategies to help boost sales on the real opening. The process of obtaining simulated location data of customer intent from the voice data based on semantic analysis and forming a digital twin of the customer includes the following steps: obtaining voice data of the customer regarding the target property input by the client, and converting the voice data into corresponding text data; inputting the text data into a semantic analysis model for analysis to obtain corresponding semantic analysis data; comparing the semantic analysis data with preset property constraints to obtain simulated location data of the customer, and forming a digital twin of the customer. Each customer's digital twin is set as a placement order as a room selection attempt. After multiple simulated openings, including a first round of simulation, a second round of simulation, and an intention simulation, the first round of simulation is an intelligent simulated opening without actual prices or intention judgments; the second round of simulation is an intelligent simulated opening with actual prices but without intention judgments; and the intention simulation is an intelligent simulated opening with actual room prices and intention judgments. The first round of simulation includes: based on the rooms, analyzing the first potential customers, and controlling the sale of the rooms at the highest first potential price. Once the rooms are sold, the customers who have been sold are marked as having completed their transactions. The remaining rooms are controlled for sale at the highest second potential price, and the customers who have completed their transactions are marked as having completed their transactions. This process is repeated N times. The number of remaining rooms is checked, and the remaining rooms are determined as those that cannot be sold in this simulation.
2. The property listing screening method based on semantic analysis according to claim 1, characterized in that, The housing decision tree contains housing information including housing batches, buildings to be launched, units, and rooms.
3. The property listing screening method based on semantic analysis according to claim 1, characterized in that, The housing restrictions include the batch, building, unit, room, and price information of the property. The semantic analysis data includes the customer's preferred building, unit, room, and intended unit price. The customer is simulated and assigned a location based on the semantic analysis data and the preset housing restrictions, thus forming a digital twin of the customer.
4. The property listing screening method based on semantic analysis according to claim 3, characterized in that, The semantic analysis model uses a preset analysis strategy to analyze the text data. The preset analysis strategy includes preset nouns and preset verbs, which are used to divide the input text data according to parts of speech and punctuation marks to obtain semantic analysis data.
5. A property listing screening system based on semantic analysis, employing the property listing screening method based on semantic analysis as described in claim 1, characterized in that, include: The parameter configuration module, based on a real estate database and configuration parameters, constructs a housing decision tree containing housing information; The semantic analysis module is used to acquire voice data input by the client regarding the target property, and based on semantic analysis, to obtain simulated location data of the client's intention in the voice data and form a digital twin of the client. The simulated placement module is used to set up a placement order for each customer's digital twin as a house selection attempt. After multiple simulated openings, the customers select houses in order, taking into account price, availability, and level of interest, and finally determine whether the customer makes a purchase. The predictive analysis module is used to compare the commonalities and differences in the results of each simulated launch, analyze the sales performance on the actual launch, and obtain targeted marketing strategy adjustments to help boost sales on the actual launch.
6. A computer device, characterized in that, The computer device includes multiple computer devices, each computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processors of the multiple computer devices execute the computer program, they jointly implement the steps of the semantic analysis-based housing screening method according to any one of claims 1-4.
7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program stored in the storage medium is executed by a processor, it implements the steps of the semantic analysis-based housing screening method according to any one of claims 1-4.