Commercial housing price data updating method and device, equipment, storage medium and product

Abstract

The invention discloses a commercial housing price data updating method and device, equipment, a storage medium and a product, and relates to the technical field of housing price prediction.The commercial housing price data updating method comprises the steps that real estate bank valuation information, bank historical transaction data, a third-party valuation system dynamic evaluation report and policy text are collected in real time; according to the policy text, the most similar commercial housing price policy influence text is searched in a preset historical policy fluctuation database, the evaluation fluctuation range is predicted in combination with the commercial housing price policy influence text and the policy text, and the evaluation fluctuation range is determined; and carrying out data correlation modeling through real estate bank valuation information, bank historical transaction data and a third-party valuation system dynamic evaluation report, and updating commercial housing price data in combination with the valuation fluctuation range. According to the invention, the multi-source data is comprehensively analyzed in combination with the preset database and the evaluation model, and the real-time evaluation of the commercial housing is carried out to improve the evaluation accuracy.

Description

Technical Field

[0001] The present application relates to the technical field of house price prediction, and in particular to methods, devices, equipment, storage media and products for updating commodity house price data. Background Art

[0002] With the continuous development of the real estate market, accurate valuations of commercial properties are crucial for market participants. Accurate valuations not only help buyers and sellers make informed transaction decisions but also provide a crucial basis for financial institutions' risk assessments and policy formulation. However, traditional valuation methods, which determine the value of a property by comparing it with the transaction prices of similar properties in the market, have several shortcomings in practical application and are unable to meet the rapidly changing demands of the modern real estate market.

[0003] The rapid pace of change in the real estate market, frequent adjustments to policies and regulations, and limitations in data acquisition and processing have led to lags in the timeliness and accuracy of traditional valuation methods. For example, the introduction of new policies can have a significant impact on the real estate market, but traditional valuation methods often struggle to capture these changes and incorporate them into valuation models. Furthermore, data acquisition and integration present challenges. Data from different sources can suffer from inconsistent formats and untimely updates, hindering the accuracy and efficiency of valuations.

[0004] Therefore, how to improve the accuracy of commercial housing valuation is an urgent problem to be solved. Summary of the Invention

[0005] The main purpose of this application is to provide a method, device, equipment, storage medium and product for updating commercial housing price data, aiming to solve the technical problem of inaccurate commercial housing valuation.

[0006] To achieve the above objectives, this application proposes a method for updating commercial housing price data, which includes:

[0007] Real-time collection of real estate bank valuation information, bank historical transaction data, third-party valuation system dynamic assessment reports and policy texts;

[0008] Based on the policy text, searching for the most similar commodity housing price policy impact text in a preset historical policy fluctuation database, combining the commodity housing price policy impact text with the policy text to predict the valuation fluctuation range and determine the valuation fluctuation range;

[0009] Data correlation modeling is performed through real estate bank valuation information, bank historical transaction data, and dynamic evaluation reports from third-party valuation systems, and commercial housing price data is updated in combination with the valuation fluctuation range.

[0010] In one embodiment, the step of searching for the most similar commodity housing price policy impact text in a preset historical policy fluctuation database based on the policy text, and predicting the valuation fluctuation range by combining the commodity housing price policy impact text and the policy text, includes:

[0011] Input the policy text into the preset semantic analysis model to extract the key commodity housing entities and price fluctuation weights in the policy text;

[0012] According to the key commodity housing entity and the price fluctuation weight, searching for the commodity housing price policy impact text with the highest similarity from the historical policy fluctuation database;

[0013] Input the text on the impact of the commodity housing price policy into the pre-trained temporal convolutional network to predict the historical policy benchmark fluctuation range;

[0014] The key commodity housing entities, the price fluctuation weights and the historical policy benchmark fluctuation range are integrated to generate an estimated price fluctuation range.

[0015] In one embodiment, the step of inputting the policy text into a preset semantic analysis model to extract key commodity housing entities and price fluctuation weights in the policy text includes:

[0016] Perform structured analysis on the policy text and extract key commercial housing entities in the policy through the named entity recognition model;

[0017] Based on the preset large language model in the real estate field, the policy text is semantically embedded to generate a policy feature vector;

[0018] The contextual relevance of policy feature vectors is analyzed through a multi-head attention mechanism, and the price fluctuation weights of each key commodity housing entity are calculated.

[0019] In one embodiment, the step of modeling data correlation using real estate bank valuation information, bank historical transaction data, and a third-party valuation system dynamic evaluation report includes:

[0020] Perform spatiotemporal alignment of real estate bank valuation information, historical bank transaction data, and dynamic assessment reports from third-party valuation systems, including unified timestamp format, geographic coordinate encoding, and property identifier matching;

[0021] The key attributes of the real estate bank valuation information, the bank's historical transaction data and the third-party valuation system's dynamic evaluation report are extracted through feature engineering, and data correlation modeling is performed based on preset weight distribution to obtain commercial housing valuation benchmark data.

[0022] In one embodiment, the step of collecting real estate bank valuation information, bank historical transaction data, third-party valuation system dynamic assessment reports, and policy texts in real time includes:

[0023] Based on the preset bank valuation information channel, real-time streaming acquisition of real estate bank valuation information and historical bank transaction data;

[0024] Based on the preset third-party evaluation report channel, the dynamic evaluation report of the third-party valuation system is updated daily;

[0025] Based on the preset allocation policy acquisition channel, the policy text is updated daily.

[0026] In one embodiment, the step of modeling data correlation using real estate bank valuation information, historical bank transaction data, and a dynamic evaluation report from a third-party valuation system, and updating commodity housing price data in combination with the valuation fluctuation range, includes:

[0027] When receiving a query instruction for a specified commercial housing range, the bank valuation, third-party assessment and policy impact valuation corresponding to the commercial housing range are displayed visually through charts;

[0028] Based on the local historical database, the historical valuation fluctuation curve of the commercial housing range is supplemented.

[0029] In addition, to achieve the above-mentioned purpose, the present application also proposes a device for updating commodity housing price data, the device comprising:

[0030] The collection module is used to collect real estate bank valuation information, historical bank transaction data, dynamic evaluation reports from third-party valuation systems, and policy texts in real time;

[0031] A prediction module is used to search for the most similar commodity housing price policy impact text in a preset historical policy fluctuation database based on the policy text, and to predict the valuation fluctuation range by combining the commodity housing price policy impact text and the policy text to determine the valuation fluctuation range;

[0032] The update module is used to model data correlation through real estate bank valuation information, bank historical transaction data, and dynamic evaluation reports of third-party valuation systems, and update commercial housing price data in combination with the valuation fluctuation range.

[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes a commercial housing price data updating device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program is configured to implement the steps of the commercial housing price data updating method as described above.

[0034] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium, and when the computer program is executed by the processor, the steps of the commercial housing price data updating method as described above are implemented.

[0035] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the commercial housing price data updating method as described above.

[0036] One or more technical solutions proposed in this application have at least the following technical effects:

[0037] Compared with the traditional valuation method in the related art, which determines the valuation by comparing the property to be appraised with the transaction price of similar properties in the market, this application collects real estate bank valuation information, bank historical transaction data, third-party valuation system dynamic evaluation reports and policy texts in real time; based on the policy text, searches for the most similar commodity housing price policy impact text in a preset historical policy fluctuation database, combines the commodity housing price policy impact text and the policy text to predict the valuation fluctuation range and determine the valuation fluctuation range; models the data correlation through real estate bank valuation information, bank historical transaction data, and third-party valuation system dynamic evaluation reports, and updates the commodity housing price data based on the valuation fluctuation range. It can be understood that this application uses real-time data collection from real estate banks, historical transaction data, third-party valuation systems and policy documents, and combines them with preset databases and models for comprehensive analysis, which can provide more accurate and real-time commodity housing valuations. Therefore, through this multi-source data fusion and real-time update method, it can help financial institutions and real estate developers better understand market dynamics, improve valuation accuracy and decision-making quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0040] Figure 1 A flowchart of the first embodiment of the method for updating commodity housing price data provided in this application;

[0041] Figure 2This is a schematic diagram of the module structure of the commercial housing price data updating device according to an embodiment of the present application;

[0042] Figure 3 This is a schematic diagram of the device structure of the hardware operating environment involved in the commercial housing price data updating method in the embodiment of the present application.

[0043] The purpose, features and advantages of this application will be further explained with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0044] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0045] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0046] The main solutions of the embodiments of this application are:

[0047] Real-time collection of real estate bank valuation information, bank historical transaction data, third-party valuation system dynamic assessment reports and policy texts;

[0048] Based on the policy text, searching for the most similar commodity housing price policy impact text in a preset historical policy fluctuation database, combining the commodity housing price policy impact text with the policy text to predict the valuation fluctuation range and determine the valuation fluctuation range;

[0049] Data correlation modeling is performed through real estate bank valuation information, bank historical transaction data, and dynamic evaluation reports from third-party valuation systems, and commercial housing price data is updated in combination with the valuation fluctuation range.

[0050] In this embodiment, the present application uses the commodity housing price data updating device as the execution subject. For the convenience of description, it is specifically described below as "device".

[0051] Since existing technologies determine valuations by comparing the property to be appraised with the transaction prices of similar properties on the market, there are some shortcomings in practical applications and it is difficult to meet the rapidly changing needs of the modern real estate market.

[0052] This application provides a solution, which collects real estate bank valuation information, bank historical transaction data, third-party valuation system dynamic evaluation reports and policy texts in real time; based on the policy texts, searches for the most similar commodity housing price policy impact texts in a preset historical policy fluctuation database, combines the commodity housing price policy impact texts and the policy texts to predict the valuation fluctuation range and determine the valuation fluctuation range; models the data correlation through real estate bank valuation information, bank historical transaction data, and third-party valuation system dynamic evaluation reports, and updates the commodity housing price data in combination with the valuation fluctuation range. It can be understood that this application uses real-time data collection from real estate banks, historical transaction data, third-party valuation systems and policy documents, and combines the preset database and model for comprehensive analysis, which can provide more accurate and real-time commodity housing valuations. Therefore, through this multi-source data fusion and real-time update method, it can help financial institutions and real estate developers better understand market dynamics, improve the accuracy of valuations and the quality of decision-making.

[0053] Based on this, the embodiment of the present application provides a method for updating commodity housing price data, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for updating commercial housing price data of this application.

[0054] In this embodiment, the method for updating commodity housing price data includes steps S10 to S30:

[0055] Step S10: real-time collection of real estate bank valuation information, bank historical transaction data, third-party valuation system dynamic assessment reports and policy texts;

[0056] It's important to note that a distributed API gateway cluster is a distributed system architecture composed of multiple API gateways. As the system's entry point, the API gateway is responsible for receiving and processing client requests, performing tasks such as request routing, protocol conversion, authentication, and load balancing. A distributed API gateway cluster achieves high availability, scalability, and concurrent processing capabilities by deploying multiple API gateway instances on different servers or nodes. In real estate valuation systems, using a distributed API gateway cluster can efficiently process large volumes of requests from diverse data sources, ensuring real-time data collection and transmission.

[0057] Real estate bank valuation information is professional assessment data on real estate value provided by banks and other financial institutions. Banks conduct real estate valuation assessments to determine their mortgage value or market value when approving real estate loans or disposing of assets. This valuation information is typically based on the bank's internal valuation models, market data, and the opinions of professional appraisers. It is highly authoritative and accurate, and serves as a crucial reference for real estate appraisals.

[0058] Bank historical transaction data is a collection of historical transaction records accumulated by banks in real estate-related businesses. This includes information on the amounts, terms, and interest rates of real estate mortgage loans, as well as the amounts, transaction times, and information on both parties involved in real estate purchases and sales. This data reflects actual real estate market transactions and price trends, providing valuable insights for analyzing market trends and assessing real estate values.

[0059] A dynamic appraisal report from a third-party appraisal system is a real estate appraisal report generated by a third-party appraisal agency or system independent of banks and real estate companies. These agencies typically have professional appraisal teams and advanced appraisal technology, enabling comprehensive evaluations of real estate from multiple perspectives. Dynamic appraisal reports are updated promptly based on market changes, policy adjustments, and other factors to reflect the latest real estate values, providing market participants with an objective and fair valuation reference.

[0060] Policy documents are government policy documents related to the real estate market, including real estate regulation policies, tax policies, land supply policies, and urban planning policies. These policies have a significant impact on the development direction, market rules, and pricing mechanisms of the real estate market. Policy changes may directly or indirectly affect the demand, supply, and price of real estate, making the interpretation and analysis of policy documents an integral part of real estate valuation.

[0061] For example, in the Shenzhen real estate market, a real estate appraisal agency employed the aforementioned commercial housing price data update method. By establishing a distributed API gateway cluster, it connected with multiple banks, third-party appraisal systems, and government policy release platforms. This method collected real estate bank valuation information, historical bank transaction data, dynamic assessment reports from third-party appraisal systems, and policy texts in real time. In policy text analysis, a pre-set semantic analysis model was used to extract key entities and weights from Shenzhen's newly issued real estate regulatory policies, such as policy type (purchase restriction), impact area (Nanshan District), and regulatory intensity (medium). The most similar event time series were then searched from a historical policy fluctuation database. A temporal convolutional network was then used to predict the benchmark fluctuation range, ultimately generating an appraisal fluctuation range. The collected bank valuation information, historical bank transaction data, and dynamic assessment reports from third-party appraisal systems were subjected to spatiotemporal alignment and feature engineering. Data correlation modeling was then performed based on pre-set weights to generate commercial housing valuation benchmark data. Based on the valuation fluctuation range, the commercial housing valuation for a particular property in Nanshan District was updated. When customers inquire about the valuation information of the property, the system uses charts to visualize bank valuations, third-party assessments, and policy-influenced valuations, and supplements historical valuation fluctuation curves to provide customers with comprehensive, accurate, and real-time valuation information, effectively improving the accuracy and timeliness of valuations and helping customers make more reasonable transaction decisions.

[0062] In a feasible implementation, the step of collecting real estate bank valuation information, bank historical transaction data, third-party valuation system dynamic assessment reports, and policy texts in real time includes:

[0063] Based on the preset bank valuation information channel, real-time streaming acquisition of real estate bank valuation information and historical bank transaction data;

[0064] Based on the preset third-party evaluation report channel, the dynamic evaluation report of the third-party valuation system is updated daily;

[0065] Based on the preset allocation policy acquisition channel, the policy text is updated daily.

[0066] It's important to note that the Bank Valuation Information Channel is a communication channel specifically designed to transmit real estate bank valuation information. It establishes a direct data connection between the bank's system and the real estate valuation platform, ensuring efficient and accurate transmission of bank valuation information from the bank to the platform, providing fundamental data support for subsequent valuation analysis.

[0067] Streaming is a data transmission method that sends data from a source to a receiver in a continuous flow. In real estate valuation systems, streaming can provide real-time access to bank valuation information and historical bank transaction data, enabling the valuation platform to promptly process and analyze the latest market data, improving the timeliness and accuracy of valuations.

[0068] The third-party appraisal report channel is a dedicated channel established for transmitting dynamic appraisal reports from third-party appraisal systems. It connects third-party appraisal agencies with the real estate appraisal platform, ensuring that dynamic appraisal reports are delivered to the platform in a timely and complete manner. This enables the platform to integrate multiple assessment information and improve the comprehensiveness and reliability of appraisal results.

[0069] The Policy Access Channel is used to access the text of real estate-related policies issued by government departments. Through this channel, the real estate valuation platform can obtain the latest policy information in a timely manner, providing a data foundation for policy analysis and valuation fluctuation range forecasting. This allows policy factors to be incorporated into valuation models, improving the scientificity and rationality of valuation results.

[0070] Understandably, a real estate appraisal company adopted the aforementioned technical solution, establishing multiple dedicated channels through a distributed API gateway cluster. First, using the pre-defined bank valuation information channel and the distributed API gateway cluster's streaming capabilities, it retrieves real estate bank valuation information and historical bank transaction data from multiple partner banks in real time. This data includes the bank's latest valuations for properties in different regions and types, as well as detailed records of historical transactions, including property prices, transaction times, and information about both parties involved. Next, using the pre-defined distributed third-party appraisal report channel, the distributed API gateway cluster updates dynamic appraisal reports from various third-party appraisal agencies daily. These reports include results from various valuation methods, such as market comparison, cost-based approaches, and income-based approaches, as well as analysis of factors such as market trends and regional development. Finally, using the pre-defined distributed policy acquisition channel, the distributed API gateway cluster updates government real estate policy texts, such as purchase restrictions, tax policies, and land supply policies, on a daily basis. The appraisal company utilizes the data obtained from these channels, combined with its own valuation models and analytical tools, to more comprehensively and accurately assess the value of commercial housing. When faced with market fluctuations and policy adjustments, we are able to respond quickly, update valuation results, and provide customers with timely and reliable valuation services, effectively improving market competitiveness and customer satisfaction.

[0071] Step S20: searching for the most similar commodity housing price policy impact text in a preset historical policy fluctuation database based on the policy text, and performing a valuation fluctuation range prediction based on the commodity housing price policy impact text and the policy text to determine the valuation fluctuation range;

[0072] It should be noted that the preset historical policy fluctuation database is a pre-established database used to store historical records of changes in real estate-related policies and data on the impact of these policy changes on the real estate market. This includes information on multiple dimensions, such as policy type, change time, impact, and market reaction. By collecting and organizing historical policy fluctuation data, it provides a reference basis for current policy analysis and valuation fluctuation forecasts.

[0073] Valuation fluctuation range forecasting is a process of estimating and projecting the potential fluctuations in real estate valuations in the future, based on analysis of policy texts and data from a historical policy fluctuation database, using specific models and algorithms. This forecast aims to provide a reference range for real estate valuations, helping market participants better understand and respond to market fluctuations.

[0074] The valuation fluctuation range is determined based on valuation fluctuation forecasts and represents the range within which real estate prices may fluctuate over the next period of time. This range reflects the market's potential response to factors such as policy changes, provides a basis for dynamic adjustments in real estate valuations, and helps improve the accuracy and scientific nature of valuations.

[0075] Understandably, in a certain city's real estate market, an appraisal agency employed the aforementioned method to determine the valuation fluctuation range for commercial housing. When a new real estate policy is introduced, such as adjustments to purchase restrictions or changes to property taxes, the agency first obtains the policy text and feeds it into a pre-set semantic analysis model to extract key entities and weights, such as information such as the policy type being a relaxation of purchase restrictions, the impacting area being the city's core, and the degree of regulatory intensity. Next, the agency searches a pre-set database of historical policy fluctuations for the event time series most similar to the current policy, analyzing the impact of similar policies on real estate prices in that area. This event time series is then fed into a pre-trained temporal convolutional network to predict a baseline fluctuation range. For example, it predicts that the likely fluctuation range of housing prices in that area due to policy adjustments over the next three months will be ±5% of the baseline price. Finally, the agency integrates key entities, key impact weights, and the baseline fluctuation range to generate a specific valuation fluctuation range. For example, for a property in the city's core area, considering its degree of policy impact, the valuation fluctuation range is determined to be -3% to +7% of the baseline price. This valuation fluctuation range provides a scientific reference for the valuation of the property, helping market participants to more accurately grasp the potential changing trends of housing prices and thus make more reasonable transaction decisions.

[0076] In a feasible implementation, the step of searching for the most similar commodity housing price policy impact text in a preset historical policy fluctuation database based on the policy text, and predicting the valuation fluctuation range by combining the commodity housing price policy impact text and the policy text, wherein the step of determining the valuation fluctuation range includes:

[0077] Input the policy text into the preset semantic analysis model to extract the key commodity housing entities and price fluctuation weights in the policy text;

[0078] According to the key commodity housing entity and the price fluctuation weight, searching for the commodity housing price policy impact text with the highest similarity from the historical policy fluctuation database;

[0079] Input the text on the impact of the commodity housing price policy into the pre-trained temporal convolutional network to predict the historical policy benchmark fluctuation range;

[0080] The key commodity housing entities, the price fluctuation weights and the historical policy benchmark fluctuation range are integrated to generate an estimated price fluctuation range.

[0081] It's important to note that the pre-trained semantic analysis model is a computational model used for semantic analysis and understanding of text. In the real estate valuation field, this model can deeply analyze policy texts, identifying key information and semantic relationships within them, providing a foundation for predicting subsequent valuation fluctuations.

[0082] Key commercial housing entities and price fluctuation weights are entities with significant influence extracted from policy texts, such as policy type, effective time, affected areas, regulatory intensity, etc., as well as a quantitative representation of the relative importance or influence of these entities in the policy's impact on the real estate market.

[0083] The pretrained Time Series Convolutional Network (TCN) is a pre-trained deep learning model based on the Convolutional Neural Network (CNN) architecture, specifically designed for processing and analyzing time series data. TCNs automatically extract features and patterns from time series data, making them highly accurate and efficient for predicting real estate market fluctuations.

[0084] The historical policy benchmark fluctuation range is based on the prediction results of a time-series convolutional network. It shows the basic fluctuation range of real estate prices due to policy changes under normal market conditions. It is an important reference indicator for predicting valuation fluctuation ranges.

[0085] Understandably, when a new real estate policy is released, the valuation agency first feeds the policy text into a pre-set semantic analysis model. The model parses the policy text, extracting key entities and weights, such as the policy type "purchase restriction policy adjustment," the affected area "city center," and the regulatory intensity "medium to high." Next, based on these key entities and weights, the valuation agency searches for the most similar event time series from a database of historical policy fluctuations. Suppose the found historical event time series shows that, following similar policy adjustments, housing prices in the city center experienced a downward trend followed by an upward trend over the following three months, with fluctuations ranging from 5% to 8%. This event time series is then fed into a pre-trained temporal convolutional network, which predicts a baseline fluctuation range of ±6% for the current policy adjustment. Finally, the model integrates the key entities, key impact weights, and the baseline fluctuation range to generate a specific valuation fluctuation range. For example, for a high-end property in the city center, considering its policy impact and market characteristics, the valuation fluctuation range is determined to be -4% to +9% of the benchmark price. This valuation fluctuation range provides a scientific reference for market participants, helping them to more accurately grasp the potential changing trends of housing prices and make more reasonable trading decisions, effectively improving the accuracy of valuation and market adaptability.

[0086] In a feasible implementation, the step of inputting the policy text into a preset semantic analysis model and extracting key commodity housing entities and price fluctuation weights in the policy text includes:

[0087] Perform structured analysis on the policy text and extract key commercial housing entities in the policy through the named entity recognition model;

[0088] Based on the preset large language model in the real estate field, the policy text is semantically embedded to generate a policy feature vector;

[0089] The contextual relevance of policy feature vectors is analyzed through a multi-head attention mechanism, and the price fluctuation weights of each key commodity housing entity are calculated.

[0090] It should be noted that structured parsing is the process of converting unstructured policy text data into structured data. This involves identifying key information elements in the text, such as policy type, time, and region, and organizing them into a form with a clear data structure and format to facilitate further processing and analysis by computer programs.

[0091] Named Entity Recognition (NER) is a natural language processing technology used to identify meaningful entity names from text, such as names of people, places, organizations, dates, and times. In policy text parsing, NER can accurately extract key entity information from policies, providing a foundation for subsequent analysis and processing.

[0092] The pre-built large language model for real estate is a pre-trained language model specifically for the real estate sector, incorporating extensive domain knowledge and semantic understanding capabilities. By learning and training on a large amount of real estate-related text, this model can perform in-depth semantic analysis and understanding of policy texts, generating domain-specific semantic embedding representations.

[0093] Semantic embedding is the process of mapping words or sentences in a text into a low-dimensional vector space, enabling these vectors to capture the text's semantic information and context. In the real estate sector, semantic embedding can transform the complex semantics of policy documents into computable numerical vectors, facilitating subsequent model processing and analysis.

[0094] The policy feature vector is a numerical vector generated through semantic embedding that represents the semantic characteristics of the policy text. It integrates the key information and semantic meaning of the policy text and serves as an important data foundation for subsequent analysis of the policy's impact.

[0095] The multi-head attention mechanism is a variant of the attention mechanism in deep learning models. It can simultaneously focus on multiple different positions and features when processing sequential data, capturing the complex contextual dependencies and semantic associations in the text. In policy text analysis, the multi-head attention mechanism can provide a more comprehensive understanding of the individual elements in the policy feature vector and their interrelationships.

[0096] The price volatility weight quantifies the relative importance or influence of key entities in policy texts on real estate valuation fluctuations. It reflects the varying degrees of impact that different policy elements may have on the real estate market, providing a refined basis for subsequent forecasts of valuation fluctuations.

[0097] Understandably, when a new real estate regulatory policy is released, the valuation agency first performs a structured analysis of the policy text. Using a named entity recognition model, they extract key entities within the policy, such as "property tax pilot," "citywide impact," and "high" regulatory intensity. Next, based on a pre-defined large language model for the real estate sector, they perform semantic embedding on the policy text to generate a policy feature vector that comprehensively captures the semantic information and domain characteristics of the policy text. A multi-head attention mechanism then analyzes the contextual relevance of the policy feature vector and calculates the key influence weights for each key entity. For example, the influence weight for policy type is 0.4, the influence weight for effective date is 0.2, the influence weight for impact area is 0.3, and the influence weight for regulatory intensity is 0.1. These key influence weights reflect the relative importance of different policy elements to real estate valuations, providing accurate parameter support for subsequent valuation fluctuation range predictions based on historical data and market conditions, thereby enhancing the scientific nature and reliability of the valuation results.

[0098] Step S30: Data correlation modeling is performed using real estate bank valuation information, bank historical transaction data, and a dynamic evaluation report from a third-party valuation system, and commodity housing price data is updated in combination with the valuation fluctuation range.

[0099] It's important to note that data correlation modeling is a process of analyzing and processing the relationships between multiple data sources to build mathematical or statistical models that reveal the underlying connections and mutual influences between them. In real estate valuation, data correlation modeling aims to integrate information from various sources, such as real estate bank valuation information, historical bank transaction data, and dynamic assessment reports from third-party valuation systems, to uncover the correlations between them and provide a foundation for more accurate valuations.

[0100] Commercial housing valuation is the process of evaluating and estimating the value of commercial housing. It considers a variety of factors, such as market conditions, location, area, floor plan, construction quality, and surrounding amenities, to determine a reasonable price range for the property. Accurate commercial housing valuation is crucial for the healthy development of the real estate market, transaction decisions between buyers and sellers, and risk management for financial institutions.

[0101] Understandably, in a certain city's real estate market, an appraisal agency employed the aforementioned method to update commercial housing valuations. First, the agency collected real estate bank valuation information, historical bank transaction data, and dynamic assessment reports from a third-party valuation system. The real estate bank valuation information provided professional bank valuations for properties in different regions and types; the bank's historical transaction data contained detailed records of actual transaction prices and transaction times; and the dynamic assessment reports from the third-party valuation system provided an independent assessment of property values and were updated promptly based on market changes.

[0102] Next, the valuation agency performs spatiotemporal alignment on this data to ensure consistency across time and space. For example, they standardize the timestamp format to organize data from different data sources according to the same time scale; perform geocoding to convert the property's location information into a unified geocoordinate format; and match property identifiers to ensure accurate correspondence between data from different data sources for the same property.

[0103] Then, through feature engineering, key attributes from each data source are extracted. For real estate bank valuation information, key attributes such as valuation method, valuation time, and valuation price are extracted; for historical bank transaction data, key attributes such as transaction amount, transaction area, and transaction floor are extracted; and for dynamic evaluation reports from third-party valuation systems, key attributes such as valuation method, evaluation price, and market trend analysis are extracted. Based on pre-defined weightings, data correlation modeling is performed on these key attributes to generate benchmark data for commercial housing valuations. For example, a 40% weight is assigned to real estate bank valuation information, a 30% weight is assigned to historical bank transaction data, and a 30% weight is assigned to dynamic evaluation reports from third-party valuation systems. A weighted fusion approach is used to calculate the benchmark valuation.

[0104] Finally, the commercial housing valuation is updated based on the previously determined valuation fluctuation range. Assuming that, based on policy analysis and historical data, the valuation fluctuation range for a certain area is ±5% of the benchmark price, the valuation agency will adjust the commercial housing valuation based on this fluctuation range. For example, if the benchmark valuation for a commercial housing unit in that area is 1 million yuan, the final valuation range will be between 950,000 yuan and 1.05 million yuan. This updated valuation result not only considers the correlation between multiple data sources but also incorporates the impact of policy factors on the market. This provides market participants with more comprehensive and accurate valuation information, helping them make better transaction decisions and enhancing the competitiveness and professionalism of the valuation agency in the market.

[0105] In a feasible implementation, the step of modeling data correlation using real estate bank valuation information, bank historical transaction data, and a dynamic evaluation report from a third-party valuation system includes:

[0106] Perform spatiotemporal alignment of real estate bank valuation information, historical bank transaction data, and dynamic assessment reports from third-party valuation systems, including unified timestamp format, geographic coordinate encoding, and property identifier matching;

[0107] The key attributes of the real estate bank valuation information, the bank's historical transaction data and the third-party valuation system's dynamic evaluation report are extracted through feature engineering, and data correlation modeling is performed based on preset weight distribution to obtain commercial housing valuation benchmark data.

[0108] It's important to note that spatiotemporal alignment involves unifying and matching real estate bank valuation information, historical bank transaction data, and dynamic assessment reports from third-party valuation systems across different data sources in both time and space during data processing. Temporal alignment involves converting data in different time formats into a unified timestamp format to enable accurate comparison and analysis of data at different times. Spatial alignment involves geocoding, converting property location information into a unified geocoordinate format, and matching property identifiers to ensure accurate matching of data for the same property across different data sources.

[0109] Geocoding is the process of converting a property's address into a standardized geographic coordinate format. This typically includes longitude and latitude, allowing for precise location on a map. This facilitates spatial integration and analysis of property information from disparate data sources, improving data comparability and usability.

[0110] Building identifier matching assigns a unique identifier to each building, allowing accurate matching of building information across different data sources. This ensures that data related to the same building from different sources can be correctly mapped during data correlation modeling, avoiding data confusion and incorrect associations.

[0111] Feature engineering is the process of selecting, transforming, extracting, and constructing new features from data before modeling. For real estate bank valuation information, historical bank transaction data, and dynamic assessment reports from third-party valuation systems, feature engineering aims to extract the key attributes that most influence commercial housing valuations, such as valuation price, transaction amount, and appraisal price. Data cleaning and normalization are then performed as needed to improve model performance and accuracy.

[0112] Commercial housing valuation benchmark data is derived through data correlation modeling and serves as the foundation for commercial housing valuations. It integrates key attributes from real estate bank valuation information, historical bank transaction data, and dynamic assessment reports from third-party valuation systems. This data is then integrated and calculated based on preset weights to produce a relatively stable and accurate valuation benchmark, providing a crucial basis for subsequent final valuations based on the valuation fluctuation range.

[0113] Understandably, in a real estate valuation scenario, a valuation company first performs spatiotemporal alignment on collected real estate bank valuation information, historical bank transaction data, and dynamic assessment reports from a third-party valuation system. This involves converting the time records of the bank valuation information and historical transaction data into a unified "YYYY-MM-DD" format, encoding the geo-coordinates of the property addresses in the third-party valuation report, converting them to latitude and longitude, and matching them using property identifiers to ensure accurate alignment of information for the same property across different data sources.

[0114] Next, the company used feature engineering to extract key attributes from each data source. For real estate bank valuation information, key attributes such as valuation price, valuation method, and valuation time were extracted; for historical bank transaction data, key attributes such as transaction amount, transaction area, and transaction floor were extracted; and for dynamic assessment reports from third-party valuation systems, key attributes such as valuation price, market trend analysis, and regional development impact were extracted. Then, based on pre-set weighting (40% for real estate bank valuation information, 30% for historical bank transaction data, and 30% for dynamic assessment reports from third-party valuation systems), data correlation modeling was performed to generate benchmark data for commercial housing valuations.

[0115] Assume that, after the above processing, the estimated benchmark value for a commercial property in a certain area is 1.2 million yuan. Combined with the previously determined fluctuation range for the valuation in that area of ±5% of the benchmark price, the final valuation range for the property would be between 1.14 million yuan and 1.26 million yuan. This valuation not only integrates information from multiple sources but also takes into account market fluctuations and policy impacts, providing buyers and sellers with a more accurate and reliable valuation reference, helping to improve transaction efficiency and market transparency, and enhancing the confidence of market participants.

[0116] This embodiment provides a method for updating commercial housing price data. It uses real-time data collection from real estate banks, historical transaction data, third-party valuation systems, and policy documents, and combines it with preset databases and models for comprehensive analysis. This method can provide more accurate and real-time commercial housing valuations. Therefore, this multi-source data fusion and real-time update method can help financial institutions and real estate developers better understand market dynamics, improve valuation accuracy, and improve decision-making quality.

[0117] In a feasible implementation, the step of modeling data correlation using real estate bank valuation information, historical bank transaction data, and dynamic evaluation reports from a third-party valuation system, and updating commodity housing price data in combination with the valuation fluctuation range, includes:

[0118] When receiving a query instruction for a specified commercial housing range, the bank valuation, third-party assessment and policy impact valuation corresponding to the commercial housing range are displayed visually through charts;

[0119] Based on the local historical database, the historical valuation fluctuation curve of the commercial housing range is supplemented.

[0120] It's important to note that a query command specifying a specific housing area is issued by the user or the system to specify the area or range of housing for which valuation information is to be retrieved. This command specifies the specific housing group for which valuations are to be displayed and serves as the basis for the system to trigger subsequent valuation information processing.

[0121] Chart visualization is the process of presenting complex data in an intuitive and understandable manner through visualization tools such as charts. In real estate valuations, it is used to display various valuation information, including bank valuations, third-party assessments, and policy-influenced valuations, for commercial housing, helping users quickly grasp data characteristics and trends.

[0122] A local historical database is a database stored on a local server or system that contains historical real estate valuation data and related information. It provides historical data support for current valuation analysis and facilitates historical comparisons and trend analysis.

[0123] It's understandable that in the valuation service module of a certain real estate information platform, when a user enters a query command specifying a specific range of commercial housing units, for example, selecting all commercial housing units within a specific area of a city, the system first receives the query and determines the range of commercial housing units to be processed. Next, the system uses a chart visualization feature to generate and display a comparative chart comparing bank valuations, third-party assessments, and policy-influenced valuations for that range of commercial housing units. The chart shows bank valuations as blue bars, third-party assessments as red lines, and policy-influenced valuations as green shaded areas, visually illustrating the differences and interrelationships between the results from different valuation sources.

[0124] At the same time, the system supplements the historical valuation fluctuation curve for the specific commercial housing range based on the local historical database. This historical valuation fluctuation curve, represented by a gray dashed line, is displayed on the chart alongside the current valuation data, providing a time-based data comparison. Through this visual display and supplementary historical data, users can gain a comprehensive understanding of the valuation situation within a specific commercial housing range, including the current results from different valuation sources and historical price trends. This not only enhances users' knowledge and understanding of the real estate market, but also provides strong data support for their transaction decisions, enhancing the professionalism and practicality of the real estate information platform.

[0125] For example, in order to help understand the implementation process of the method for updating commercial housing price data obtained by combining this embodiment with the above-mentioned embodiment 1, specifically:

[0126] Establish data channels: Based on the preset bank valuation information channel, third-party evaluation report channel and policy acquisition channel, they are used to obtain real estate bank valuation information and bank historical transaction data in real time, update the third-party valuation system dynamic evaluation report on a daily basis, and update the policy text on a daily basis.

[0127] Real-time Collection: Through a distributed API gateway cluster, we collect real estate bank valuation information, historical bank transaction data, dynamic assessment reports from third-party valuation systems, and policy documents in real time. This step ensures the timeliness and comprehensiveness of the data obtained, providing a foundation for subsequent valuation analysis.

[0128] Structured Parsing and Key Entity Extraction: We perform structured parsing of policy texts and use named entity recognition models to extract key entities within the policy, including policy type, effective date, impacted regions, and regulatory intensity. This step accurately identifies the core elements of the policy, providing critical information for subsequent analysis.

[0129] Semantic Embedding and Feature Vector Generation: Based on a pre-defined large-scale language model for the real estate sector, the policy text is semantically embedded to generate a policy feature vector. This step converts the semantic information of the policy text into a computable numerical vector, facilitating subsequent model processing and analysis.

[0130] Calculation of Key Impact Weights: A multi-head attention mechanism analyzes the contextual relevance of policy feature vectors and calculates the key impact weights of each key entity. This step quantifies the relative importance of different policy factors on real estate valuations, providing a refined basis for subsequent valuation fluctuation range predictions.

[0131] Similar event time series search: Based on key entities and weights, we search the historical policy fluctuation database for the most similar event time series. This step can identify historical cases similar to the current policy, providing a reference for prediction.

[0132] Baseline Fluctuation Range Prediction: The event time series is fed into a pre-trained time series convolutional network to predict the base fluctuation range. This step uses a deep learning model to analyze time series data and predict the basic fluctuation range of real estate prices.

[0133] Determining the Valuation Fluctuation Range: Key entities, key impact weights, and the benchmark fluctuation range are integrated to generate a valuation fluctuation range. This step considers policy factors and historical data to determine the fluctuation range of real estate prices, providing guidance for subsequent valuation updates.

[0134] Spatiotemporal alignment: This involves aligning real estate bank valuation information, historical bank transaction data, and dynamic assessment reports from third-party valuation systems. This involves standardizing timestamp formats, geographic coordinate encoding, and matching property identifiers. This step ensures temporal and spatial consistency across different data sources, providing a foundation for subsequent data fusion and analysis.

[0135] Feature Engineering and Key Attribute Extraction: Feature engineering is used to extract key attributes from real estate bank valuation information, historical bank transaction data, and dynamic assessment reports from third-party valuation systems. This step can filter the most valuable information for valuation from large amounts of data, improving the efficiency and accuracy of the model.

[0136] Data Relevance Modeling: Based on preset weights, data relevance modeling is performed on the extracted key attributes to generate benchmark data for commercial housing valuations. This step integrates information from multiple data sources through methods such as weighted fusion to form a relatively stable and accurate valuation benchmark.

[0137] Valuation Update: Update the benchmark data for commercial housing valuations based on the valuation fluctuation range. This step incorporates policy analysis and market fluctuations into the valuation model, making the valuation results more closely aligned with actual market conditions.

[0138] Visualization and Historical Data Supplementation: When receiving a query for a specific commercial housing range, the platform visually displays bank valuations, third-party assessments, and policy-influenced valuations for that range through charts. The platform also supplements historical valuation fluctuation curves for that range based on the local historical database. This step provides users with intuitive and comprehensive valuation information, helping them better understand and analyze market changes.

[0139] It should be noted that the above examples are only used to understand this application and do not constitute a limitation on the commercial housing price data updating method of this application. More simple transformations based on this technical concept are all within the scope of protection of this application.

[0140] This application also provides a commodity housing price data update device, please refer to Figure 2 , the commercial housing price data updating device includes:

[0141] Collection module 10, used for real-time collection of real estate bank valuation information, bank historical transaction data, third-party valuation system dynamic assessment reports and policy texts;

[0142] Prediction module 20 is used to search for the most similar commodity housing price policy impact text in a preset historical policy fluctuation database based on the policy text, and to predict the valuation fluctuation range by combining the commodity housing price policy impact text and the policy text to determine the valuation fluctuation range;

[0143] The updating module 30 is used to model the data correlation through the real estate bank valuation information, the bank's historical transaction data, and the dynamic evaluation report of the third-party valuation system, and update the commodity housing price data in combination with the valuation fluctuation range.

[0144] And / or, the prediction module 20 includes:

[0145] The first extraction module is used to input the policy text into a preset semantic analysis model to extract key commodity housing entities and price fluctuation weights in the policy text;

[0146] A first search module is configured to search for the commodity housing price policy impact text with the highest similarity from a historical policy fluctuation database based on the key commodity housing entity and the price fluctuation weight;

[0147] The first input module is used to input the commodity housing price policy impact text into the pre-trained temporal convolutional network to predict the historical policy benchmark fluctuation range;

[0148] The first fusion module is used to fuse the key commodity housing entity, the price fluctuation weight and the historical policy benchmark fluctuation range to generate an estimated price fluctuation range.

[0149] And / or, the first extraction module includes:

[0150] The first parsing module is used to perform structured parsing of the policy text and extract key commercial housing entities in the policy through a named entity recognition model;

[0151] The first generation module is used to semantically embed the policy text based on the preset large language model in the real estate field and generate a policy feature vector;

[0152] The first calculation module is used to analyze the contextual relevance of policy feature vectors through a multi-head attention mechanism and calculate the price fluctuation weights of each key commodity housing entity.

[0153] And / or, the update module 30 includes:

[0154] The first alignment module is used to perform spatiotemporal alignment of real estate bank valuation information, bank historical transaction data, and dynamic assessment reports from third-party valuation systems, including unified timestamp format, geographic coordinate encoding, and property identifier matching;

[0155] The first modeling module is used to extract key attributes of the real estate bank valuation information, the bank's historical transaction data and the third-party valuation system's dynamic evaluation report through feature engineering, perform data correlation modeling based on preset weight distribution, and obtain commercial housing valuation benchmark data.

[0156] And / or, the acquisition module 10 includes:

[0157] The first acquisition module is used to acquire real estate bank valuation information and bank historical transaction data in real time based on a preset bank valuation information channel;

[0158] A first updating module is used to update the dynamic evaluation report of the third-party valuation system on a daily basis based on a preset distribution third-party evaluation report channel;

[0159] The second updating module is used to update the policy text on a daily basis based on a preset allocation policy acquisition channel.

[0160] And / or, the commercial housing price data updating device includes:

[0161] The first display module is used to, upon receiving a query instruction for a specified commercial housing range, visually display the bank valuation, third-party assessment, and policy impact valuation corresponding to the commercial housing range through charts;

[0162] The first supplementing module is used to supplement the historical valuation fluctuation curve of the commercial housing range based on the local historical database.

[0163] The commercial housing price data updating device provided in this application utilizes the commercial housing price data updating method described in the aforementioned embodiment to resolve the technical issue of inaccurate commercial housing valuations. Compared to the prior art, the commercial housing price data updating device provided in this application achieves the same beneficial effects as the commercial housing price data updating method described in the aforementioned embodiment. Other technical features of the commercial housing price data updating device are the same as those disclosed in the aforementioned embodiment and are not further detailed here.

[0164] The present application provides a device for updating commercial housing price data, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the commercial housing price data updating method in the above-mentioned embodiment 1.

[0165] Reference below Figure 3 , which shows a schematic diagram of the structure of a commercial housing price data updating device suitable for implementing the embodiments of the present application. The commercial housing price data updating device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, tablet computers, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital televisions and desktop computers. Figure 3 The commercial housing price data updating device shown is merely an example and should not impose any limitations on the functions and scope of use of the embodiments of the present application.

[0166] like Figure 3As shown, the commercial housing price data updating device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the commercial housing price data updating device. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, hard disk, etc.; and communication devices 1009. The communication devices 1009 can allow the commodity housing price data update device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a commodity housing price data update device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or have alternatively.

[0167] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0168] The commercial housing price data updating device provided in this application utilizes the commercial housing price data updating method of the aforementioned embodiment to resolve the technical issue of inaccurate commercial housing valuations. Compared to the prior art, the commercial housing price data updating device provided in this application has the same beneficial effects as the commercial housing price data updating method of the aforementioned embodiment. Other technical features of the commercial housing price data updating device are the same as those disclosed in the aforementioned embodiment and are not further elaborated here.

[0169] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0170] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0171] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer program) stored thereon, and the computer-readable program instructions are used to execute the commercial housing price data updating method in the above-mentioned embodiment.

[0172] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0173] The computer-readable storage medium may be included in the commodity housing price data updating device; or it may exist independently without being assembled into the commodity housing price data updating device.

[0174] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the commodity housing price data updating device, the commodity housing price data updating device is caused to: collect real estate bank valuation information, historical bank transaction data, dynamic evaluation reports of third-party valuation systems, and policy texts in real time;

[0175] Based on the policy text, searching for the most similar commodity housing price policy impact text in a preset historical policy fluctuation database, combining the commodity housing price policy impact text with the policy text to predict the valuation fluctuation range and determine the valuation fluctuation range;

[0176] Data correlation modeling is performed through real estate bank valuation information, bank historical transaction data, and dynamic evaluation reports from third-party valuation systems, and commercial housing price data is updated in combination with the valuation fluctuation range.

[0177] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0178] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0179] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0180] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned method for updating commodity housing price data, thereby resolving the technical issue of inaccurate commodity housing valuations. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are similar to those of the commodity housing price data updating method provided in the aforementioned embodiment, and are not further elaborated here.

[0181] The present application also provides a computer program product, comprising a computer program, which implements the steps of the above-mentioned commercial housing price data updating method when executed by a processor.

[0182] The computer program product provided in this application can solve the technical problem of inaccurate commercial housing valuation. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the commercial housing price data updating method provided in the above embodiment, and will not be repeated here.

[0183] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for updating commodity housing price data, characterized in that: The method includes: Real-time collection of real estate bank valuation information, bank historical transaction data, third-party valuation system dynamic assessment reports and policy texts; Based on the policy text, searching for the most similar commodity housing price policy impact text in a preset historical policy fluctuation database, combining the commodity housing price policy impact text with the policy text to predict the valuation fluctuation range and determine the valuation fluctuation range; Data correlation modeling is performed through real estate bank valuation information, bank historical transaction data, and dynamic evaluation reports from third-party valuation systems, and commercial housing price data is updated in combination with the valuation fluctuation range.

2. The method according to claim 1, wherein The step of searching for the most similar commodity housing price policy impact text in a preset historical policy fluctuation database based on the policy text, and predicting the valuation fluctuation range by combining the commodity housing price policy impact text and the policy text, and determining the valuation fluctuation range includes: Input the policy text into the preset semantic analysis model to extract the key commodity housing entities and price fluctuation weights in the policy text; According to the key commodity housing entity and the price fluctuation weight, searching for the commodity housing price policy impact text with the highest similarity from the historical policy fluctuation database; Input the text on the impact of the commodity housing price policy into the pre-trained temporal convolutional network to predict the historical policy benchmark fluctuation range; The key commodity housing entities, the price fluctuation weights and the historical policy benchmark fluctuation range are integrated to generate an estimated price fluctuation range.

3. The method according to claim 2, wherein The step of inputting the policy text into a preset semantic analysis model and extracting key commodity housing entities and price fluctuation weights in the policy text includes: Perform structured analysis on the policy text and extract key commercial housing entities in the policy through the named entity recognition model; Based on the preset large language model in the real estate field, the policy text is semantically embedded to generate a policy feature vector; The contextual relevance of policy feature vectors is analyzed through a multi-head attention mechanism, and the price fluctuation weights of each key commodity housing entity are calculated.

4. The method according to claim 1, wherein The steps of modeling data correlation using real estate bank valuation information, bank historical transaction data, and a dynamic evaluation report from a third-party valuation system include: Perform spatiotemporal alignment of real estate bank valuation information, historical bank transaction data, and dynamic assessment reports from third-party valuation systems, including unified timestamp format, geographic coordinate encoding, and property identifier matching; The key attributes of the real estate bank valuation information, the bank's historical transaction data and the third-party valuation system's dynamic evaluation report are extracted through feature engineering, and data correlation modeling is performed based on preset weight distribution to obtain commercial housing valuation benchmark data.

5. The method according to claim 1, wherein The steps of collecting real estate bank valuation information, bank historical transaction data, third-party valuation system dynamic assessment reports and policy texts in real time include: Based on the preset bank valuation information channel, real-time streaming acquisition of real estate bank valuation information and historical bank transaction data; Based on the preset third-party evaluation report channel, the dynamic evaluation report of the third-party valuation system is updated daily; Based on the preset allocation policy acquisition channel, the policy text is updated daily.

6. The method according to claim 1, characterized in that The step of modeling data correlation using real estate bank valuation information, bank historical transaction data, and a dynamic evaluation report from a third-party valuation system, and updating commodity housing price data in combination with the valuation fluctuation range, includes: When receiving a query instruction for a specified commercial housing range, the bank valuation, third-party assessment and policy impact valuation corresponding to the commercial housing range are displayed visually through charts; Based on the local historical database, the historical valuation fluctuation curve of the commercial housing range is supplemented.

7. A device for updating commodity housing price data, characterized in that: The device comprises: The collection module is used to collect real estate bank valuation information, historical bank transaction data, dynamic evaluation reports from third-party valuation systems, and policy texts in real time; A prediction module is used to search for the most similar commodity housing price policy impact text in a preset historical policy fluctuation database based on the policy text, and to predict the valuation fluctuation range by combining the commodity housing price policy impact text and the policy text to determine the valuation fluctuation range; The update module is used to model data correlation through real estate bank valuation information, bank historical transaction data, and dynamic evaluation reports of third-party valuation systems, and update commercial housing price data in combination with the valuation fluctuation range.

8. A device for updating commodity housing price data, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the commercial housing price data updating method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the commercial housing price data updating method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the commercial housing price data updating method according to any one of claims 1 to 6 are implemented.

Images