Data processing method and device based on multiple data sources, equipment and storage medium

Abstract

The embodiment of the invention provides a data processing method and device based on multiple data sources, equipment and a storage medium. The method comprises the following steps: acquiring position information of a target area; if it is determined that the position information is stored in the preset data source, obtaining pre-transaction information of the position information from the preset data source; wherein the preset data sources are a plurality of data sources, and the pre-transaction information represents at least one of real estate buildings, floors, building numbers and orientations of the target area and rating, traffic information and educational resource information of the community where the target area is located; determining target transaction information of the target area according to the pre-transaction information corresponding to each preset data source; wherein the target transaction information represents the transaction expectation value of the target area. The method provided by the invention can effectively improve the efficiency and precision of online evaluation of the real estate estimation.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a data processing method, device, equipment and storage medium based on multiple data sources. Background Art

[0002] When financial institutions provide loans or other financial services in a certain region, they need to provide a reasonable valuation for the region that adapts to the market and balances risks.

[0003] Therefore, how to solve the problem of abnormal business with large differences in data valuation and inability to value, so that online valuation can achieve full coverage without business "blind spots" is an issue that needs to be solved urgently. Summary of the invention

[0004] The embodiments of the present application provide a data processing method, apparatus, device and storage medium based on multiple data sources, so as to improve the efficiency of transaction valuation and the accuracy of valuation.

[0005] In a first aspect, an embodiment of the present application provides a data processing method based on multiple data sources, including:

[0006] Obtaining location information of the target area;

[0007] If it is determined that the location information is stored in the preset data source, the pre-transaction information of the location information is obtained from the preset data source; wherein the preset data source is a plurality of data sources, and the pre-transaction information represents at least one of the building, floor, building number, orientation of the real estate in the target area, and the rating, traffic information, and educational resource information of the community where the real estate is located;

[0008] The target transaction information of the target area is determined according to the pre-transaction information corresponding to each of the preset data sources; wherein the target transaction information represents the transaction expectation value for the target area.

[0009] In a possible implementation, the preset data source includes a primary data source and at least one secondary data source; if it is determined that the preset data source stores the location information, obtaining pre-transaction information of the location information from the preset data source includes:

[0010] If the location information is stored in the primary data source, a preset data call configuration file is obtained; wherein the data call configuration file includes a multi-data source processing instruction or a single data source processing instruction;

[0011] In response to the multi-data source processing instruction, the pre-transaction information of the location information is obtained from the primary data source, and the pre-transaction information corresponding to the location information is obtained from the secondary data source.

[0012] In a possible implementation, the data call configuration file includes a model processing instruction and further includes:

[0013] In response to the single data source processing instruction, the pre-transaction information obtained from the main data source is determined as the initial target transaction information of the target area; the initial target transaction information is the transaction information that has not been processed by the real estate valuation model, and the real estate valuation model represents the way of data processing of the pre-transaction information;

[0014] In response to the model processing instruction, obtaining target transaction information of the target area based on the initial target transaction information and the real estate valuation model;

[0015] If no model processing instruction is received within a preset time, the initial target transaction information is determined as the target transaction information.

[0016] In a possible implementation, it further includes:

[0017] If no multi-data source processing instruction or single-data source processing instruction is received within a preset time period, the pre-transaction information obtained from the primary data source is determined as the initial target transaction information of the target area; the initial target transaction information is transaction information that has not been processed by the real estate valuation model, and the real estate valuation model represents a method of data processing for the pre-transaction information;

[0018] In response to the model processing instruction, obtaining target transaction information of the target area based on the initial target transaction information and the real estate valuation model;

[0019] If no model processing instruction is received within a preset time, the initial target transaction information is determined as the target transaction information.

[0020] In a possible implementation manner, determining the target transaction information of the target area according to the pre-transaction information corresponding to each of the preset data sources includes:

[0021] According to the association between the preset region and the real estate valuation model, a real estate valuation model corresponding to the target region is determined from the preset real estate valuation model matrix as the target model; wherein the real estate valuation model represents a method of data processing of the pre-transaction information, and the preset real estate valuation model matrix includes a plurality of real estate valuation models;

[0022] According to the pre-transaction information corresponding to each of the preset data sources and based on the target model, the target transaction information of the target area is obtained.

[0023] In a possible implementation, obtaining target transaction information of the target area based on the target model according to the pre-transaction information corresponding to each of the preset data sources includes:

[0024] Obtaining a preset transaction information threshold, and determining a difference between the pre-transaction information and the preset transaction information threshold;

[0025] If the difference is greater than a preset first difference threshold, the pre-transaction information is screened out;

[0026] Determine the pre-transaction information that remains after the screening process;

[0027] According to the pre-transaction information retained after the screening process, based on the target model, the target transaction information of the target area is obtained.

[0028] In a possible implementation manner, obtaining target transaction information of the target area based on the target model according to the pre-transaction information retained after the screening process includes:

[0029] Determine the data source corresponding to the pre-transaction information retained after the screening process as the target data source;

[0030] According to the preset data processing algorithm of the target data source, the pre-transaction information retained after the screening process is processed to obtain the target transaction information of the target area.

[0031] In a possible implementation, it includes:

[0032] If the difference is greater than a preset second difference threshold, a prompt message is sent to the user according to the pre-transaction information corresponding to the difference; wherein the prompt message is used to remind the user to process the pre-transaction information corresponding to the difference.

[0033] In a second aspect, an embodiment of the present application provides a data processing device based on multiple data sources, including:

[0034] An acquisition module, used to acquire location information of a target area;

[0035] A first determination module is used to obtain pre-transaction information of the location information from the preset data source if it is determined that the location information is stored in the preset data source; wherein the preset data source is a plurality of data sources, and the pre-transaction information represents at least one of the building, floor, building number, orientation of the real estate in the target area, and the rating, traffic information, and educational resource information of the community where the real estate is located;

[0036] The second determination module is used to determine the target transaction information of the target area according to the pre-transaction information corresponding to each of the preset data sources; wherein the target transaction information represents the transaction expectation value for the target area.

[0037] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0038] The memory stores computer-executable instructions;

[0039] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0040] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement various possible implementation methods of the first aspect above.

[0041] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements various possible implementation methods of the first aspect above.

[0042] The data processing method, device, equipment and storage medium based on multiple data sources provided in the embodiment of the present application, in this solution, the user inputs the location information of the area to be traded in the system, calls multiple data sources, queries the location information from each data source, and then queries the valuation information of the area in each data source through the acquired location information, and obtains the valuation information under multiple different data sources. By using multiple data sources, the online valuation of the area is reduced, and abnormal business situations such as large differences and inability to value are reduced, so as to improve the efficiency and accuracy of online evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] 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.

[0044] Figure 1 A system overall architecture diagram of a data processing method based on multiple data sources provided in this application;

[0045] Figure 2 A flowchart of a data processing method based on multiple data sources provided in this application;

[0046] Figure 3 A flowchart of a data processing method based on multiple data sources provided according to an embodiment of the present application;

[0047] Figure 4 It is a flowchart of the real estate valuation system;

[0048] Figure 5 A schematic diagram of the structure of a data processing device based on multiple data sources provided by the present application;

[0049] Figure 6 This is a structural block diagram of a data processing electronic device based on multiple data sources provided by the present application.

[0050] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0051] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0052] In the existing credit system, when applying for a loan, financial institutions require borrowers to provide collateral as a guarantee certificate to ensure that the loan will be repaid when due. The collateral is generally an item that is easy to store, not easy to wear out, and easy to sell, such as real estate.

[0053] When banks provide loans or other financial services in a certain region, they need to provide a reasonable valuation for the region that adapts to the market and balances risks.

[0054] However, based on the description of the real estate appraisal method in the background technology, it can be seen that in the prior art, traditional real estate appraisal mainly relies on professionals to assess the current market value of the real estate based on relevant regulatory requirements and experience, and issue a real estate appraisal report. This method is too dependent on the subjective opinions of professionals and has problems such as low efficiency and high cost.

[0055] In addition, the current method is to introduce an online real estate evaluation data source from a single third-party real estate data evaluation company as the valuation of the property. Although this method can improve the efficiency of real estate valuation and reduce costs, the business relies too much on a single data source, resulting in low coverage of real estate evaluation data and the valuation of some properties may deviate greatly from the market price. For real estate in small cities in remote areas, due to the small sample size of the underlying data, there is a large deviation between the real estate valuation and the market conditions, resulting in the inability to provide a reasonable valuation that adapts to the market and balances risks.

[0056] The present application provides a data processing method based on multiple data sources, which relates to the field of data processing, and in particular to a data processing method, device, equipment and storage medium based on multiple data sources, aiming to solve the above technical problems in the prior art.

[0057] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0058] Figure 1 The overall system architecture diagram of a data processing method based on multiple data sources provided in this application. Figure 1 As shown in the figure, the system is mainly divided into four parts, including real estate appraisal task applet, real estate valuation management system, offline real estate appraisal task distribution management platform, external data platform, and model management platform. Among them, the real estate appraisal task applet includes channel applet, WeChat applet or HTML5 web page (H5 page for short), bank self-operated applet, etc., which connects to the real estate valuation management system through the software development kit (English: Software Development Kit, referred to as SDK) or application programming interface (English: Application Programming Interface, referred to as API). Users can select the property through the front-end applet and get the entered real estate valuation in real time.

[0059] The real estate valuation management system is a comprehensive management platform for real estate valuation. The platform can display detailed real estate valuation records, conduct channel and label management, and has comprehensive system management functions. The system is the middle-end business processing center of the entire real estate valuation system. The real estate valuation management system contains multiple modules, among which model management is used to manage the valuation model, basic data source evaluation records are used to record the evaluation of the data source; model evaluation records are used to store model evaluation records; model data source management is used to manage the data source in the model; channel management is used to manage the different connection channels between the real estate valuation system and the outside world, real estate label management is used to label and classify different real estate; institutional data source management is used to manage the data sources of different institutions; system management is used to manage the real estate valuation system, coding management is used to manage the coding of different cities or regions; dictionary management is used to manage keywords and other information of the community; interface management is used to manage SDK / API interfaces.

[0060] The offline real estate appraisal task management module includes task trigger rule management, which is used to manage the rules that trigger offline appraisals; task distribution rule management, which is used to manage the distribution of appraisal services; and real estate appraisal company delisting and delisting management, which is used to delist and delist appraisal tasks of real estate appraisal companies. These modules work together to show users detailed real estate appraisal records. Among them, the offline real estate appraisal task distribution management module can automatically distribute special real estate (such as villas, self-built houses, commercial houses, etc.) or real estate information that cannot be provided by online data sources to offline manual real estate appraisal companies in the form of tasks according to business needs or model analysis results. After the offline manual appraiser completes the evaluation, the evaluation value will be entered into the front-end collection App, and the valuation will be automatically entered into the real estate valuation system.

[0061] The external data platform connects to multiple external data sources through the SDK / API interface, and can unify the data access and management of multiple third-party real estate appraisal companies.

[0062] The model management platform is a management platform for real estate valuation models. The platform includes modules such as rule engine, decision flow management, parameter management, instance operation and maintenance, task development, and project setting. The platform can establish multiple real estate valuation models based on cities, subordinate branches or specific business needs, and establish differentiated and exclusive real estate valuation models for the specific business market conditions of different cities and branches.

[0063] Figure 2 A flowchart of a data processing method based on multiple data sources provided by the present application is shown. The method can be executed by a data processing device based on multiple data sources, such as Figure 2 As shown, the method comprises the following steps:

[0064] S201: Obtain location information of a target area.

[0065] Exemplarily, the target area represents the area where the real estate held by the user is located and input by the user in the system. The location information is the specific community where the user's real estate is located, including the building, floor, room number, etc. When the user enters the keyword of the real estate in the system, the system queries and obtains the specific location information of the real estate in the database.

[0066] The beneficial effect of this arrangement is that it facilitates the acquisition of relevant information about the property and improves the efficiency of querying property valuation information.

[0067] S202. If it is determined that the preset data source stores the location information, obtain pre-transaction information of the location information from the preset data source; wherein the preset data source is a plurality of data sources, and the pre-transaction information represents at least one of the property building, floor, building number, orientation and rating of the community, traffic information, and educational resource information of the target area.

[0068] Exemplarily, the preset data source represents multiple third-party data sources connected to the system, including a main data source and at least one auxiliary data source, the location information is the real estate information to be evaluated by the user, and the pre-transaction information is the real estate evaluation information existing in the third-party data source, including the real estate building, floor, building number, orientation, and the rating of the community where it is located, traffic information, educational resource information, etc. For example, when the user enters the keyword of the real estate, the system queries the specific information of the community, building, floor, room number, valuation, etc. of the real estate in the preset main data source according to the keyword, and then the system queries the valuation information of the real estate in other auxiliary data sources according to the acquired location information.

[0069] After obtaining the location information, the location information can be searched from each data source, or one data source can be selected from multiple data sources and the location information can be searched from the data source. That is, it is determined whether the location information is stored in the data source. If it is determined that the location information is stored in the data source, the pre-transaction information corresponding to the location information can be obtained from the data source. For example, if the location information is stored in each data source, the pre-transaction information can be obtained from each data source.

[0070] The pre-transaction information may be the result of a transaction evaluation of the target area by a third-party agency corresponding to the data source, and the evaluation results of the same area by different data sources may be different.

[0071] The beneficial effect of this setup is that it reduces reliance on a single data source and improves the accuracy of property valuations.

[0072] In this embodiment, the preset data source includes a primary data source and at least one secondary data source; if it is determined that the preset data source stores location information, pre-transaction information of the location information is obtained from the preset data source, including: if the location information is stored in the primary data source, a preset data call configuration file is obtained; wherein the data call configuration file includes a multi-data source processing instruction or a single data source processing instruction; in response to the multi-data source processing instruction, the pre-transaction information of the location information is obtained from the primary data source, and the pre-transaction information corresponding to the location information is obtained from the secondary data source.

[0073] Specifically, the preset data source represents multiple third-party data connected to the system, including a preset main data source and at least one auxiliary data source. The location information represents the specific community, building, floor, room number and other information of the real estate. The pre-transaction information is the real estate appraisal value existing in the third-party data source. The data call configuration file is manually controlled, and you can choose to call multiple data source processing instructions or single data source processing instructions. The multiple data source processing instructions represent the call to the main data source and the auxiliary data source, and the single data source processing instructions represent the call to the main data source. If you choose to call multiple data sources, the valuation information of the real estate is obtained from the main data source and the auxiliary data source respectively.

[0074] The system is preset with a main data source, which contains the location information of the property. The data sources other than the main data source in the third-party data source are all auxiliary data sources. After the location information of the property is obtained from the main data source, the multi-data source instruction or the single data source instruction is selected according to the preset data call configuration file. If the multi-data source processing instruction is called, the valuation and location information of the property are obtained from the main data source, and the valuation information of the property is obtained from the auxiliary data source according to the location information in the main data source.

[0075] The beneficial effect of this setting is that it makes it easier to obtain the specific location information of the property, improves the efficiency of system queries, and enhances the accuracy of property valuation.

[0076] In this embodiment, the data call configuration file includes model processing instructions, and also includes: in response to the single data source processing instruction, the pre-transaction information obtained from the main data source is determined as the initial target transaction information of the target area; the initial target transaction information is the transaction information that has not been processed by the real estate valuation model, and the real estate valuation model represents the way of data processing of the pre-transaction information; in response to the model processing instruction, according to the initial target transaction information, based on the real estate valuation model, the target transaction information of the target area is obtained; if the model processing instruction is not received within a preset time, the initial target transaction information is determined as the target transaction information.

[0077] Specifically, the single data source processing instruction indicates that multiple data sources are not called, only the main data source is called. The pre-transaction information indicates the valuation information of the real estate existing in the main data source. The target area is the information of the real estate community, building, floor, room number, etc. The target transaction information indicates that the real estate valuation information in the main data source is used as the real estate valuation result of this assessment. The initial target transaction information is the transaction information that has not been processed by the real estate valuation model. The real estate valuation model indicates the way of data processing of the pre-transaction information.

[0078] The main data source is preset with information such as the transaction information and location of the property to be evaluated. After the transaction information and location information of the property are obtained from the main data source, the single data source processing instruction is selected to be called according to the preset data call configuration file, and the property transaction information obtained from the main data source is determined as the initial target transaction information. Then, the model processing instruction is selected to be called according to the preset data call configuration file, and the initial target transaction information is processed using the property valuation model to obtain the final valuation of the property. If the model processing instruction is not called within the preset time, the initial target transaction information is directly determined as the final valuation of the property.

[0079] The beneficial effect of such a setting is that the use of two types of data source processing instructions and model processing instructions facilitates improving the processing efficiency of the system.

[0080] In this embodiment, it also includes: if no multi-data source processing instruction or single data source processing instruction is received within a preset time period, the pre-transaction information obtained from the main data source is determined as the initial target transaction information of the target area; the initial target transaction information is transaction information that has not been processed by the real estate valuation model, and the real estate valuation model represents the way of data processing of the pre-transaction information; in response to the model processing instruction, according to the initial target transaction information, based on the real estate valuation model, the target transaction information of the target area is obtained; if the model processing instruction is not received within the preset time, the initial target transaction information is determined as the target transaction information.

[0081] Specifically, the multi-data source processing instruction indicates calling multiple data sources, wherein the multiple data sources include a main data source and at least one auxiliary data source. The multi-data source processing instruction indicates calling the main data source and the auxiliary data source. The single data source processing instruction indicates calling the main data source. The pre-transaction information is the preset real estate transaction information existing in the data source. The target area represents the real estate community, building, floor, room number and other information. The initial target transaction information is the transaction information that has not been processed by the real estate valuation model. The real estate valuation model represents the method of data processing for the pre-transaction information.

[0082] The main data source is preset with information such as transaction information and location of the real estate to be evaluated. After the location information of the real estate to be evaluated is obtained from the main data source, if the multi-data source processing instruction or the single data source processing instruction is not selected to be called, the real estate transaction information obtained from the main data source is determined as the initial target transaction information of the real estate, and then the model is called according to the preset data call configuration file. The initial target transaction information is processed to obtain the final real estate valuation. If the model processing instruction is not called within the preset time, the initial target transaction information is directly determined as the final real estate valuation.

[0083] The beneficial effect of such a setting is that it is easy to improve the processing efficiency of the system, increase the fault tolerance of the system, and ensure the smooth progress of the system evaluation process.

[0084] S203. Determine target transaction information of the target area according to the pre-transaction information corresponding to each preset data source; wherein the target transaction information represents the transaction expectation value for the target area.

[0085] Exemplarily, each preset data source is a plurality of third-party data sources connected to the system, the target area represents the information of the real estate, such as the neighborhood, building, floor, and room number, and the target transaction information represents the expected transaction value of the target area, that is, the valuation of the real estate. For example, after the user enters the real estate keyword, the system queries the transaction information, location, and other information of the real estate in the preset main data source according to the real estate keyword. In the case of calling multiple data sources, the auxiliary data source queries the valuation information of the real estate according to the location information in the main data source, thereby obtaining multiple valuation information of the real estate.

[0086] Each preset data source is preset with location information, transaction information and other information of the target area. According to the location information of the property obtained from the main data source, information related to the property can be queried in the auxiliary data source, thereby determining the target transaction information of the property in each data source.

[0087] The beneficial effect of such a setting is that the use of multiple third-party data sources makes it easier to reduce dependence on a single data source and improve the accuracy of the evaluation value.

[0088] In this embodiment, the user inputs the location information of the area to be traded in the system, calls multiple data sources, queries the location information from each data source, and then queries the valuation information of the area in each data source through the acquired location information, and obtains the valuation information under multiple different data sources. By using multiple data sources, the online valuation of the area is reduced, and abnormal business situations such as large differences and inability to value are reduced, thereby improving the efficiency and accuracy of online evaluation.

[0089] Figure 3This is a flow chart of a data processing method based on multiple data sources provided according to an embodiment of the present application. The method can be executed by a data processing device based on multiple data sources.

[0090] like Figure 3 As shown, the method comprises the following steps:

[0091] S301: Obtain location information of a target area.

[0092] Exemplarily, this step refers to the above-mentioned S201 and will not be described in detail.

[0093] S302. If it is determined that the location information is stored in a preset data source, pre-transaction information of the location information is obtained from the preset data source; wherein the preset data source is a plurality of data sources, and the pre-transaction information represents at least one of the property building, floor, building number, orientation, and rating, traffic information, and educational resource information of the target area.

[0094] Exemplarily, this step refers to the above-mentioned S202 and will not be described in detail.

[0095] S303. According to the correlation between the preset region and the real estate valuation model, determine the real estate valuation model corresponding to the target region from the preset real estate valuation model matrix as the target model; wherein the real estate valuation model represents the way of data processing of the pre-transaction information, and the preset real estate valuation model matrix includes multiple real estate valuation models.

[0096] Exemplarily, the real estate valuation model matrix includes multiple real estate valuation models, the target model represents the way of data processing of pre-transaction information, the preset region represents the regional information corresponding to the real estate to be evaluated, the real estate valuation model is a pre-constructed mathematical model, and multiple real estate valuation models are combined into a real estate valuation model matrix, and the real estate valuation model matrix is ​​used to process the data. For example, when the valuation information enters the model for processing, the acquired real estate valuation information and the real estate valuation model are preset with codes of different cities or regions, and the codes in the valuation information correspond to the codes in the target model. The system matches the real estate valuation model with the valuation information of the real estate one by one according to the codes of different cities or regions, determines the target area of ​​the valuation information, and thus finds the target model corresponding to the target area.

[0097] The beneficial effect of such a setting is that it is easy to select corresponding models according to different branches or cities, thereby improving the accuracy of real estate appraisal values.

[0098] S304: Obtain target transaction information of the target area based on the target model according to the pre-transaction information corresponding to each preset data source.

[0099] Exemplarily, the preset data source contains transaction information and location information of the real estate to be evaluated, the pre-transaction information is the transaction information of the real estate to be evaluated preset in each data source, that is, the real estate valuation, and the target model represents the way of data processing of the pre-transaction information. The target model is a real estate valuation model corresponding to the location information of the real estate to be evaluated, wherein the target model and the pre-transaction information are both preset with codes of different cities or regions, and the codes of different cities or regions in the target model correspond to the codes of different cities or regions in the pre-transaction information of the real estate to be evaluated. The system matches the real estate valuation model with the pre-transaction information one by one according to the codes of different cities or regions, finds the corresponding target model, and uses the target model to process different real estate valuations to obtain the final valuation value of the real estate.

[0100] The beneficial effect of such a setting is that it is easy to select corresponding models according to different branches or cities, thereby improving the accuracy of real estate appraisal values.

[0101] In this embodiment, according to the pre-transaction information corresponding to each preset data source, based on the target model, the target transaction information of the target area is obtained, including: obtaining a preset transaction information threshold, and determining the difference between the pre-transaction information and the preset transaction information threshold; if the difference is greater than a preset first difference threshold, screening the pre-transaction information; determining the pre-transaction information retained after the screening; and obtaining the target transaction information of the target area based on the target model according to the pre-transaction information retained after the screening.

[0102] Exemplarily, the transaction information threshold represents a data processing method preset in the target model, the pre-transaction information represents the valuation of each property obtained from a third-party data source, and the pre-transaction information and the property valuation model both have preset codes for different cities or regions. The codes for different cities or regions in the pre-transaction information correspond one-to-one to the property valuation model. According to the codes in the pre-transaction information, the corresponding property valuation model can be found and determined as the target model. The first difference threshold is the data processing method preset in the target model.

[0103] The valuations of each property obtained from each data source are placed into the target model for calculation and evaluation. The target model has a preset transaction information threshold. The multi-data source cross-validation method is used to calculate the differences between different data sources in turn to determine whether the differences between different data sources are within the threshold range. This is used to determine the data divergence deviation of multiple data sources, which is convenient for determining abnormal data sources.

[0104] A first difference threshold is preset in the target model, and the difference between the calculated real estate valuations is compared with the preset first difference threshold. When the difference between the valuation data and the threshold is within the first difference threshold range, the valuation data is judged to be reasonable. If the difference between the calculated real estate valuations is not within the preset first difference threshold range, the data is judged to have a large divergence deviation, and the data is confirmed to be abnormal data. The data is screened out so that the data that meets the target model data processing requirements is saved, and the final real estate appraisal value is obtained after processing the data.

[0105] The beneficial effect of this setting is that it is easy to judge the divergence and deviation of the data, filter out abnormal data in real estate valuation, and improve the accuracy of the final output real estate valuation.

[0106] In this embodiment, according to the pre-transaction information retained after the screening process, based on the target model, the target transaction information of the target area is obtained, including: determining the data source corresponding to the pre-transaction information retained after the screening process as the target data source; processing the pre-transaction information retained after the screening process according to the preset data processing algorithm of the target data source to obtain the target transaction information of the target area.

[0107] Exemplarily, the pre-transaction information represents the valuation of each property obtained from a third-party data source, and the target data source is the data source where the pre-transaction information of the property to be evaluated is located. For example, a data processing method is preset in the target model, and according to the transaction information threshold in the target model, an abnormal data source is determined, and the abnormal data source is screened out, and the data source retained after the screening is determined as the target data source, and the data source is processed according to the data processing algorithm preset in the target model, and finally the evaluation value of the property to be evaluated is obtained.

[0108] The preset data processing algorithm includes multiple algorithms, for example, the weighted average algorithm. The preset data source weight depends on the backtesting of historical data. It is obtained by combining the real transaction data and judicial auction data of the market, and the weighted average algorithm is performed on the retained data to obtain the weighted average value of the original real estate valuation. Based on the weighted average value of the original real estate valuation, according to the business needs of different branches and the market conditions of various cities, the average price of the administrative district where the assessed real estate is located, the average price of the community, the community rating (including multi-dimensional ratings such as transportation, medical care, education, etc.), the house area, the age of the house and other characteristic data, the final real estate appraisal value is obtained.

[0109] The beneficial effect of such a setting is that it facilitates the screening of abnormal data, avoids the deviation of real estate valuation caused by abnormal data, and improves the accuracy of real estate valuation.

[0110] In this embodiment, if the difference is greater than a preset second difference threshold, a prompt message is sent to the user according to the pre-transaction information corresponding to the difference; wherein the prompt message is used to remind the user to process the pre-transaction information corresponding to the difference.

[0111] Exemplarily, the second difference threshold is a data processing method preset in the target model, and the second difference threshold is less than the first difference threshold, that is, when the data is not within the second difference threshold, it indicates that the data has a large difference. For example, when processing different valuations, the data is processed by cross-checking and comparing. If the difference between the valuation and other valuations is not within the preset second difference threshold, the valuation is determined to be data with a large difference, and the system distributes the assessment business to different offline staff for manual assessment processing. After the manual processing is completed, the assessment report is uploaded to the system again, and the system evaluates the property again according to the data processing method of the target model, thereby obtaining the assessment value of the property.

[0112] The beneficial effect of such a setting is that it can resolve abnormal business situations where there are large differences in the valuations of online real estate valuation data and where valuations cannot be made, so that online real estate valuations can be fully covered without any business "blind spots".

[0113] In this embodiment, the user inputs the location information of the area to be traded in the system, calls multiple data sources, queries the location information from each data source, and then queries the valuation information of the area in each data source through the acquired location information, and obtains the valuation information under multiple different data sources. By using multiple data sources, the online valuation of the area is reduced, and abnormal business situations such as large differences and inability to value are reduced, thereby improving the efficiency and accuracy of online evaluation.

[0114] Figure 4 The flowchart of the real estate valuation system is shown in FIG. 1 , and the method specifically includes the following steps:

[0115] S401. The user selects a submission channel and a city, and enters community keywords.

[0116] Exemplarily, the user selects an evaluation channel, such as a channel App, WeChat applet or H5 page, a bank's own App, etc., and enters key information of the property into the system, such as the name and location of the community.

[0117] The beneficial effect of such a setting is that it facilitates the system to query the real estate according to the key information input by the user.

[0118] S402, adjust the benchmark data source query interface, and query the information such as the community, building, floor, and room number in turn.

[0119] Exemplarily, a main data source, i.e., a benchmark data source, is preset in the system. The system calls the benchmark data source query interface through the SDK / API interface to query the area where the user's property is located, such as querying the community, building, floor, room number and other information in turn.

[0120] The beneficial effect of this arrangement is that it facilitates accurate location information of the user's property.

[0121] S403. Input the house area and submit the property information for evaluation.

[0122] S404: According to the preset data call configuration file, select whether to call multiple data sources.

[0123] Exemplarily, a data call configuration file is preset in the system, and a choice is made to call multiple data sources or a single data source. If multiple data sources are called, the multiple data source processing instructions are responded to, and the reference data source interface and the non-reference data source interface are respectively adjusted. If a single data source processing instruction is called, only the reference data source interface is called.

[0124] The beneficial effect of such a setting is that the use of two processing instructions, namely, multi-data source instructions and single data source instructions, facilitates increasing the fault tolerance of the system and enables the system to smoothly carry out a complete evaluation process.

[0125] S405, adjusting the benchmark data source query interface to query the valuation, and using the queried valuation as the initial valuation.

[0126] For example, if you choose to call a single data source, that is, respond to the single data source processing instruction, call the benchmark data source query interface, query the valuation of the real estate to be evaluated in the benchmark data source, and return the valuation to the channel end as the final valuation value. If no valuation can be found in the benchmark data source, the system will distribute the valuation business to professional staff for offline manual evaluation. After the manual processing is completed, the evaluation report will be uploaded to the system for re-evaluation.

[0127] The beneficial effect of this setting is that it makes it easier to resolve abnormal situations in online appraisal business and ensures full coverage of online real estate valuation with "no blind spots".

[0128] S406 , adjusting the reference data source interface and the non-reference data source interface to query the estimation in sequence, and summarizing the estimation of the reference data source and the estimation of the non-reference data source as the initial estimation.

[0129] For example, if you choose to call multiple data sources, respond to the multiple data source processing instruction, call the benchmark data source query interface and the non-benchmark data source query interface, query the valuation of the real estate to be evaluated in the benchmark data source and the non-benchmark data source respectively, and summarize the queried valuations. If no valuation can be found, the system will distribute the valuation business to professional staff for offline manual evaluation. After the manual processing is completed, the evaluation report will be uploaded to the system for re-evaluation.

[0130] The beneficial effect of this setting is that it uses multiple third-party data sources, reduces dependence on a single data source, and improves the accuracy of valuation.

[0131] S407, calling the configuration file according to the preset data, and selecting whether to call the model processing instruction.

[0132] Exemplarily, the data call configuration file contains model processing instructions, wherein the model processing instructions are used to call the real estate valuation model of the model management platform to process the data. If the model processing instructions are not called, the initial valuation is used as the real estate appraisal value. If called, the initial valuation information is processed using the real estate valuation model to obtain the final real estate valuation.

[0133] The beneficial effect of such a setting is that it facilitates improving the accuracy of valuation.

[0134] S408. Use the initial valuation as the property appraisal value.

[0135] S409: Calculate the model evaluation value and the final evaluation value.

[0136] S410: Get the final property appraisal value and return the appraisal value to the channel end.

[0137] Exemplarily, after the valuations obtained from the benchmark data source and the non-benchmark data source are aggregated, if the model processing instruction is not called, the initial valuation is directly used as the final property valuation. If the model processing instruction is called, the initial valuation is processed on the model management platform, wherein the model management platform contains multiple valuation models established according to cities, subordinate branches or specific business needs, and the valuation data and the valuation model contain corresponding codes. According to the codes of the valuation data, the corresponding valuation model can be found, and the data processing algorithm in the model is used to process the valuation to obtain the final valuation of the property, and the valuation value is returned to the channel end, and the user can obtain the valuation information of the property based on the information on the channel end.

[0138] The beneficial effect of this arrangement is that it is convenient to establish multiple real estate valuation models based on cities, subordinate branches or specific business needs, and to establish differentiated and exclusive real estate valuation models for the specific business market conditions of different cities and branches, thereby improving the efficiency of real estate appraisal.

[0139] Figure 5 A schematic diagram of the structure of a data processing device based on multiple data sources provided by this application is shown in FIG. Figure 5 As shown, a data processing device 500 based on multiple data sources provided in this embodiment includes:

[0140] An acquisition module 501 is used to acquire location information of a target area;

[0141] The first determination module 502 is used to obtain pre-transaction information of the location information from the preset data source if it is determined that the location information is stored in the preset data source; wherein the preset data source is a plurality of data sources, and the pre-transaction information represents at least one of the building, floor, building number, orientation of the real estate in the target area, and the rating, traffic information, and educational resource information of the community where the real estate is located;

[0142] The second determination module 503 is used to determine the target transaction information of the target area according to the pre-transaction information corresponding to each of the preset data sources; wherein the target transaction information represents the transaction expectation value for the target area.

[0143] In one example, the preset data source includes a primary data source and at least one secondary data source; the first determination module 502 includes:

[0144] A first acquisition unit is used to acquire a preset data call configuration file if the location information is stored in the primary data source; wherein the data call configuration file includes a multi-data source processing instruction or a single data source processing instruction;

[0145] The second acquisition unit is used to obtain the pre-transaction information of the location information from the primary data source and the pre-transaction information corresponding to the location information from the secondary data source in response to the multi-data source processing instruction.

[0146] In one example, the data call configuration file includes a model processing instruction, and the first determination module 502 further includes:

[0147] a first determining unit, configured to determine, in response to a single data source processing instruction, the pre-transaction information obtained from the main data source as initial target transaction information of the target area; the initial target transaction information is transaction information that has not been processed by a real estate valuation model, and the real estate valuation model represents a method of performing data processing on the pre-transaction information;

[0148] A second determining unit is used to obtain target transaction information of the target area based on the real estate valuation model according to the initial target transaction information in response to the model processing instruction;

[0149] The third determining unit is configured to determine the initial target transaction information as the target transaction information if no model processing instruction is received within a preset time.

[0150] In one example, the first determining module 502 further includes:

[0151] a fourth determining unit, configured to determine the pre-transaction information obtained from the primary data source as the initial target transaction information of the target area if no multi-data source processing instruction or single data source processing instruction is received within a preset time period; the initial target transaction information is transaction information that has not been processed by a real estate valuation model, and the real estate valuation model represents a method of data processing for the pre-transaction information;

[0152] a fifth determining unit, configured to obtain target transaction information of the target area based on the real estate valuation model according to the initial target transaction information in response to the model processing instruction;

[0153] The sixth determining unit is configured to determine the initial target transaction information as the target transaction information if no model processing instruction is received within a preset time.

[0154] In one example, the second determining module 503 includes:

[0155] A model determination unit is used to determine, according to the association relationship between the preset region and the real estate valuation model, a real estate valuation model corresponding to the target region from a preset real estate valuation model matrix as a target model; wherein the real estate valuation model represents a method of data processing of the pre-transaction information, and the preset real estate valuation model matrix includes a plurality of real estate valuation models;

[0156] The information determination unit is used to obtain the target transaction information of the target area based on the target model according to the pre-transaction information corresponding to each of the preset data sources.

[0157] In one example, the information determination unit includes:

[0158] A threshold determination subunit, configured to obtain a preset transaction information threshold and determine a difference between the pre-transaction information and the preset transaction information threshold;

[0159] an information screening subunit, configured to screen out the pre-transaction information if the difference is greater than a preset first difference threshold;

[0160] Determine a preservation subunit, which is used to determine the pre-transaction information retained after the screening process;

[0161] The transaction information determination subunit is used to obtain the target transaction information of the target area based on the target model according to the pre-transaction information retained after the screening process.

[0162] In one example, the transaction information determination subunit is specifically used to:

[0163] Determine the data source corresponding to the pre-transaction information retained after the screening process as the target data source;

[0164] According to the preset data processing algorithm of the target data source, the pre-transaction information retained after the screening process is processed to obtain the target transaction information of the target area.

[0165] In one example, the information determination unit further includes:

[0166] The threshold comparison subunit is used to send a prompt message to the user according to the pre-transaction information corresponding to the difference if the difference is greater than a preset second difference threshold; wherein the prompt message is used to remind the user to process the pre-transaction information corresponding to the difference.

[0167] This embodiment provides a data processing device based on multiple data sources, which can execute the method provided by the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be described in detail here.

[0168] Figure 6 This is a structural block diagram of a data processing electronic device based on multiple data sources provided by this application. Figure 6 As shown, the electronic device 600 provided in this embodiment includes: at least one processor 601 and a memory 602. Optionally, the device 600 further includes a communication component 603. The processor 601, the memory 602 and the communication component 603 are connected via a bus 604.

[0169] In a specific implementation process, at least one processor 601 executes the computer execution instructions stored in the memory 602, so that at least one processor 601 executes the above method.

[0170] The specific implementation process of the processor 601 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0171] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0172] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0173] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0174] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0175] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0176] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0177] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0178] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0179] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0180] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0181] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0182] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0183] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A data processing method based on multiple data sources, characterized in that: include: Obtaining location information of the target area; If it is determined that the location information is stored in the preset data source, the pre-transaction information of the location information is obtained from the preset data source; wherein the preset data source is a plurality of data sources, and the pre-transaction information represents at least one of the building, floor, building number, orientation, community rating, traffic information, and educational resource information of the real estate in the target area; The target transaction information of the target area is determined according to the pre-transaction information corresponding to each of the preset data sources; wherein the target transaction information represents the transaction expectation value for the target area.

2. The method according to claim 1, characterized in that The preset data source includes a primary data source and at least one secondary data source; If it is determined that the location information is stored in the preset data source, obtaining pre-transaction information of the location information from the preset data source includes: If the location information is stored in the primary data source, a preset data call configuration file is obtained; wherein the data call configuration file includes a multi-data source processing instruction or a single data source processing instruction; In response to the multi-data source processing instruction, the pre-transaction information of the location information is obtained from the primary data source, and the pre-transaction information corresponding to the location information is obtained from the secondary data source.

3. The method according to claim 2, characterized in that The data call configuration file contains model processing instructions and also includes: In response to the single data source processing instruction, the pre-transaction information obtained from the main data source is determined as the initial target transaction information of the target area; the initial target transaction information is the transaction information that has not been processed by the real estate valuation model, and the real estate valuation model represents the way of data processing of the pre-transaction information; In response to the model processing instruction, obtaining target transaction information of the target area based on the initial target transaction information and the real estate valuation model; If no model processing instruction is received within a preset time, the initial target transaction information is determined as the target transaction information.

4. The method according to claim 3, characterized in that Also includes: If no multi-data source processing instruction or single-data source processing instruction is received within a preset time period, the pre-transaction information obtained from the primary data source is determined as the initial target transaction information of the target area; the initial target transaction information is transaction information that has not been processed by the real estate valuation model, and the real estate valuation model represents a method of data processing for the pre-transaction information; In response to the model processing instruction, obtaining target transaction information of the target area based on the initial target transaction information and the real estate valuation model; If no model processing instruction is received within a preset time, the initial target transaction information is determined as the target transaction information.

5. The method according to claim 1, characterized in that Determining target transaction information of the target area according to the pre-transaction information corresponding to each of the preset data sources includes: According to the association between the preset region and the real estate valuation model, a real estate valuation model corresponding to the target region is determined from the preset real estate valuation model matrix as the target model; wherein the real estate valuation model represents a method of data processing of the pre-transaction information, and the preset real estate valuation model matrix includes a plurality of real estate valuation models; According to the pre-transaction information corresponding to each of the preset data sources and based on the target model, the target transaction information of the target area is obtained.

6. The method according to claim 5, characterized in that According to the pre-transaction information corresponding to each of the preset data sources, based on the target model, target transaction information of the target area is obtained, including: Obtaining a preset transaction information threshold, and determining a difference between the pre-transaction information and the preset transaction information threshold; If the difference is greater than a preset first difference threshold, the pre-transaction information is screened out; Determine the pre-transaction information that remains after the screening process; According to the pre-transaction information retained after the screening process, based on the target model, the target transaction information of the target area is obtained.

7. The method according to claim 6, characterized in that According to the pre-transaction information retained after the screening process, based on the target model, the target transaction information of the target area is obtained, including: Determine the data source corresponding to the pre-transaction information retained after the screening process as the target data source; According to the preset data processing algorithm of the target data source, the pre-transaction information retained after the screening process is processed to obtain the target transaction information of the target area.

8. The method according to claim 6, characterized in that Also includes: If the difference is greater than a preset second difference threshold, a prompt message is sent to the user according to the pre-transaction information corresponding to the difference; wherein the prompt message is used to remind the user to process the pre-transaction information corresponding to the difference.

9. A data processing device based on multiple data sources, characterized in that: include: An acquisition module, used to acquire location information of a target area; A first determination module is used to obtain pre-transaction information of the location information from the preset data source if it is determined that the location information is stored in the preset data source; wherein the preset data source is a plurality of data sources, and the pre-transaction information represents a transaction valuation of a target area; The second determination module is used to determine the target transaction information of the target area according to the pre-transaction information corresponding to each of the preset data sources; wherein the pre-transaction information represents at least one of the property building, floor, building number, orientation and rating, traffic information, and educational resource information of the target area.

10. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor.

12. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 8 when being executed by a processor.

Images